From bc05d6fade73fe716a6bb43c971462536e18393a Mon Sep 17 00:00:00 2001
From: Charles Weiss <69219836+weisscharlesj@users.noreply.github.com>
Date: Sat, 24 Jun 2023 15:56:03 -0500
Subject: [PATCH 1/6] Uploaded images for stochastic tutorial

---
 content/tutorial-stochastic/circle_square.png   | Bin 0 -> 18578 bytes
 .../tutorial-stochastic/circle_square_dots.png  | Bin 0 -> 35350 bytes
 content/tutorial-stochastic/galton_board.png    | Bin 0 -> 57809 bytes
 3 files changed, 0 insertions(+), 0 deletions(-)
 create mode 100644 content/tutorial-stochastic/circle_square.png
 create mode 100644 content/tutorial-stochastic/circle_square_dots.png
 create mode 100644 content/tutorial-stochastic/galton_board.png

diff --git a/content/tutorial-stochastic/circle_square.png b/content/tutorial-stochastic/circle_square.png
new file mode 100644
index 0000000000000000000000000000000000000000..2d508db8fbd112fdadd21c8ff44d8e0d1575f992
GIT binary patch
literal 18578
zcmYhjc|6qX`#(Mmqhe^1C2Nhf1u<jak`a?6OZJd5W2fx<%yEt;LWXGUAzRiES*H^!
z#*%%DNm1D&`}V!(yg$Fk<M&68n0dYK<=XD+x}MM5<6AfN;U@%6Kp+q})&OG)fiSy3
zAWX~0VBnLB%c}_R-*F!UYhMUN^KZsKrlHabKk(rhKRqiyGjE(<;N6GLkift|SywN2
z-+Om`oMpWq;?tKk1R#*J5G+Q=JSb!FOK_9_#^llOk-}Hyu$RbcNqF>Cw6xy#v+D|$
z9khq(3M1Wd4c=z;iRTl~H<&2=!+}W4KZWf`Hcy5<n`_W&)gHc3xH9&mp=T^~sdjTU
zL`&pH;>OOhd$#h;k;9A?o9Pv01#T=^JT88=f%7buoIg>mlO&E6kXLdci(|z)U`Awd
z*S66d#v}ZKXz&2yUX&!3jCM*{Q6q?B-5fBBoQqTb@xf}6DD44%l9EidPAo~2xL5a7
zuYXB~t<*fS?ARq3@6brskmCHpPD9J#4>*;)8-fiFzZV{^>C;6RlaQHYr3AagPJ45A
z6zc5RjxdcYWuK|hBua6qlf<!R%cpa?VMby!e4jX$eC-K5O&r@#dXNaFANb`$&yAjP
zH>B(7EyYq31VfIh1wyi`J{w1E3et6q*b=W%ktNwnkDwC}E><Nc6;$_8?r!YwQ}q5_
z?W4TI2BB>!ALoN!+t%`xotxcO9HsK#+&6Z!1DTgkOtRMRJvj<X*j0SLil=kX#p(Cy
zd{iUdU3=5i7WT!_A?04$0C6BasDf0VHU=MmOxbxXITb0ep%|4yF-+q`*2*9)pl@Jr
zUb=O@fmyi!T#{qzVLD{VV6(dwnaQ=Uh^nx=_NJQfOt4ddBbCYW)`9TaHAfytPscls
zP)FSo$#T)H;?^u12M6|y6B!0WHJQm2%RiZR0tm!sf0nq*-VfZ|Fl}no0Q2tAH&kdb
zu6x%Xx~fjEGap!q%<<|}STA|k|60W75z};@jMV)(hb||~B(cO~0y6sC4SNJ7?3pO~
zt=FEY3_oD46h}s|XIvSo%zRGy@ki8wd@TW<CTW2wW!4ZFWgVrInEV{sF|Yg51L?_k
z`*@f^S>{uEL~DX=-#+k9Ct1apFn#%ZK4ndJzG9EIUY7dmXi<_nwGo<S?BDp4pZ<sv
zyg@&Lix;aaxui)W9ypXld+^Z{FL`i}*xvbfDLYb43?=7&>3i}k(Zp@v1OGo|8zd{}
z=#%-eR$Fh)Y2PgGM$T38?m_`ch1hVni{_x5YEK@&8&yzc(M#488f6MX4lPyxvx^#9
zH<B7W(ojcLS3ONjrR_@%#Z-t++r*MWO%>fHhK|CHb=lWcF%Qvx<q@G`GpFdG=G}Cz
z`4us&7%;GVQpn+awJ%PAC0t*5QV*rPeuNwzP<I|vKZ&WSZyrmt)eKSbnLab3d`nT?
z=xzPGt%gim(=nCThe+hI!O+v`U7@cQ)RL~C^hW01;#RMC(zk^z^$RGuGp2r60TMi|
z<0_`~rlRf}wxQR5+S#|i;n!AvB;D+!38ov5meMrxinn4&?y>#kkl=&SVm^nkIxuib
zp<BOKc+cvKOU+exvLbuS!&Q*+(0E9TT5eoJ{(0x9f<zv~MYAsrlbLQ^|Lm0SH^Nln
z=TnB|n=Sa=6z<P;588S|ydRTli_$8D316&sEktAIN0uN$LI~}=H0!-q+Wv=IQHK2r
zqdBhmgSIG*EVlv=zPUO+E7P*m8qsdJ+5FuoTQf<N+{+dT0fb!M_?IwzN%l*b=b-_f
zh#{E)PvRD)ZL1hJ-13>4a-Lk{sN^DW98tx(>O?<7^R6DXC1f)@z*;DjNI@r!xECSp
z$=O2=d-`p62zQFpj)aSNx&OR=KA-yc2k6MPwnXX+O7Op{W`?HiFr&<3(d`JeA$tq1
z%nzd0S8F%g6R8L#XB*P)n^`=ucbMHMAg>|3h1*xz{S~B_HA@iD%BBSk8@J6NM|<+)
zIj$S>Aky{Q&YAx(7WwyedUZANfZ(s-+ep*+ICmrJBkiKXdL?Z#ZvM&VAI#ItDFN>L
zE!0LLJ936Z8a=1+O27Z9N>qUbrY*DhjcSnm&;#wRHQy3EA)ZECe?&1FkU`0@aY8v`
zNsVSQ24hifE4B8mZL$Sv!4twNQb;Y<uwe%Qam7z((D2(B4QZs7q5rLIHmeZdfU&ZQ
zPqatQb4TMD#YU8!E!w^d&Wp=~r76j+AW&9tutHTE8UKV-Hu3Si>)Ke3t2EN7k)$H9
zEitr|_fq(+pW2YGi#vYK9kpKPc|SQt5_Ob8@rDf-jEAlm%(bvKXsn{?-$^Pm$jum%
zo{ZizG|{7P@Hxp!2+^qD)=T_WZ1Jvp<4Mmn5lW0x@QtPIV{rB(78b583cgsJNIE4H
zvS6yo6})VE_;HT<gP@IR)7p4&pImbmXx0idDUaM_I>c;Dj;8oF`5pJUG_<a{aDOg>
zvQwDibRF77i&a>^;;4J5`6^&QNUoJ@RfnESQYq51G$+pirH03nHjpz>)PKxHG48#;
z`(G{mhAa4fplK+ee(c^#x@MnXT^q=p+WUKLh-hgdBfX8mOjeX-kULW0X}p(^!^L%<
zw#6#Bd_^q|0_hOPW?GmLE^EXTQ>;kYsoS-#4K>yD-q};NZ#Xq{VXj(i<|irWmhBmd
zI8i}#w=HH;9m$!y3kf;y>pk#La!B`R0Y7)Rp#<y4bkPJA)-RVl>okVk%=q?FXCrLx
z%tnNpVC^%L{_RSg0R_FbJII+YRM8@@AzCeR9aF+p&^`a?u)_Od9{R%kM7BPDF2MXp
zWJK1y%j^D!=Ap$0l1N}2@NwFC*BYS3n}{k4OcR?5*J$b#Tk15%KddKe{?1`S56wgF
zCAvXj{SR%Dy<Xera^FH~3Qv*J11)u=){GM~)-kF;1nE>u8clV(JttVyBX&vVh0VK7
z0xc{8ci7PVq+jI|O&d4YRm6K*$YAA~r~K+e`Xot39J%}%cMY2dWL{UiB_9g)(Hf#e
zz1j*IJ4KH*j~f&5N;=o=fU_r4_L#PyoG-U{g=34ee(&GI2+_6N`u$$(a6=GP(4q39
z6{g{zzsdP(H$v8FVK`h*t*KEzh%62Y>+R+ru;G7ANu8c#3c7eZZ<9<~U2%7f*_PW+
zjwS8swFMGHZ)r*mbX8GPC~s|Xhp(Ic`tQFItZgQ;DQr3Y70Ubwq8&?mR7Wv34fN<M
zFvm<5PbqvGq00I;En*z^LVU*tCJd#FKp?-<{G9&Iyf<Le#-&=q=W4U!2emR-@}Qbv
z&3SG_mwuaJ(WXKuPxF?-o@S+c^M&<7@NIz=?yx{BlYW<q)wDllZtJ_RgxpLZ*<XAm
zVFUp$nrh<%U_(pf+K{I2C+I`e0?JONQZ;tBj;6sg8b3cdz8>0ipNH;g&h~nR2k{xF
zg?*2YQes8UEF&K95BcKKH-kQPn{!>5Rz`7k((Jh|8M>KR#OH@7{egsdcR%o^`%)hu
zsve~8h{IFi<1DeA_Ec+g!MmGly7Y6Dw}H6Byk<Z0oEWO2n|45qE9O1*Cq&CLl%9&H
z^2S_pLuKcGt<*`sg?J!J-!pH$GyV31;o-5xM2h<TIqS0Mq#8%c&Pd3)cX`Ec+Rm5V
zsEz#Uil_>H^;KN42j=<jU@T<wWt!r|iw}n7Fne|n(`l_l^fiTbDRX>S3rl_J2SX+3
z&3ICsew*Eox$6QClw7#Qks=%!H#ThjDu(WSxFrMGzJl8ve`nXv|B+^^u%1MP7I}rH
zSU{#YGI$UPu8JA?*G6-U2qY_2<R;tAm%H5!eyWv$I4xOJXxXtObo6{)-X?Rv%PqHF
zIN_eyOeLw_tnrsP{9l+SO|R`e0actbS<&}R;t`V|eoo2;E?KO&@kS+`S@flvTwp<t
zjkq7Kc_=<#-Z4t40O@3MP&)RT8m(#nP^8iqr=^Sv)htB1{&jzDh_Z8nj-ZZ#Z{+BE
zhzGYYrK4VISa#<qrRe#4_7RwkQfpQBH-EbsSF_>fw#IuTi)|^vr-rVAvp_KBYmS=E
z_dg&)OpJ+lXT!&zKPKT#zVwIPPxx9*@SNA|J{<B=z~&)Q-kmgPaTfL<I3d;Js{i(G
zWY7sBI?bc614O4PEjXQ>I^XVN+MT9(2^D(ae9861P^gfXp<=p4`K0}sZT{6Sq<VcY
zhfF4XoS#H0BRcf$p$UcrsljU8$eZ*V{Y720^o6k+eaMeLL7(mw-#ix-*7!+WCJsJ+
z?3Hq6xVjJX(8Hbn&*pn+;jg~jCwG9D$Lzr=G<9#goT|LQ%Hrj9F%FnCf(PNwH2rei
z<F$tEN(eA%ZcS~o{xIjcXOtZeM=pAd)Aleci<Dm5ZrP(GKah-x6=~_Opy@{&{95dz
z7ydKjN0Ns9rb8c^JYoAaA69h<W@0l{O9f<f5`3KWnABXfsbpKnf1R#N<)!Q_3`b$p
zq&JF@2?c3!tyTOjsMSo;s5Wvx<Ea|GHAoDJw1^=YGiBe~R831|R(GD$qF67xi(|t-
z(IhCrCs(EE|2hRBhK@_<W7^z2@ks?hKF3I;P^dPOec!!pjuP86Z5QQd`L2l+DYGwY
z`*#z*7BUy=wMl{n6{N#$J|LY!OMY~}nU~)WcATJT)O|507Z~B}Pb_i>8EhD|-w-tO
z^w_Hbt2FC`m5G^*rOqo4H}bq!hRAi(nibX?HV3e2*EX_T_n3NF%FjnzzHIoiQ%;h$
zOfhtO4!2=LI>`@J<5qB+yaIg837s@u8!k!g6<oyQ`R7H`yt+F67v9x{%NhyD3f83P
zwWU$FeuiJ58W&r*9+rZY_=Qq-)Is#I4CPp1$+)GhebM!pN1u(k_aR7EV~YEw2*L{M
zD`nB-d{tn`)PW*gx7Yb-QOt(jIIfH>sek~tF+@6D1Xagjdmo(YJ710NdjCYC*vwk>
zWRSvYh10e@H9;(Qq+py3bBr4PixhOqN2r<)YR9ygL2+==ekKm$y9nHa-R>4g8E2R>
za??xu8Tze9U-Tt#gvT>moR98#Iezuqhq6cHe69O)6zVWlF80MNF=6CUnf~6V{7?6y
zl*AELAa`L2dpdTcek3$1iR$7pC8PTl*00hNsq&i94y<9SNDDXRXXs!saL!@ZFKPNS
z&FI$awQ(KoKu!6$!C1DeV_^j!R+p*rUhmJrJ78sZ5mhHvjY?XZu8T4U1g=|SzsWLO
zjPI84o0fe3h|@lHn9`w;%dS^Pa}=eK7OX9-i&h+8n43zp7Mu2CZ;(4I!bf)phzqeV
zx{2ACHq8lRi8yV+nrKF@X5psQz~8_b^bi+Oe_&2Vhf#vXhg7pHd3CuU5#OWV^#41S
zqj(m%4BIEoyChS}nX+!l8K>qyen!z|5`o&;aC}LfA0)yVL&^!(FzK~v7Nu3Q@#r40
z1kh;rz{l7nP=MSjTWu=hx8YOKLMnLzsb+cf!A>F;m_C>pee3m8T^*%qyj{9M9()<H
zm$O9B=F<&ii}?BZR{#EJ&c=D<vi?wp=PizdOgF(eGsci#x@f+|SsxDW$@^KB3}sH#
zWM3DMQ*sF>k=P*GOr2~FN6a3nlvbcWP^i;1L`Owb8u@LY+gV0wHGWDi?57ce5bc~@
zBcB3aB1lA3mkP=GpOYw&dBC36om>=4x;>P=!7@cW`gn8fFC0R1CP#kMnWOMO-eg}V
zU$ey7GimUu6!SN1Jl!xF2V2(?tO<?*nQhsyT`RvDcMt}b@+w6f*uMSoMPSPuWvpSX
zEvR#@Fz_6Sq*%lWn=0bp6$8Q9emLR+RzQ@pBj;$DV|T^hxa1$`0+>bMj*?5)Nkm|N
zLz%TKTszw>ySlX&Ox|IPv)A))Tz}%^;z?)QXd#m;b!<y^>Farv@T(wAWM@9?XN>4T
z*)cA;_aefQ!xK~6u-*f<2x`=EA>gAvr-#Z%Q3p|O+~W_quVMQ&?$1e3<IP`9<3rB+
zcpO+gMh|)Pg^)<I#EM%7Dar#p=H1qBD-y(AnH1KUOC~aBnO}7iyfJOp8Dl<z+jxtz
z1YC3*F%=Fw?BZNA=x+lFmPw|H&ja~C2J}kOD(bpfm+0YDOcNp~*rbIsC=8ck*d~F6
zexzyN@_hFoSiVMmwP%wXoA(ap8BH1$4ze_9ITK`q6B*GF$EF2Qb}p7Q@{aK6?p<q}
z62_3#@KF}ABpG6_!d_%jxWc;nk`y`r7YKPwy-X>mbw%SyYl+;hGh;bSh$^jB8OLW%
zKdH2RE4D;&*ZKQ%Ce#SMV1!Q)COOpPI=AP%U=69Bd+0pV?AIUq%-(L=iQ+~Tv@p5V
z&$&$kt4k!S#wY_*se%TbS6gc8r|P}s{VuFF(JmE^OJLvEajkae1{l-T5mg~<!TG~R
zo>9CACZQ7=1^l42j_G!1m})1@mVjrPeRD0H*`Z{sBw2ENP|1ZFX`=a5ZNQl-yCFM5
z&W|5_^h#T#K8Jt&Oi<+B<NN?4XE2gFv-ibLW#-0_&@}_HS_*~FRPp}NrD*#zh+cQ?
z#KEj$_deu|7B#il0`}!Xah9rY1qv&0j<O?2|79L(+Vkf#DaeN{G2i0G?I?@vr2z3t
zocy11+P)JI1h(rbWg0qVm2CM!t$Mu&2sPTPL;y{9q`%NxdPKEV|A@q<71H)0K2|37
zeA`Z#OY^_=^Q)8;;Wn72Q$hA7TB1QA%}xen^te4N<Mv<x%T&J(uWM03F6d=>61I3|
z7l?(pxtCyIahY2<d#J`gW3jL)0fh1LSuz^UJ)NW1_N6FG-PVqySp#LfaF#4yY)skF
zca-yr#Ni>?@g#U7RzlG`SFk1o^<In+%A?DMpDScEw*+p17~S+rx`HW85xLx_BVPP~
z`%8|=0sH>P+)Wf+QTTqMxZ;m8>Q>A+l$hZ6RL^a)P00mOrMWtu8+LpMSEKBA5=$O@
zx?B1ke@nPmd0-tm^9!s~Krs<+(=6BXb@H%vx|^Csu@(_TVg+<5!K{_)L%9_cEnb9s
z;7P0-4FmM|;rYSjn7YFH2gY=8Ebfqbv`)I>xX|*UivXT`1Z*#spc%7POjTDSiD3m=
zxS-P)+!7%6(>lDx2<{>9J&d{+yVgp;JI@(0qy)FdNv>X{ueA3aVcIOfCom;>u%4G4
zU#V{GeHZ7$eZ{fdpf|#l#r6Hk+6nVIHOnQ*XM?SeUHb@7!XuvA3f$a}hGSw_H%nYZ
z>O5_hqI7=~tI+>3odlCXzPY!lo6E;6w|q7pG?gl#5qAbR<4Io{kBM!#FETtpY?ak<
z&Mi}d>Z`E6=4FZ{H$0_`m<hAqUJl%;BGrciJ8F3n9tCR>w5ls=Rz@W(AfJeX)Nsd;
z-Ws!JL)8&(OWai$hTDX@`>y2fvzLfn0nNsR18S9?X96k6iSKUyKLQhAB^E54cQ;*`
z<Y+WOpkb^4>xRiKIhJzSXwG<&q8dqD=HsZ6i}}C^m$chTN#Pp_teGsT7r$B76AD>b
zJR4tg_TCr}9+areJ3IZY)erPv_m25EnM|l7MLz5CyS8+c0}GrbBtT>F$*B;z63Z0>
zGRtJZt98A}h}%CNQePmdOqGlCodp|V@F1Sm)!fbBG>sRrmqGkbp|nD$%#xL1Q-eA}
zuJ#=zU?hLS(fLk3CU1t|T*I26Dvd=4c#Ov|n93SFkQb7YqhYq>Oxfv`{nvopp^KZk
zQd{Et>B-s}^&FzAXe*oCfKmcZv&gh)k=&X=nf{3cakT0FTyN1Ee46V;+)Ckjf3Hgd
zH6$y_STC0y=i-2l5Vn7NoU1;ks96)aJPBr!z4tkXsRF<G;HEc?77LVy6)>g*^9(sv
zQ-<5PUC>U~TEJ36nf7>RQG{N<llo-zoWi<0bt`tQ3+Xf<yJpb*BrFOhbZqiP(URGU
zrx?~$+g{gSgI<=xrqyS{>zb12)rWL)r&IKH3@O23e8J+_q;sfVn3i>NAc^$BKT-ce
zoChPeg`FgwnO!InSxpvqy>-NDXEDebLuzlfzf|jbUl2_nqrQ(B4@IrZ-T51Y(G*&f
zP*AAJ)X5-gwg>qWXFf61e|NJL&8HCh3XUbiek170dP|<5&<EyW8+Shnwl7tA(_}&p
zRq+d$m#c#FTsQSq?3w^IGVr8+L-$8T7sLZ&y1(AeY5FSXi~(8F4kyAcWR~o33bD0<
zOkfck%`p)UYgv1;z+#_G88Z>V_J0qR@fmosphulh>qN#`fK4pi62_?yASl6C8T%YK
zhl*qi%avXcL2xZ16VRq`fmL3|_A?`O5H`PLJu>>v6qB9$w-D8R4paSW1whUlgyxvF
zuaupM%>e^O_IwCe$(PnXk9-4OFPQj<b}?^#Nt+Z}<t>@Ufqs9NI`I|Wj!i4Jfb$6k
zOfM+EXHaO2pA&8PD27eDNeMpBIBML(|Ktp&CA#z#ZKhjCbZo>?8^L<9X<jSP@(XUu
zu>}_XQ^4*esUmtiNt9qOuynZOg$ez(Nd2}Kh~J5%(fS2DM&;scj@Rj}xrgzX))O%*
z>=8tlOkc;%)r$lL>RXG;=wUR}k*~LH@EzN_L^GnOSy^Yqxz&e`2RE4w4??wlf=w<a
zoK21{7yzmg;m~+1Et)~$^Gnn>JwiHJ(t{k=%c~8dI%yY)M>3rgdTsX_KIZ)z*x(o!
zEVB4GIWIt`#=kb0H^XQMZ7Wn>AF<Adg&(WWFKT`fdp1oglc7CtoOWn{56*s4PXrro
z`)FS1y}F+;#?2IW7&~wA<A%CkTfv?0pZ%;O#^lbVg%fyicGH-RiJ1J~YZ3H#RJj~m
z3p9gsKWd)u-E`nnL$`n5Q6rgOjf^lgaRx=;AESBHT!A4g(%Tt^yfXqUU*Ka|W2w{-
zO8qF4VktMf(Lef;_6j*OKy}9@XY(Mue+Rq5%`EFw9R6*M6ns0x)^H42EML(>Qy$H5
zWfo?c)c6*{N_Q4^{+#U6%!n*ROP*O#+}s&YeB$79Ib1=4v<uRC&Vf*IdN%c1TM1+F
zKb>HnTqTcU@E1}Q3<X4$O*Hewj9zc?jJTUFtxLi6_~7GO?HenEm4K(Zrl<(3-pdBu
z7g5HA<AmS>%aOo;@;hqBfv)q2Wie}^DAWY)T(OCipYRnoY;YZ3lYU<Kd*5l7P}q`x
z`-TMds5V2#wEA$^A5tta4eOD0^Rj#O!leu>6;AlTGs}ga+wgRLiavd)URr!>dg(lu
z$utrvG7OC4jS{}k{^L@De?y8J^a_^T(f)%HzHj!nq7YqaAyBh>uJZ@)tQczjwNgu~
zIM%3WWjE}N^vW4T;NtIx#onIXIhrE%c$2;RhSRp>e97>?=D$C&EjzI|X2NS!^hTiO
z;qF!-6)O|&jU@{tQGP(Q&v#DEnde0_%($7D8M7ueX`@R<cW}y-*F7P1t6_5=4|Z^j
zvlI1D<=!kUegAGf6L+<WXO@+7%es`)!BNYQKH&%7EI8=2qj$o=*-;Qubwzb-HG^dJ
zGFBr^<9(LS#Bp#uy;ZqFMj!9&tsWv41|Tp=_)++HY|Mf-YVQ&XZ1W~Ai#5YE`Oc-B
zYa9$YH8M5w%o^k7$alkyv1A*Io?K5p#MXlNW693T_`WR8(#zj=adcnZ{Rpyn?UEt&
zHmV#NWT9`3)`=d=Su(MUltO8mTa(f93hM&&kGXachgf!{WZ*!<us7#B9RxbIKyq`>
zLAG2up7h9%jN!g#g>nh?*^ByI!PcUgzaoJ(O^s+<gbrrv4O{_3cK<1(HI@9h2sU_+
z63o6jl-q>IU@Aro*FOg_!WYyQs3q-Ci>&s5#iwv);bNvF`I_#IYMoZ49-j{SOp55g
zp(%CB6|60&zgNVHohiX$Lk~R3UMo^mJ*p;ta1(NKNix3U%Vn<z;IV{q%eNqnOPtr#
zYVI!XKr<{4M%9gdU8gL89mv^lvK1U{h&?M1Y1Ese*<9Zupi=O4<s7zOS`ATOS@br|
zEZnt0=VIi^RtjZAabFYUXQ~^XJr4)QHN~7pf7rV-D{ks?gF=t%Lg&;}vba&wn(vAT
zb?y$!=OFjjucqJDx4^a|qE_Uv{Y86chTM860l$!>4%;NS%?>ok4rf12-!o*?&nV&w
z&+J2HU7LbyjKh*cqd~fnq35_3TRU$aMBuXc;|>cmluH7{;-cHE_erw2QIse|xwqb)
zWf2^4am57;licK@1mDzMk-;*;z(s;t%<JA4t~zOMeVw8j-rm>A1=hjozEZ|KeOEaq
z|Fcu0nAZS3bxnJg9Tmu?v;dZ7#tkO9SPpWiaq8Z6GP*p1$<A)Dsk=DXJy+*qw)S3C
zAsaXsC=;G8x1b>8RcWj~&s|(H!jf^?kKPzzN<U*y#bxT?`vAl#=Qhig56+;UdsG=z
zc`BR8kkRS5bREGO&)9`^h4lnzOQAUSo*YUpFND{#V5#9_?r)S!l*M6=ur_@UV9MB=
z(&b%`;l+h5AWzm#EsI@y9MulWoZRH>Sb*eQ$Q1u<b>=>7DS~RF2k<&_e&j`bp9Mr|
z1?;2iEZj!bC{)5{6S5+O?Z<qg#S*pooU?TY6yW_inoadu=TWH~r>>FnkAL@dv8j~A
z_cb-2$M$>7{`mG@EVsD2Qt`#^E)zh?2yroM*r*R+-kD_hc$#_d14G~Wx~OSh5`g}o
zg`6V#<ow6JO5ku=S1L?#dkXU`aKO#A!r)@q{`}(J*?nu1H#!5R8xuL*HfJxpfb3k-
zDmZ-rW@I>I9K}o3jY(r?0d=6QYGM`B&{&44@d4T;miUnG`+xu_Q~LAOpdZhSFqMv*
z@YV`08vK7;fH-1=K+Ut*g;xY$LB?Yk#<A7P>kM#>;%u1b%bDFLyG#Z^h;^vgg&{TU
zi>f|M)Ml*YU%(r_cEY;Pfae~=mMo1}z{dVPXs8Ek%-D79<K-D?^+19`guC3M&#t{#
z6&}Jn+D%<aI|e5Cdr#9ReB>Nj1m@Y-^NA)XfCV42bls3rM0-amxwN{9{{z(h!cO|^
z2HGVmAVBOq*cj)muZyWMgFjIF0cNzW;1adDcg++mLpTg=!1#3zVN4e9p8kjGf9Fx(
zPr-bh#tWzlmrIWsYtRz-{0S~Ia2B4X?FeeE$?OKsoX>c`I52JW=&QLAg?5Q_y~LRG
zTSht5<&Wxr-|X)XGL)P-Vtx!uF8H`}hpq3YFT*|p0PsQyWBkPH3|ef@?)>O;S*X)#
z)Ic441yM}9C)c%j7i`U4;cq}Q0AvTlA@8UFojk@iWFr^U2-j>|;o}l<1y99Y8@5$T
zUe1G;>p!0c-pD72mU)I^Y_j(;=l}1g+u#Ll0V5Dn{C*AP$V`Wvh%4PeyIlNJbZ4AV
zsTF*5)^t;HX)t0um(B^~dHUCeYD3Y+X#wm1WOfNv0ZlpWjPLVH2O4K77rDv{-ul$t
zUW)>6X~W0KG}>K|kGjT8n%k*I6-@jY$oZo11eBacXYhUKLNM7Z*Nxy_J0Lzg)vupd
zhAq>stW$2v2%;Gw0j(lf6OU;VCbU!Glwi-1;E-R1I{yjl-B?cTS!4=Sgk3{q6gJ9l
z<=?TrVZPUx1ruTu%B1`VIJptv0T>wb*LH&4qJ}F;qufDKKG`puJS6B-8zV`Cqc~D8
zlno$5(b=!-BC>SWd4an}0T;Cs?|aGs3R;eZJ$|W-Z@$E(A-a7Vvp5-4AN-I(<M`qO
z^E`%h3Z_fbe?eP@=BXn{r-^rFGLvB-sB2&D0rV4e{cD}ro2ECi4v2T=`1g2xSbRiQ
zl}jel7nsx`#*P6FHK$f15mnYWd-=ahebbDi=D41SW4nF-%>&&=#A=6#ZX`788RbLw
zZ+$LMjuU&KwtV*%AS=xF<5qpa&wKsc#&UL`64-uvXRnzQ2DSymc~?dvDtAoNP!NT6
zV`?5Ddy_vR0#iC*@Ne*ZA%i6oRjuO=5Qk$Lc^~=!?CHH8oIq<L&X3i)$Gm8#uES2$
zUtuhL5H47Q(<GnSOCO5wrQPFQlk`Vzjfv<&D}Fv9=^-9$k?I36$*AzUZw!0#e}6my
z_pCRbNoedxXgD8eF@?HdFu1AZqdJlmYmocz@e1d;^C)}YNP4$<`fRy<Di^c8rX>OB
z9hh|RO#*s>Nz+YxWxe@uFz*fWw(mx7Zp*1kZxeMc71pyzd(JSzSZ{~S5D@M7S3~lk
zhUhuB;pWgm*`Mppb86YXzpqY-Bc~u?f3t#w${`B(0i0#@eGSjy`SuMNYI}Igh-S#3
z7wEJ2+9PNFp%TL*j)K3;)a0dt$$N4X-5tDI4d@-TrnkLYAvY4nvr)b+h3CuIn#f~E
zq7H2P(0a;S{4c_x09rl5^&@iT96E5Z>q7g+Lx5iCuE19pXiZh`wvq~-!N(!I4K}{A
zh$@B3z=Rhom*}4Mtfh8GKP0GksZxY&JT4gKZVcp`_bZ6bsT;DwLmUtYYxO6zDs4yf
z*ZBN<58cddRi}S&#Jeg|r-UDY7<ba{@d-F-wY~_ocn)miqIT4e(7hYFrx1IeLl<Hz
z@N-u!|CU^R5|M^_KFwhheDtPxLKe7HwO)HI+(v(XBJB~R_m_Ow`PDS7sZDlDuwN@>
zZouQ&)^$(d76KXnffpYj`2I%KM#QKls(0aA*)+<ae213v44zh}^75;CLZtTl%k#T;
zBqWT~y&nWfBbToZVKh^xn!B}$h0b#cdqI1x0N;bQExcklrNC?2WX%ExIlAXe4d)=<
zu|+6Iu(Cr)Zclaf4}d#*y?q0+BbSw?W|GB=1$%O8FCha88Zvj7LX`0UJU<n*4e35Z
z<$>;7Q}vjEWxd?z$Qn7cvZ*K4bFH3p9C_Ka*hK|Af?Qb3EVX+xEUhd(X5ry=3r6G!
z*2?SkRl0=a)oXJnIG_T3H{BgS(85A=yRF6MP*E13o2%Eh1{KOaizR312$q1Z<0=pR
zvv1RPB)yD^|IyeOnGTMZ9JQx^UPo7h=+A>hK0i3K*ru<Gbke2sJH8hIILr#`R3>Gl
zM!<s!gyCT-BT`3{bu5+%U-RO{3xTE@aRs`t#ec}O`kJ<H)>zD2o{jH=410ji3f3%t
z<iyqgTJ%V|AkC}C3pT~Fi014*^QVqWfNBG{Um!;Q*%jL0{Xw_q^te6fl|MeP=q~*I
zmu;&pZnE~jFrM1DQKTBBMA+5nuG`=bnW|UB_eDkxFR&ScBPt;~uRB!Dr!aT(7w9wc
z-G$9^0P5M&x^GQzuXK3@>(r#)Q%M!Z5wz#gCvX}O2obSP28e!ZU}E9%b!+jySO!(?
z07Qx5_XM8Uac<<y8m#rhGs>9zLi~%Lbvm|<|64?;zp&%K8u|L3v%9a(&$jsM4z0-a
zY|P(z3gXefWdr_%<JAvFn9_#5quwao?7a?HHXAG-nj3rM?=FA#ClqXi#&SDq(r2O{
z0y)bppC}#lCmmlGrZ1k0Ojt-Y)vhecl>ey=4q97L73V$(<D~HRR=R}Jp8C4g!aG{=
zYintXSIV3beO&L_xfD9T2GOnf&ekt*0A@3`ur!{t01*fWr*E0(up~$U#w!2s_l0Y1
zXCv*&`L6e)3Y-P<-`ODQL(Ld%Za+j7Ki_c|5m+YEx{f}UJm($mXaZ7+U64vFPaB*7
zXWDycBWKR<%OF1>{4YNc8T5z5Jp%cnkpPx)fck*+Vdg)PKlooF5l}(0s!kLK8>l2%
z@hAt6Xed@CQ0i1Aur_auT<3f(&2q9ulYtR;|1W(3`D^2gq|*ZIAjKNt8{u;OU!oIs
zxHx~))a4R5Iqz87O@I(x<KY~&S;6=WEg$s;8}0{Ej5OOF+8cP<+#n|E4L{!rAlgEb
zm0-QE$tG{%+~5k5Xc#-50tfw4S5wWJ`j+GMZ$Mqabs)Q?`Lcd0ppS7NS1!dYI4~PF
z9LxRP2NDaX2cE!K`X@VkKdt$iH)Mhw9*&$5iHZhe^kdp$Xf5roQ3Z@7L!GC-s>l=N
z2#$Wq&lc1ey`}H6f4PMH8Om{<^QWHC8=J@g_GuBJb*PGxTLiU2$65SeJ3>HJU32Sr
zklhN_Ji69)A&QYFkTDpDEgwh}Wy}DGdxFXfZOR4>vAO@tqPqqI0bh|1`s1{-x9@fG
zAMe>i{1Hpf@_#us%7yL=tU|_U=Pf|g8g$B1ihseDz9Onzs9T_CW}1w0k@6>By@&6E
zE&V+cVno0De>px<iCIay^Fv^w-Zy*>Oa?UH4o#B-1-@%aVAD=Eo*uFM#*sGX+II#`
zSm7D@U)A99V`g`h)>ND%E}(9NcA1tbS56=`Dy_Bv>gh|8)$!35Y0&{a-nc?Zftq_n
zN-N?Lo5mX=qpY^`<VsGjOAXA(SA|dJIO8fp=VxomL6VpsHu*!D5*#6gMW>`a*NGY%
zc%!a|F=G@=_2;E7G&L8qx|Te?kgaRWo)8Z7^@3z2TJLQlt1b2NrCW)PI`{u-LQs}<
z_O`k|Z}u*#F^@yLP$;yB?ax0z&>tw;-`_LAP4$5ys7x}O`{GK4H)tuit{#AL*L7o4
zAVC(?iGzPBj^#X?@VvyF)&F1pHy^-cA>$@{vhOd&VW3fMqA1U-W?D!jDCenJ?Hh6m
z>ytOhE~SdiJROMkjXdN`7Ce#*P+xBXLgu1Pa#ydOt9_bRU(1O}tEQtQ!9x)sqTCOt
zz0EmGhOLc&qH20>U&mxqsZiWiAUQiwyO-t*S`t;tPrd+%c5(?hW3Rid1>X7__)(CZ
z$>wIkuF@0O(gJm(eJg1GWJ`iLHgD!QwG&m&?d|ObiBom~9olN;vJJ+F<Y(EwQusLs
zMw8=mDYU!G^~)puwg$kA1&53za{1Vzd2;Kd9<NdST}78^mh$um!a?a~WHcp<r4;=w
z<hYMHXg8dT?gv|MectT5hKl~(4D!m+f!GCZ)cU_*>rNc*FgVV5#S4Mp5}DZo(dag!
zN@;bJQF+2Wp2NqLiCwYdvC-QHpd~rMUeuG-G88wOQ_Q66-lwo0LTA_8QQa`%2OF#<
zS%F@fi59>bmXHaOU7!a7(XzIyh>v9jPVlwr%3EEXowrgO&P8yW|8-IvG-xa5v8INg
z<Dw1KUOxLsvab@~=eX(3odEFInpH-tCWcfmSZQl=cpr!33q}WzyY#iN*xeqq|Gzd*
z7Tf>2ER|llE~ntlI$bpPqO=-H79Zjw=UymCx@t(raK>nmRr7&nbW(BL8T9k;^z|Mp
zx9#o}SzOUI)bU&H+zdpq<QecCV`z_br!4PN@wmK)#=Y!>l|ax1dQ}E|M>lri=!X*%
zwqK=~k1csZFZ=?^`xn@yWjcKPD^-!v*)fWpb|B~LG?OPppG2^){)&I?@>eax=$=vW
zF>Ahn%>?>s;>8XdSQR;$PKQsl^~R5RpN8i+1gLw(5fk-8G1M-bp0kV=yFu+o&jKz#
zFnPrg!=+hU?2{ct5P>eJN8(s^1R|CY9<yeQs@9Ovcf(AeTp(<`BZ16W6FQtA{4boR
z!t|CR8;|Aw>I(q@r;u5SXLe+$H50_u7<*g0Bc^Q&(C!g#V7O_k|0G+`RX%Wz*rbty
zSStNZ4yS2${h-VDs9d0?0vdV2tpYSJK(xCRp>>BjtOYb=MKaMY8{WdAmpUh|wJF{C
zo+w_NN*X;jS|%NdMuDdj3iK^eF1MB*2Uweg-eZiN_Fl0506*(beFyrXr+<|))I>SZ
zJ!~V5zK+!Z@%1!fK|VB<*b6#z<HmWe1G7LV`p?7n2N=zFZ2t{!C~q$a{B^^(4Ane=
z-8s?o^nynKf27NRJeamSR*mPI?RB101zprXzd~Sex+e9u-V#9;)a2&s5G&9ZH=?Sm
zcjlfS3<eTOWfHy6nGi=>YGicMy%1H$EAha>!tGuR#`Fl*jPDUH#*9xig1S5{gw1EK
z_rn4)&_7wv%uQUNhSqdy`-;hwEb`FdKNR3RQsfwDcSmZV<N!ibFk*mqspW#q_Rk)H
zc9giQTXWRdURHBm-la4rv4Q`&VOVfFX%sXb0rq?fVGBu+>lE#w#WFhLN(ykBB{6C{
zP#@B1@Zoi`WUqSh=C`JyA(haA_$TJyk|-lU*R$QkW(GQ#b_!7?Sb5JxOZq>T0}zDG
zk|VuBZz&T|<;Hgxc%2NA*KA4h^1v*0Pn{&j1Yi#5xeb70?}$*-{~IB!f<;NzZ4Zxo
zdyoWR1ou8S2bOp_w+he&X23;hHxLgj89<#kG2uTX#Xt$fWa=xT1gbNZ7#NrYZ0f}n
zXQ|1ceL6+iA91Z=2s{Cy?6A|<^>&I8Rk{ozB}o8GpeaW>@*=8rLQllCAknkWZBJqE
z?8cT}TP_3tlI&z7QnIC#nJQMKWBt^{zJPVM)20IQM!Xs3VT;j#2br53-ohQWM5**&
z0^bi!vF#T#fG&#_2IAAC2M%?u{e4mM-aM?>-S2`xQHf&{UXwhdtp{k(idwyvGs#1j
z`5)f)AFB0~qR;e!ch*wxe>NOfNE&@Uw&!*T+cpQNlWLq^ltrkf&-#;vSprC;|A}7%
zFr7ho`T7g$byVl^Ccsr&J}AuhdSV1Ds+IY$PFnk^TZs)h-+4?h2xGEmjytT6y3}tP
zXB1_jP8ef{O`Sq;{ba0F0}yElfxNS=-{f`#Oz!<J(}*o9$oH;A`nYKN%V16AMDJ}r
zW~%tpWE59Y<?aUPgw(>=H6^Oyf1vP#jV!$Jh0f_7S_Obu(h{nG+A5&37u?vcwKe~T
z@)>PpQGkD1GRZBSjYoR}=#vqK++)^+|I;HG-7v*A`Ko9s6@WB|YiSi#9(|znK1NSx
zc-3e#!!|#kLL@NTTO}JqI9;{lYA)ZK$Qe3>N(V+90%~&gf4JwZ>G6Gzlc-K*NGN`e
z48Y%YWdP*j>{*)LN>{LkDIs$|hypn8Q3BHfPi^4+xiNrw^Lms55BoqA<*gMaS_VGV
zBM(-Qf|OQixnXKPjzI7XwAjM<wl-gVDSwD1Mx#E;0Pq|zZM#(c*tJ?}HEO*B^m4+_
z?7`q?QF1KycFC43hjK^@zz+~FcHW4d&3<7sq&?uSupS7&@LeSYTmTTs;M?XV5s;g%
zhW#}`?3Ljrd)IIgxv`h~&q@~Pyjp_pw-hx4bYohNA8V?PbTY)r2{b;RC-}K8-Y^I1
z9f9;R<FxQ6sfA)Q%U|-z;&3xe=?Njw;m^yUvMa35fW1diiWn<0X5*CZ41A$>>r0uk
zxa(RN%V<$i_+?b<fF6JGae(g+O~HjM2Lo6cfIhbWDW=W0$YQP6k9V~I;F58akFc_-
zkb83UHK(6<5Wh#kPRRnih;;eA(Sijc9yhnaARM3)!JfiTE*r+KA?fUhssIKt1OAw#
z4s~GbEK3Hi*b1aESoGMFp;ZGqRBuO?syr!bMD8$ao*v^P_{Y9@k6NdL(c{v8!pb(U
z(WUg3&H*eQ<k;}#C2Eh}(ha%<_$}ILhT%zPM!5mUB;*06sfeKsExk5w!a>X$57kUz
zeH@IUEB_m;sF|y0nF??3)1U8#OJK!hL1xOCH$J^)VOZ2Nrcsz~-tTimFADaQq7AjT
z1zL*-yeCGZ4sE=Ft8su@$VG1kwxW!3i(MJZzDNBLvo>!2s6=iWoFM%QgXvEqPmJdC
z@A9t31Io{P<=Y_Iy`=uq^JJsnV=P=|;t+tGOB(dxjh58@HcA5!Wz%Xg^<{fstk{e{
zgDcT}4w=Q&^itYEzgC+58Z5l*c>_afN6Z?6^>6t@j4>Luj16AJXu!5F)j6DgN@Yi_
zKe>4oD?{mIJlM*%uWw=>Kc7$ZWE93FdTj^93P^11i#psKA0V03y15CW2{et<LEa|z
z$G36K8MfrX*CEaapQ&l>eRzfSC9n(|<srC@rvv>cX55A<4?t|TU~o_jeOL|W9?jw3
zJzm{wnIbtn2ogaGm7SOr^8!w&xYicKpql+M%dQGmsq~lkQ(FBF`ZovWrpg5^I#ClA
z0a}Rdd-8vd(S0{WfcJjgg{*$h-3+8Zpakmyic!yK&XB^osiQKmEEi+?o&T6m2t);&
z{q5umrhr$LQ-)^kfJ8;x*IX6HWskk}#x%VJqCo#f&g@V_W7f*>9$CYHGvlk|@()cz
zBuIA1ULDokd<ZuNlo;T^KGJp53mkNCIbZ|GRqP$C>=A8Wfzb_Ic}(J~&D1ALnqV|o
zw>he{V>xLwF8`BQfip@jz8`5@Ol+rTA)J5_9Kh({U&AaK)V6<K19pV+ZDouF)^%RN
zHxj4KS0&_Qg;|`60Q8zj#BU$E`<1tGpYPJ_rOz5k2-Y}HaH-T6$>ge?ntvetJu$zE
z2Vu)J&ANPxBmCL?lWvLsBeE$B3XZi1ZJW#2@NZwoXq0T+BBP^`GeoL9gD|tj@Um{k
zqo9P-7&IC;B<97uct-Rd9M}N-QA}F_wThY<^Fox#m_~aTD&|@OfH$*)^e-raHy|If
zv^Z$5Ucg?!wCNJR5gK`QwV_$&*>gw+e~<MeEuHYC_%N69i<9~p@jHLh4BP)RhO|_K
z`!swZI)ZgEjbd2`2z=pyXqZeHVFEWKq@yiZT7(eB?hHa=7HO2|rUMwzeH3aupc$1(
z72~3Yft>j&xrd_4P%^NV(+D{RA2lwXG|HorHug%<m`x;!as)m@YkBnTf>BL{%MXW~
zTo67kn8g9W_nWuJEMjYW$F8^c{Wk9&a|T=Qhy^V{h4pKWTqWH+_!IOf#P1ZaR@1=w
zYQ<Ja=`9XnHVs)+g&P<&0?;v&DRmGz$4xC)$dNE&#Y+{GCP?HVbX%x8!CNh@M0L+{
zuQ>nr{itC=12$BC^{dExz{h(e=48@UC0@*9q6*pOuhzEYWXqbd5a|CGFj2)XRyb`k
zEkG(DEy9S|<uNjPm_ZOO9kUJPh&(mg#m$`m4`}sRg;RGUG@}EUZvrNBUAh4|S`0bN
z(!!=u_+eF_*sN)5HV=4<C-2V@&8u;Br**k<-TIYWfpiqX^)t4cEF!l#Bvw;sVS3>=
zvhuY?a{wDF;`AtwwB@BT_6%@`2XI5lFg{>IQqV2AXs`T+mphw43`xKqNeb(sR51d3
z%!?s{Hy{@>eDiQfe_WVtvW&lhdGtK0wJ+j=>lzr;8kcq41HS*7-$rCR2qSbF@i{^P
zYx6t=x|~P29rMDM=!sfq5Q8O?;WpqXxmxlA9Wi=u`!@A1!eqH#1}k<BnUX-_f{NbX
z{LyiqI?UjYBw>@fU}b>WEm4W`F-Z7|H`7cF$PNJJ)DLdY6j`{n<bGHkDUSDQ$p2#A
z{~gE*RL&U`IaYgkvSF_>^ky6>bKF=GTdmi|OLe8*3*m@77UUK#Ta^!BWdE}$F6J!u
z$y*#>9=qvIDDT*%<;&`|brrq&Y*onLa3;tZxBN{6-@iJV<DYN;>yHn;37FF=XUXj>
z_nJ(@e!p1KGvth!xnQ@fY_!}<HM4cGC8?x>Sh&q2g>^n^3Y9B_LtA7!7~?VSbpbnY
z0l?i6Cz^6TtjZB&P}L*TmSh27)m5~n)1#~^Pu<v-DN4CE8kP8kcj89RNI~eKb)4-c
z|Di_Z9dIAXP1-ePEGLdYYmz{1K{p|Q4`#{Q!jD*~;F3tm@4&R>l7a+%F8Pc&ZHLhR
zp}YkI+>r=1*AVc|Q`-KCN>-l$`O{Q)!hqO}4xoag6Om5Bbbaa}?NFm05@e2xXjrl%
zd-Pqqi900De<xP_;h#FKB7xj|@T@Rj2h+A}E|sD2`on4hQAS}s*+LiFz_>}!Nqbf7
z6$tuNFZt~syD6`D4+<Jw?*}RBJmNPi{g`97lL|2q3a*#5Gj0b6g6jm&o&_>ZFf;BX
zcu}npzqbRDumYBd-<RorbZgCMIi`Rv+7XSm#;1z~mwp8wY{*1EGA+x!@a36XYmF{4
zSEI>_Oql5DpX5^!8O`}%2z)>V)%pcosqn4R5rk5LZ{wEr{3q69oKy&@w}iQCtrxzE
z#{o2)3tV9wo;}gNx?!&0yF{i$dMi`%UxIhU7-VirruLHjKBOehb6Oa2@xSX6k4dx0
z83`(d8UQYW@K)Z&i6m2IMV^q=a8XJ)h4rwKsMsy2*M(?H$R_K}Sa7wjN75BNDD^bs
zm=JTR1&7p-&JWxBa}|t_LFnkX)m*hiG-p3{IQmT@ompzQx8PZ%s$tqKMAcPr5yjPf
zVk21=7Es2e*81X$ADI{2X?fy2S4^Fw7CsNZG5FBDw;=NjLcK22$g~mZq+T*XS%HOU
z&iRN}g8Ov?ZkMs)U@N|qV1Hc8u~Cuj@PyP-HX&|=e!X`ZIv6<<k9cr$m75-+X}_jS
zccr}52b^kfr{&<aPWnkou*T|1I)vUKA~z<y9e&VPnScBwqR~`y@#q5XC_Kx2V%;N+
zqF<Y7)bHrgCuxAQPo?aEyU%!_!!$tQd*E?!vMOI5@WrpSjS#(=+_!>0tq_(LbbI8y
zl{51t!IhpI+J5_y_sW#hVrl2)_#@HlFZBQUYt}<1x~9ey)AQ!+qlYJLO>`9#NdkIE
zd2?BgW_k09@67!d&RtLb`|;!Biu}?BRjf~HBr@9ip}a5txh_L`F$zsK-3|F&jx{{k
z^usm$NY@O_a#(X#M!ByX+*Hfds&1(rX3x;e@~&xi`q)lAffXiq4BKQ-Hq!DF$#cvX
zi5D+MFEV>E-Mm;mk5js$np0a04idyV@jP`V<{TT-^jYuFDe+%VZP?M(UKjCccc4uy
zlQ%ZMe;M(mjv?fwkO6}>ITXcAs7*ScKvJElfrJv)e;*|_wj9oV$-<TC_Xkr4s9&g`
zd34`At)9iFjQOJ6p`0#JS6rJS_<T+U@8!91zx(vvtGAsjIRb_{5XF8loIe|gk0@|5
z_#sI+{!)-2n2}zKV5`v)M=I&J3BA5E_#Pf@#Fmxhm!2=baT||=kgpl;o?k`2<<Q}I
zpF&3AM(Q6GScg8mBKSAJ(Ma_|^(<C*<nK%Sh^@N)S_-x*V@-o!C0{d0GYVkak-x0-
zS3Lm&ImX8Ly8um2qu1!^)E&fckIW5<b+b?(tcqlHH7hefcr`obT;9j2EIGrpi@(JD
zhw)1M25R{k#@k$uB0lErm4P2;k8_LVzVGht9?yo3pXEcW=(lB3SzZ$#4ymQcfA6VE
z?TYV3_z$}b$6ueOxqn1;MX(Cl%3u1(Yn0TvO!EZa;0``8bwfy`I;4}**hIBSMT^)c
z;cPkVE-}9(A`&;uie)q0ReIa8=;as|^&$akW*A#w>3*?~X7d*`E!+T8N+Mk(6jSry
z(ZbMu<{*>)Epd2R*_CRhk__hn#Y$Lx>|&DbESBC+Qqe|c6}{3zxyx|6Se!?u=(n{~
z(ex_Vd##&OX=AsBi-hfMi8$!r`MO<Yv>~eZr*B>*r7SHcG6WH~9~q{Pot+`z?!=Is
z5f2b=zpWR;-p5Oh6nQ>HJM`C&pFq2tkULV|+z|X^OW_vexT6cJHWPCqDnp*1QOU7Z
z)@vh^RMI)z;@)f}Fnd9Uu{P4bG8k_mUMB8@(RtSRQpE%~?ierUWX(9@aC;B0REwO~
z_suv?LwbKQS3UNeN#oov1lH1^M9pKM)YG8hO8?b|zmMSN+4o?<869<mB;?G^K*;6l
z3!E;)_g?xBt^fvO7g6F4N9(bmlU5SHY_NIrMW0JK$<f#bn|{=Ho9;8_+523TLfa>T
zQ^vk<;&8(}Z0LpBQ-dP$B*TxD0aBHD?^dz1>qq3lbFLwG{L>WE^B<EVVEajS+mRtr
zFB*w#1XqN-BJvP~jD?Z`8cdcA?H)r4(n6Mt_4@4|uYCKi@ALi0ckN`0)F^Mkvd{AF
zXPn=7q~y1M|MxKcV>Q#OCVeG^Y#{_n%*h&zZyoA$rMe)7G$Q6C8_e>7i&)M%nt>4s
z+e^z26*t<lQFK=%OQw#!j-zT){RE~v_LX<oJAVW5O}k$hpp8F)rfobXjq)PaKcTW)
zI4><ZZC`#k@XqOB*?1fX0JjRPC9sbScU$sXnO}Vzdo6!QW7e8(<7kJW#gR&;-r#Uw
z<_Ng(l0UoqcQ6_HSx|p=)vmse;&dg)r2Lm;oO-FXuy~ww-DN)J3TPmt(EoR`%=d;)
z6msSXY1<!zwuy4Z4T}N80)N0j5aCPU{ureyn$w`F{(WoC+)?ChRSv2&yfn+r^YT-)
zUH=WNFg5+V4DAf{+#QW2>$UyY-;gs6Bo{x~9Ex>?@Z>b>D4iRjPGqGrV?RJGp(9BP
z!zCQ&-jAEpEwBlR?3F9Aq@&?muWJ$5_aC9DcqRu)E~}~Rx=*VC`k2z6@7HKF2+$@T
z@ms(rHs6*g2bpG-g$gJ-ie8oN&*EHsT63&kG)Nk0U-9C;AVFOCxZR1c#Ef%-V{wJy
zko_~;a34?`jo?|+C`<2|x^1pv7MYi!%NLDC@MM(GoquZYQd2ws$@l;6Iq(nFq4P#2
zh%KDRkp%zf9rmA7y^UX}+}}A?G!a$B6>ezMLJTymHiI<E;RgYs_$f-H`eQlko$%f)
zgEymZnMUos{*h$?z;JX++4!z4MWXR3$9)v>UdZYn#rx6=B$9vlEpXo;0eF#NEU9jk
zdpI6e&fEeEODR`=`$RnI3kL*yk*G(_qpp!g`&0dGr<2g9RMI`90#sG+4JXAJ8z(Mw
z@~TkNtzSI=Q6aBXzEQZo*+aHIhQo1ypu4sH$E<Thj1I-V`cyrZ0!`S{{y8l5%WBhu
zmvSO3E$e_|LhmqK+aUV&hLK!9trRQN=W*piI{O^cx_I1K{9r*+EY*0bci<7ktkYkU
zkZ<(;_i;m_Gu6!g{cx*zra|;d@$3UrIr}*{-S~Uiay#O8!1@Is6Ln4(CAwalI+gse
zI}y#atr0x2;QJl-*MVwuv)5y0TM12g=~-j415@c^Qee8>VUE<Vla30ZIMqT3p6SuX
z%xnPpTqxr0rjK*=JR0>X35Yn8WW`?U+`Bl=df&0}X~sXlZnpM*{ytt1ySY31{{k`s
z&HV?GUILyk*UECOkBDg67tqEejRQW#o*B$jfC(Jf&!V;DaTpH)k3___11!_btlv4H
zSz9Z!Ykw>kWmo9A>{-WjCNR94FE@k?6BEc?rJc4)S_QlatOs7%>v3a5H0qYnc1pAR
zV}bGI`b4=-BEwj3X2tfl6L^MPOSY8U@bTsWzNVR3%W*)nL8a^peXv|e8Va0Fu3?*2
z9*^qb%Z?^P-?<f^dtcH9J{;QC1Fr&`fHxvydr!ZP{vv5OFqRBqALqj%Y&<ZI{cqUl
ziMPlwwya!FyWgdm4F<glXrm-u+Vo1y`q!#*{Sr8i+-PuOxyIA`nV+G+C(Bhy(hguV
z*-q$fVB22T_Prk8C1;R!0`HI~-S2%nZ+H3lzJ`;tf1O5<|Mo|g$6@6fL59tdWc#De
z>!ak?KZfqlHulC=_Jr7%ffs-cK<Dk_;lTMhNoUp;j_A)fm(+QXb2C(J;<-}N2~B$a
z<q>gzlU{2;(EgUrNV=EoS7&BsW_{<$h&ZRNH<L6MxVf(PJ3v2=h}r#JM4ftasH2&g
znVHqV0nN<J%&f&YpqZJOnYEbitU;Ry99d5}X4VbE$jt{M$zQUDkPH0xX9w_p`SVtC
zlR?#{0yFC$TO#85y56kGn*{orHwl=TnVDJt@-0p?Gc&Um<A7#nW@gr69MH_n%*<Mh
v1DctcnOTc*Kr=HlGixypXl7<+W-aD_5tq@Qu@Sq_00000NkvXXu0mjfKLmu!

literal 0
HcmV?d00001

diff --git a/content/tutorial-stochastic/circle_square_dots.png b/content/tutorial-stochastic/circle_square_dots.png
new file mode 100644
index 0000000000000000000000000000000000000000..88cc936c11037ba6228fe4ad5ef7d5e9ec505664
GIT binary patch
literal 35350
zcmZ6z2|Scv{5CxHCCV-#8e8^dY-LMXCTq5oz0%nCWym^`EFp;uSqh0lHMTL9i6j~O
zI?Px~$u^WSYAnz3d;ib#zR&CP@e%jj_c`}D-}61!b$zc>+7&BPPWDsm5D0|xGTg`(
z0-^VYK<Fr}%-}Eblr3)XgDn_-Jq!ZTOFsIhn|NIx4*n<<ZhS4=E(j5hyb*dEf<z*f
zd;<N#ZrupJtrQgMRYcJ}1%Ze|E*lxzM?GC9N5{HEv>*PQ@_M8+tXY|qKAdkko{^-G
z<j;PVHC<TF!4v!C;-<Cl88q9o^pqCESwe+<jR2DC;nh`szK6!xcX#;&FBoZ>6R8!A
z=F-dCw67MbdY5PV2<ZL&SlwUvza`sx+gQ@WzXasp*a0#(_{v$$c^M9Yg0FX~Qr<^D
z9Zc8?Q&Usnc{WMX;8)w*kIT})@Ag9fzso*#|J`RBkBC$V_OJZ<X>5XWkZZ<bV^w51
zOjyswC*++G;3i(9KUqo>VtK$+7+TMZ)eNoQZq%d>MO=6oBf8{PKh*AajDt@Im-=AN
z40(7%XnwPH+$w3uzLMc=bF9g*KAVW$>IEYsqf;c&3+H&%t8Y5p{l7aEz{ADO?PK9c
zZ~gK2>p0Yq>5LLn;DeRF)Q`WP7TUm*BE{aAl2EDkDCw^G4F(iLVmr!Jb^yLD*Jbcv
zh<<4KfEtD^6+}HjIffpRwlI;?GCj8x-b|F0_F)q`n4?6uoIGX?4{4m(7_&w0h0_aH
z7c@Q24ZA<5@>Ey&B}&Ns`A&(~3Py?ysbTa}q`jM4XiOoxo!tEDN#7}kpy9_wXiNGX
zmg7*1&pRyAJ->IoQ1?;y6MGZ$u%-O?uatw&h?_XUY3Pe<W{XS<QeB;Aydci>V~L`P
zu8CSa(joVz&r!F3lGYL!kaW#l(gDq_G;=0XC0i-N>(MiC{xQBPbq-k3aS@Ax2cnGY
zR@%N-Uq;{=@bhf<=fxzSJjTWZg^awDP<i&r>v8`8<shnIgdoi&?Tdp1K}n;X!dn7e
z$x80d^!JzIA@nesPB837S7Zjxz$I!I3Y{=zD;!sZ&GKk-L>UD0-FSZGC4cf*AQh4z
zW%22B2y)_>FbY@CeDH`CorjiU<sEM3v69`)qY=*ynaYI5&9f5-dSOh9;Ug1xPRg9)
z-XRkdnpe(fxtfk{N2{EPG1v+;ar_W**NYgnKc+`Hxae=F*+Sw;GYvIx4D{B*)F$e&
zO&tUj+?i7v>a}9A>f8TaL>yS+(L^3P$BtyAKEBVRUhRXmdB=e2MrCtZm1a&#B(D_(
z4(@NqBdOC#kK0;k{mD8VfuvysVwPLlmu2|?D_At&pqdiA^jpQF4y|`=FH1$JO^K=x
z;@*<Y=`IXrE}hH5WEk9l-e7Nl3_%ine0~2-v_)^%1O{ZIEzjtZzg+7&u^3WBd7IO?
z=k@-tB0j+3{P`WFFSB}gRJXnx)=zOu>x4v0fAk9YKrUs>{~oV`0fQXdeZFfyF|8<?
zu$IUhW^f&blcl!xllO@{_mrTve6yqrD750OujM6_Fluw2x}0pr<mBXCp0p423!)Mv
z9>^1B!{NEHF}snlVS>NfA}f)jD`4f8>BxTlo>$yxEu};Mfc4cAw4#hi^o&O)E*p^(
zKcR*}bV&wupYLw(Gk7ZsIe;k8<vaL1SBfAI>TZ8k6Gpbs4)W5gP9h>jf-hG@=i`)X
zjCB88kYQ7QX)pKZuMzYoi;2~s_};#@eh!>8F*DQZg}xY*hYq-b5L3e(V_Qq!=g=-3
zknwtjn&(myFQrg|kksSI&bK3vFn5+I*O8qQ<jz$JjlN#S;)}A!_I-IRZmUdpi0&<f
zRuRz$u`@Gjq6mE#Z8m)Bid^2EPFzB1aIKYoleHv|BQiYPLh-f>S3W`oV_iu6mfYA>
zC;qf>W;`{UA%S`Dj6%<wJY2#jvhvBgy}RSe$b>oalUABVSF1k@#1&thEYT(51AVII
z3VE%Lksnz9Kzdx03Mcw-I^FdN2q4!~SFb=#+z<U`{WWo^!G)@kh@ImL$M7LbjtY^G
zU5Q|!;Cnd7aQ3S;)^&`ZH?XCcFo|2HyjgEV2S2%A`A9ED*x#Ea<kK63Q;W>S8dKqL
z32#p69C&OWxmoEA?Y>?0xPC~_O@tyMG968}YzaQ((=2|<lzfb4&GG_Eiy_6meFW>f
zk26@N7(`G{a9Q0u&|0+LeUX(jqlTQfMC>G@BfQz|jXpn<HXXJy*#Es^X=!Ok)|(}f
z+HTIZMO!<be{o8!ykL+LuV7q4Mj&Wh(zkkZ-5d94sAH&79F4c9t(o-#<>kv`sAB``
z8p-9idwBxYPp)i!DME#z>Whf=Y*TgQvPTL~TXv1yvH>*A>vL<wnk^#I#m;WbimT+7
zri#i1HFTTcE*hu&*;CC=PQ-Vj@LbsUd|nwV1z(mrTqovXJfcZs(dnHs*J&!|9Fm7p
z=e$ahXOFhdiEW`}?8#i8&EMh}7D{fMN-4U1(!78mdQ8_JVL%^WljFjjW@l*;^1`-S
zVyfQ#@F6-*XxgX1d5)Q&g`vs6oqcoFqCn-w?9I{~d6DylG^z@wl;<?xT=$DyjG!jz
zD`hjB+VBV_D}zj!Aq!$@XYh6SW;P^Ow&xR)o;<<78a?5e#>ic*?@(GMmD`t%qXnU+
zmO^M*X+~eZ+sicuRe!B9HspGpwW#{)7q*XZToWVDhIBm8D$);K3G8}wa*WhIKt6Pf
zEr9lfP)$ku^2s>EY;lFaBGJVi!~!oq0I?$j)9E9a;J8hVmK+?4%ZlUwtprKGj?*YK
z2<Ij3JBEEHplzSO@tu4uYgZyM#OTL+T684|ovDGjHLz~AAl((Ar`fe(%@BriCGU%3
zADt{L$*=iJLE+ptDKL=!VZ;v!EO`Cogyz$P35Qo1&+$-OH_(oThDNb@e8#8pCil+x
zeRN2#-P(B_9R_4))2Ch+{(w&#A9XpSQiI9UaESuCV7<kEB`cKp7dQiZPhIHkuN3Q6
zn#)4wo|k<<g=?7(@1#S_C}B`|;}?Y6$KRo-EFwJI-!w#{*$RCw4AF7#ny?8pXE&ak
zTq*`b5WWe!6%ex!O^~Rht-Ibcto#2$r;s63iO_pSS`IT8Drz`kH9G+dJ=}q%90Y07
zm0%RQz0xHl9llXB!>Cv^aJuKy*sZ_QzFo;|PH%)q$mBTD8yi&@pGHuy%N;inV*~!G
zTh<HeCi<`c`E<!qbXsFx;S8=W(9-P{kqL6mR|9mq{^TE?T%7!wj4Rk2Dz<-PioMB~
zGh^4tc53nW1r6PD$^%iI9mxfhO(ZQuI`?lay4ZA=E}UKBiO*m8#pj2`r2TalA%>jR
z@02yt{>851&tlRFHM$}aE~U}gXhl_wYd?Q^>Ufr~)iC?@m?mzRu#acev*NJ9bIP^O
z%@hw9PCtA0ZlmASj>5G!3(*UPUDbs-k)CrGci%U71&$of6kN<dKRhv^5xKKYj7Vs@
z9r$nC3~6vOiY1tPam3Sxt;@-miYDGeG?}0K%9pcxb>N<FhQ27CtmV-8@>y}h!C&P9
zA}#c`g_VS^{hh5qq65)?Cq=%l<x6Gn=@@@$39+klCtNr@N&7)k$DMsG<nm^w$krj$
za)SSAf$A-|bgmz1|G0;bX3_pg*S%v?4(A7LL#Q}ZE@55xf_$*rrOt&1XB58dU53%<
zwgUDyYV?kx^j-Y^zZHb0Yz|yk<3?Aqsg91$U9(=P##e>B4LTX?n~0sNYtU*ttb}ho
z+upm{+6|2~qnm=rplC2{R~21be{X>iY2sB1K5YeYIUajmM^&n(y*;iAkH=F9>x_7U
zrju3cJ+vsh$aw^z0A^b~ewj=rC%lH2-Tp#3WbE)pcrgSd`)QS@&0JfsUpR*SGU&Ay
zp0qkSF_HIUZB1v6e8@5_25-?}U|{&Yv!h>RA+0QS@}xHMeG-#gi()yVNXKN5kWbgk
z;oCYy&N#1hR?OAab)dbyU7qcPhSG<PmGFOw+P7+u2+jPhyI=e9S0zXSkSBDm6#dbg
z-qlb<lgPB+m9bMu<?8`;Sy@?^!JwZ={)7MZ_VjM}`QnaP404hUHcO|S5p4G!jvH`f
z@bRd_9pYTxUXDM1{(RHg=B7IWbmAaTG5F5;VmFa?55yEtz8`VnII_NPAmIPrUdw!^
z$|52o5#;@%dplZ~`W_+cb{M9c?bX51t=%O88#00Nl~Q^&R9d1BfiaLdT;k};DL*zl
zJ1dNEEXN)8lRGa&JsoG_NVxc(alsF7FtE-Cdo|NJmHDE){1(n%GbZMApHQ+y<-E0Y
zuDfi6i>-UjKZD&odB^x6a{cK50~qac-P2_M6m)wJp^m<e;lM9>wvJ^7>_S*tX}@6c
zcwtjh(+TcCKA~F0yW-bQB6TN}p1d4jjPzO>V4S7PK+O)U<3m5nT#AT@korfXJy8uM
z_vXY(<e9a1@~K{qt660X=zAo^KsoRc-~1zs*vaVV=s-(xyizJ4`h`lt4wxVOHvKBF
z@X#fMh&yUe4(6x$oOY(Rwl=0$z=AV`%0k+gT-Zpi;^k=G@pNDK?&6cRa+~vt+r;c_
z%*7H3FPrZabX{GYuNzI#p`wOYJ+Y*u<cYJBQ<k_wRBLs2M=3)`fmM}3d(_XH4%K2P
zv_=t8Ho1|2fbE&&BtT4YwD%OZsf=bRebA&c-KN}kp){lC4@a6?7b(<lRx(jC!D}kb
zCvW&<brunch$iFf41A>h4CC+wb9eXo8*iB;B5GGbtAm4se?VldN32b5EKo|dFr`@9
zCdv;bMqlcLi`*Cl*J3)bt|vGZng`cUcda}MNWp%SS_oeVpy)3VEORVXF<Q1ugTb(v
zFpI@;b!6u;?Sd`R%wi-YkS(0&^rv{+@S@j`Kfb<>Y0|{x44xXyz$J*+MOAd<#l4L9
z_&~_gJYPX5u(${DU*3QieBOtb5d59HdJbi>g3SeXRfF?!298bmin#|3+gd@CgF<ck
zY8I?=k@>)SGhXNd%O&$L3#NGH*hzvF81#M-#3dnv_`NKO+d4kQswJoGv94i}hTr7m
z*N>Sx_ktI<oU1I0G-c5iJM>g~$D>4>1QO$NrETv>YUq58HKQ7SQi2r85ZsEJcLvQW
zp|6Yd?PFAR%j=fR{GSGZjlYBGDSkLC{RG{CKf?7wGfwcg)HTglKX?O4t}-OJo7wpu
zv{|K<kX9h68*JwpyOy6_ed&%f4!VM!uDj3k7p(F@IX9X(m~4kP0E=b46wiS)aOp#T
zI0JH*(Y5Vr55$YHvnC6a>}5?J5tC~?GQP(aTo$YmnuTgIk7SU_|B{7aW3t?jo;;HB
zuD16r!6_q_%zg`7(8WJ8tL(6;xpwMuAnyg1Mb>YN-K0^|YkhkFSvS0Xf7!LjAmPBb
zOPT53FMmziTFaMeN6JA$vR7;geVYnFF^0YwP1G9juLujPgk&2W>~`a~dvv=A>3UM8
zr;IN1G<d50WkLptS&AVI<nzoj8%)f8c_4yV0wwkY^hlJtS8Q64-z~VvR<m`|zB7kA
z^d^Sjzmmjs%pP*?1Vw*=VgQMhcwH)>!Mw{JT#s(Adi{RlE$QFN%?=~aKT<}&_+yeZ
zy#}AkCbM<D#L}X%2Wspfa48Quajc!!P1{)s;nWi?xWVMyM}3}ZNcwr@vb8Xxf26(p
zDkEv1NNQLf;pm(V6I{3h!wnM}=p>j8xng;*Il|pxv}c3g9>?~Sl-0U-9`Kb78!*~|
zMQ^}+OFKf@QRQcSvNPqr&e-O~1xrf2;dO@Glt$l)nz2NAlaX(g;;dOCERKtzw?pQb
z6`;Dx$Tyrt_YMl>8zqc?tgJ*UG(YfcIL*{?3aM+`X{Oq9-TqmhIP0m_E4MocuVtyG
zU!)f@yGg%J20z9fHsek-TNzhK3Mjjg=0`_EITp`7D$-e^y#Qaxo!`GnwkgA_g*Ymf
zrqFfsJ@rIb{|>$p5m|!Hln)C3Q;EaTbh|_w|5_~@jE|3pdjcKCW^JnC?PI9nY;D0H
zLUT0w;iFug@877&c6}o@n8dBEZ)Ea5@>`ZAV;KemgIA5sdj|&2O%T4f&@w3<kAhKu
z+VLmI`=7$k?^B|;zwcwZ7AN_Uoq56Kcr-_GI;@M=h@y!}Irp@KZ*=ANbxJ(P)|Paj
zFeF|ja(#OLcZ^awzn^G>5DcLX7F9qPPE*UP;*KkQ0r6+@*vanwm=3|+r#QbS5AE+^
z!<O|g?;1ZZi>S6OAW4^DvCw7%`kf5Yud7|%Q@MC*1ikqUH8i0f*V<a=28N#-tI?su
za}eOhMiOFt{|;owUb#~h<FBvrHb|N0b4cd)Jvkf8c`Dh<*DM*`2w8^h`9O~ELA(d}
z8~M23lQ%UmcM~PII5kg)%+v2GZP~zR4{!z!X(#<$y}Xw1EHq=qa;6{OOyBN+(oQr-
zK7WQL9^gY$tOrY&^w%k{yr*gK$2c!?oYLY<!{UptbEZ-3?^*hV(W(As>uiNML5HtB
z1bYc-8OQLQBK$z|?6>kd$=7~6MZZj>p^YEOn~)tkrPJSkttHBb3bWdiu2!&rC@ISX
z>E=G->W{kjUPXn4@u$3W8$T18=<3cWXcGCbZ35b&yQ#;u1ao4sG<ixqy$VBW399V|
z!~0r9lO6FcZ%!t7MsW-UTMwya3Xeb@j*_rpv@coJlS_jmG~TVb8%p!X)|V;EJ~!%9
z`JhO`YzbcMKDJFT_zAkbzRf1>lZVu~)oKt%&@w+hR}x_mP$F|PZfk%Ub6Ne0Hn^}$
z_=^jolsbk=<BGFbJLBULBAM=D*fx#eJalmYLP`g7-N@wXyTdII4MapFebId0-v_va
z8t};3%JfQs0%8=5#=QkgDJlP}8(e`a{Z3&LRfR%%z5z;5$|Az9%Z()&MP2OUffd<P
zrj1UyzP_#bycLI2F42qG$-C8?rAH(i(C-N@-W>Nzqz$Z3`Axq5+xOf!<7%E-maiAW
z4%IK@^okWoSU`00jxOiPxd_0%#i^4gr{~G@5Jt*DJpd2O05-n*bu1q@k3huGcY6F7
zP0wb)6%l($?bELRppRr`NovwCXJ!%D%N2cOg7f8aUvWevYp~GPzZ**KMp2*s7XC7k
z`tyO1&s!&dBt!&VuZ~*14uI+ax$}4|SL*4iaTb?R5^3*`3*CIpEyMs`3k74<;^b&z
z*Cvt^uJ7PiAERB5iKxC@IgXs~wEfA~O~_(UN>d*Sr5fj@R-Jwv&S+_ZK$z^BZaH(1
zE3wD52grg?^i;TI;m*#p3b3^sOP#NB6VU*~we0NdSPzvNbgr@&wZ;f&j}Z<y_P7dE
ze*7}(S{cORuT%7|q@6SeFd!h~`}gk~N#ZBR#>amrYt~(^JZtz00uwgh?G0+_!dOE}
zgQ>Iq!g;BDa%hVe1poMw=4M92tu>I=N5ap$=4o({_XV+%0YZzTk2xP~Js4^ytY1Uc
zXDmq}Ef&-8UWD}p6bdDs=&xz6hITpb(h8E~rjlFRwH|z>e}hgHf#A=+r32Q`0ldZB
zt`7~*^bQEnOC2fIm|=7wO-?q&v0Y5Rhcke*<*HoHIM35^t~tKxMPp-Qd&uf|bw8>U
za$hCf<W`W!!G|<nAWj@QRVX|z%d@H5{i>L(^WwP@<T#RA)qm=7DxXvioN(*M{X6<j
zg!T1;?lgzM<aOTUa>R)2fFA1!mwC)Osz)-<Y$G2o8K{NP`_&RhGlGU(0{Tos9|Nx;
zn-j5s7>^I|*L8&~-ofyOdHL)-F;L@{wFjR#7VN>Dz5APhhP}GeopS#>PoO{srDgtf
z%LpMwzQ%RJO7G8j8YTW7E=Vsu@GEJ56hO^lbAbYQ7Egnk3MQLA!Q+S3z>~ys(*E+d
zY%`;De#ZBU#`-t=(|Bc0bD671eWy6mv(U*)JdtLYDj*VmnL4!m{MsucbnxKo0QxCh
zaxhKjbk12RZz%+#ihEK!Bi=loPx})&NFnA5l;;>Mqhwdrm!hwib?x(e@*(^BiM?~7
z)k3@RlsA98qqAzp0O5cfR1F_c4$^@7ruE_EqfcCB!)6}{g#`aIZxWv!mTWQ}52kh=
zy>Ob%h|XdduGKFEXF%5`+;XR&AA{;A_{T<<pDK2Ai~c5xZ!*?}=D;Nz1T4+W*qqpw
z4zyj5$NCiX_a|N=@1wywfrf-pwb=(vvai+L!45Epogw`_8KDpyp&@o64=x#*xu_cS
zU{MGvVVfiX12Sw&(pI+P_{D{5#T??cVubY<P%+gvf#lZNn`|!#r1p8TfqB&Q9WHF_
z*)0~>?2C2OxA$Zj0UFSUMNAc-5;jQ!60joHy_C#sN@8%#zje}$<q-o<sBO8ElM{vU
zwCoq|PMyQOZTD3960=XDO$V|b0ZXI$_(L=?@>{m=7(fa)OSu`}+l739s_{s9tEysZ
z*^s`c1+Wdw+8@cCb_XwwDjxqQMjZO0$P5dwwZB&LA>G+UnA&)-4Z>SAUwQ8$xMaQ{
z?E%=fW4@#sdrF!O-}FG#v&5fhlL+<E*jgm*gmYJ4LR)<2SukY^-w!=sTvv1=8hL22
zpoibiF%Oc~jVSY-^p8Ly50CBIac4(GfBBH6^?^V8Q}E+5{yxIog@UKX@;03uB8!x%
zCkArdvQ-BM2X?5~HKA5?oL+7pLH@Qy-U6kc4H;#kWxWm|c_M=36YM4anLHC6@DKFz
z@(MR|l)P#-obG|pq1WO*{`JHTbW0yFxt>m_+WBLGN-j^Vs;t#9xrzJ|<R?0bd#Mx(
z#R^INWqeH^`^%6879KFygy)<HRksJ^k-o*VVV|_0bvajB@vI>nDlFTYVqLC=X@*SE
zjWqIG^GbUqfaamLN1Rx2pg{HOqm{8LF+RrkxG=x^e*^0w$j&+(4j1@BU8{#Irh(~B
zTtmH=QgkzI!EG~4Y%xue4T2EPbYh<{{qCgwlbI!#&z&`tPegB+w47Op$T2^ppIf7x
zc(U4VeYE(Fusl?-`zm553B4cS;jutPTbO*)F_QB?;%s=aFayqhvSR`9O!DQKh3hG`
ziSuY;PM*~$z!!x8ti(qB`@JGc(PueXy=P(&YzWQy0ie;V{*%wuRiwPjJrOvrtf$7g
z7*jUzZT_<ZgBX~(vp)UST@)}2i-id}G9?Rl3lZ1n8Tx*v(QjGNsp0IMvbR8)#nS8$
zkt)HQZ|2L)b6GQp9aH4ZI*agUE*JMVh#0R!4?=-zsklO}`T)7NkjM_h^%3$1L28#w
zm^C)JS>()o1JR#&i&=xbOqpmH#`uSh@h31wrn~&p368RG=(!KHksuj`_@W_n992t0
zBQ6T4s8Yf`xidEr{it?kjoJ|E58@lBRIdE$9sXdCrP1wVnO7vogO_qcM`C#^`u`)A
zUz++o@ISkeckYG%NEf+qWNEz~k2A}A+St@YfotD<vWfbP<K*BV4bRP;7G31!u4Y9h
zFlmF-9qJ>zFhe3Fr*b@JR6Kz-u5iTsyy=*jKyQkTxh#h&LQC<anWLt%-mM)s<Wf*F
zwtzzK1yddHBY4*w^I7gdk?Ci9Hfi?CQr<;35Q@nX*G6g=<yqIB=B>A6gAIwhY<Q89
zEuGs}C?Y4A^KXgLj;AI52%Pl6M_^kYL6dkIEI*6J#!FqYW{slPCXf#uK2uL5E$l+Y
zey&`j=jKjJ!*yCjDU37ZnB#aT6jJL^V`5U?5-OOt_;1M$Z&_lp-V9z>WszJK?mlCz
z|7BSF3m1@cDQ|vBup&E8H0cD#1zt~sU$RTm<be4x$6wx640`i~H5WrO7ro@@ICZUy
zsi9|DKkJ$i5MwFwY*jkt!moE2;{y<1@9*&Vh}7KGY-7UThXx!<>+bFi-A+FP5qSeG
zQRT8zfI^v8e*BnLVomaa0RCcZZ9VjAEt0(djFiTZ!02Z1au#=_ciT};Ki0aLvs%We
z*hLtGSY@i$)9L@9j3|DQ8Y2?XmeRS_yp&+M@z1e=h5wu3p4OfrBR>Z`h!SWSBPdx{
zjZKZOVNp<?PCIM8h%dW8zdECM6SV@oL2&{gXcodc6s8k&u=n>BdEXGG^XSck5kF?V
z@7KDvb%zxEwxA9d?VjE(Ail+)%lWRb#fCh*g#8*q6;6-+5K)9XlV?_}8AximkJ?TI
zdSG4hyeE=Hf0^P4VrOo0Zf@>jPnxl3I8e&of9=gal-Y`4mh!sW)<f<D8{%DnS6Cn|
zG<Q}n#pk^f5nvx2HBqoFeq8pgfY^bz7W%ij1k{9@J#M<-8{BaW$iu&ILBI`os_j>M
zDIJi4wrUnMQRl9Biw4@Fqd7IosA8}Z=<uQL3e5vwcQ!!HN$gSI(hUeDUOpJQ_$%wZ
z0Q!1(UmBcjm&9B^w894^{`jdCM&8Hqv$7>xNQdcd;plPh1$~|enxj3S^BD5}l8tT<
z&sM*u+BuTeO>UoHu-*%C?#vHFjhjOdO%08We>lP8&t0lgFG|c9P;knyt*Fz8O+p~*
z&*(~t-%%g6UFiRo?R^UX<;C+4Ms{No5)OSNTy^(<kIi!sWW}G>CT<E2TN|xDMMu!t
znamE6o2?{yT<^LKu{>YavZ9aoLyV<^heoQ0C*{A2XyS_sTN-u6d)3^aUO^(M+XDjw
z_aVq-;<tPN%en=WT&8tKIYEiV%XXJJryGoW2h$FJ&iU}~XfLZs>P>dP((#cIRiEKC
zz-*yZe-@WKoha7|iiSVvGV>l+l=af6M6!<Nq3glR6fGo$l&7eu$bzE@;m0IMJIV_Q
zV1qsG`o`luOhV7^NV@5%TMnk)N?%ci{*fvg=y)<>8DLVq6*cg`y#Sg02+aL}s6`3`
z{^x~;*CVru?n}N7>En$i2T}$Z!G^0I%8<<=2W*{OadEL9>MzhcSDv`X|1Adf4N&EE
zg2j9!P|T~w`nP58smA^LT}^Qtw~?cCn5ym@S9G+{232(t<z6i`IT%emSVtvdxUxKv
zLq#Wr%2(~gi7rDExi5HCMC%2=#u;2gJ^VFEBnm;Azs0*vkjcfH66t!y5Liat6mQN)
z&1cgrEwm3eW=d2r<%vaXQ~1CwDVQ^bVxYJaXI$gZZ5dKX9K_#F*14-0+@;}lyFTJ-
zpdnWqU-vDyBWPo5VB&NqM+=s5`Y&T5Zk{DJ{f+cDj|{^4Mo&jQywUe1qaw0t);5Kr
ze!iEiTzdh2`^f;J6mnJYZ$ZuJ+k83iaF}TpNuD(B(nU%q!(gg<(B&wEmyNlmQH{eT
zDQ`SAv0WlS3*!Fjf&%~B;Ki;8eB+TWQ};ktgu9vnz>Fb$_mK>nKqxghoU<f<rRZ@e
z&b2cHSEDsJ$BZjpXb?`R!)QEPX!th!f*n@$5@$C-&3OI8UVp{q+;qL98fg&C8vuIl
zL{g_1;_#P_)E`kG&H22X7t9$5L0VVZx>DSRS7a!sU3qmMDf7hlosRuY;>J6oFvp^U
za(pMaB)k!k5H45aPJ!JPoPj&)q1+KIM0k9-Ri^oDo`CqKDK}mVpz<vcn0knvH#lXc
zL6&%Cl3Kt_LzP{%y<-I;7v2q~+dvB=Rlc!I=~qKrxb2hTG`3V1zJ02!N25O<!d<Ir
zi~|HW>lTWFQ~9zz^3aayVhuYbo;|q#Y%3$a8oN}dGyuq?3!qV;LO~##p1+C^Mjkq8
z7PTv*Ehr9?5aXHx91Ubl{oWs0RXE>2s}nNc?V#Snv^`$!w9KJ(^@U!<&PSWJX1K$v
zHAY28LNME#xTR4lX}_1Bwc6KH4Xptd#(f-(i9_$H_Nvc<1Q1DCZnM@xL1AEI9I!%p
zSjOZ>;Xd_+f3QLATT`|lrEJXw07_W>*(+u+L--DnC_&J-ty8=j8X97~e}3sHS7N6C
zQm|}P*i4^~zCI#lU{r$&pk!pA6&aXMh|Vulf`nHNd~YJQQT7#oBNwh9-5pU6Yit80
ze;m?@Eg1CqcjA;;l-!#G$<(8UYHrfy8>*rA*tZ5ocEYHgbuQS@O<%Vs2mlk_m&f^$
z;`+^cBr<OdK0RkQS?f$)1mvgyXN^Q^VfgW4N#ZTftEyzqTb`3c<U{J{vmUtotHzbO
z5HS5fZI^Pn)cjtQ(veX4MK%R3%HqP~Q}T^666PRf9Z>`p-5LBQG3xQwbq_J5`*rlo
z8h0=g0)|`-7HG9^*gNiiO@@F+e<X{Y(R~;_PTI$S@Rd=$&o3<HZCigtAZ4IcT##NY
zO<9g>^yOK@T+8Zy*QeN4Z9z;(Xg-sE^^*S>z;UNMEGxgBtrBO|zky&<{-=e>Mb%gi
z8?ENyIz17+Jatu~20uoT1M33Fgtm*%()eoKrpn@;JX;&=_(svXDlSkRzp41{5C!uZ
z98Y}=XIjd?8E#Zq1rdCuUpW4*)f`xVw($?(+phR#Ij*en6d&WAph6YkDtT)JaLn%U
zts?j=?qn<T^$Nte14y4Z2v}Nj3sK0;`U`MdhA+GM#c;{hP;4Sx@l)Q)uE?b!#{CrZ
z2ADLX^s8EIPIVO@dpKNw=*c^3nR-fgpB~j^p97@bNFgT`Zb;g{zToMxHQ210Y*)-H
z&zlEdT$MItXiY?#%;aNfLvq{?#*ZTpZ{=iP(+6p~<607TP7;=;k?f^(V#g$<L{h@`
z&nnaqhPf-$3jfWvaEzbT)YpQG(H!;X-VTy#ev8A@C_R_)K)|O6J-Z=m3-i?n9~S5e
zlVYitU{B;F@ArH*l4|q>l_`0!Lrw38bh&mzZJ9`Mii<W^Ms6<6YhVK8xgNm{!Ho=q
zOp&P#14ycYJ@jNX&`+fo1LsG6AgN!&8owG<n6=PKQ5fjJEM(b1TqGxH9BgGpGf#zl
z+>XcA(l5d}!S?FM%*?FsiD>>t{B|387%ZKOt*$_&!Jnz&|Kv0YA$D@i7$wx4G>(Ex
z+e7t|^)VnS3bvKNPfY=Bx#T*K)o&ms>Dtu00_cK$xENz@tD*fqpDamzkc4ANuGD%i
z9M$24aCQ)v%(1EdHe=~UhcliT?Bfi`;PYJUy0?}Xjqw`Nug7Blsw{{inrhMQfVW5(
za=A2myif9y6Rk@1FTvHTU@+5BzT2GmW|Z<(X}O%eanGZ9XYevAJT%-DD~6ARrp;(z
z#ki|omw8K+!iLM5(1^%toL^d!eQjaU7j+EdVixZ0-9m<iZ7f*_c+&8%?21dhzPc8(
zE!;<F#_zg8^Blw2PN@iMtBmf%Av>`=?}33WB8<wC7@hN7i_X37f;Kd|x*Fua7Yy^M
z>IQ7FmGq0?BOAK{!3h-sS?G=HX&y$JRWEqdyBZlsU=tlbD9Vn|lib|ZoRp5NU`H>N
zmsp`|{s_x%VElSoco~>*n75w6w{KGp*33RgK%tF2WWX<m)TiS)YO7>zLp0uIj1ihV
ze*8lTqQ<~N;9DfXhMtn<=M(te;BcLj1UKe`5g<h$S&K^Q!egPf)IrI;cLotxX0-;^
z)sP9#E~=(+*zmHQdU*3kh?Q3hZq;TY6{r%mg@uKKp;SB6PY7aX^$)-=;vm`6$DS*;
zGH`pQVq7tZjj2ZuFz0jnmRyXY&+PbZKJoIOtQBnb^p8~ad4|0T5Ib~(+Fu{I@}_+d
zrIbiMdCDn4_Y|T4cB)M!_i*T_H?S|@8*{!Z7ZPXXxB;`S0m1s6o);QW_04w{o@ZWZ
zJIler;c}^^QcrBQg%$*=lhm`fU7({|PHfpMq%xr&)mIdtm+T|JJkuCTv(yhSPL%rH
z#~nhZqaTx{nGJ(|9335NE#7CqGef8}l$cTB2`$VCd+6z$mmn7@xRf<O-WU$}u?j|+
zal$KYY4l=>Z)ky_qAT-3C_5GY;rfN}Tli>%W@Jl|@#pG7)3a8PIU%2-P0C@7k;=Uv
zKYkPx4j|@PERfU?fQVMaSp!#AR<N_=_R*htPF#$=oO7&K62B&ve&o%B2cZ9l0>p$t
za|#{}AlyYj0cwA_B!(iNm-VUySXmG|mYO9qu@Z}htH<O(Qh6!Is}A&-T|~uSwv_yt
zmu4Fq8!=!+p86q7bA;*CVI)ylIVhAr12(EgpbnVJi}+qf6W<%_Kc7B;YE*$smk^Ws
zfB`U|UWl{8C3${Rsb0V|lu3yX1fs#S(U8fUZMLD+*tN1ID;Nz6P{FeTqngO{u;VIv
zqmeIg^>s!n<vAA82E2^#ixE5Vnk6No>)`IoVC#woW2+}NiF3`_Z+;5W^y6z#?&?rc
zQBhF+Svo8v^5b!d-Vrne(m<p|AH<IRa)Qq1k7NvfCFgr>V!b0sHjWOiVCrV+`rzB5
z_#S>%FM9wzWD>;~zW!PdjSULg9IE{kjhCBrUuU=z6O$320&n#5^P7bh4Y-|%l^jx%
z`TggQD=-TYR4X66vT33H!B6CTw<D}~f^cHBzma4Twe?rvuA9!onjH;i&@(&ozSjd?
zU(H9^%}q`5O?;{jD1PIegpiTv#;<Os8C9gCiAdILk<UdqG5wG)AAZ<!$+`#&Csg~>
zpO@#$fJaDqBQ%S*RA%4jx6lUiQoYncjjEH~|N2n@>kb$W^2Vu9>RS3r5Mt!wBWQ#S
zAU>knSUjbwxw(0h&r3J+Gg%Cxl&UV~hrl_4DD<6`+;Y$?IV}QdmE$v?Lx9~L0d%Hb
zfuE@x|Ni|u&JZu?Xz|xKC}`dXXed!Ioupv${Ivx(80{7pW9KJNwFJ4}M8GEmSq!%(
zNH9}HR{COrGnot9d<VCqU*i&(Gk<^h=A7L3D@A#ht!t<(+d%>9bIkz;23?0<#<);9
z@<?PX96^JPbCzu=RQ?(l<Nc4kmhr8vtseok59eY$Q9#s6L^9~`D6P*=k#iA|jzC!k
z-0`6G;@mC3OS5?>59K~=s-Yj43|COFv>f9d1G&0ur;2d~ObS`*3FCyFS|i=j=^AN6
ziM@QasEXT(TeB95(;d?+1;lY}`o7-ks*>|>o13Y3x-<lfgvsZnS(9}B%Nxg{>+|#T
z&*8nRUWx(pgTdQ}RNiVSfthEYdcD(OZu89lnA<hgFUs;?;b$vEZ+sq>D2`vJoVW@t
zq34TJdWq)zzzsjWc?(e6&eUMxgpNp&lP6nl0?UkId0gjFSsl<bF-RRyw8-FJn@%mk
zi(%z)$~jJ9pJl7m8G0xm6udWHaVR^|{B0`!{veIqh2FN~XFGMH9sPc7agt%#{%pQY
z7`69Sl!eI9^lN~et*=b~G!Fs-7QvA{dI(h1cEC=TO%F@#d=NZ)i*iuu@an3l$`Nt9
z*Om>hz1|iTVsI(@)G2;sg4&DVC4*Mf9K2}t`Q_^lv7ofjp0{;3=8aejtsE32xSRtT
zC){IVVoK@U+<(9T0@VNbP_wcCW6`M|v$Gzg=+dI{@4g=<^tNq2z4`3SOr$0T6pNei
z8HQYY61kwloZ3>6zO?$UT{ud4vG8LfzU$N}Zsq1#)CqwZA|WtCRe+AP&jfRZ#0Fg1
z=0-%O;tt&_zdZVA`;#$q%eikMr>zl><xj5^2UO4yAVw*~q|<`L=@Q-OUy5&;H68%F
z8^aqUclPviuuq@$xU3oiaJXrrX?k>ueG0l5;=<=M_nz#yRJUn)t;VDDlb$2J*>K7Y
zggL2w0kn{j{Xv<5K<@^7xl!~WFgg|fUhaI452#&drKu+jk^KVG<$>=}II0>?2?N?M
zCgdYb1ep-?c1Q)I2Nd4bY_upR>BI1nh31W(bp9t0DnLbp7Sh|Z+Fx@X;yURoBnDWD
zh%q2BsF#@48~S;D{Y-m>I(nhAKoK1(BFdmfq@6NGSHiI!bV0n`Fm^fYnLh)B<BUp|
zj!l~W=QY8z;X6%<jZ*}xx*fZ#zNCu_M7VQ|6n)M|ySIRbT!psotjACeETq1qT>|t!
zf^u+X;ae;PNj(OL`Sbg~^B<tU@lPSzPIkj8IxJ*#dxI}lGE_SNa&j7ZsC`NBMfOrO
zOa~O(aKkxTeRpy7(5I^+>u^|%v(%TIkG6f>4P(<$G0_H#&3T3SeV%nbpj1pI#9wSF
zQTmK>27<~Bv;_ij?uDinYtn+4s;<des-zqPhtm6B(5<ktykO5ClHytO?X5@mo>Aaw
zua-4u$v@7)u|7s7yZ$j<m`K~CtLL~AaN*s>w{V8H1DRPxL^Vw}naEO{;Gd261ZnR4
zyaL^qf1$|i63HuLGqbZYjE2FiZ*tL@oJk9^Fq~Ae)sxDKkHKIA=*9!sc>;ilrc$k-
zxv`Lsl9jjrj|6&gC{r{r7td_ff>>Uo%xQJ$J-QF#M|f*doHY`LsU29yinAUt@14)>
z)3smOJ(Y>R&Dt64KYU`{W&O?yDZ1Mfc(A(3e(&ZA|6hJn82YHnY~zdWz06!#Vu=}}
zt=abSkUOV~!-_U@81*!aW`!ar)PVq53`f@gwb}B0SkyZH`}QC06T3Wze+eQCvD~|%
zJ<vz3jynLx_%S0)3xk5GF`q@vB?>{1GvR;Hx9ZQ6NG?~NIr*?Ykvo@r=NsjaK3>S@
zKnzxNEiI}-)&3^u3`du7&t2nYHS@Ia$jCYw-OCH^<v*Hc$Og~Y57m<5J*+D4a>>4>
zd|H#mFUxVKs;8JqdRG~{89-d@P}--io-dBq&4I78xD@qnB(NL@_1~HjMG5Q~tuArf
zX3~D(!bkY_3ikS$oasCbzzMn&_n`yZ4!u=---k*M{m&QckCNxDucgHXvt>2nK?D*(
z3e^L}VED3EI>cM+nR@yU|Dh~=uN>EX^~6xGgOS?4A+_+S`;Tn`{SGxC0B8r&eFVv5
z3;WqbO5=OA8H>2Bbf*-l?d@z?Q)IgCft9EBZNR?#1s51{zHheBf*ZRk=-JOPx+X8K
z?Wc{4BB`V^tAZT9@%Pc~W8}@3_Aa)ipU?IDJ*TNZxiX*31Ti);^6fF^&^uT;md9$e
z>U^E2fdu`0n5C{9K^6S`^8f(vkWT~u_S8p#fzVIrdt^>ho*(1JU3_Ftli1^xc5wff
zaJt1lAz=$f{p-)JRaoW88)h6o)Q6CqUQh*qvYd%C;4m^j;ZtaL)8W?<7^gQiDOA4V
z!wGQq4TA@5b5n$!*KkSOC!bZ5cFvUnz3mTvsDG;iv|Jf_ZtG@+rOYw7zgb}!`Z~S#
zxzRQP*}=;k^!jQb=0f<JMI+ekJD#8Lec3;(GdcL<Ihp~-xwv!gaP8|Bam2Rqpum-g
zq@BN?)=W>{$wveDKM+EVL3yK`0t6mjd#nIvZHhrGUHuSGzH8fF1+JrwO-Fz=xY=Hk
zr&_*J#E{0Pf*4*?*uwC1l!D9HefpEJ7A17Oj%Nj`B`Ph35k_wA-zewpuNxVyrht<X
z`6h+sr3ujTtB;OemX5`!Fu^9B$^+i^O+U1L-V+hy0G=#ddCIWp{YRGadZu`1aIgei
zu9%1YhD2mOzieZMF5}!0MsAAkSb@Vjr@jM4@Ev?xW`K}_bC(o*E8~r5;(ZfT5q+7o
zDFNkw%NS+3wEToW6JBxN$Y42=e$FQCLWREilLhq1%0L2xW8OlXQ3Zh%r?(gq0DbrN
zkfDUJNqAh7q2-m@BD_|<htDhg&h}@Lk|1cT_3^8p)jn2fmamU?ar$*ppUK}ZQd8BF
zek_yKJr2znp^eHE?gndPH!7WD@7`%JOA|i?7SiBFkzr<rU#y0occwbF&<YFYFButC
ztS-GcS8nWQ;De~tr#h`(@$XbeG)cTMt++l`1ci>mpO?l2L3XN*#BFE45LUC(+uS%^
zguiZspsFEnB;(Gp#3X=(J|p0jB(Tr42Xb)c&%dBWhXJzau4~1)^NDBPU4JVHaG-#;
z!szP(I`GWYy0o^rAwp9f2r0~$Q-(2uDzc*j`^;y+HP$+YcX!>i=<XlQolS_8_sHTb
z3weLBphOXzd4iGlr53W_n8{~-FF)j!87KTyZ<mEaGZoGcL|0hxKO8xG9z;tu-dSS6
zY#6*;j<EqtGt<s%(EFk<+6wy&Ia7X#1|PRvz%V{qSzR>)zEz6#?zyINbYlxGmlE#?
zM75iMLJ#r(-2H}!;n!Fi+r?U{QoYO=(j*Ks>I`r;RV*OHG{A9``{?T_hUHE-?s2GK
z(6>H5xc<aKT2Mnvt5oku!Whw?Cxg9)<*EA1zh@U_jZ>63pTGPsPtNiFKNDtOYcDs!
z?y^iNDhw52X}FCcIs-I+oT<YhTy%yG(d2*{dc<tEeyU*~)tA%sL%9O9>j3IyGT4}u
zH@}VbBazfsL%Q39A6~Bdbxh36?Sah46&KEpCZ-pE(LMX?pDOauD`)8Ojqr#F4eFmi
zqCY4)Ma0MAtR<=#gUYcL7J1PkxC=1KzSyBsH$4%#1M6sD38eum*WM=Z8UJ|(jH@~e
zF`(L84@$K`^zNrDfv^8PA)kSE+*kkP?mYd?hs<{VNs+-ze=Lplt)YXUGkyE}`y2Q}
z1~-Pq^J$#8#@xQ8ILg5vV0NnPxIuRh&Iv}{m$I>;C#20EMN63vKzacH?>93uQx{1M
z`u+R&9`-rPYyjx&Ui8ia({Tt>(_Y{STCNkh4Q!v<AaD7na=coQ9dyxqvM({v%qN(|
z0oZrbQ6)kT@Ayf|t2^oy+I4bf=FYcuBE}i0Ch(E}UUFw=?zju2Ev~@130N9HEe{9!
zrsZI2#y)Z6FVMI7An_5<y@ZCu_>rNWIKt~;Nt;t}RlngmdVgLYyCi|!BUi-0Iu&pA
zmlT9B%?8$|U%>CG9r-=|u?y&CBzW~^I@(f54E?T|v$OM=F+1pMr$%3v1<oUF`}o<i
z*@2v?Tc0+OZl_#S*_^@)cK8<#pd~Wr0RHt>!yMlBrf<7UiH`z2&e4o7AMQ^eyd$oU
zx;$GODIiWxMuuKadekbwXlT<Xl!yy*yin?uXbK$|`DO^c#FtwpdNMlh6^^BcQQ}#(
zT~!I=x|;`eXUy7Q|4&h;Wko0$VT8)>Ah;W0eHPGS-kZlSuey)?IXCcnm{WelM!oh@
z?m&7Nqvco;@DB{}jl^BFv$IoOQ!x5`1Hm2F41CDF0%_{Wz*SodNuPn=Mr89(YyA5g
zRfg_~5NH~&PKq}q_zQbX!MAIB?n{8e$5+{4&l?ZBzor^j@ByNRl`^*a*%I@ckvGTk
z{E?dhLIDn6iktVD9q%N~d%>d3pHkTe7EaJJZ@&0!yQJKae6`l;4|BS5f|?>INt)dN
zVPeN7XeKC8KLCT?#nPC7^Y?XU=V2>7ZSF+dNuM$GDt}v5wi%CvNUB2*vxJI@%EO?D
zHEtk24{^!n89`O`Q+oZm0hE0I+6DWoiZA}!U!f!0fFr!uCG+#_QOfYlWw#to@#i|L
z$;DRd*8cBux{J&rrChP%tgR+^@ff+3UR|N1Cn#Kh=PAyblub93_0CVa*h*RP*GBo+
z)Bm1ud6;8be)I(=y=tGRpWXWTG~uslCX(@>saT~HiN)WQSJ+3##<mM^VhfZ6P}!qf
z=to;f^LIO&CU_yA?S50R?Pb3_{88=q%LfKMTp3FRL@DEN_foiIypXdBRLTR<vzK*T
zT|+}LL-C}KHV~V0CSEyqG88b8v<Ql?j=V0};pgM5EP8*CyFX$im@OVGVr{F~`{v61
z4DO&zZ>1WCN?R5-v;Ybj?$Jx%n$QWV8t$t1C3#+f*{$r&6s8(`{PLz167Ow)ACQk^
zv^qul(vv|$8RMS=(0PfAQKyjTiA)InwbVzA1eh&z8#pQWVKE{F`Y*4u6+U?RkWsM}
zPdzO<Dq0U{V<RYxih=U1mTLOlxPkSdxVX45vy+8zg+YVEJwcH2yvX}c{M#gA!%i~|
zp0&9)S{CZ=+yAp?r{4c*nWbEJj9I3fXF9B~Ofg%6i+ByxmO~f1Imm^2kDS5su)%8h
zLmldIxEP_W!^DGF3Md-2&}e`Zlqv^!LZx_JsV}(Ig=|D5yc5zSxP;`2t>zzENK?b9
zL1<zX>dZG7Vf~&s>mV9HRwN)wQ;y;mIY}Tt_JD3DSW5C7OWZeUsTI4XtD>?sab#)l
zKj}ukTxqKV%5~W4Hm{<hqC?H2jBnOEap6E9x)%80Jd28o)iJm6szoigt&xt8uHFQ$
zX5j@ma(;r`tcIx~_(ucJdM37!58ADU`R3oYeJ2yQtQX;S9DxAMf}v+Y6|?MT%>%np
zUBM9_$jf?r6*&8k5_#Mtxs$O?F*Ldu81iDvaX9CmkLCoz96Je@=1d8u?)URsKP9Yd
zi?_ZH_@A?bWz&p`$1K9BN$J!y_{zk^B<ac#P&m~n8aPmXGlU3?5Z~YZnq7+Z?0bY#
zOP+j4crEnf)(?wuX0zcXhn~}u|K2=;fg{OdGc*5EfE!W1$a+wm^fISVGhpU~xyaQ^
zVN`{!3zc6V&Rp?N(sbEB(r3kC7$fN0<dM>T8X6?dLs?^sUp2ApOX+;YWn?jPK476N
z0<MUVg@ud%3W-x*LnUOMF!(RAkxY7Mw=Fp0Z0kkZe++Hyj06r7u}sC2Y2c61vYLi8
zQw1Ba6DlBvO7xCvSA6Of;Wt%KQ&8l5)W%m-wvsBtog=3PB)kpQAq%Af^u|eZ6}6`_
zi5hvwFV?t&v|Eqs<a3q;V4}faQ^%I={zz&GRsk&4%$M&uiLY<+sP8AGrP`NPrN<@W
z41`R@)t=v%6HT-?I67t>A&C^3oX?0(L6dpxwAFN_yx(2#k@P-HS7Zk;dh8MOA2aYb
z{+fp7Eb6+fKq~(EFj|5#KBM6qJi+a3MLpWJ!Q(ys#;~$tT>NJQe{PwcfFl<eiPEFE
zx+|_tcX9(;m`z{JlPoFhZ1aB}aQsOBC+&w_a9frtA{vnP<Bll!6K!>H6g+zPlsb3L
z`Mf^Q`0o@J2CbkkO@HuRz&43Qs0k^$DKj898QiMFMQq81$JVLOacfV^jVeBa2O7|A
z`hp{uvjlw)1dd)2Z-;2o1v(-2zY>86Lc)n|-EBp@;tqcy=%p9vrLB{mo?budTVB>B
zw@OA!&FW#<!MwL7N2u*uy3$#NKefY*8^mknM+d(Z{)yyS%7v$g*{|_~ou>&h_Yf}0
zJPD2z{svCg?HPxo38;Ep)+Y@fAFw0n2UMo7g+)c39*Eu|V*G_J@{uTX0mvqn_<Qn>
zb#1}G2UT7>1{8hUwFcEo|21xTa1$6L;y~ek8wsNwf0M8jS4ddD0;BzG@EN0A2F@Zm
z6=s0+oGQ81i4_-l8<tI4hrvDylp5}7+3e-@<0N2<=rBcvfOGWY&lh<bE_yXq9RHSE
zmMQciVA^afARu72h^UNGH0ACFz$sqO7#7y_zr6rJM9R1M4UXzp-|jBXt6{WsbMQ{u
z`Ss?6xnu{Ozug59oh%{P_XqU<z$tz3aDCIF&!_L%*G}^^990WQ`^nIo=OVx{ukQ9I
zAe>!8s2Ufzd?r~7+iD&%4xl>DoG_Ej68Szi^53~U7J(6WfM@ePCF(Vjr0eA*4Udt?
z<yu%;oiR%;oNu4wh=h!YMb~nxM?0Khn|Tw_&y!{}lCgJJyuf8022SexCYua<8vT{@
z9&s=D@icn+B%`q)*<6yxT9EeN&D^3}XB&R!jX#S`u`6erdAMSkcw`1l@|Y$Cs8eKj
z0C0zDTx4^)S3qR+P<S&)K6G7)O5vSlodMR?!%x!e)87|SKvSn>{7?pyWDabuD6|w|
z{VYspo&YTO`X2mS&^I%L$pYe6#Ev|yC;;)7Z$=pl#slmT3c-QTP%SZz&*F~Q?v>x$
z_H0gsqyMbH0QCxGhiXTq<;;F$utR0jFVmeUBxVoz-w*wG$^o9Fxy~nZ!Q8z6FJ6)9
z!_PIaj{4bu$bb&KdM@ETBgw@Jo9!YfF~!rZ>wcyT;QR3Ig!Pxxcl+)9CA=X(nOg(J
zmfn*+PHNzIG|=HbESe#Yf<ZO2EH4qQ!SIBkRPL8eF3KHEH0&|exbt^U&1jS83DrnA
z*z<C%b&604*1zP}#?i#QJGnaXYW~P%a^_wTc!^aPbwf<LkxjxN^PE9fV<*I&E{kQ3
zAr`U=ee>YiZENwT2W=k+FFuHUfAI~I5jNhbk|C&kptV&A%+a8-2}`_$^10xF$Oea(
zzz*|-P^?4k8_{<LL15+m{VW2}B(Fju&RNs-;%H(fKmO^#VkCmO!4jAWUl3VHxOq(d
zL=zTm40ARta0%FYjtg=feQ6}A`G3yT&A+q#nF{|zI87fZH2yms7vxYKm3{-!OZUX6
z&<jg@uGSkuw{;J`or~8Y?N{sm%Vwx!niIt~oSvQ_JAUBtKK%>*W&GhQ5V?ELB_#i~
zDPB~<o)0WAFCCIO#}G`7NcNk$YO0jUq;F@RSZ)tbdU57D2+=RHh8a^hA*YL9rIDR?
z)KBzDg&Bx`w;j<rKk&Mb(4>K>MhNJcg-INiw(DevVHBta2Y(TW*5OE}om%5yL!$i!
zK5jl6Mn-!^xr``XrE!UfAChRR5r*#FOV5fW?e4sE(t3RNB|qKmT;nTTZ&>BTgN=yC
zk`jk~%x70D>gL6))5pBjoPSB8C8ubA3a9!>L)#>5`o_}db{FL3$+C0HPs0L@^cT2m
zw`NomOZlg#>RDG`a5j`m-g{*QpP|>53E#{^G~LAO#c=ssX{UG~&oXLEedpxId-JG+
zdk2k&SS~zo^eSn>9a~@9jGmF^k#ww2o{^#3c-AD7$Palm2x&##FeP-Ez<O4MI>0$C
zK|S}2e6{H4nX3ZRQ&*P5tWKKCJepzsoRuki?rs;4`p_;o=8FCDciE@m#eFv_!;s+g
zR95s1C|{b+qAG^yj~$CWw6P4iW3u^Q^QQl+t~ZZ{x{dpQEo0xxS`^Bftu*#6OO_!d
z$-bnFec!X|Zk1#d#$J>nBiZ*UAvH5JBD;}g5<+Ax-mm9<o^#%RUgzBBKKISc?>E<6
zzw7#bKik#!Y=AVEi?~6Qb6p+&q9$iKdJU~I<86APna<UHWxsnNQGogWcTQzfCf>}V
z=&og_d#I7D9}nYLzG<bPM$SEJqZK|=J;A&iigSrhzVctyufb#YOM38mT3I+D166ta
z%-BAOE{kT85gzH4qpzd4nR7y?`<L*Kx&LS%ZjgGv7eQO_@Xa~u&s$tk4=i1oT(U~F
zo$f}e<zlL9@!f>Qxhh7*90akKHFVknR`<uyan`FUDftDWThSX)00J9KE%lPrRUh6m
z?lIPkn=?I6ru&`M*6@kY)g<;cF@p_7atmW|h}u&r^A@0X$qA<|Gvvw6|FDx&iMG~}
zyceal7p5h=|LZn~&{?xA1!wDFlYID2Ii7wiD6%mLa0opb<WTVWG#%JYVqRgLoxLs;
zqw3y=J})S0ybrzgn#8!&JYr8fR;y1Am7gJLe&Y;)i@DUMP*SQC*j?x`ob<n>5<&*q
z^1RTNynTP3xqlZVGCQd0t(~&4jQ~<pD_Mq6T*VgTcrsm04Qfr>_is$+S$<1Bowj<~
zT#{EFsncn%hpCe=dA4`+ZzE9_&w}2_g(93x*t>K-ib29lCwcCZOu7lctI-eA%o%Vw
zKoz=t&XgC5kX?%cXv$WDk?Pd5&FsK1L&9s(|DZv$2ak^9Q80W-fom6&dRx0n)y5lC
zV1HsPN_lS-5SgzL{u6un&P-mY)#~Azvl(IH@50ck+Zolu$>wxSeCc_#ElwY*@jo!~
zlj0N^H0()C^ns_IrSuoy?^LIr<S*zHw26~bjlj5^o)@ItxV?8_`_!8|SZB2n2agVE
zjbUN)x3!Av8d~BDPN(8texyd`gDEff<h>8-)MtD;g<rmf8eO<_v*Zeemh$67Kn#uA
z7{TIfwdZGn@fB!v+%ZPg5yZx4s86<XK^LH+#~uFfJKXBp;TmpC4POw?qpK_TWN3Qn
z3h6iGYp&RzN|pS=D&=+Pn90ti4^?Wacd_P=?~khap?SnuyWw`9QUn~gkVD3OCr{3&
zBKom`gwSaEcO!Fb1V4X!dZC+82ON!pG1euYyT2rsOMIAn!k3!&8QVo6TIwY8)1owK
zROy;$8)JD^43WDrU>j)Gf1yTO_dw$i^>&bPdT(Wp;x!|yTCcoN9OCzq=sKdp1S6Q}
zdPYrsK}`Bv*m-4f&x>})l@k4*aeiow1wCn09JJD0eNG?OFu0#Uf~Ts<QS)T4wDnpQ
zewUj#iq|yoZ$&5*aj$i?7-Va%cSWQdO^qGOl(Q#aLpw9*w4KN$#w(K(^FkE_N2%U0
zE+=P5{fi$%=lcgT^Yo@z9NOCLNKZb1a9e;s>T4GkTEeQA)4`-h<}Iq%x&>VwYi-;l
zA>Qep+x=NFuYfVfI=|sAsC;-5M~${ku3U-%bM%!@4e)uG_tXVjGYl$SJ=Q(d(llWz
zmc2I=a9+O@8oD-xNYS$82wf<2uNq>4uI<^`TXT7#w^k7H`j{6q%N)wC{^(wtlLgYe
z4nc!FO12S=oqN>6;I5<l$mriQV%5WodW}n8g%Z2P{~h#T*U(p{F2bWJUQlGX;H=v)
zH)|~ZPxk$$od<f`H1hHJrz|6{O^Sm8*fSNJn;09kHmk9hWo-6f6ap3_AmT_FJ*nlN
z5qi$*6wYVo2%ko0WBGmg<zKK04pchJ9M?@9ZY9&6ujo5m(}U=!?lnGQX5#}?_(9wO
z(<0L%&1;6e0Q9#?KmrD5KWFXMdBgf$*~1Y;cpY|38QpElbg0&yQ+x7>hD9HcQFZyi
z`068fdHW8vDV)*)57(XVt5Lon?5UzVp+U_PDy*ZIw9&XL7<zo=;=Rdh|IRG28Tcp2
zY!L6G`XcDB@CxZFA5`1L5O6YLCC5KzP5!eQ6{{ziajIsh3|9D&@BO)lk=21VE3K{!
z{O895pZfNR9?>h;45gCBHTYAU&G!uK*6yJk9)q~R_TbAR*>FsHQH^F;Mvj>0sRb*p
z+^*8`M4JK06h};gcl>6nL8H1CovgwLu>g^j$8;ivW8c1I-90M|pVY>i;QHJ7-ziBw
zS;wln;F+lVyMYnUvZP?rG;Ma7GEutP-7%@(P%?AdK4H4)y~|^eGGi^Cu13u(zXEIJ
zVLqr?PU?+UdWzlm7|W<JK$J2sF>CSYsgW85LCbyA5e$!2_*Kk?m~?j^y_U>;4pft7
zz0mPz$qGG}y<NhxB}uEw+W9bXU{t@mwlm@p5p8RH_--h!4rJW_Y%5*jDoe`6^BETz
z{LJ3C%p0KVN&v9<0_%I{C!?SDYlNbGJT(Na_$AjFi(6f0LB_OvR8Ub-R<3v;euU~o
z^z!x993ccCtLxK(7BVrJlHB(Kw{HxV)mlEM4;pwngz)b*dG?YU9TAuAJO+sdHtW(b
z|06&&+Ir9x^A5SQrxEXUPp1oXg?X$F!iba^RI!Y>q@TBvcwt!>uf1~lX|GwC-ScbI
zv8~5MbUW>ZQ<N{HD6L;9#PYPXqQ--zRuLX{yFj%6EiGSkI|_85X&RDLr$6_*r<ds`
ztSQsxRdxhl*()L<dZERa;FDCB$cx=8F$ErY7SnYDH^&3bq<D%O+e^4JlN~!nU|o&l
z<Q@JzQhK5x_xl$skKys^rkpthNO9JZRNSVe1KL}kKAjqeN;1Cf!&P-^S?}om*!b@2
zXB+*+(;GsDa=mmSosUb;oHkWEb=3QtmAPqY|Et@#Z?`6j&`dR*x2ISjHI*}ZS^`1f
z(fdSOm+GWEB$=#Jmr}%KD?IhbQ%HvURype}-ZEz{C61`p!1Gm?^9@t@|8Z>ff~rKx
zzp9fz(9h3rtgXF0!5m=BX#wZ3FJ?60&3kX9LG7w~mO|S2^QV>9P!uQkexdgY4{uy#
zz$1O`ns9s#ZRLWB-stt=w;n=CcS6rW4d9T#FyZ)NtrB2m<o*MhBeo$^2!D<*51us%
zUjE2S-RWCs4KcQbDJevcY;O9ffOBk%jZP4M*AT*7IqYJcF70G<_oQB~?(qQLAX1}y
z1w88-l&5qes;IWx&rD5n82pa=Y!vU0Jz^afUvYoAl*sIUF#q4iZvT!)YVt^5=UsFJ
zasI^1YatTVu0Q@5Q3gyA-^&c1j>g&k=OW<X^+lcf(*f3iqiQ@y!t>9gRN<#r*7-6H
z!O7XWhkW-if%;qKdIk;tIQ|R0OHA@yo@_Iil3N?As#c?rF<Dsu)85)E(krsaW)P3O
zE)RQ9oNiH?)iu59DIrgPyWDp$5G_z)U;RQJyy-7Ei-pd;FU*Lfe7-q$M(I*;49b?K
zo5SnIp{<iEqkR>c*x_@}IC|BojK1F9!*#D-y%JKxo<P$P{3QAcdaf(T`UV+#d3$>o
zz)B_n`5(!G8M&r{+9&2U+`MI;$b=Dd$`7G<l5G53E=`|@ID{2ie_6soqy#@7N{W6e
z!8erX=PmL56~iq_FD9DGLw<*bW}=YICx0`;DxL^X4nMNFz)Bc<4GrML_&py@A9D;)
z?1P{VE6<X%|IT1uo?T*)II2%XCZ((*h#XIgfDUn#nzzI^Gb*(+tssc%wr9bSAcSnr
zRLt{~ex;ml@|UNf=z7u<U4^IYfgeK#PHDAnXJfUeyI(d<@rFtc9e?_*jT2r5`AD=Y
zJ9Gt_2ZCt(<VSfzsj&;ac|unnvy8-J>ZB!)z$EzulD-I99cRik2Y6KU{+m)$m0`Wz
z^S(dxU_mp)7Aey%OFugYe|hQJwdr7819-r9OgueH3vYb?v?R~2L+asCQhk;T8nc)J
zH_csL9pZeR>^(@TN=SFU;M#iQkB}HkSK}A9Z|7oey|+vY3NOh%th5sDMQS{oUK3Xp
z2O&LHAHI(r`R|;-@>%5Riwj1);mHw?N|H-OVOKk1Sm@}5E`P@Sp;3`Jt!UgH=I_7(
z-sSw`Po|&CjSi@7PRv)GZ2s8gUM2PHZfE0{N9&Rlj;C{@vWHX3bqqmlwQ*?W`pfOR
z?mJ<m##kt&KvaL)+fe4o?<RL#-b2<_m(+umNhSipLAl+xu;OY0b;!v2e19O*-sK-_
zu-ZIh?g$Q0ddS||Hca@-Zlfw=CGOSE+B)G%jySx&06Qeud=9QJ-sg&+j=WH)^H0jE
zduHsSxH;W~fKOW+cU8krUc=-F<e3#AJ@&1Oh<_T?F*K;70@A;#bafYad3mV;uhbDq
zY7Ds{a!6r9xF9$rz{C*v(#${$ZLQaEjdWPf#_`_x9ILUtQDC0v1>_ypo$hsnD9E*p
zQT329Whc`c%6L1O1=)q`wDm7tj?;u|0A>Fi2$(>`S=}vzO0KQi5*{R$uqyy;R_wM|
zSU{idEz7_r#dIu3!p$&-ps~akOhmusKJ7sIy<<1lozW4I;;=-Goq_!`^5??Bs7@{s
zm+)u6w$KTxrSc~adj?LUnrWxro)J;1cD?hf`LJ57Za*uMt#H(yPduO9iQlKd7i}gB
z)^o21FAH~*JQMSoYK}8NrI{z&c#BOyhfT|IUM=r4i)A3rBWV00^)_FRQVByx&{SvI
z!5pSKX|pEmjk}{^jlEayV1?sh>#Y<K^&Vy3jf6Olu3D$))Xh6N9kVa<gsdL3I5dnI
z(XXuj?=PE+6JI@5nG~gT$-O-=6VL{*DEB@rOMsmo#~OQbeJ2gN1H+TSHu66&9r+By
z^Q6Z5!}1gq5viJ(I+}-^%6HBQ<O@A{$x|bnIB{{mn<Kaqnp0b|hgVnD=VqTUf3Rsc
z;i(x@qMAQN7tV#juejb9Mn>ii7xUfwVAFc(@-7z_RanlO+7b!XP^hvl`7)&g{&XUY
zK^CS1-y5BE;qEL-99*$+^}85;hPILeerb4D3;0@LMuCby-WKq>TDiaKky%)6`*ag0
zbLoMkxv8t;H^p0V=a**>3Z4fgXv*D-YnBJ|{rGd!zIc|`LMskiN~H${)ViV@Iq{o4
zh01robKvevPP54e*oyQp?c74~ptFxob?&NDeL8>=6aq48I}`fFe!>mn;yg&6Hch){
z$CxcxTiZGa1+M^cM?V(V`@DTBSITSo(Ygw<x$?i|`Mh#{pv^S@07K|82;nbD{seX!
z6j)rklTsimZL&3No~+Er@wM>~sydPDR!-cFe!hy!)_I36gzm|H-Dm`90(=*p)2kUE
zRNO<OT@iIXp`Qcrwo>Lf>j|q-fAc*!dmGbZZ&McM&2PZ^XjpU|3@CLj<mbAd6X*KH
zYjcOoi{}k6-&eQ3Ao`2%&}h>9!xSi0=Sn!|nLhuOs&j+tqz<)HFKS2SoyI`=qTIad
z0rT?X*RQtnuT|=*+$crLIRhe?Q3PZUr<KctaDslz;>Vvbqego-P$mX~-ZhfOmcEpx
zI#JRMgKa&k)<M_<+*ZLqFtCu{qmR@`2HJZ!cleS~R-XS^b*M^%2kkxm?aLbSgl=-t
zPO&mf^=eaDFOgvm?$NzwR!)d7p*lD^Zh{(dzZKgW^PeL_-pIFak;dS6P*wh(CsYcH
z)JZpe+O%JNqocdC(6!)brh2Qp6DKc=a@yWB)lO!-*=~O9q<8PrfB-1pEy$-ow)1;P
z?`9AG2G}s<Z**R$A=FcWkHhQ^JIB7LuC9KZo0lh)S+bOL&44&rWv=OzCwobqJExFF
z`)OS-dw3{>aFvx{8CrUG5AZt&TG%l^Eq^>&I9XO&+O5joV7jC9?rpC5PNJC%&;4>k
z2}{uK$m?NL`bs6t*(Wst;Hx+)87*|LWJA9&ob<#}j(@avNJo5$Ur(BpiWOJfs{ZMN
zjH%;ZZ5X+XJN0fwi8_ck?ofpqeN|dz-{|a>7??EUDNz&Zw!#_4Z5~mO2*aDCW}CQ4
zJJl;Vd5m(>CKJZ*7wsOek8q7Wp0FXa(R$l)axPCu1V-ziY2{DZ_PSO6ILN&B2|g7b
z&H-GA!rOleZ^G~kTqYy^1YyCxIvd3DbhCQCP_j5s-P-U%1rGQD?yVR2l<CtT?v3-{
zoZU3knQXt>al2XU9&9@w{W+PlQg#Zke?V+&+x!Vz^pDvNaiOP`zwc9Gx)SO%->xKV
z61UuUgK&d2b#<h>o$hPXt6RWld7`dY+q+jCDYvbRhr}{DNYDa~;ccEsL&Va^q(#2Q
zpJ=yT{erBp1&oB*-^r%(|4vtJzx(kIzX?L&@~a-QW>?YWi75ueQq;&*{K6e+*n_Wq
ziBq#R18rQ)wW=X8ygi;YwE)S6E3TM5!L)AAEU_0JpELcHs@GWKCI}kO9(2QwSi`V#
z>*CrhdgHRh_u$%!vG9(wh)ER{EOTsdKO3@{bI9)eJ{S0jegqn7EjyWeLz_S#1klwT
z?_9DL|0fQT$)*oiY0rQ+FED$!mO<-AJm|iWzZ3I>hCNwS8aci?-_vzklJx~ea2mbs
zt(@LRN(`c)7EN)haL^NXzIZ;0H1HT|JpV!>I-zT*><`=46~MV1&3FfWL5A>_NAiN2
z4VhRRXGB&7zGJ`naj<$;S_vbCaB<Ba&95Wh-Dq<8+3&sgeG3(d`$OyQ;0!;G@4vS6
zl@Ndhx-ISg17c&&m%hFrm0SKT*lf+)uVxe)D9JYcFU&Pr?Pyxg5-Kd|q<|Me9$aqr
zF0t`Z8hs#h?Q_|~cgwj1=P$GVZ`s&K*iiUs{#-NhCZm!z<6@h)z=f0PLs@R0f4_{l
zo-_Op>b5&jy&D<^o(;nBgRkp?pO4QC+UzS{B2{*ae}LgnGd?o-2Abm>h<<s9S$9F^
zqTY;6p-`$8xhhM8kk~d6()ryfyQDdho=HiYZV`M<30EJ5i3M#XzTiWH=W8>~6Jx=s
zz^2@*T>X6eSEN|^SNjNW70W(Qt0Nk?Me{B8Ux6k+ALbl4g>rSLhb}8%=*`rF=Vn>B
zQ}#8}AE2VEgNEa;mrCxqD|rJw$dl43%!GqhYjf*pP(TLcQ?yCt68ZD;XtRf>@bzM>
z-siysI8Pg&vl|>R_9%=wSIU!S-W`La8eMvYSdyVE<As=NBtA-b(KH7B0!sWI7rhic
zthI;pA~(d}F^_VA;I)A!fY|fIWGew4sM6fw|0s_SKRT}<rCC~A8*T`CdtZPto%uKh
zQ`w--{N}!UrurE?Fh=6~mHRAz110E!{}i7D>6V9tJfnhO-(O+WvPw0P`vH*l$Ag^h
z>5my7NE4weyX{L{Bz6EG>5Peoa6Kxda=uNy(XiS>kn}g5Nx8Tle1T-6i3+59$f0~%
zxjOvG-R^-jQ$OyZ8F$eZv|qdg-O);t#=>j)-JKnr$SHN9q8>sUFv>bsWW1BI^p3Q|
zxvgP!nvtQu)gi}Mh^(F8f0}f1Lv{P)T|&<}nfXN14@hDEu?EHb-3=9fx=doerm9nU
z_dq&Oz*6r7iOE>(H^I<wb25(o<=IDT^vE@9Ij0_*5Cli^DN-%H3)>3o6v8?ez3~dL
z2c4_$|GQp7+gSECYV|ucX_D_tXFsTyE>uxHG;EhNhFTs{j9O}L%VwDRbJO4n1z9zZ
ziKQxOnPElPfj@T)K;FahKNY#gJ&KnI6G%n7u2j0THe;8LrF6<ctwsQGfB9^FB|73^
z$t3TVU-$3X&;M4a+|co0)!^D4iE#iy0fw2rUjJv|+y1A|45?g=!zq@xa}vDJX;)yu
zOOUz5B>#1P5E0&&!=yCng*HC_M|eOQY7v&$*V#JYU5NacTJp65+G!3TbS-Ej*q!4?
z2z%cMO&~Y8Ba3mU1=3CMZrW;9IXv5Go5^p!q;yYbNOUHNpAqYokHbGtO-=PY?bHzD
z5nUWgk7{~Ql#G`YN>Zg-e7N^hyM;4H=+g62HO1<zM2V+!T&Nqa65o#+M;zJCoKjX&
zT7<TF0CH}GJ<tirYQ#-Y?b>77;NuHJ8M1sjGIn-lz2CBzDKm8{-4{SQDQ)!>mzbDc
z3rqk#Nh~3R@!jjLQkV*RylLGF|03NwO-9(51M7Ay9`|5F#a=}vXJ*j3aMtGA-qY<$
zm#zz{JieVdasW34ply-sOjEj}bgEEa<OtO|AN1K8`FqJF*33VdIA;wh1R$K#BErK5
zmL_vAc|*A{`0d-KEaiA{>~$g3x9;iHFB8kp272ZS(-xA}4pw~Y=>t2Tjc(-2Z8wz2
z%kx^(AA&?)6n_y&=`6S>j*&qE!KR8GmU!UL;hKT{R|3J6=vUv%O2D}@4c8hcE;6Iw
zv7q~V4BTHLt`KOk0386gh`MYlPznKVg^D^VM;rXWAYv}T+{2+q*70k5%|vlT&smdj
zuVtE0q9sCG-0!@)B=@<t!ad%<YH+13R9L@?Y_4!I)<3YRFdhIpM`6Rv$9sx#dOLm0
z_lUmstNRHGR>^$2eR;DR{a;^MpX(TU@ya>4t&7s+>3mRmRs}02GrFODkF>;Xk7FJ}
za`O}Zluq2!2KVC0dor0mnDTx8y$wzN(z^P3f$-bUL+P=@DBdbDAvNVPyRjAVR(dtb
zuYb?E)C}9aZ$R~hDA2uc=G-qVS>^Za0Rc#ba&;x|*4A-ovBRS&>tJ@)IUg+6!2{N)
zD6jKVYQ}Q>nk63<IDdPS-fnB?X_L&aOc#6N^t)`nUqkyQ-FiCrFG-)R?n*5L1SnoB
z9Eo~SRTUf||7}z7T|j5Vp_I;uR8dYU&6(=_l*MOPA;idV`Da8&Mwnb~Rtrr-AHn7I
zc`Z_EIYOSAi|>D0S80~xaL-Mq0;tmz4Cz`}_r@4~OAH7o!!?fuqBBnZxRxUA9;{IM
zBe@+GOQB-s53^F<bb883NqY>}!G0HtSGxf9mG&FauPtILv#kGF2Sa5td|4(u0+#ei
z0#4L&n*-S_qSgvm7@rT*$Qv8Xea6L-_LA%1Cf)bV1ERj)llr^ZP2S;t6Z3M(3CWg~
z5Q6jT>Q^8o#k0rK9%+aWJ2AhD-q>XAyle%-mcaP15GWOX>lYV>b49)549V93pPI;c
zoAgZW<ZE2o(a<lLFyzG*v=p+rGi_YvIBJx3|F}>5k*zBX?}L9SPoLF8A~Te@e81oP
z@PAr>E&6@o*<2bYn!Jlu_^u=<OIlgSoafcL%AviW0^i?0OZp;&L?u`}zm#_VcviV9
zdczv!O3#`TpS9j`*B~VKbL3ltF+!}vu+7(o-0x!_2z$(b17B`Op+sQ7aT?j!PWP&Z
z`h{7%dy-2|R!}}8(RB^@?q$;Tv!BH{KDHW>M-zMh%c)eXcC|SvOl1_TXK}F5?Bnq<
zL&>~&@u)l)OcPRw{+VlkZh~gfxA<XqBc#I?(Ep8ikk%^tsvz=uR)@PvrB!`8MKp#g
z6W|0L`G(fb&jB;LUDIQ}ax3<fGDWQjdmsYxE_KfQ9DVEYSp^5#gGVTztaN@yqVB-%
z<enBAYVatGF39U;^gZmqS~`GOJ~mkNg<R5&0$(8J1z0z2kHgJ3!6Q5^QG4hZLgz6x
zu^$?BsZiq+>bBemlwC&8^@j)U=R3C>mKczln*1rP+D}Y5!qa3iCHL5M{{Cf1{^LbT
zWfSyXcOvuo#fOn@qU$12#e&B=R`Ih>=Q_b?LsD}J2e>~MY=ddyTXijL??gv=@D=z}
zFnnB`=cbzaL(WWK06>+XLsqTMlK8hYUs~ugrKw_ONgl@A8W3I2RKG2VmYFwFIsLHt
zJ%Llslieyk>}-(z%V-={9xPh5MKatqPRCSf=~bDpC*342;zGI<11DOX1%-spAqb!N
zl;R-lVe!|my_=PMfGe(=lYimk{MyPl^e9W{LEAYyExk|!!7LAz+mFOwK5joXcjV0l
z^4{za=Qzl$Htggg^b8C-4o_)a;D+w7>iXGe3n)biJjwu2C4^8l60(RHNHG)fPdRz&
zsu&-;n~aIrai$Uj;x5ga*}n;(B9T>gehfh$&eXR~5EN3or_cRdT$I~sI021zdTz%Y
zLmw@;h}&Q3%8@wAeYk7#EEofis5z1gp5N$ztI@qv#jzB}&dh)Z>z@h6lrICi?5gw{
zv6Vj;*FqmpnYD%9dRYdY${=l_*b&Uc^^+^(V}0QzfceQGn-NE>-%89+!(FUdbx#8f
z;Wp{Ea*x*a_nOLhl#RJ>A3VL2raL+-!?eU@MhmH(>V6WVq`>bYZ2l;j{JR4Z5&iC}
zNm9q80g^YLUtXR(&7VR<41!7;GIMc%GnO&0&o$<Fim)lW`l6?P(vVVxY_f`G#hE!p
zCcJe=^-&N+_DOoe?O+G6F166Ex~mY82hitL{2!|i(|JPq@KkCG3JQ`S_*=q!qQ=vh
z8#a*}C$JaxL_r4i2x3!grY<@ko$*26P8<12+jcQ2C{L)iEa%|iyh1xA=tVrQmaO9O
z>2bYclv?Zs!eZRvTkyWO&Y%3koze+1#Nio{e-nd*5%GVnTEbkX`6FvjF)SYQaXd7T
z6-_mL4qjCnq$B6wvtMItO5BZF8CmylDtsU??*x%j^?^KQYk2g9$nGaQkG3TH<dzr=
z$EvgAmlNOemxSXEK_vL>Ux5|VmrFvJh)<DgM?6xNbTQusf^qCH{<}wa6}5T9orTl7
z>tzft;NFH<=L%GBOIC8=k0E7uHk(7AUm1W3RGTeU;%f`X%1!srPT9l#omzzp9e4Wj
zWvj;8|M1@WrvvS_J@Cd|cLHgeZ;!O0(eYic%2^@od^VPCEBxhBkeiEQJ_*{%_+&wK
z24r>a{pbmG)wj_8EU_)x{#e88K|fyYpn9QEOFWKSP2y|p={Ij+QLuefX4w~FFtAVC
z!rK(qR#MM55@>8}ocWG=Kee;Cztpn5_%1a+v>3J{PLXXKBv}qZUpb*#7UkrD8sT6r
z+~1N}K_M3)cZ9@O0-?V&$QVXuf!q1aPLi*RG|-^4U}7D)f7)Bm*!WJRUMOzeMb%;_
zh%ZytE?)5+ZZFA!xVSHK2ouUsj=dU(Y`#R^9E$BG6(9^o<ZrD*)~(A0klAC0!yhcQ
z4;a3>{E1Ce!&bOh`?kLcdX7pRyj`6X6kY6^JzW2Jb?!hU_6JCfr?8QpUFikwwGR2q
zm#N|ioG2vt&*rflV{eJp9d$yf<_s&}3d=Tq9$+e&(VabPdBoYdMgj!dVJ(j~Lr8ox
z!^}HTz_yG@%iFzi+W`eb9fXH>tu@Yy8)k&j+*D1~whYp}(L*TEZoUd6ePQOhD?Yx;
z?!vI&it*3+d3(OJ?gT7QQFTyZw`ZQ^w2kqRfg-CGW5MuiW^%HOA=Z`bNPJynxDTwx
z?I^9b`Vx!eTcuOp*7Uy~tv`WH*YWA9Cbi3gd_32JO}g)PS65fev-{n%S<o}+zTurU
zal0YMUtC&RdJd3zVY>+k23dkO@6WAud2g8&u_ABXYT81@YHCVqoHT%CNKax;INzK7
zL-iN3!W>{R>w$#~w9YTeFIP2;6sN~mp_=H_0(ATT-}PGtQ*xT#6`p6dW4?xalK;0!
zN1uLEUIOX{KR5s(A4Jsa7(tSaE<~RG2V$?%M3`ycsj#{ICw(nsKjHw68iqV-mLLLi
zy^cS+6nz#u+Px!;iPwE&?^hInlpXdn(h{DuC$n~4`5J4bksmO*u1`)y*f6QsUqv$+
z@m*6#X<*+8EzITEM|Ip5dhTG}=Z+`hcMY=Ua<K_FgK=HZ6e1H-Sfgrs2@^o92tUw}
zWP<pVQH$&|QxV9RwU3eXeX{dBFvewH+U}I}Cz|OK6KFZlR3{tF7?J;%8_mZ|C=Yr{
z<TrSyzLoL{P=j0oq@3-IX>0b0r0BL1F35JEI<bJ8B*B_Ia4pV)9BWB3Er!V3K?o<<
zK7v6ef^MW8*pl8aV{-FL>^gPc+CiqT;Qzy@ShJ!?G=$gX&!2m^e^qQ8vCd!-Y`N08
z&-QeVk#Y%DeK7TL=MV4!5VdPE99cqxTK6HiQJg<D{2T@yn<c}9Bfi+0D5p&}$J8<6
z+*fia4Os1q_}zzwTh$(N5&k|t8YkbHI1$TUnbTcGZy-_Qx(kVO{z<MTH`1^b<rjhU
z$Qu)UUQF~mhZ;4z(Mb?qUS4j$A*VTcz~=)_w^m$!rDEq<NhtGP1vRt~D*;6S@ylNp
zCmnPI`f!@aFc8kh&`5V|E6in9Ient+gr7TG9mv1hCguQ%O<_et-XF!1T#XJrEWfG@
zD-uCUjS=nUpBD!QZS>1>r-wcSBi|g5&echc_!9GOYJh{lXkT9+^uGaTtItbj938l8
zg1g>f2qM7ArTKaF2Stk{l5Qnd`)EpM0Ho(_@;2Ll<fw$kL+ZX-JX;YEt9GJ+$&7i%
zk7n4z&UtL*PfSkkYa|b6ySM1vw{!9@--gX_M?8+Mfhk*^LZ(WL`=ci-U?c_(LW0J@
z+KFS_5S$w9kf^xZJzaQExfzcp;G8<b8w-ggmtIvdEObF9`^)0u_m^(yx|p^Iln5>V
ze>tv<IsxcP{<VVQbRxR`Zc*;3!|PK%PDGrZkhCom^}L(G53*t7_uD`-L9^>kLRWt~
z6B1I_a~+ihXKWOk9?eRzfcAO)0Em$9@W)J?e{(I=?RS=hn&;XV_sLKt@qc2;I?tqW
zi#|@y;$9G65hLov;|Ug6ltG0}Fv;*Wh!*sduMKrQdq+?RfadPX{cNWi@zz6nBE5H9
zEE#Z!_dS!1jniA7PD0qllhOaKJeV}*eo*cmo>2t2i)y0C?Htd;$I4vR`ddjh4$wax
zSF6Bx*Do(D$o_D0wsiq~=Y-oeMIgxj<?hudGu)rNw(@d8nO(uu<q{f=!O1;KX#*n2
zy&y9D84e1S(=?m6M|7BDi|MM=Yy&My8W;u(@5&sq)qwK8lBS;ji=itl7I^1}RJv+|
zO)c734cpDPuc0nGO~dNEywM6WRjHHg-2*Qn7AK^WEse>A-Fc^_<UE6Z2(IAR<(aiz
zfV-58x$nuILTXmt?QXA!h$_#iTGl_FcW{+rL%b`O4li51Ibd~s(XMioFUD_&{i1H(
z42>ReK4|_d=?W1$`dR!ajW#-{Y6ZlXF8hf<|8q@!x6j7p*9GD-@5+x1A=LmaAzkuS
zJl9aHbs}w{a`idB<JS*EdCW!h(|IR(>o97^7go(Xp~Wer)Rzhe+gvm4R^`Re2b7Ye
zNLyGTd|Xs=IhIQl{u9W?af2s6^r)lWpeLZE#-JYhom`@w_&JH?X$(oRTEv+D;H@uY
zVUOztZBQ?&nC=+Cq)1BPmzVi$VQnk)Q$>&d<A5%kNP!N^mPdeQeW-#y;CwwNn}>!b
zCtbs^^tQs#nzh1Jx@q@0Uc-SazJ$emfB`qD5reKA|C#waIn8|ao`L&^zaa+Fb7p+?
zK-<!&(qv^1A4S(W$~@8NFeZ)JZIcYWq+Tk;e@d+LPh5~V?uDMJ^&vIVL1`x>aZ4a3
ztuqkrp1V^zPc~z0p40Up;(Zf3a?2BHw3KlCW2eUZniBGm1lZ2>ND1rqb&2CCF5WEI
z(=GGDuihxxPX7l%0m$&eqS?9&3H(D(hyrKYX&dy(Q|K#Sncg1|KoLV%@0>b-0Z+XU
zp_Yw<e!21oY*+3pA3u7<o&FT%v@Hh!vASr+ZjWqa*Ie3>*uhx?d@y>@v57ff$W@7)
z9)`iuJQV6%FTyT?u2x2utb)(ig)E&?e9txQ=1RZ;)9mCn7${!JGnGkhON3T@FMKJH
zz=IkI{*J`W!4?v&8%disf$h1@xe==5n^nS=6jaenO{5RaZT7ieB9zp@q*MV7E|+`d
z-LZht&-%pwqu;|@8U2gKF3(lr+x4?_X!FjE#6vOA|JX#l39j)E(e5>YZ(q<cmsD$M
z)C4IDa6n5xzKccTnm|_qhY+Q%RwXE@sKmd|s2-6x)kB%_lMnKfm-Hm1e&DIe1FKyC
z^dC*ZqyF{UPu_V()S2ykGKmAc%_19Qgvxj=qXL}?MR?zn*bDJE{G<GGQ#2a%Q0g{h
zuM~qxh=JpRV2G<#-3txDrsM>=6n$bYX{e?2;6Vt6dzS~rrkJ;I&>{?bJ%id3So9l$
zr&GAJR`4HUmRqyH%M{r3PYWePkW;>#0A*j>p{>3n`d(+M0|9(82H}}M!@gc#`B{)e
zjxy&#)=Gj8no4u$?ACut?Pd-K*=rs!Pun(L8liT?SDaNU!x{U0(6$E~YS*nMr<)L(
zH$2qepTRhHmLTo!>M9aB7R<Ccu{+Xpkuk48wzmok8Y50rByuZ@;H7l{sVz5yB4m%Q
zARPA-AkfH#o(!q>3Q)K(p|tS_Nonc8ADWtxyIBUeZ!@v+=hzc%$2OH=Qx8{7KDb%~
zq)L~Ir#9@BS5>8Nwl2phsj7x9RMhJ~ij~h;FT;ZW!RnIiEeTJWT|%DvS`fvSL1)>?
zruoOS6c@Sx@NVE@#gAL8Bnj^wb8z7LAF!@j*$d1V)HF$TA+O1}O^?F3jp6mPj7}%#
zKbUhIc+zQfoGv(FbS@FrfUA`kKaOx>xxnt+^xr!nhP-mK@FzvU3XQYyucQs1xO411
zz(^{sexhpJKRalem+D3z;vbysh%rm=1!lcLYCa!P&0wvcg%ee~7JAv!QNwoOrwqho
z72&<dAwPFDv)(V$z??=QD-3XWc@^~zLY+b#7qqFp;!E^STo>4!n+~gW5_Ud`JPDn)
zZk6!r=3QHX7@zIfm)>VrQp#~nKK1T943Bt!jRHq|yQDQKH>pBDD}YwVVey_kX&|Qw
z)d$WjAr_e(0l(d)dRI0lA)kQw^)JQ=5ZvVYRj&cPkp-Ir^w_54cm(xwfI!oF4CNZS
zuI;atx@y~id2$_`rQ^-JO-=1|?@!`kIeym{Z7m$XHMR2SpWW`pjdP^N9I<(~WUIIS
z`dPo|AF5Oj+$;<s!3!haF$lE0r|{5qeIOJdtHbfeiIW^H8+XqAeR?8SKFWV#$>rss
zx~;Ex+#@#w{CeN>-J}kpTx?B2s6uG~81;|FZwd?(3q#{7XdjB&4YA@spKd4I=aXff
z4~0{ZtgbtO&Ivd3>8LZ2GM=+ZcLzJnHk<aT@u!t4lxz_)`r@GZDo5NYZy${K<{Y_7
zxykkL`R8zSM2KWYbWt|Q00Xqr*IAM^JTqXxq)bRIG6|PSHd#66P;OwU;Q*jZ%LIyk
zznqc*_KEM>Cy~wVfTWdObgV2H#&0HB(vAgnaI~zvXFC?wr+09+SA)WG#`-XD5z9fU
zAWBf~$*+i3ym`(wfI$b7n*_aS5t`?~v4J`$-^f6Ok0kojmgrl$yKAp(Lo=Y4LLj_$
zC3_~O;yr2iwz|*#Ug_YfhSa9Fy*j&EjkB4KDkeFMf9bc1OA0N4Cn}5m2bZbEKrds+
zUXb4?n7!1joG;XxbD{5lr5MeoWZJ`F^%i8Q{`vKBgYidZWF4*+)>sy|@uu)GSThd(
zsTA9~rQA#SdnOFTe^x6?n@$watS2C1M^gGUR8^Gg87rPYf8JPGxojkQe`Zk_bq6Z0
z!{2cBMGQYcAgmDNAHWMD448c^c&?tpyf~(<$5OB+Iulci%wbrt*d-f$ae0zJA~nSD
zS|z|bZ71q?L%$LholpyjZ2DObY2u~ky^xOfy0HgesmTb&t@!KHXob@ZZAycaPf3ls
z<`P~9-aY{GECIn)qLjcOkH5HmLDKr7F}m&|S&*Wid~-lGT6W)p+*LE)526nqRP*7y
z*Kdt~U}&k?!_fybW5mkZI<IlufMFT&D9qt<Rrc^DidT_T*nBwN8T0V|&sM-%^2A$t
z8dBc%*q?s)_yv3lzE^|XH3lis69mo_>Br{(#%Yex{a30~O56TeN$S%k;5wHw))kX6
zM@R1{w6Y(&iq6VBCqwnIggeH+24=ht`VJ?%Drt1YxggO-Yi33-M4QCCKA+V-h>|`T
zlCk*SBzgTTVWx>|==M`F7fAyz9nAXfZ;;JS8@3e<5DHG%o!?#1%5qFJ6F1B`qCs`K
zEUs+2BjN@VOZ5s3Q_gV5Y#O0)#KxK>r^G$dxa|!X5ub5h7P*hDpnHhOoNfGzN)Gp~
zJlz?iNp*TE?$0)+dr?7pQ6{-Kch7#}WnOula%~DSmpCCazjRCI^n9lDG|T4!x}D^b
zJ4x)hQXfIzBs%|iY(&{M@j#~tM|&(?q_`nRkJ_E~_JA@d^#B)s9TY{f;X^HpW|PMx
zdS@kc%dy+{q)AT>zBtIeD~aZ9$gsX-&tDJ5Sd0r@8{36rLEf^-$#qm3YRtc)FAIx{
z4=NmLf36?cudkssIa|=^5AIcKU^6cy%3&=^*UXhQsf>@-4U2@BMP$Z|A7wjV-h-PL
zQC9B63Z1Zbp-i_g{ruUa@+s<e#^`+5p_TJLF43<jCp#A)Kk->A=N`b;u<U1<?MS|v
zz6c4$qe-~{_YBXbkQ#rU^v0AdALh;Bkn%iDC$cd^Xe5`vLU6bNfm}+@1-m{q@uN>s
zY9{tyI>n?c_qUS{V}m1kVm7s`$%G7sIR(atLQ7(JTb_I8TmHMMZu>->NEbk_lR^D0
zl0;9Cn_QNqI(_g_&~toy9c2juxx@HYKnD+_mZ1`}%sPvEnmwF?x5DcuvyRcX-g8^i
zeOfB^wFM5Vj7H`<<BL<k2B@_iu3${wO^W%L@NjjX`}IQXv)6j+w%zcq^mdRY^$B3%
zn-aA=>^;<evH2E&A0pu?-Iw)@g*e1OG+W{@!ZVpuiEpc_<if9u?pZJ%d6LKl>6KM*
zrS1-x(1+kyQ9h5p(vGqF2{g3`Z@tFGeIg7#Ij2GWX>0D!edHxX8fd?H3DX&{zMPvx
zKM~~U6|x!hA5*{@O=gyr7(FE{hM+d-ZRuh-8^nwF)SSq#8o$?v2Yz~dYMDMl=2;3?
zJ@f{r?ca*W9?J?1*CQ(+imxpbL!%{vlCc%iftN|@FF~f70ZX9{MYXXoxR)TD9wxdH
zNBOUBwl#?l!%t)OGcK#NWRrKe^8@s!^dDVyhZ=Jv=g%iMJ#d_B{3}EeN5-_lz))SR
zGpzFlNQ5gq7b4@2{@`*hIDe72E6_-X`Q!KTc<!|~p$Je&D2sy*gx7&YnIR;yC34*e
znRD_0*|&u~B^JW@i=zY7`L|L^u6+_3ZXgTkiA?+Cj5c1vtScmQTrP#nSyJqfnx6^p
zUD@+PJ?2<O)Uq7+t3=*uq`z5W{`p)!gIA}eVGd06nt{NdS|11)qcSzks*g7uk1{B5
z44|1nqdm$Q=JSLKq`YkKgd2oKYeav+={pK+YWbAxm&s|3Wk#3)xwk0^2Pyho>4@nu
zH3@H9%9Z3-pI`LN{=sWeq>(YWmUMOM?P(SVKE>+7!+FEejs>4%xOwYZb;%#JzWE+N
z-)UdIH46bTqFN7Hl^n5ClJjAdcnU?U{x3sRDc0F;S?FP&P@0xr`C0S^Z_tr9G($(4
z#t=31n==u~gDrM)nTW1fyXulGphlyC6KuTyIbSz~>74@6`{`$+puTNQ!eUZLH^^*`
zTlSS*#JyS4Pv$@*d=C9Qfj{0@>pkU4Qhr`uzMu-y?7BH4R5j!RUNn3F^)DtT#FzMs
z_IDgA2GYt2BqijeD168{_%O)ob2Pj3(9SAaDJIu?Z<=Ym9jkg`E%RijsU#YIxBp3F
zdbJpYfCrp1@FG1)ExF0^0(qL|w|wZ<(KlIGXV*b|UMRyVqT&;F*ax|LY(<As867ap
z*Wg0_?SRY8G<~k{cwL1;ojIMqdOCS0IB<1_Fu;u>ViXYZY%LPK^82D{hu!M1t(PZ$
zfLEhzI|K3a7Is|0+cjC)%ae90RMQfnBki4pjcZ<nd|fyygjww=ARdq{tc@o`0F)p^
zT<ifW?%#K+hz19-c`r&X{<T&XM+0xRCwgDT*NxQp418h+A$N`z%FbuuBa`9`>it;Y
zJb+wE)`sh+<JZ*XfbLeN6ko@oQ8&aM(dlS>kl$y@3qaRrotB|GJ&wI!&4?WqNs8qD
zs_KwS&E%rlL^Yi!M|f~R;d%yTEuPP&rMoxtn#+!PaRF-I0U}S0pa(h*9dTmi3gv}X
z{fET<#CB7kEZzd{a8fEyV-C8IZjUqUP+pJFh7`paU56(OW+{V|eFmmRFnZ%i5Msq%
zbdqlBD5AM-&uO7qJHOlr!%4eG^Y_ruiC%eaMDZ-sj8SiXs4||XM&prY)W2PPF7u0X
zzmK17V|o|Rn=8Hqnala1H%)R*&2uM@V|Qm8JDEv8;zEBZ(VU}<H41)baX1bnKGBc%
zU9goZ*t3|D&Y?b;jFiQKVw^_YJY(I4ayZ$8`BUiVGP4muXV%k8!!{Rg&j3=SvBz1C
zacX5#GbM}oqRvLvQ6Icz{NZ#QQ*)~X$zs8zE|i@|t@BLWr<w3YGZY#u<O%J=D<P5{
zsdwt3x^COGv=`i8ZDKBy8!<Vbj~0gh(Ix*k_H-^mO!`GjT*0V|gk8Z3NVPw3sYc>9
zqL0^Tc%p@p0?nH8+#-jL>Kgp0t59*ycucp~O>mJ9EFlf>qs+lJ+lUV^7(?S{b#p<T
z`J&Ghy1#&HU>99xLUaEeE?^8$tS*O4LxKMA0GiZw!wY0Sd@y~Euu^ranc$Q1?6F`J
zmEM>mbo5+eCH>?oeOA7Z5Gobn`<Zk??Y_TsJ^c~{C8~dydGbHoGpNO6b-A<8e(=}E
z@az2fYR#5)+SNrh_qh1D$(yg&Gx*S%%a3-0Ey+E2kEe5ukX+Bb`jxKmdswbw^)6wt
z10QpwNpSxmexD}IL_=GZo02DFgv%U$g*U)&9@S8Hq>cSZm~dR`u{Sd_TLTh5Q1nQW
zh>SYDmr8XdF-Lh}1n|14U!k}FQ1AXeTdhf4q{qL*R~U@dvAtoBlBqZH|NNHWhtrcs
zN{Y7EH}sOL6(^NGRB+K$Cq?Gkw|ytuJU;+xhlZk#zI#09bsS*31nE<gBpd3_`+)V@
zp(E~Kj~ks~PuM(Ezofguv3&|9V0y!Om@X_J4^!j(%kG6I^L;{_$6ZH}lO_aMU(c04
z;h=$5c<;imGn-W!aO!g&Z?rDS=BQ=g*vsr;B6>q1`Mm$jrGM5*{1io$ty$TpT3!;L
z0a-}GnORG3rPE{KL_l1g8`B?0-&2b8kHnF?%ldFKVyGB<cVpR1v)XtzybFet=Ao3`
zOp9f~s5@Q}uZRhtCFB3puG1<NfNZrQ#M(!MaYEcX2m3FB^14eF6fTvEpa#F9@@YhD
z{-P-DG4s9eZ*%{0YzYQ=S6tZ-gp-nJq|xGWo4_={p_kF3W!ZV<D&Q&Wl8X%cI*T7o
z6idpz)A;WU#es4fqjTEZN8SCkEx4j^CB{hs$zMp$L_go;;uZ^9h2{DA?a;GWts+eD
zAS)_EJYQyBIJq{b`%G9!gw#rKvIF|u>wy_|(M<{5ci0h$u?YDz=uudpN71-UZkF%|
zSVEO1jkX=);SwstVy6uQ&Mz`j7*T-|FQ0Cla=TP8x`}AxD3NexaKgwwUN|X=0;(bx
zGxy;8MjT<W4(QMjnI}zUGw%jOQGv8N9I^aE=xoPod^nx~9btS_Z6+v&hK3~+bzbkX
zzL0>pzref1?E|sDQ|)hr|G|-zU4Uy8UPZg6*T^Sg6@v_{w1nF`2_v8z+PACH?LGk-
zhitJ|^jmcA9BN{lHA)YEP1G<a8{j4I5c&Q5Era91ndA0wVB(Bl29P1e5N{p?3LNVm
zy7ChkN!o6@QhE`$EpGw`K7_J>-bnCZ4s?QpN`3E--#zt8>RC`;xv5Sk76LppfWM(?
zARXELG{44SI8!>^BLNENeXQ70b`{+_%fI!DjsVt^_%^8^+BcWTAt;gcr9aocLBvun
zHs2aw>_{{Ddw;GYqXr-==7?(wOgbO?dWO#>S-7EpiLN!7k!WClE$-X^s{$xLa1PPQ
zMrT4m0i)o#cAwONrHNG)PTRe*aw2<J5ZU~wXs-Vhe))D|9Cy&kAf9&)wO3H1PfieW
z+|VdD_oTFTq;Q%DzlT<>E;$pkXGRuDYCn{RY92U~HpUh!9F>pF_eF1$>MDdltf)%g
zY8Y09D=qbWxsyT~V6f~<gfZ`x%6@x<4Yfo1yS)}EZFr&fJwfFlKVb1tvc^R=7NeuL
z-%35A-8(TKi6O0D_xEZHVHA;no113Hec?$4EV(=q&Kz1yvGhZc*~T}R2W>ziK5-Qd
zap8Yv?}oP=)WTePRulSh3E*3bpQtSN1>o_3zH7n~Pp_=L0!M=DL!}}?G&(`KngK7D
z{66m+jlt6Ol*7kVYmY=l=)P5%Sr66Ln0|n)ql-{@n;ZN5($D0Q9?ZihVJs_j?|A1F
z5ydkGjafzU!*Cp8H{o^}o831+vNaR+Id%6v<@k4fzOJg-`v26?TYyw8!EBfF0)^Sy
zF%brrSHIFD7l?dwTA38B_Y8RJ4lOdiJ)<_kqzOeX73W*qcQp6%^E(#6H03p5L(Y{=
ztvYpTS8By9IaSt?eQih<QS1@eo0=InN*H{6VyvtdFz_b`*AFTWrmDg*50`)b6byJg
z-q>_;6PmW0DU0sS&Jn}2#B_x99fIF;tUO{u_sl>9$D816V?kzq@BKqj7UU<GJ?l%(
z7RqqaPwO!~)msljF7u&AO*9P2mWcw}k(X4QoZI3l-w?jiptQ>zx83pbHHKLpu96$q
zj;%P>xnyagAr4xQdY6I5CaX;r!8g{3I9|=p%bSGPy@dF5A)8U*EiNOALCM47;geEF
z>|>N7`F}7;aHtyEAYWMI1K;Fs_V}+d#;xlxN)fed=93l1v%*C&#!Drh>d?wz_$4}&
zr1hDglkI4ro@phjs(T>i^!<j5L%uWFcKtmT0z_4AZtf;nRCJsdoh-(`0l}KudFALw
zbam(Am5>wYjk9`jHD==ehHoT)oKLo9yS=Nqdn0+rS03+xs;9H1Z$Dc-_2Odr72vy7
zKv`&ZQM3V0>I?tx1h^ag6E}Gtyb=C9#G0>z`1_zJ@oiS*UAusH`}%HIA>*PBl8ceF
z;@bJ9&wt+NE)O+;lOs5ynua(*#^Ce2BSGs-b;9cMb$=!bBH8NE%_H%MDAvX`U3dk}
zU)BZ&I6ued1v6TX-^{am*zyt{@@?ByR8?Iali!$Hka;Q2i0*sGQE#S0<n}p!Ndn1H
z?O;ynE(Rq=i|(5f9qOtNnhL)^=yX@*8}6KhnpHSW{D|snr^90@ArhJ{Of}rE4+|34
z`*n1Mg0xpoqc%|vIhw}7S!6@!8wV@_&*T4&l!LFX7=BLw%r?~{TQr_Mk|Oah$!%({
zGO3bg7x{a+T8E;NoP(}Zt&YUnk7OXJV^Nnk#k@e=yc-U|Pu7Sh%iR~qoghjuI#K^4
zO7V>ynI9qMBZAP;4?43IB$!w~7vIJ#Ixm8l<%u_b!#E#+EYEqh07>E>O5y7_N=`5N
za)v^H(?J)wZ`<&qDw#MXhu+1U(MxTqx*^<<?pC%diHwl|oIey7_A?$)0XO@NK$2Nm
zEj^H%s*w}Nva!SE=!j~pJOt^ouzs)OJ~pE>^8TqN_k}wyG-I4C((~UiXE8b%jzKz&
z;t7e&a$vW<2C}It3>hJ2*b(hQ?gku-9P&Yh8^t5Olq;K0mY8Qmou*IYUL4fU|03nt
zis&C&O9GgIvr#N7eh!LWT+T<r?RLHYFI!%AV7W6#?!G@F9Bo66iTn0tD^ti>lUMD&
z8|`)hd&0**K|4w9^qbUp;jR6p@m{mbR!6#4mlYX2{mzIxC|xuck_hENc#K|=AN?c1
z%vaMF_vOWTJuiWpfNw7hQ%-ti9O7X({8;a0%76UUiZ8GlYjshTYGN-s{x*aTQ0eb{
zb_)6xenMwco7yTRSY0<Na_IrI>x_g&jUa}PQ(W!|Nt^f#*!S*CPfw>THPjz^kD|!s
z@)1rH6?T<vBk{7aJ3G%OEG1(MnWxkT9NF6xtJ#*C3XT3dgriNX&ujBW--|jlmcsd$
zmkJ13XtA9f|EkpTxLjCRm{Wds_C+-_H8}3F!0_fv+4Yk;{t+x{TwfiIYW{cUUVKY=
zScg0Fl-LSGHp86E!%4zoLbF88hnblf&u0OH>FMdXFpY7fvNE69AL)^(e`><)p<5|;
zEvI7Ma?%<LwtSFT;m__WEiNTqU?Uk`pR{7|Pl2$ks}u#7@K+-zME|>ZrrLNmWINtz
zf2E{WpV@hfZtZGpe*c+0;X1T^M<gn{SfhnFy*#%QfHpI4aWOOOZ|Pn+6p{S%P-aK2
z>d*0pIL&h_XErnhqn9F2?cS2{dYf^BZbYk1^13U;9=6`RdGp_^%Vm|9Wh(esZ{3R3
zIal4*<`S^kiu&xaYIL*z%f~NKvz}72c*_>qRe_aecR8D5`xL$s8@Ho{Ar*NfSz~Iw
zsnx$X>0RYi?JrfDg5IJ$`RAMzZ>&zXr;U`S{;|7`{1DHeGc~26*x!B9Jc3Kjc2#{a
zkzc>zfvT-?$I-w4Za#6LS<YGi*N@()K~2_5edU2L&GRMO-#NV^6GwxcEA_Yti&vTh
zPg*dwrC7tS#JzbB{^C5h5v}>be_r*mzo|lVER`B@zJzgHSD-Dsoj#Dp<l9Q9Y?SS(
zt>nMlqpEy&O=5V7iv~^tz9AX9<*!h>2k$UqW}OE~Lnm2^6D8qam@}*pyY>J7pZhc-
XGfMXB4$izZ@Pjh6IFHkJOa6ZV`WmbV

literal 0
HcmV?d00001

diff --git a/content/tutorial-stochastic/galton_board.png b/content/tutorial-stochastic/galton_board.png
new file mode 100644
index 0000000000000000000000000000000000000000..0b049856784645421fe3bc052cadcb21b22fcd3d
GIT binary patch
literal 57809
zcmeFYWmHt*+b_IlNI_x<2`LAW?v_-Bl!l>8kdRJk7*r$$QIKvG7`nSeLb^d(N$Ku5
z8~^95^PKa(AD{Qz%UXNE3^TL$zV9o3aZQ-IsyqQ6H68!}1d0j>O#p!EfyXQ^Hu%i$
zecEd9*BxgCeK!DrbKD+~mLaGg_#~CPte(4;la;&Yb5~2i)6<jdrK6pj#dBv%E+<#(
z<ZW?k0AK(V5l^(eQZ{G3y|kBqN$u`jr6gi17`4n+4eJ=z+Zt9>a#X^|B9gE+D!9n4
z9wp2hlIfBZR=(VXKVc6au7+7*7mQQ0f6yz$>oU~;5<b<ZQy*@Z&&h@PAW?MS>cYb6
z<EIB2pA$vzoCOqZB=n~8yKOU4>@JHAct_>3g@QjUfsykB#4s3a%Ym}w_KE#SNW|^)
z1OJ~t<XG^;KrE#zJalD55xp=qv@14h@Y<XAw|}XQE-aMjGZ2%wFhJ=1FfX0<vkwdP
z>p;m0RH$I@hHc`*67f+GI|_X}DZGXJUlZuMU!AW)ZGZ))r*JqtOWdLb`~~mk$L9F|
zAO5$jMmg#>NRF)cmws7Je{@AtTE8a6rQ?cnt5Nh-`O)wNTP^mR(zcUR^QBb4i4tO|
z9VLsv=&y012*iszFeY_Yb%O>y@3_OzD9Y0jM2XWuDUB(_vQ1^0d}60}Hs^n0v>zC7
zqKd%eF@p^Oe9ylN%YP%jjG+{rccJNYdCj8=s4`5FmZV5OdO;P6%kT#fxfA}0ZJ>5J
z;LB3h@i_j?-;-M6p}`JOJ%j*5B(2y%E?J6)I>G%;m*MAZq`4_Tiu7ZfBYP(2*G#xC
zgqRyst&~!k(fz5WzfaC?-v?f8li2g`?G^<tX{hebc1p?-(xQ~@o;PVIa%CrpR<r<Z
z1(eAd+KQo^ahTcd<|r|;a{$lEi~v)`@8~Q%F(iDQ4|0q%DA9@b?V<X~mpGK~p1}5m
zL4Ey>K_ak%`6kG0Hz#iO>eQ=wAUgEjBQP-c-z$7_(d=&oBtHaj{;frJv`}I!9@6!#
z(+%Na@@4DI#$(rG==#L61B;mN#5!i~<IPs359BB!WQZ~D!Om9jEpFTh$t>#e;fWuZ
zh<X2V`u;2tvk^`F5J&a1`(1wTTHKy$sBk|{-Rqw|^lCAo?^te6+8)bVt|Yr;;H2^c
zNHoK;@Oi59$VSm~P$~Mw5p_FWYzyXaD|(eA8xmRjWqs3-=ww4Y%*MtX%qP=^Uzw(m
z-OQOf_rSPqSmAa|;U*K}=i5T%E<8;B-`yf<Of<^J5{zWqhgoSfFaqzpdWa?bO3g|c
zjk22<+JI3zX0?UxC>u)*a-T-A1AX&X;`d-05MDD_jOn*c^`Xtcvgs&oa`j;J)52g6
zEoUvoTo2!X&)$K@?Ap=k;z#e^;Cr$m5REQOo^ZB0Qq_dYV$4DLg`e->(&Q3PlpK7@
z{}zwe5es9%g3wPfOUA#~aTWA!T1z}pM&5OPh?)rZ$wCOc08gheM3o(4M;{NVm(SpP
zf@apUv>ktHOfl{&s%|9xfv&HNt01`>lT&R{6Mu}1xsFt02#m@YqTbvlF330Ti{(f?
zeF|G+y$NY$JZC2UpKP>sKPU%$%OUJo$=;?u<?0KlKWU6G0!#4zwcR_q0%x06^zxpL
z1smk}B9x49%#A_?KWGnNdLe@a9eor-dVL)peb5)iN(MvaFRXAhFx>MULSXdYg?`mM
zM*dw@qqpPyQAa$X!d-2qMXWpABgDXeCBbhHXA<>*wyti~))FHw`SmnynWprx|5qDk
z1%wRU4*X$O)^y49>*+P?@7~8{8Aq5*$x5vrpPaRR6|!Fm{tDJE!_RxcJo7@=YU9^H
z-B0B%*Rh&Y`53iNq3?L2z#EoAY=_v^6w~WZU_JDYH!F@SEc3i)kX$RyGW%(E#FN%Q
zuTp*D`;_*8f)3x&X?RGI7tRA1Il*mgKINQ33|hBnBK3sF{PlUXdO3zZ1kgP{`JOdQ
z+SKrA(f2*-WmzHRDgqIETPT_+E7K)UJEpzpT5vATYYp%ze)dMB9hLm}!u{Y|y5SmC
zt5S2`1=o-5uhcW6Vv5t=zP$Zmp)3(@C81puMB+TnTF7GWYX4D#frk7SJ^{#Ab4YX#
zKTbZrV;TRI;MmyJn2JZM$|EO(=Jk&F2oDnk0=T`(HQ^1S%S32&<Fq8Y%GcZ%?d$6M
z$mVOE_@`-KsP4&&lNbA6w^}*fB0MA!2>sh=zCR{s_hwrg*TkpTzi{IfPX4wA+W@Xk
z_x+0DY~AUYGA-dE8}EF|)u;a{fK5JrN3R3*$Ea~%!Esp&JnG|ZocZIiXM6bw{yux7
zs5hYkJ-+nVaP-OAwU$OyFy7|ptkd{hnZ|n>qJ>|^-s#8Uy`on%Z54gyOY9pHGp=fL
z_nF{Rir}>fFxa0S^#u|r*m9uSflbGN-r|Dn&ceXM73A4QWT?%AOCmO$nrFP=Z0|ns
z-J;XPJ)2qp!iOdO*SDb$t3>X>grlDC!TNVkMa1D8*y(Lr^qa3gO92Uw1N_<~b>>8o
z<fK4@>4OkzhTN8XR0Btr8Ybq6#QECg#MO3UXxDA!!!D?_ORffLn9E@>0_v1EvIuZP
zt-*@}f4pyN>VMb65DC&D6mm!#HhKKY6$<^vx3Hk~C!y^}jEvcfd|odqITMmM<V-=*
z7c#oyhe`8SBrr=beTGnOo0~r^Tl+n^Jd~D5NO^EXAVDJ7j{r(}20219#_V<gj;mkF
znKQ%l_d)L2cw0IBb>aLKDQu7A0gQm9(^%kl!N>l>Ko96?8m~x;2y~GW{D3=@38)~_
z*j_6$rMoE^lv?IZa3-()*ko0G@qq19|4T_CIQ7)+f=Uy^L><T9V#68@?-G*Ao6!W_
z!F~AQdL0w<5ev@~3@x~`65o^jA1#<8PkQcjSL{D;OHXiL{1SccuZj?G|9Ab)GX;CR
zLH!U0bIcChI+@R(NXwv5W;3(0Y`s?HNu_A3R?NPkRub#2yaQE<?tdLA?6xC$Udk@6
zXHsJWFzHC?lwLn}d9$*4>o%l%T^mxZgl{(6P<5~cbBTd<$W&)WyR><JRURQjbej{l
zy#;%u46eq<m6SmVDaCUimJgeZ)-d_q%9Qx#t)C{`!TqtYrpfG;oPPTj(%ZMlA$|aT
zyVv@$w5=r4Kkioz&!140@iFTCiYZKs;SQn{-B>zfjy~Dp2(w|i?IZIvp1&vafTp#=
zuW!f!h#B95XXp6(qOEKTcXZP<c(VCA<4GT8J-7|9OGc8d?9XR#Vg}j@zGN@?>av3h
zs6_mok$9|;OguTh9ayN@jG~*`<GN65IfM+&?dAN@;%D!MXm4&`FeNu(5;N1*d|>t1
zS^PCG^3B#WS{6}}4{lBuMVre0L!fQWfqrWv_*?T>Z{R4hMlo20brg#JMJs**Azm2u
zOUHm|1fJ&7!1sg01Jr%q^I8UGsK+U*e{_G^-Jr8^w$5h1k{<f;j?Ox~QNPdr*8s-o
zpEvE|QvV5nE(*CNo-x{uBwGLOcaPW;OJc8Wje{tI`(E%@qC%~jboD4o9DQD}-!B_w
z({`zmMhs18goW-$#N&o_(X(9~=^q=d^t@wCzDl~IDik+26Z>7o0KCNMxNF-_LRSZy
zO%l)Z4<inmPK)9ng6|7vyluDS4ey%dO8Byo<F@C+>FnyCnrK*{lbbei&<-{P=I-d|
zG2!#|Zx~4)M_WhnMe{nnZV&&1VlFe!ZJVWB$!!5as2!Oz|8G3NER&5#Cqu}8i0E}%
z*j6~LT%EvIb&6uLzrCTMw`)ibJt(k(YjN3;|AEsMJrr||yH14iB=&^-u^rgIn@Df9
zYV6GovuX+~+O?KN#NL9lr3j+yjloLbdSsP|yzx=K@2b(S7q7}oX5ES#41G*KtNcp4
z(!vwYb7+^4fm3(?+o{6BLM{}}`9<y2;n&7(=eRpcLV1m^W0SQfiw;*_S$;=q)-yNM
zv*IUfQv6)Hk`<SLQ~&V_`w;49!60m~=DoH`?>pY7Y$AVN#z3Yn|3K(~*yhOq4To2}
z*RIi{3OwOpF=3<T?aHhaG8jzcwJbvNyzf%5`Hj*>{g%aS+OyZchFEtt4oL|9a!Q0R
zH!A0rD9&zAj(UcBsDgb&9$W|OAnA3s36DqYJY~)PqijZ4k$uXJ!imdNcNxIe)jcPh
zi$<xaeb&`2^4<LAksR*+7<}WuGx^%jSqxy1KtK3Q(DL_i*C<Z&PoVQpaCJ_)kS9hQ
z^_O8Wc1@;{2MqB2f0-j88Q7;pen|wJNO<=5mUgT9?RZc;*IgmW%2#LKsIFz2AC%kj
z<-~<&LBZE&L7p%6*-@~%<DrB-&-xO7Zl!%UZbgaxjmFpUT*{MxXBmILh3Op~XB%`?
zMG|x^j)nSP!{f221I(}M+{Wj-I{y&I1pcdK-mb0Z%@VwU4wcl2DEGms#Eiqc+V_=S
zA2UV|m{!+h5RkyOFy~|y5E#Q9$>RlBCC4>&i*j8h!=J{wd3k(T3TPg^=7f7;>6o||
zUhICtAHV6_2?z^q`1j${lVy9fU*yY9bMM2c1#b85zl(lGcR$F2Y+dA}?8l%M{T`Y1
zK9^fE>rCJh>F;@BXDavd@03$j)vME4MwkW{*nO#;li1h@1zQ(nqj<-df?AkqEI!Oe
z;zsiFL}8S^y7;cX2FtzPj8pSpFY4%!+wj~0H<BAhG6W23YiP^~yd171!M*I`T``1M
zNWz?HysFK19Q0ZeSRtLYix>mq2ksnXkH>c07~s&``$pM3K3gJca}i>3es7_i=sC)^
zFxvoOC*BPRR33B*h&w%>Fa)nh<gpr}>EHGXs-%eALr1gkDt1y*S}cTS=yvT#nr#tR
z_&8Dctqsad@7xJ~cj0gHpY{<`48B<s*Q^$b1E63*pAxN?moN)ASw0J^$9c(>*I^_q
z`dJz>lwiXDZ2W``efWpO5+%G{sc2T?*<6V~5bDZdemt{nc*0)4+~2-$@~Ah`(em{#
z{fOq{O6=wVkWu`jF)Fo{<>aR?jw_em<!{>Ptk^XlltLkx{KctrK?SUPW5ofJ1GiP?
zUuW7YWYr>ky>2;YAY``eDE78ca>Wd*AzL@m+o&Uf<PK)j#sC$`korGD#`1T)PCdxK
zL2%FUD!6d-;c3d5UQn8P9N`Ov8;CWc-`IU6ap&YWS(pv(E#EiARUf$_YOgolX<5!o
z+?)+gG>a?r43s-}y9*6Me^0@JY0QJmp1YQ$DtXq1=jUU6Jhu65>Yy=a#Q;Aa54pA2
z_ctk*599|LF1(U(w#Rl`rT&E(9|%;{w|;#fE#phByvG`|y%0xWFkT+b97(HH;Km4t
z{!3&Yc*xP&8|B<G>46mjWTM%!K}2k&LM_+FM9#Rp+VSsw+tZ{qgmr~QTzda1?t8FU
zYrEso4C~HXeUCdPNAr0S*8vRBzRh&nJ3S^`hmKX&+C6LR#WZ&pmd#T^HsSD(O`y+J
z)8lcGnd9HXTfz_DvcW<tC7!dD7w`GKgZ^dshBx8iD^~`h3Vz~AgD)eD@Y^czhrgp?
zYU0b`W^Syf8-FXCFY^Nw$laQtpSLU?_8@0p{VcO|y0^OdpQ4VVbJTuKN3w?geh4cl
zyU1rN;N_`>u=D55`m8+v%EzcbK1G4=r&Rln{LBj>&;l|eg6D8oz4V^@WRv%qm^O&k
z)~7z!53&sM$D?&i_Km13(9V2r#jkMnL>WyT2Y#H8w~LlLrgQJ_feG;2_$@+4TYx(C
z3!0Iin-k>#|8s9~@_^neLkoF9ATihD%WC(#&hdoyO=HtH%~?;_iep}HYH;F!4g1nr
zXjf2I0S^Q~`?xzeaLU{pBEHp!FoU0Fk{}z$wD^EDm4_s16!|z<+g{b_*73$&j<cC;
z2mU9Ym5%TXSO)?UcTA^rbdEQkrajZw{{=Rs&;Fe7EVPuPt?i%mQiKdy-~lPYlZ(yr
z0ZSn2IF_vCtHF<rV3m9wPSS-^&uQjm+S2tq%CoKL{PZFA9R=O^%K4Y}4qI$XwY}+5
z&02_}-EnP?UVQEbVy-2ZFq;K%GpNn2dK2~nkd0G@q%mTD_Pn0Rd!K*t`Rc`0c+}oU
zpi^J+)#!vsey4tCt6d~ck7Jy00pg^BOwLhBekIKtrG~)3#{h5CqOcJrU7J&Z)e;wQ
zI9y{pmQ7rH+<07$ZhSLR-`luv^k`-{PAS!2$Ieb;B@Tk(T`>nz(}p2Yi+(wJoy=K5
zGM6=PLPIZMVF*=d30sbzzBnBS=%l25nlu-GgcSl!bt5}Z29osVDoe}oKj1AuMH*d}
zyKxTY_v-OO+9tw6g-hz-e2?x$Top|=f;|FE0s(}8pdc176RUNt#Y5RpS$q{Ci$ofo
z*lRRe=FDSkme9x?Ck8|9OVNS>Z`lDBR@O5*luFviY;?7f>9YyaArlbs*@RA3yc}Ty
zB)1B~x`H`5ITh0l*2imnJkTy<Xnkle=3prf{gENiDOhOWVVY(zZ3(_+C)akHX=3lU
z^XW#D00Pkjihx-U7-$IT+28}v$pNh<cDm^FMP0S4m*`v(;-D6C^+rU{aH`+*Gx&a^
zwOmwW<vo}FvHCCsJQ~Q|jlCWl8}m4%^_<zOGL?X7>^U=eW<8Kb1iYR5jc)Up{S|O@
z;7F}od`*O6PiA9tB(_iuQTPf?CtoPBUm%GQ);^LA6^Bbt^E1j9QL(hL^%(fZ@UFZB
zT9y9}n(=s%qw@XiBSOR9f)&8G)<)p536dVGj(!yfmKWV_K5;QQ?pSO4{cTKYQT<iN
z(MI*zY)^kE0xpb^u*~Wa*2P<@w<+4}17`IC?!6(Cg1kJ|5BjCEVy)-JmX?+WSL-j;
zjH<2r?gyNdu-Dbq6|u6i-hqe+Xt50)zPQ%<cV^V5nXqGX?uOm(!9dgz7^35sX9r>z
z-uTNy|86?ePb|mJRe-wi@aqFO8#OjZR^w<S6+fZIn4FUeVq5VcNfU=Dk2bB#57-^x
zeuE$~m4YxN<ZP4#Mh*dk)1=#DwiY-(iJdDQAHNtINJ}!-Kg-NlmAYyx&ry|_+%b72
zYhjUHIc|d6;?qqp)N!{f`EDqSl*rFi8*Z{NL<dwaV$Q9&i9EWq_#p3Vs!*l(_tJZ>
z1Ob-8!SNEu2f(PVj-&iJ*Z2CBs_JxprdW|&_PqOmG^Uh(sQ_OF^Oih3CK#}l`09W@
z2e)*uL5&ksnOra<Y`97Bf@uK!K{2DN!iI)RxpadmCNwTUdB^Mv<h(Jmir^1$%7Y>@
zjL>Lbck-+)@?}EZ_$akOW)`%>5ZY#70rpMY-`~H1>{5X_$xX*WI<2L;?;x!MEhEX|
z_6az2fE1C%q+>|4&Ts+jkOH#SdB2yhC^+=XmYUI1OJGDNf-$OnyL;b%gE89J1;#p|
zGtH_ffaBHO^Jnk&e_3>y>Rqhd+<_#GJDZnoJe1<E7{tp!RX*f4U|^jtD_Nd3Q!66<
z%K=9+jg?hZb#T`Q!vp#K=U!}aNn`WAp*GHcZbJi3{hlrd-5j(^uL|E!)#Esppr4+y
z6r6|_BVn6>pelvtUM-*FKr))j_K{zhYv;wP8~r<CSv|L>kyG9hK<=MbWDjG{<%Z7$
z0v?kN5t-JSg2U+}+Rckk$4Ftz6d>|FhN`HjbQshFje%-6vj$=rI|UmNNUA)vb>6x@
z&kD;xw47BHA26wtMgv)R-FtlY$FuH2`-l&i3z6KxFpE;#BG!O_9b^m3#Orr3KH{P9
z3!{$;534SQ2kCgSSOF)%ONOKFf?@%dTZFkQKcCd|3EWU_<W*+%H}vY*_;|q2;<Qkf
zW)Lyje8?{>q_r&cCu|8y+n3q%O7YAgFw0cW{Q~av$!+;g-(Fi2X{xLoJId#VcN2jM
z7lG^e)CL$09(6@MiX#|Cc6N60XcMr0*?W7RVcnJz?{*kR))V{l!@m}hyv>jWukMMC
z#l4Q}IsU=mqKn}tiY|6Q3%UNpT*)yNkXu~PKq^fP-&m=toHf$-o(^?T-4zE)N}7!;
zInHaM9d@b|9+uHaBabUX8(_GYl2gOO`}FkF@GOZRx2Hkp<^80zaFpF~K6(mn<%X`>
z+2G&FAvPP0ClR=8;!=-ETlCehpnyG<PFe9&L$WDo9CcvbtXtwxhi6$a(&GhR;$>4b
z80>VnO<6Np$RQjMX*JXui*RbbIxdu~MASe3`H_j+tW$oaHy2zjZBIE84JSzReTFP!
z&+XdPC=O1}tLLiTvhWza?PoIHU#6>We#R0?5dx7G_4IN4)s2l4Zg+^D{#p^PSbPCE
zk4c)2J~}AK&bCkm`=>BsNha}Q>G<43_+spVNGLW_e=D5&ZPw5l6nXV6XOs!v2^u-8
zes<x<3L-RVZ19tn*qqMAJ*L}*_I(T1{ttPDg;xcY$9KF|Ov1W|EJ`QGB&*_tKRJn1
z*&}S{qao7j%faLMbpEt}m9CE5`%nzKn>oLE|NN(!zA3`?oi>1Tr2j$d_?nf}MSqBm
zz&Sheh^u&S2duj8&z|)dHVMii>VrYi5F2#6COn*;?u2b|Kl=1@rYHD~&P((qDch^;
z@YzXA%}je^6c&0a3$6ip(HatI>fRI;T}%98D!<wg2`s2A2i$#>LcVC`?VOGg!L}s9
z3i;$ANtiNe%*<F5_u`M^Mj3d_DLcyWwl<OzhDdE`JwsF^-xjzJB0CKS#{}4Kq{w2n
zlR^u^+s&JIOA8zD4OW>ZYILC}>VxESG+K)(@sbf5R61?|vk=0N{%P3%d35(MAd2_C
zDq7XAl~OSOv#e0A`Cz|4af}`Ehz1C;R)WB4@3bIp!^!vu$h6-e9+K2jp*(|+xjJ1W
z%bkCJm%13!dN4LIN^^F8F&_Z`z{eQkM97g4cv8&eSAE4i_JbaihpNSNPF&<D?>#5Q
z!-$cW*I+0d0GFd+5UImsYC3a1huTnp>evtikN^3h8uT<hWnabDuqMga_$v5UPWm+~
z;B~!5adWWpd-^2s>dnr=JiY(w>u=%V03aavlQ7UxCGC9VO$_aCjZ4A%MURl3>#Awg
z&8~kEONZLUA|&D!9&Tgq+JSAxQT*oepvTWPEc6u&Y$^aV{G)!U#2V{Oet!N2PQX#D
zQ#rF5SAKDU-_wFwpz|drs_5!n;N6y2fV#!1P?1S06qOU=?}GF=sIf%4b?REp-wX~r
zHDFtGpx4BC%XkbaV%W7^QuVyS4*K(p9r0afG`b@JAM!<f`2+_V#D297o|ypTb_C8>
zMqH1@ViYcCaz5|>*&k88umOv*bN~MG#=qiu1Ek<GU`<@L%v|i;OvD;~i~Vfx?-qWi
ztM03Afp6i;xr;oy-4ue0O6PXc^ArNK`>1@i|HkaxSa0YTIvyV|r%~N^DDXDOWXw!x
zcJ*E|2NDDXn=r%QkoioYEr-&#2Pc8y2_NgCjQ}4oeFH%T1)pN20duPb%q>YE$*tS&
z9=C~KHT~7nGk?ov*G`wT%JFNbsz)s<z`cm|n%a~38*adBAq(emylHK~uVMD_Mr>ew
z%pXgSpoKcy6Dqxy_JI)|{pxCQnF75MxnolFe5`RurL{k*4e@2_PQncq>gT6G1MK!h
zpb2hU_oip5Tb4eFZ~60ZR>~#UWRw3zHN=bl+~|*p>b8Xk=)&Ft-N~kiwECX_!*bnr
z@SCkY)}x%%S8JQ=>xyZ^8w$}+Y27S6j`RQ<M<-Ls>PCqfFpZ;6PDCAaivoT0+v>s`
zm7+y#nu|h!jDz&z6wC!4Amsj#fBD6DFO~0cD0gL(Q~R*<v`lltH3#7S-kAux%Yq`i
zyWPFL@pxtR=kUHR^Vmbj?!}iorD9;l5dic3tmztthQ3MkSHwg8AYG)+fX8$(YahYE
zU|Zn^Tl7i5QH9t#J9}}+qCJV-P7?<iH6h?Ui>2-m(xv+@@VNZ`t0VrMdY`KvP6~Tv
zsC3Ivv-BQ@^v&O?!(5%^Xf{Ia7$(-z!2FkV6SPS>+{xFM-Ig(|Oix4`Uikhr2Xb@6
zX|Wa#@M!N$Vw7E^iF*u<Dq3?%21Kh$63HEx7rgpkvjEX_jp|6>U{$-VzTeJXdVxC+
z;5RO`99cmd_YTu0uXm&woC{6+HVfXN(f%B}UpJ<wws8Ore-&9JAQJD@t9JlLqVLUB
zGnRT>^x~}VS)GbP^uBxaVS@H*A_^1I5-y%vsM|+70qx4(UajT`TnnFfz(W20x>EQ;
zsaSKt9(G9su(2gU`>*Lwc}MB^@*ZC=bT7vgFJ({64oyzlWDl(=Bd-X2t~LA~qI!T$
zLH1M9Er(nD4+OXUF2)dH&GBoO4t!)RW4SDhJhIeqs7HTWc>^q9zHtHa$wfR3`SfGM
z&O#zL!|!KXvpCDU8ro6;+9o&c17Uxl8jTh;^=c;#RX7H1#l?EmiRG>@mnO+i<aTgS
z3)eeRu$Bh^!|VAMCla-fB%L%>F89OvDH@w8S7XQ{+J(^TTXRXFM#hGQV!5Bw8K{+R
zFRNvAZ0tR8j0x$q><eRYx@La5=!-F(^rWYmAEUOWn_b)dPb#fff*YY`^nkOmCpIcS
zu*UswV5x;3M{e(Oo2iu$fGTwrAMT;U9If+&NZZU!{x&w=_to%M|Dj(|@w{&bFl*mm
zV<ffvV}W$3a_LP4ctB995QGoGq_KMhO@Mxpuh%JdRL*QMnsC6ygpL8n1F>>?cF7RG
z#=*`<S;n1U_lG=6R2G7YeAjY?^wQXnPH(WYtIgN>Up#_*o=6WkR|Iwkp0{mdlsrXn
z@wL6{JF0Cr`7B)E#7j7r(}K07>!3#j{N!@OMrCU+J*B9+&=AmaqV)XH{WYdjhclwr
z=agdPCTWhM6Y7NnkWEQEnWOUl;RL40lo~o*Hw)zm0)z=*$pn6F0OEd@Tef=Q3?gRW
zPDmR)EGELO8{fQia>wswmki=dQ<>{<=<skSHMq=och!<>Bfr6KFwBs4cKP@VWPxH^
zrdG8f+rbLR2gKqy3oM~vK-sSN?Y&`Jp&#p8Ow-ILEqp$E1(cY3ds)hQ?L7z*-g-G*
zD1H~n(Qc1^)5;9-8|E#$BP|A`XqKPyClhV^JerT*ppx)8<ODGd9>!Y0X*qh%Kv(x9
z@$=`;PcCd2vKnC^8pS5I==B5UjuK3?#^jpMf7Ugi*UOLM;s(&`Z9DeUujqi@mrjA$
zEye(~?2GaG!0&0`-Caz8(b09X%GK<;HQRH4++SH%@|RBYF*%^_(*MNgP8ct-3+iyu
z8=cgd>N(iy$Z1^4;kq+b)pZYWeorl}12`9ci}%khXmEHNY+Qb07X%ibAKU}h&F|m8
zXGNyoIrK?5Vg`v=(=QO2chMVx7yt#*Ia92`jpt2plBjm`h^w{L@DVlo?4TAqDTAiV
z_Gfms$3%78&wy^=GQiRIqBK~<N`P8|rsW~>stg^ViI5CW6P1^Ktk;0Mzzw89cNOI2
zJF`KRe0qOO#^YeJG^<8hR+Zz|_4rWX`@l_f3jg*)Mm;RE`tZ@JvEs&&i?r~;KQcEv
zX@75Yf>o2KFCJ@ecMJIbMO(%s17?~ko93ln?y`o5e<ca)pJff%<fGG;SsQ8ZVoQyK
zfOS1BKnS*sbK4n#Om!PC5Go&uE_Z_D<)a>l&Zr5O#6fS{>z_+}7QGZ^TjD@`pJCNz
z-+6a;Ixew$(2f59(J!q3FdU*V1#Kkz2P%DvzXvfvuMaOP7y)Idx~YlDwGN0~<dGC0
zsG8q?DFtpzF-}QSo}#iv_LMufkLvj#<+t#8Xv<%>N0E0!O{^muH+s_j?EBWo|Kb53
zT_@UHib_8eW2vk=0ttHMOA0}~S{R8Uf<jJX!)unl!`Zwmd=nly476Slv-uZ%XBa??
z#F-JioBoy)07Ev1IOuauwV&wqJ7I`FVdgZ=P2W}&@(q02_Ll=~ZEg7s)BX0j6^bhl
z<!mQQPG%E2VOboo7;uUy3N2(ARhgrWq$iF!_Y%L(5%)8x9&9MhuB&tY4DGBIEGWi8
zC5bL_sXxI7LKiMAk2cQzi++E}+v~|Vg$;|Pm%6?@jlbHeF9&<m7|^uCnum@8MXdS;
zXLi^!J;uG50b4t}=(6!^i1bPK419l4k3*<@u(K#XAAkE~J--K%g0~P<yR~Hvv}|^F
z>qBXZ(Nay<O&4@MCoa~Y@bqB9V-aXd*%`q8Ko+xs5!B*|FS=J>=WPUSaR;WK4SL(y
zwRKc~6H*fy4{yXkdp=UJ-McEMzo7s^r61{V(h&{u&x?zQiqU_Xm&sKBDS5GZfP=is
z&AHSDLvWQ}_&#w=G$^t9-3vo(%Uh{@jl8KV@;&^>^z7O&bkX0gJNC_tnX|i_;j|o(
zV2nJ<$W_H&cpT+6>e2IA!ZdWz3WS?%K*W%*Bl3Yg$cqbt@hO_Lb1}4Moxk&TJnpoT
zFGjCMrQ*l^0y0{{90)e(j<!u<=Puq1f|t{P88WcZR)0y?*Y#52As<!Co4F*k$p?jp
z_l^(l!P!Vab7CpmS;Xl59B6G7aUg2YQd<==8~NyM1uQ5xdR+}1<xtdi!rDcJYZF}b
zTAOs8xHNwMy(<jikp1084y1fg`bw8B<S@k>{8)OL{C>brqW}wADliA^eqXIBHchT?
z9?{qQh9*EynITkXMixPC6QX?-aEmXLlZCcW*K;z6_EyDhgyfyzr)@pm-HwOjh^3#5
zQ6gCkJ(bTGc3qGX!Uy{niS18x`y8BhD*t$Ag47#dcIop|`p#zvLN^*~OHeB%j%ZI~
zKivB)SWs`(&8gKSWj}qN-qBv$a8`VKK%toYxNHBNhbiX|UgVKEEHO0gS#NeEuZlu3
zXd_7e#=RG#*4@)nOcq1rt)zpr77`MgdP>8sZ&24-daQtKq(P6!xw{vz|8P0~sQ>!U
zia9NJ=M(h#!mR+r+R;i^vli6<^(gvE^uSdLV1&eCw7eZ?y!5dybJGTo(Q#>SEy<{A
zuf0Fb5ekm#H-Vtw!GCt@2cMDv#{-t$fTZj>(jObN69LDF&P9)aBW;#M#Y;8l<ix6u
zj;FhOic#;K1rV@TQg$f>UpsnV)zOo!i+Ff=Fn;{Gln%H{U5XxDcHhC+f;~gXV1ZTW
zOd9DVw^NTj4|Y~viv0xL)PVCYZ3Z4}Kr`x~x50OZ^E4~=pG<MVe@b5jWMnlo_}xQ!
zw?8&Bys9$^5+$q4S$ba-#SM{G+B(Re&I;`5bTKe6m<yB3K0^C=R((S+g4rkvZ2QGm
zlV}9(l049evE06VERl0r2=<>Fvi+KI7fHtPB4Rt;*e{y0-X;s*RFc;L8q-LNtuNnt
zZTFfcXU@hI$c;0z*r8E*eXG`;=A}AF|4EQl-R}qCX%Mkv*gG1KMZ%K=?R4@&dk0vh
zDlL0HH*Qy*JBx@bBa8RyqiHSxmNkV;-LV-LPC>WMYMlXE-B^q8uCG9Yojt9Arlw}a
z0aF$oC{oE*cx;THrvyJhBDgp@8W=W22BaTi#(dyinFy9l3mpybdLAs<U!*yvU~Fux
zaZb`sh4#5eMhdjhl6yUqm0_cP9oJx52kuUw<`|af@-r|8I`{oK;69$<7HU5n`KBWF
z-6iE+iYxqH#IpZaa6X{f{jXh@cY^zay!FU{H0HJH=RaTU-v?Ii{nm4OATd#d0q8J)
zbCM4VB>4FAg#{1gWfJqu=NF$lMQT5EGG)zqQGiQ|$R4sp8*H&Q7NX^uNx}lp#<hdM
z=PZyO(ew>Q(t)9!i&%!J3Mp_at(Hk~c5s00P>kwgCkghQ0WVAxD5M%ANkR0d{J!11
z2hT+uJ_Q4#gZzmIjie~E5u|0T{jM$n5=jmM0s~Y1Jn+vEJinS^veSc;(VW}bcx_Ja
z-lw%AmMfrFS9^PKj1B4KF8%-&3c%-mBzj%tHVW}Pl;P{|ArZMPPczjO>Dd!*Tn^WU
zr1rjM!qvyPFJ{|(6~Ahd2TRI<jW}`4twV5BAexB$T+bx2vX~2VA$8gl!4`++wxUPK
zP+{ED2#Sl3Hzi!KQB#B%O-@cGu(`4q12qIK4&zhJWc$)+gTo%D`rjkLQg4k2T4{pi
zfQ*Nte)svBu~8RZ529(JJJX@W2jkk60UeQ4^y{mfh*<fQB~@+d#2)qeZq^$Cx@d|^
zt|p^C2ZsR&%c;`dkc~S%OtfOK^OqKUf9Pb6y_wEyVWwK+t?3&Mi(cgTR31Rs8~d)l
z=z<Z@iWtKfQomKepsvQAbbJGuJ(DDNv5OD$)6IE0XmHJ>=OhyrGoI2*)1GK+xTV<5
zMBw=sG;tVI*p#DJ`j60H24VO|(F|qW0$gaKr2jd>qF1+35O${e?AfzcdX15I_5qPa
zJ^UE}Fz=mNsj4Cm7Exu3W24XL;a_4q#angIwLfh<Im*kNWD$PJmtVN?k-P_9>vpj3
zxG`SHxxBp0e_IjskxprXcH@i(s{=b6hkIe~*uX|kE)7QaAmyiv_*MQOX$DVNSC)o_
z+>;k1h({2X$whOTPAW3H=3F%AAurld<aa`nC}~HE%herv2ueE#oBXj{rUk=((^GnS
zfG=XQAK|lYIxheC@nbHoj@uJ}$qH5Ysu>TQ)>J=&Q&d(|JiPFJ_B+oJV>i0D>Z^K)
zi*a?fdU~o_N5bnXsV<TUZ}oOZ_X0P308@#H^#e23{zGk3uEV`@5I6a3o(`_sfi*)X
z_Jh0t87Qx4q=8gQMs{ghbUD4<ymYKdAa-bGt_ji-119cxq2Z0OiHRd`3uuBCa-Ktr
ziK^s;F+_?cJF$RHmm+85le@r$rP6Xof)%iOHbgWu=O}#xQ4pY{vRKJHxlH3M+8|6k
z3NbJ=1Zn%v9m%-}-j&*?^fEy{8l$b-yQrNk!y4z`&9X~4U^=DT2Q8w*eCDi1DiC7t
zv(ON#5yuoS#}*rxy-*zD!a2&h1xFsUQ~-nY#?0|?4xU#{4unRdWnkW7eCoAScMb^l
zY3C-$GwI`TG~1d90G*==P`wI3uF*9>gIZL6zTktlT<oqICMP9HZnV|eBYXwH?ORsV
z($WH23fCGDt?6%C7y2YCM<eun-vR_sfl!4f6u-z~ZrGPrSA))nvj2D64VQEs9UlHj
z7Bj=dD0%c9pPS6Vfh#NXH6(&X4eZ?RF`-LEW&wG{q|^T9g^lw&baQP^;0|mAODcdu
zk(91*^t2J!MJa+M$NNEPjvd0$#~R2@5=Q1{%#)P~YLqNQpnvCri<-frHC)^~l?gZ;
ziGT6(FLvh?BduNZkEp=b734qdk04mQBaJvlY|gj1VUnmt;l;h=)ZN;6(;ekkQS0C_
zMa|;Grb*;qi`g>1iI1dB6qAYwJ-)jN-g(eQop8qLHV5F<Ny(q_sA@hT&F?zeoK_7P
z$N^_2+wiJi*xH(|zA2!@(QNg{=F`k<#z2AN2-CO?8j%*w$sq7F7olk~K{O>7=Gj(&
z^9@5;vJrUak%+9!r^7_X%vrO7pnB)hks!F++ei|V4^lfC&>Lt)=A=vVk>f@}P_c{R
z{5x~L_;p!+;5ICrt)|~Zgx<{!!Ove$LBL(&=sSyWx#_ItTn7NaBGp=#BmEjj>Ks6U
z-Rf>jx@&;HP!yfSIX=jNuuR{^**JARdyDX8Aj1>wNWfZ?D7|vJ^{Ot{^Q8W3=gc8H
z_qt_G7QNEG+kfo9^mV&>TvIMunVwq_uEZXhwxLT8fOxJ7qlP2LZw5@5Z~vnE9Vi_W
z#m2??leUzC5!?HRe{R^kR4+eNe9e=dE`Hv7HC47Ap*tpiyuH4%$Bs_!G}SGz*bYa)
zOKGIHHDPXGgS!qml&KK@O~a8j>wbN<N>77}S=7hM4fYaQ<7pdf{Z4N=BVkOSBY`>G
z!^oodP@C<jB9um_z~Xpu+e_S};O7<q1StcDJOCF^lMQuBtR8O0Ht#EM-~1}okpOz;
zQc#w@Si=6^zPcaHMWNVIpf*0G^4nSD0es}YI#mREiDTdCpAMM*X+NI+-4>#zS7P==
zBmI-!Ew%#)A-n&<b}OZxvJXjKVlOnZGJ*nI0@Jh4mvf*Mf-MFXrdeXbkZ6h+f;Iod
zt0XWO{F{BK*FdQ-5q<7P7Pxe|gMKU-qd<1`>rHJ^Qc`a>GvOQ&FayJJG@bVu7i#u}
zq7wP7KRZoVZRvwXjZ`s6Kuk5SnVwV_ir_@pPzVYNQhm|2Ke@g>t4Gf*Xgw4Anu$hd
zHI-?Cnnfk}=Nf4uDBU-rACpV-%Cz%?p0hUtX!z<Kj9w735qx&!x;>tGEEOfMBxB*<
za|hkqGWcTKZ|AP~cc7&NBA9v`5M+43_r0C^DBWCEia2~IKqe+>(HjpDH+|c7m6e}w
zxA{F7-`{uF{lD~C`rRi?piX<Y<z_k7DM8fDs+MSrn84@u12e!ZAVbZBZEZ!|<D_1T
zeg{G60yEePLUvoGm$v3$f<$}1dKEy}LIQX<Up|C8g(`qrk<><%*tVD0e0p=l?Emb)
zEu33ZZ16t#ust$x%gITs?AFG-7+gKMT`xn>k`qX9A-p%l1#*0R$f%D}D*F6yZ}xK=
z3fb(Tz40mf(60FXU6*O3;7Z+gW%Yc(g`M|lgM<#az2ra$#LLFJtxoG|+u9lg{)T|j
z+JCitsUvHYF@{u=z&=W8q5K0JAP@y@uHUx8V2h{(R3i~^ix|QpYv`n>uA~g&8oCfA
z%}|p2_3PJ+{E;0tW)!#5u!yatw6fJaRcdPLJS%ASP@^{6(w`Mn9zc|jOF6Ti+<J^+
znV=$WKUMKk0>$ms&5ik{HM+W@qG3_jv_2~ny)FVsK>*~{HdyOT&u4}St@@IXQ$s^8
zuS2zS*O`$=*>FB3L^mLfoF|UaMIMPF{YhFF!w}}u1<aNFss!zFwTcJM=W$&6ppFvJ
zOnbyh5;h9eTLUYVCFn2=fDQvTEm;4z-mazxO0vP{oUvfFHYIQKBmK2K?gF7*kO1M4
z_+Grz=6?G(CSwHPgqCKjS+`=7|NJIFpo)hr@wbZ!v#;}4N7f)N+fzvv8vA}gga@l-
zr6DX{=%Yc1g@E?=TwCpGnwTacV4*N?y{%NQV755zRm8dwaMNXP=(la9K>YvOu#fAT
zuLXpJ4D7a)Z!OF~J#fSWY>ln&z>&>484;RmQ`lKx8VU2&uqsvLr<q20jKW=%=iGyI
z9qEcspcZ+^1=4pZb~wLl_XNMuP``SH37JO;-#loE%d^GR;k6{E4Le)(8a1CkpjHN7
zKS~6PaTaMHY@v`?rqIe8?fhrt1sqk@uiM#1X-}j=0BA+OgHvGlPTIR9R;}%s>imiW
zAAq=&s8G+Kesm{o?%6|<M689Cl>NLtugeEg;0JTuesDBcsc9SA$hD6?wo(=W(ghMv
zQP>b_#L`H>2|t+!Ry6^R^AjI8$s3akB1~FZT72M=D@VMzsEBJ#UJCIB3xuxpx75WS
zd4wan90%@iOSH&fiv}3SaqBBC2H@`}&Az{kK~<_K)F^Z=e><=NG;ZLa_f35lR0z)1
zH8uA!V4}TR>zZRvt|+=gtLIG?^~AbMUyXv=V*TZ|HA~X}-7oj+(^Em2cRajn7OeAr
z)kQ_yB_OF57`>IpX(}r#)1eEEcEoT#Zn|iqBrML0VQ_E+uLYci;El~)ki?+M8=Qyy
zT_&Q&`CI%1TyK!Yj6hz{UpJ`nC4!6Wep3ght^r-TE=K-Re?b(f#B%&QBKqsS+ah&3
zrYmXWasHQ4E2xDMP!R3sKiF>cl$Ox3V#)n~w8CcJDe@SFB{o3nFjgC>ru>k^?s7fM
zCgTtI?X>8>BRT0IpaubVJu@TH1<Yty`OUZRN?*w;vU!BhU)`1MUl|R^8fIfF<nbw*
zzuH7cMMcp=cDXd*a91}LGS`2f1Uf9;p>o+5p<O8{`(Tj|h~_33%J@He+^Q${+2GXF
z6cfDMwL6`Yo4fevD>w`Zez}jO&A^uv)h6*Z7TrJExb(QrBgLA5<h4Q<Wx1~ShEoP<
z7p62b<Xj(cmdBdY9QqLc&TLt=`C^(DoIQCC)JBJ$KQ}g>4FX%HfV#^^F&IkW;r<<1
zVxm@)C>Zc)QNEp(^RLfLF<ORd{!D#o5z0R22J})BnrMAni-SUq(C8e1@-ypurAMD8
zpr_xW9l%+8khEYjkc5dtGrnt`>w*kX@7A!rwfR)Y$%D2mEiZtU5*TBZ5Ln00W=GUV
zMn_-hNV@C>01Htf&KKw7<yGL*+j!t?Qh1kO+DGIVDM{E5Qqb`gK!J>%z#H5S`$Ixq
z^|79lZ_Zf2&Sw1%=0rkY5pVMR-%au9oq%^)f@+OB8N+6OS8k6oZTW0)@xuxYt4(kg
zyw!e&cB#POpocDy!DBY`;of_>6Nt0Fs`u8P_J~?y=B?88l~Vrv)kwSCmvr>|_3?go
z4i2-}X0KGe?N?NdvK~Z3BHjrguLw~m-b!Fb)Kn|m5A5Ngrhyr&!mEh+zPkjjf|zb(
z)DWP$!Y)5lAVQ%WNqZ<v4bo3jVC`to8dlp>ROBd?ZUBC%1B}sk1<oRuFxXH3%f7-=
zJ&u#sD&Js`K&=9!XS1E^Rdq+nv_R2eeYBq|&8p^vM<5OZh_Pir4Mh+r+AZaT&w~Ro
z??B4u2YgK%Zblx}OIFJGJ^-5p_9)HY8dY#g2hZ~N_u#;LF@~<)6d`TD)h>pKhk#ZX
z2lYn~FX_Ww(ID|T0*i`DvkzMZXhtmpmzaR|QN7#rbl_jNXTFWT+@{q(FV08R?PHS#
zh;mH-{v&U#FG|k2P{rBSw6!Q+D>{^7lLumnKMGt^EnQvVrwCW(s^aL*MX95&nSXxC
zBRg}~DPf{5J67*rqwlMVe6#9*%WG{E_+1`g7|VMS9Hp^F8QQSZI47kC4i|93UE{#X
z5K_>iN(?wcED2+CP`lnvK|y$?v|Qiw`fmI<ZkmY$bvz6ds7OD%-!EbTcPiw*>yjFR
z+?4BlTn$KPXn%xyYci-kJz7>@OZ%v(Wig^kI4iWq91QAt>FD)rP*v;~yEUi5MC?+#
zt0(YfbbOqS2_Elbhd%!#8*xu!OINM^5BmBE>a2*DK&tNMx_LDH)l?>sgnY3K%Ce3A
zhea$;C;b0rB-L6lTbbgQv|b$G7-lEya^Ta)&%vwhRXtLmaqUTWFMa=vPU^Sshy-dQ
zX*+8%Q5&p*EiNh8U=`g5zj{HyIzE*=<ZFHrSXlYSr?oTHL&o<aFll<4`+8`9nH!42
zgno*tJ$Qzs@7mTi)%UiLL5}?d^^?nk=M>t4(RSN>+t1LhPL?Asj6h4cAAQS+y5iy4
zqkPi=KV9=kZxTRN;-IPxH0gIhN807w#iJVQ!fzg^v>D3EL3(7~?msB+G2X5;#Wh4p
zMh^6jAUy4$taW}1NGEbW`;E<vSN)(qP|WS;oG-Iv1$reHBe|h9phCXwwf~d;eC7{I
z=jsiql)9kjrGVPsc|Zx+T)oRJK?+Q*PdFOQm2A896dU<^nx?~8hV<bzKsbHzsq87p
z1Iko!U%O@c%y&&d1;N2tDvqEDmy~?SWv3P!dCdLG^^h)Zzk3e|?%aA5;B*Q<eE)%(
z_u|@6cJm<UV*1<Jqh98s>y(gzxB%SM50s=kdY)$f4%(V_!q^=t<F(M)zoAg)_uLdj
z593NhZ6)_3*e5O--Dl$o*ZH<*QCwBi^#Mb3HG8SEXPaSTd(#LW4Czi>VGjl03#=XG
z0@X<JAzw_JV8-efZIjaE@8xdN(bvUbaON<PgyEd~f~?$1{W2odMlCKb&Nz;=sDRh%
zQQK1|P^p>FUs%jCm<Lx52E3lG4kT~!2IzcN^KzR0I)z;4HaKo}f*d9=Cr|M%ko&k9
zYXRUXav8uv-A=~%gZS|iXbd*{dxDa6fdO5uG>s_9pi@P)=`JBa+4>70)LkG^TxS6i
z#LsdpKjm~tR(3M$0`fF2KO6ubi9>yaBdDe5yp(c!Fty=K%Q3Z~k}i3rV4=LtKXQ-D
zpkmF%l$v_M(Z(t8UQ2n}@G8K9`r?tI1JwMf7?F!uoMD0E_eh@9hMcTq7>tN-!!2G&
zW_a12)^q{|UUt3<x)*V;X7l7e)0G9T`kzT!S-nO3#wukFV4QnOZ?-wayazr|4+$c*
z9n<wlZ?eCu2ENeW`gFE!;VB5})HVV>rRXAz4~;TMxwmy0&nzms5d6lWe2Go5btE|b
z!lU*Q9GJVTGQGMh)VH-2AKulO`FQbPF9Jw$NAY;b(alrmOP{pnHu$kW-6}rX!qLr@
zE8oJeAT5=3Sr;K_L7=40#l!Y2Zlm8W-?YAB`StssPfsdb^_S$?<7K1q5=O&*B}w<I
z2DW#;!%C$9%*^{fGBS_<;1>PL7T^__j^qHFBrnjot%@AG)pTCH1;-D`$uaJ2je%v8
z3Q#=(HGlN2ZhUxfZ(RnAJ2y9Q+V^<-^?FDQ-I&i;`_H<{Isa=Gpyx9<p!Xkk<?4M!
zWvxubL0aa99H6=pB(H}JCQglc5CRpZmDl>nvow}RfsPmF_*a`dt-jn|f)|YjsTd1F
zkZtb_!OO=0Wz9UXS(>1ii@D0?L6cz8ZxK}qRJHh5Skxlu^uEJXb<JrUFVHVn5_|mk
z8ffv2IMo7iU%HcngU5w0{Z`63|Fx9w2_2oR#|_ctRpKv|*S|6{#>FyC27U5OgU`!R
z;|hPU9#D)ru*bfzg67G#-iK5O79k%ngtIs>{z`mn%bib5^1=4WE>zDjxA4dypJ~)~
zEL`b3Q@z;1*;Nce*pR{K)$yid|Ax08-C2!Ty0EyNi0?|TsD+wVf?8U+E2#CU8yj8T
z2j;N=*A#v`-6B6Nn-&w|&~UpDQ$(avd+Us4wUd{F`@;8YebH_lV3|*3RNP|GQ+8FH
zIM{N<%6)G5YV!Khl)1oAmz0x+q5(=c3t%-%a!@<0n@q%UBz>EGia4;aL%6@>p)`u`
zrTG|Z?@I7FwiE<WRwNpm3*FCGSY4gtDBW}myl`5?fI&fvI2;t!Bu}-Sv!MUxq#|bI
zb6M{SL9vU!+UMom`Lv?ngAT-T&B(znUx8jBntrw#RRimF5+0bW(Qxm;s2oWa<`W(k
z8h^gt>}ae)2DDHTeMg!ZjmfRQ1g<rVF4vw9*@QIOj=iUKw5AsK+WkI0K8^>N(p~rV
z66qq5sk*wltLIxtMH1P5GexRA(AfBZMmqtg`w4_rga)6HtUNj$$w*CC+aFa#&4J6^
zeE?5(&FR416dbdVkDuJWr>L(*m~j2ZyCDszTx<+9eIm_7s^2%ZVTg-hs%*O<T+k+#
zXl(Ggii4Nc7CNV#VN!ktO!P;-m=5Zfe|vrA2&h!)CRTE3@6ikMuhj*xqO2FYN0dj5
z)~rkwNfd9dNf9{~97<&b8?pwhwytOst^fQ8Gd=JUp9h>tP)6{5hz-UrEB{ToX>&lJ
zX@!l3FWk4^(eYaTq<Mga^{2&(+LI+7;&nPBBn8C)hBG$5)cSp)&Ab=lK{XeRL~81&
zdjMWgIZ(lq@XTf@Is+kP+q6Yg{0I#$PMk0eVR{xzH?h?<HUBDGI0;tCn?xyX<k1du
znwPm<Sz3cpxpMRIzDx6^0cOl%6UXCIN!$>O8lesRBW!?$<xbkV#@|Unm2+&Xhlk14
zFO%#%i~~tp1bLU!ZIkYmarBI}ralaVTbF!^w4m&;?7dXBe;?|Ii~S}7VX5>^nqlFk
zgF_><MFfb?S`8ZaHOKG@4o!P6m)&e@Z?8Pbz^LP)|BKary1(J`=Rj;cJl9uC%Z)?}
z3cyakVd)<ME34-D;z#Sp&&RUc8t5H*sBoS#Er^%<b#z=nGTgVj=7Y{$q2qo{Vs?jh
zNghLpLkyseC(3$d127^q6G654c=rea1N;ZwAT(dHh?c05(9rjh!K|xz=*12*mTxi4
zPd?lLGD=4MaNp(u*Iz|yc2D}wal$t9H^5nwxwk3E&*!+JEg$*9=XVD7&-{v^A`;&&
zt1mAv5A1AhNscLO*{GxfE>S5dDfbh+@lY0ozcmA~d4#2;ZthfD={j<9N+^1y_yEDc
zcEa>99}a+yh=|A7<vZYBDb#aOzfeL-Jnl6V_SX8sp#H(lOZ9Xfz=ods9z?#k2KUk~
zBwYq?%RZ^;_blQn;BMQg5dQ$CGx=j-Itj{pK)i@W$-&?MO3KII1Nxrs%J~?L6n=Gj
zrItJW-C^gAGY8~GZ}v;Q>#L0Clv2O@4L{A&0BtHGe!t!ae0=zk28>GCi6b#!hE&U3
zR)Z_AxH#~M_M__4s{lb^;S+hpp%xIrygM9dvBLV<vN55>?wF^s=5*tg$Ync*npC4h
z$J!8cS!X#`Dn{)5fWymL8UTugB`UZvzBM=D0flH@4?Df>Fng0YZ<AJ9N&+a^$#Y;j
zOHk&sFy}Y?{pOL*%-8(w<(sgz2SEFsh5{9Y6qpWDdHMOz&J8NFJ}!6{Ech}k&xiM^
z@eL&cC1Q2H2NCSWHykjDZ>p(DjTW6z;CH1IJl}^35m5`Qy;hzp&{<Dj0-kkK`qp7V
zGKK{D@OZ;!Mvf>hoq$WJcmp0(h`*%i5vZ0K`wwqc4G;5^cP0`o@R?sbZiSPpk-${w
z#f}A`1`Z3qFANO=s;f`pN25;hA*)au>#W7({E6zgURrN)KtQ)xZOwrT;JMpowi3K{
zCA83bj!Nt_{Ct%1Y+`3DSMwR8IVnJv^(>%S*;i6yVqCz1<A0F#mSItaUEA;;QV?kc
zBt;r2LAsPdTBN%K1`z4)vFMU+bm$h5mJpR3KtLH9q`N!6i~D|`?>OG){V~57c3k_~
zYn|&n&$WiE`sZ+H;X`U7Jc_?^ahi_}9q~An{MyhYsHK^gjhMCGy7wEmZ{N<Lls^%i
zpf!eNcBHF1*xUPA4CX3@xQ<uq9r2l6wofD_aqH+vE$q$3IN>3UA|m*(oY}DTxZrvl
zYZrv1IG<@h-eI5J#}~)f4Fi!vN5{v*L?pGIVe?iwG~>-|m}57_!+S{D{-yLb`ds@}
zRH}VXPfrYGqEg%hQ#NzL!#5Vx@8Rwq;164+B_(IhPFqR}!4}449Nly1j08Eiuw|_A
z8jO9Ku9d;?9TC4?$Csz8r|3qg6w4VGJEpz4k5N>DJHzcKkSm;Z5nFx4sGyFyPw67B
z+_=;8?Zlw0TvI$hf?V<ef3>0L>IWs_N>VNJq-9#2JJ`q$IVYCWQ?z7MC?U)}C^}}}
zTk;W<&(;7sdYPTbl<g|)EzZnf8Dv_4lWPZvKTm^A1ohPam9!+pt(fTOC_FIzcAR4+
z+;p;95>w^1G4`Q^qd2E{U~F-*rd)o#5rTfU=$kg}_=*UE?frLY?*dP%mRj*HqPgcw
zDKd1*anR#JdVfOv7aQu+ck}HE)I%jr<}Ramnqxh^y-hSy_<H7xv=8l^AK4A&I&p-5
zp?iU+2RVm3jQ1257k}$|bviSc$GGS%8T9qGwb9Wq?FHVUCEk?fjMNL)3st4;ei4#4
z;2&h+UUq4onT3~*JHAavkZlxa5&HZF*@r^axCBL4JQZboAmp(Z7N6dM%)Fvf8EYTd
zziHJcSU5U6JMnLp!4frczk|q1UN_SH`|Fp}C%5sa<i(n=MCu5qAN=8|K4RjS+^|26
z<A=Z7+uK{%b5heICM@mJ4yBk+J&aGphlJ+r;}SgQiINhAwRJLMQoi3t3d?K6H6wnh
zNoQ{n=eEueLZQpLCYVWM<CcP~2%19HnM$j}On!?eL5NGSpCsi_YeDhLfc)M~{iFk0
zXeUHkhTo#?-6iv`B3Lc?P0g`Ep$%r{-Hzc<4pOkyFKwGSz^*Rf2zO0irW2q<m@2}l
zT;uXv?9<biIxZWSp3jJVGplo}5DYOhm3Fg?rwyp8s<KZx@fIl$h~)(b^Mm398ux@7
z7<ipYJq{j&rVmGL%7xp|WNmg#Z(m<CeXFX-nR49tJkJwO9uNAPdp6M0&xGl1-=?c%
zCHo2?wGwt_IrnI9w11+tK?!{SSv&Jlxf|UTfmf}iD7DkV(o%M!UApUPLo?L+HAOQe
zw3&toZ~6{+BZw2f$#dl80d)OLuK)XOXd*@FZHZDm8@(J{hBVVsJ=E6si?2=$ePcsI
z-SOn=>@0iyUoD-#w6VT#xgpV<>S~YDWzw)a#35T&izBID9v}ks^_i5EA&^Q2`*M}y
zqb(M*e<lXmr!5-Zdu>b}^|S-KlRVRsuNmafE~OQ?J2^5QMn?km|CPl2vsj=c;Vuw;
z>3P1y1ltIOa(Cs(DJC8Hi-kmM3ejWQ+6afc9@QSr;};FYjh8OQ^@^AS@>)NYI3o}b
zl_h}IE$y4tRI8<tK!e(?V+{;22)~DT);)|%^z9iueW0HA2GJtBP4n?oyr7wX#lo-$
z!F2xPp|4I90~m^cNt}k4-3gq{Q)ZqV2|3h~3E$;(o@O;Ri9Zq&(uXcd^-T2v$Osn<
zi~GY}-)W-E9c&TFf@1K)64;wOI5;Tt^HUcGZ;3cvEB}Dl;rmntSjw7bwhu^*p35XS
ziaxAoZ7Q%<3*Q#&;r3ec(U{PudB<aa)-xr%qH(sr8r`}9kP!nkvcB$GqW%D}7#<!@
z3&Q06=F?pn4)QP{U2Ixe#pc4}1obt?w$CoO1ZCc2#q_qsCnwj+f^>Fm9D)_1+`y!)
zDBz4yx}w>o<L$!YEP34hQhuY7U;JK*4;)pIY8#F+o?kq`Jiufb59MZm$ybtD7-gG_
zaXbwF`}_B28YGQgmKb>bwX-x5a;5%rwoVWmV6F9)kC@YHKwAOv;}6Di@M*;z14^hf
zV5{lq8P4awy=;Qv5nG5EYOJXe2fHGVD!pVUmQNk`EEWZQgLHhqIQZok7h6LOBte@t
z<A)be`BcX^3+F;7%>zyz)eO-c0K)Y^Ku*Sc`+b@qe4Y#OEW&A>A!doP){lP%pFj0A
zIV5_D&bg0Xw?VYXeG~oA)DVp&F7N^49#%p^ZLIr(nES3xFDLlaf2)%&%KimngF0;D
zwjM))-Pr9e^gX2zWq?oZzR&HTah>6+c2r31F{I!C@zw?FtXOpXe#R$zIbkIGL|u);
zxR2snzAW_mYIdWVJFx(eJP!+7u(#Dk&VJcDIbGHFFO|U2k&noDGQ>Sr#ZpBrd93pj
zt{yWhHI$QdTuG+|R#+Pt;rvu0WLAz~FQAm~@@VYXwB5)0>w-r<u;6&4oGjx7$Y9PV
zl}|p!Zix0#LX}5d>fq2V8rp11;?J)`q@77bA=SsFwnMK}pG(uJI8M(9;?FX49T)8A
zJLQJeQimAF&3Ojm5U-+_$}&d39SYK^WFGb$9fwF<HPS(n64H)tRhTIuA)!~lJuWcN
zi|o72L;R6u)`Kqknu~GR4><E2CL0cXq3Q54&hUq2&CSw0cue>`E*Tpu&gFc9LH|5s
zR^#Hhp?QJ5f;~e+<4ILdOu31Jbau>#yZDk@J%>|fuG>#O+5dpr91lkr!Nd`=DA@0S
zV>bq*m|`2EB+k9?I#^i)y9;9%`gNVF8vt-xPq0|Y$Q;NrErJS*S1-rt7IDpq$(%_b
zBC+ybL|cxkcfzMqb*qx+9F%x7tN+>wW>>S%tXUU#<nwebG>UY*2U4<0oU1U+ATBdP
zNA1HYK5xp`rpYLk;tta@zQ<`Mp*X6KS2Y}<k-Xy7Ueqp&!4r{w_pZ&FnwngvZ9@P*
zaby!Cc&46UDkY1;Q%$6BM%fxNLe-$<<U}_D<kIANE#Jn*#!Y|eY`l+t_JqJ{%S0+#
zk)O}T#g)u*@D%JI&My8)3wZ9Y;govMo!MVX0clE<<27bjGogJ05y^7kfqGKNYq;ws
zFyn_!YrFHADr;uTRcg2+t$+#8f;rr5BJePY$B6AF0gKX^67lEU1d1CtlpQX2J}oV|
z+3V^KOKPOXmD%%sYzYGg%%v-rvN_p}+Dqaya|=@G$%a}1_$c}6`7?iTj4WMwF*;-6
zNsqRS&;)VFkMceaG5A`_NdM2k7<{L?QTrgE<voIbm8{9<=#~OFNg=G8MXBjS?Tx&I
zDqtB?W^Q1rX-A6yzkL1ayms+DR36&jajSw-P9wp(Ygy1^fBCXL93@_Sx6HxO@eD_S
zJLJA3C3K@Nn|zWF0RQ)(I=zBKg$FRtVjsoGTprsv3hQIED{)%^YN9Iy4lOmEzdaBg
z9)y+zT>k|2OvsCPrNOK&@Y3gL>*^9)E&9!M_v<HBKT%|Q9coLUc_jQV|Mc_}6F0!o
zF?W(v#xb69LIW*}d}b8fX29Me8w#SBtgtufuK?j1Zn4OU5)1|8UR`47tW71mj;^lh
z=ME9YIP>clh%<U_0-woqtmQ||MiFW^RNKsK`XzO{CZbu_J;|H-=$?_sTrn|J&M;s(
zeu$-`Qvh|kR`owV#zfOgWVttX0erh=I$us|vU_Ho_E~=OniP2H=H|vuu5q*@6+R~#
zgM;<@Ca8@x4|+oXC|uu@H7JRtk=-MA1^XRdy*h9FsMrQXU_Yp?IrbcCs<-SQ){8D4
zrC>Hh%ksctSW9dyE$4I*m)2iSH~5$vD(tz#q&X=GH#8|1hU<1~YaA!Jj(){y5(~I(
zRm8C*labk_)sVHm7gz`aM|A>CrdA<^#zn3Ck@D#C`vYPPV$oV7zkhF+7GC1M#_Iof
z(RSn>{4Y7Ve_~|*Y4&wWpA+p%M?ZMQSST9Q)88*6Lt{h{$yFUp;UWeh*H7$|)Rc?(
z#2U&gu$-+`S1b|IlV3{v<*nm#y?5_?N+9Rr;u6}YGkzVKe{cYRf@riGKA8zFlbQP+
zD5>+i4iyQtAOsNx!deqy!$2dE0Z>yH%BRK1$XYND##e6*RrORyDgG;CO7Xc%W<to+
zShD|!xq+gU2g_1PlLVZCW#V{e4xe;jy>55aoPW97EMo;g`2N%rKZyBF&Ns5Cr}2R!
zjt3)^B_$CN(`CH8o&g&gl0!l~EIY&VQ~Yio{L~XH;tIu|AFR<MOsVynHHN;ry~Byi
zm5RlFpj1~{TAGb@Y^Z9dPJ8pvF3I}hbt*U0W>K4ZO1*YxB=dk0^z12SbM+dCkXc)s
zCnUb^D|bHk&3Fd_b2ib8eC^r#kDMfHsRVRzj`CZ}i0)D~dF$bP4LzeJ_Nt>x@YD*R
z7bF3Pqyx;#A###=(vOKhvwRX#lL!f&jgd-aB*HV1B4nXANIKwl-$Z1sKOXKt`=?qP
zY_ZhyLCDvbFk3-ntwd1oH`m38?6QoLSsR{5>BiHvJYY+#E-!PyVz;Gg4}VmQkB{S)
zwrEAa*nW;jqC?};wKd&n&Od_ZKFM|2Ee~)gCbaXu(#|}yml8EI3c!e^(B;{b-Ls3+
zgR^$v3mSWmtKyQDZ=wKaYc>p;&G$+@QPy}{B1Q1OFiLL5xTtkE<#f48V-}9H&%;xJ
zy*J<A;!ktEID6fuxptQng9W{9xq219(_v*Z!e~O$QHo9Kcf5B7{PaZifm-Bh;QlR$
zex!7wqbeUE4vmr$zw$tXI+&z8Ex69b5e{j9coeGjx+U`*_w}2MA8u{`fBAB1b+CD=
z`CJWtg!SCy<xo3XW<9Mk!B@k;z^7(TwBqBEoY7HQ{)weVDhoku?G4t)Y^o{0r(H6{
z07UWCB`!aVu}cd&^le%q*MMXdm@9hGjN}^i)&|x^{B>y>#{OO&E-sUiv$MzJkCi&m
zuMBj{P#n`(+xS$5rB;hh-QWLSmH?6<Ds^qPdkB<{AvZv*HUSWmoSB<@&5>E0H=ojj
zZV6%Wdhj{WMf*UzY4V(?4cWj8x>?y0dvlL*ix7HY7HT5if0U_Hh*lEwhuEx;^M0y=
zLds}AIxxh$GE@~n#tL9(i!n#YAY15W7pPkW(f*ZoX_h=aW3I~tB)uT-eMY$qXIy`J
zBGy`_&Ln;Uxl;zVt)$ASqVxB-fQXf|=sL-+fLF5*?7!R4RLbr}zTGpbL{5t9`07r#
z)Cjf1s9_(c1HWy^K*P|nLtx<LP}i8vimWyj6_66#A--M*I~rc`{w&+HLmuY4Br}BW
zh>fUQGq(|@UFaA9e!s0bwqeH?D=e%>SWw5$*?ggtr_nMqyGkfj)tqL-*Vi0eX=o;H
zWfjP~@@|?ETwPslCZ*(@Q_U2A)L2%wksgjBvRHf!cdwfh9SujVgNxFFw#1_Mo{BTb
z!I>If_I2KeWLHN1eu!izAbDp&-GMEdo*Dv)0>wXiZUp{k>XFK^7vj>MYfC&U8oN}M
z>Eo->FAJ>9;Zo-(CJ5>AFQt=hZ<GR(0MVoL_W);N&Shaub?Cf0R#tP2tiH3UV*4z+
z^VE4M$PLz7H8)q|v8L&Sa8oDxLEVn#yN@`zDL8FmFdP8FP(Z@<F)XQ{G6=R1%)Cq4
z_3in>`z-N5T649Cm$M#AmO(H`yduxK41DbjWtS!ozb%lL8IH;@0Lg`mEB=p2SJjQY
zT#LoKAW+IXjAt?9>kUc^@IlVvFg_Ty^n9K0nM}5g%-9KI;sJAxb#ad}dM<TY6&j(R
zY&!Xsh`AY*<{mU!BlTl$Cjm<o1tyBliMql3^~@g>kz9i|PInU-iq=0M!^jMdj2st#
zRMbo>PXES<#T0lH#QFLas;3cSe$dlhk0aY%@qM+%sw*z$){h(fdv67-Tgulw^6koR
z-%(w4n-{*N`9%_$rG6_Ahlz<JBH<~e{D6T*ct)S)8<rxyw|KXF-=)sAe3Js~%EIIv
zElU?J$f>TG7Sw@1>G|5wLs}=CT$~<ggJyrr^@@wvRaI?bAx=0Do8g#oQ(#SsRcg;Y
z!-Cj3d?+SliZpXc_V1rR@JDKmuuMUx$q<=rny9A*kUkS{>YwCJ`OUZzP&W}rz?q$(
z&aHB?0lXn0zBv1e+zS_byA>safkKSN-^uFUUPkcU!Ap==YL_PpYsL@Dc`T#>tFtNr
zYW?|QAQrJ-(-p5k@f`b>+b*amx@t@}Vd(ogIr5*v90hyi4-srgZj?*Z^r<q&;qGiv
zv2TgPcn<8iLHXjxzwH1>=yheT^b-)ZFt%x)cgZFx^)5ls2=V<I`X}W5OVgX!)NJAk
zY-d6f($eGUll243$j8Y{QFrP)48aiNvoydLh-ZMg6!3*$3(31gcxL3OYTf>>9~$TH
zGW*_;^;BJ%1I`W!`GpUI6l6Szk4eZ5xXp*begHT&*-;}DH$zhycg`+~KR?&ZX0rLr
zqGy{X935I7$=&aNzSA*;kfG;%^ha2vKjy;Y@yAv-@0M*T2>L&aLace}h65CXg?wvk
zSfNJ<kme75N1Sa{)sypY-z2e3S`?IA-x|;JvSv(gZ7uDcOhNpj`R4_I-o1t}bdM`@
ziSAL=tKiFF4sJv3KND)eCd{p@+|klV%|){T&imcoiNDv!rI~IG$^|^Jx;Wye*NOPC
z`$ME2;AV{Pi^n8n(RI`-X(T*>#7y#Dhof+y2`2uegzxirA8>vG5$YMt*&bAQjAa!S
zS2<wgHry8{XzhZc@sUd}v(`etJml~0mbKA49u8<R5U2j%DK?@n{>H6ax3;jBT^dtE
z0}JiOt_Z?etVPA%va)Jp+72^P25YV}d}#N5>vzem=X|KXTYNO=6oUGsew}U&A_hW;
zODk(xC~R<QDzKt|i8iJJF`^@{!Eleco-aGW*%isk8fiiO3+}E1F4ATg%n;SnX5+j7
z!EvS1MuSPVn|qYXln^2wI^(GlZf0dOU~{`vc`l5NRI{bXWYc)^={K+1P;nT?9}~+(
zvb6lD5PxMIW&UfTAhi7bM#ZN+U1A9NUk(?m{!m$&1^h`|yP;erDyzdQVE({Yy#jEN
zPry0%u8ZP(VD1Qlf3Hh`H6*p5^LwIuA%c=>y0=vT=bPU6pe8q1Z!$;NHkH2zbRhsl
zd1C1AEVEMTQ(o6(Vgt~k$ArjY&=UqExPc-QXO8odfonVs2Mn3hFDc%J4n!PE{EWcu
z=uu2gO!*PsZs2zP;pHp8YFL&GL!>RzLJVPLWCLnx`I+}P;u2ni7tFm=TPJ|J)nc-R
z4b`7=;`#bRF43I^VJmF!C+^Xz2#QQOv>=3(THS)qwVZR`-ACQ+aA{V6cX%XzgYWYr
znLpI$qVHkMl|p{<NA{$gq}J`mfFNBDf^_?RQj<qE^JLIR_w`lVqS3Ef?)j>M#eW7v
z>-HWz`47LW(o=QA55#3$K_igj?@|%rEv!I;_u@e%^LFv*tO}B((+kXNYBFJvxmUj!
z*UCD|;9BF;Ihw!UlQw-Ok&EqNm9(`Jt=Q3e{pqwZ5(({_yE7z23;RZGWVwh-!Tt<=
zn^LKp3BXYI-~Q5Oj|54=I0XdNZ@zz01K!8>|2zCIO9njVaCe}V)psYZ6%br&2&6#D
zU@c3Z`@~|_GKpt+ExzYQf>${AE$UibL4ZQFe&9<f)zR)9C2>*o%~m?*83u^j)i}NP
zokHq1hnxYQxG5VKhds6AOXKY^jk!0N=tCogh`u?tA)zaxkJ6w@`y0=u)?N4OLesSi
zmgN5V4iuXCbUG_Bk(H`OrMv{>fI;J?Ppju9v=s%Rr*D=eQxz?Enes^m-lH@!IK^Ye
zDdp?wW!Hl{FX%daWVIPM1v|lET8Vye;PCT;!^?n{!n5bkSvawK?+Px?)3CDogrk;A
zIpm4?c@A5y#B7cgy-{U(ZVKgmsTUh$C|Bi`ist4(T0zWDaC3k7Be_APFqm!pmX)5g
zWjcFd?_`#$rbXC$+x+Cu#{|+U(5_-$vKsK55*vL4g4lFZ0fwxTg#Wb<PN*lA?C6^}
z_kn{wI_Ge3ar|mq!!^F3<;|Di``TYB%=4q3kB~qN>Ps}SsgBz--&<@Q9R5N?Yvlra
zZADrISxwiJ)a!v<Ay%;9*m23pUN?~=y~ot8w}5e3<1yH#@i`py=DhMtyyLa#yMl<;
zEYptlQY+^ht!8O9j{dknb1^1tXV&~16q7FEuez&Q(9-6z=zY77-Td?sXJ?RS>dw!q
zo=A4x_g~fFHY&m8TI~6s_G}DmwEz?^*jV6+`>O8B_`t43Elp?zK3+48GZVon1KuJM
zI9QVDKLa^uM|-|bus!5hQj#4|WOL{75X}s&nR~jW`t4`OkL8(OxL+Q{iQU&F{T<Zd
z{Xbp+3nFCbEIh_Ycx^#F!d@XO54j}hrr6bGI_y5w&>z1ip<*JRcWX&Byo_u}hk@0%
zYe<DXNMHYDCc!Ki_wza=+hMREypIzwBrQ1n_wuh9a~fc`zXG(cvN}lTU=pH3ze4|a
z9a^$p(nN)BA~6Pa3PBA2b`E&@1=y_?pyl9&%CkO^rJAn~CNY3DZ@|}sp!emLC<6HT
zkad;mB_$NPV*({pX#Ad{mu7^D8R!ACNGvhYG_CWJldg8YQ^R`r2>Ue>3o0G4Asgz2
zg5j^WbfC|O`a`_XwJ?4I4}Jw(^VixsO}Av%KlMxN=q!bI-_PT#2Uo`jd@@u(o-H?~
z0G-IB9~6|$U@bECHVPdnK<==XU22bpyK^FAQpFfs$AKD0|A%L3arM9fVgMeIV?~Gz
zDcvi!aJ&SYk;z^%R+@Qkun}4?ssYANti6vku@QQiaU%CZ@(J?vocrw*_O`2n=(%c*
zhy>wpe8PYOdB5I=mT|3xoECuNVO(hlBtiNJEUXEs8ND(Xc6;+e$xab)K~01>SPUI5
z3@}-N1(9#2Tlf9^Vpul1_Gf2Ryw;~K?g;W_ni~596O>Wq3tTcCxSQ*<%<;k9Gx(9Q
zwA+t_(g)JIF5bo%vEa!n!%-qi3VBbg*1tz4{>EJy|1fv(gXwGfZ{~l#t}v;R(nxM6
zr8)ui(>n-4%2lB3DSFGt3%p$x4zfpygDlnJlUf>-;@SCrcJ=q0K{M4Ocgdv4Z{W=5
zzWX{2N|#m8t-q!Q^@VXy>+9)Jk%8spgTp6l^JVwVpc6<|fcEdOu!x8>DdC1Ix7_k#
z)Ob?w*!G}a>aiWxFqU_b-J*&S#8f;s&5nwVi$8GLnfO4}kjVPs=~-D$M7QcyGVbC{
z*%ZQ={pgIzWbD=t2F=L?$E<=Y^CM<~oQ9ZJ=l4&-hU9=3?T<@F`fRrim}7PM9Hb^5
zpr;H<1G(q{SrhI|&jA;FKi!=FH~>H~Ar~W;okT)slF&Q74vxYwb6=NArPc!C=YD_)
z3-W6WPA9~|&GLAZS$ki_Uf~<g%oAwCz~H?4cQ371RJzpcII#sGH)Z(#+7-H(Rxb}d
zcPc-JUO}f|%ev5IRMr>-HO{P_Qs^j*5}MzX^(wa;WT2oEECaO+rGVchFfgF~8|=~o
zX1kPEes``sv&#;(mA=N8W58_a0I0>DpJ5bkQVjiy?wes?4g*DKp^P9m<SDo(%zTPZ
z*7S*^J0gOLFHq~%>>oF9BN~L;I7nmuX)(a6bx@TX{uQXmlb^<%T_dA=s4Y^U{RTs#
z<gzl%t||4mT0_w1!blk#YwM=xVD7=M=JHy;NuaoV&hd|${r-sXQxJGWjZmwGtz_$5
zn9nz_j-@4R?_Yo$v~P70GX_NGAi_DKyu2lregU7zIAgNXa^zYx7mdUeuJOJ@nG+#v
zF+64dS6}S!KD)Yzzr96g8v~*#qPDiytP@Q|K0pe+1%q7#xzTj@Q0igJ+30gN!3sv;
zNhvWgqP6;x4jD(6YjLOeK*%#_|D^h*<`w`6U-f_}Vzo#`T6Gv6S`50lz6E^aaqw_J
z8RD5UBbnVde|&A3!r$gb)I8|%?MX!1&D0231{cF^{*>$Qh(e$w?Z@M%hsP*Lh&u+(
ztQ6F4tOS6(ciJ!~x`391wQ}PB9>m+0M6#Mz9EAa&XJ*KGdgwsY1~zO<sCR@P2kKso
zEHrQP#}o1Cthcv2V4PC7QinLUMd;STo`zJI>edrMPZRNMNC)U3^O;?n^!;fn+goDY
zOLRCH1@z;WlMP8-_>#2LH*gXFw>bb8`jFZIEqg&uS2(Rs^c{A#wzebwADf2Wm#=wY
z-T0aCU!Q>iNSkUPoqkn#E!#RYHr7DUS}(BR<u5%gmReKd@?UGpRcvTJw&)5e-x8_D
zO=RPn?=xl;q<jwA$qABJi;OVaBX~~1MD5GJ?ANK1bjLfoG3aDhN;*%^)KnU-ksuMa
z+$g$Fa}X1@{5YngivI(4+3Z=%p2zzQiez=OD`qI+53!m2M{cqz%<$hmg?R-Baj~<t
zj+Wm|v6tqz6Y;hzPzF$E4qV;acV(W0kH^$M2~}J{woMYEak1{&wDQ~+2McBmnk*?&
zeD3%<()oWLez<3n>OJCzK~GIX8N(*`QN5rpZ1_lmo>2;s1vvB27JMBvuFVjlB_9pp
z>0QTbFp95*bl?fyDaaO-2wv;OUVw0g0F7j}<)ma*8$;`5h2}F;SbAk+`g4v3AF9$T
zKYykEw&Z&20T>liTwFmu;LU=lZ^NYcc#6^msttV|AgE)2J}%TOU5!fBVL`b2bSb9R
z+i9CkH7K%&p*{}BO(au{5?gIUhk?~uPZM$Yc<F2|P(UyIbHRj^>t0(vA63=p5WEWw
z*Qol^TV*#lD9LO*$JYZQ^z<uW+HOThDWbvk^0K0qJWQ_g%GVUwm(w^ut=UZNgG!rZ
z@{6^~`xLll1E3LCf>c40PdR?84wJMq7#@0pRo}XGR1$14u^`%K2-!6JeuB&I0hE$-
z&~x9i(suAZO+(Yw-@|36A2ej0)g~ro5kO{iey^kiuJEGWc7PeEp{c3%%a`3hhlhtz
z&?Xd{x%>*g@4;+Xw04RGkW}LGnh4n1UMJ{-rQOZ#M`j1}Tb`G+S}or})<O=7P4hk|
zp|AW{=Q(dMSwU;?Vlj&AR`kVg0AV@gcKdBe^L8>t2uxP=%b6WkVDHB@ac26S2D3)Q
zXl@JROHZ|-z}({1o@HZnw(Yw<`rlUouX-8RHS_1&31jQuHoA`*P0OdhE&=cWpSTh<
zQX@qryG|0FiIxm-s!$ivDtOl0*VA*xD%jzau^K$2qcdqs-Chl>1zt+a$&|u-^@Pq+
z5J$9|2-3cxW@BV&C@(EPAR<&3CfdCaiesMEza-(+_KtuxM(S|n5H14HKcyROT*bZE
z>3d@|pt{fluA!T(X9z^3?ss9N5sWD$;R;(!{Z6zXUuDjK7v-<UxKJCIw~>W4^t)c+
zHgb(TH8E6i=<5mG-Ho}Tk*WjRdze46*qonQ^+`+ab4u&9InkW$zsYYZ$OcT7jc@QN
zUCEVykMsTQ5g>{@SgtQx-pIG>yF<zOsbN^F6z6%${4g1W@eH7NCSjIEwJgdv3<A{y
zNR^K_@B{KSd_R8EWb`NxJiZqlF1nxA!b(}jD2YQ9>IFK-Xs_P>zz_cM$48rFTXrb&
zRxOsSh20N%rlt4g$vVXQi;w&VD=*d@H<kWYPZhsTjSoO@V5huDTkMaYz&r}JKwB)1
z%zb|~UeoXN>XpBaJ_n~YFlr1Yp9i)Onv?kwmtX$dJ7EAs+b68oNKn*XQpd^EVTore
zo=4@|Q4uT$DCS2qOv-f3`Glm}r`QUUkwLKzW{s@uOX+8VbzFRWSNU_IJc^fK;|GK0
z%t!Sujm}QeqghQ9k*VhBuQci#8y=s2SJ#Zw20D&@v2I3wzy15fZJx{oQ?YW8XxBEk
zGjYq@UR6m)$3x@jiXx6u1pp#5K+fPnBpt&kCtN*WbOAQD1J)}>?Bk*tYDS6ypQ6BE
z%hs*_mp4PyH%vd80(Ym1dwIo4YvsnjBbfv3wM)|;{zyqEJ;f(f#pURxAm8T)+%&bF
zhsCYa&ZX>azaVpo^Ybypg@ef1e+?hi=~9P3h#{(!{8X|fsnv$d0H`IrOknSbr{^>Z
zkPP8~H6wtYo0@`sUhI_PrlkNuWIQBzZ>_N`StG$hkq<;DMtOvks11Enbq{SSVvsm&
zWJ<fm?6i5fQSi6asJ5}8be%H%X$Sq&uZ8(}3&<K-AgH>qc&iOOet}?!=QN}Cy|yx-
z&-I|9ZI(5AARo$sQ7QWFv2d`d=#eTfl&>~171K1J5Ah`xrIPYvP-Egi&viU_uhE1j
zXSi!bp=8+n(U}hODUGHj=v9$7nSP^1P6o`pYv$4}3Rjmp5Pxma%H-H>?nV0LnQs2b
zC%Nr2gv-Wj7kgn8><xkGuIP*iyoBNC5nV%x7e*@?WJh(APU<Nq_pZMO_4W1k-WK;u
zQ3R40#B^6n+yVrs+6Vx&*?>*MoVuMKx_vF~H-RZ0LE%aX`aV8Bx1m0Y%=>*4ATYD}
zN4$CaA1nqW{_GY|zEDFqN>(o*X^4N?BJkY2LIwU4O~S@y^M+{GTT*M%(N(`j4Z?${
zW%vJXF2B#aMFpVi#6iqI-Jl=*yx9EhWowK?%%|6haa=uyO<qp!#~Pfn#rsP42mdoF
zaz$k&SLELgTrAixmkjyk69eylmyAeJ;tmjKUDPjf!zsqc#@ND%1%LzhA+G+f)?XTn
z<FJ|U`T6}`3OVf87QKz<#FpiSg&Z(v&$c$UzOr&Bs8LEn6|PP?Ktc5EH2M;(#E12)
zv+tnIG(U{^0|#(E%iwKir)Vb4iQWVZon{Q3`GJd3tz)Jtoa$#{fk9HWk>W=jK!WKp
zFNQ{FKY_Phec7q5t$={bo)&G^_w|8s^=howx*p|1uv}BHO7ujNUu}tc&HI<b)gn3-
zN7o;|>`E6UuSvw29AN6a|7eUP3UYG;>Yf=DF<Iw{r41BX`c9f`&Jz3am~3FATYjiE
z)V{gEqse$5Uq3+K+Im425gk;#Ni!s*M@TSFOcqnHRZ&IsLlju}>I)E)4TW;rD;(V-
z_Ijl$8HH=B4T0o>R4l8$VeRNA2olUA+AIB`T)i^8!IEL#N5XXjK;|VBDNkoo0Np;^
z@DRm>^K*X+*%-O(Fx%I_$M%L<iIYX=&V@3TXtW@$l-Hll&ko}U2b^7?tdN8>Pea56
zV{l{ljTEbtm7i5NdM@dOCZQ*LEYKn5M4D$eCw_s{0f_Y_N8<@bj&1o<c~!{VQ@6eE
zMSWCgxYo&vv%Cfv{d-Sbf%(s$KcYam()zF8<y&?sN4I<EH2G8V2Z=$DGH-EVAvGaW
z;0Ff>Aei3E_DbRc+UO|{bRoaA{ELH3&0$=cxYY`ZPZiU^zie;#`QDx_u9zd-uXf<n
z%SvFc8tu>Xx;Z270hfbl!DqCwi9Vv7mySyHc%}u6ip3c?i#iBSeeb_GISBkOsi|ex
z`t6{Q!)K84i(|1%r8!7%aD<~I-}GUJH97!8ubaHJE4CoX?Mw?9qTb&oA49^3f76P{
zFiJ>h<89L*`%@~{da^QY{O@3K;0zIjZLaNj5B?Jj+PzjcLy12q);LTPGkFSsWhAry
z`S!`+cfewueH<RvrEh%?bh4~#(w_bebN!pp;N0D^I9{K4c6I4Htsz~n(i$y0R2tpf
z@UdEnJH$RVmHEyA?hCM0fy@;vc+9R2`8Eq^Dj974?V!uI;gin5PQ+hHYjZ#UmoRK}
zbX1PC){`@n2TVS+G{M+Il9XD_Pca8QfFpdW&8zf4taa70J%&++NkZbRxo-Dm&zGc|
z1oO;@XU9aZX#sd4P~3$|z$W7mx6vmr2mb92)Y7`GGWpJle%04mb?BMP+G+G0T{bZV
zYGwCo@wKg!liB><i91wDQZ5OsQyz|>!5<FJM0b5AS6A0fi^UvEWees84Sgmmfhs=w
z%P+9l<n`d%+f<Bsq_-hR&?yZw824GtI*enbCHw9C*y*=7vXA@zjsCNPW}u*#sr43R
zMollsG>X?Jn$_+0X-1vEpfO>hIXpxlEEC@ZyHy0VU_?O-q||EU@bd4ga$MZp{g#Wx
zpf;ZTj~?r+OUbO9%txv;O{M6P;e-^!StLcOQ200?o}G-A@RkQiM{iEMP~UKqP01lI
zUoEFfctphee|$!q-x~fIg>CkrcLn*LgZ=?^cuN%EOih9<==iweS)xGzA%nwf9Qb7W
zjYPHpFg_lCpUT2RZ0bSR5mhbPMyk<Jx?r#3DVOL%F4%9rNaLL0#CCcLPq>rq!`xli
z?_UZO4O-vJb>NC0MeQoicEWTSKdt$mFnD@3iw)hW={V7LM_&9B?W?gmiu7&@vXtk1
zA<wB98kpQ^PoZIWUN2Z>FD3&rdZs?j(^4X>&Szsjkt@44Bup#WCsuaAp&&vwNvn7H
z7^MH=&2qka7L)w=Jh}f^9YKB7JaV82-+#qV?XPKGYUQl}&PCeQ)unX$X^cepQ2?=d
z6fLIa!J3;1Mh52WUcq-KG}L%}&%va(fdkpQ<KYKg&fDc^LFRhzWL!RZi2E;oN7K|l
z_+(^cG>$EuU4dmL^;ao+?g6l}O#{86rqx!HybIi6Y+~Yp7S!=8p)DL`HQ#oqk3KiN
z`@r?8F_b+L_^z`i>+5}FmxOPHiTd&P*+ZI#g>(=T3NzW@c`b^-J@<{F=Lww(DkWFj
z(oks?mnU}SxKQ19mki9%jNp|#kUv}GL!7lZC<*P;JnxfTNay>Tnwn0rKrN(+D$2Y*
z5&S=Nw6!yEXHM&O-~5W8YT;y7k88TY^tXkloMOOT!Ev+JL4Fj$-Cgr4#^wpCLLJV>
za+(%~7(aA#G&x(oq`yebP*d$=3;CPgxQ1(eOMx=c@ICM^{j+98v{6ZuFi0Nj<X)ET
zEM4m^1NSBn2E#8Q9`NEf*A^GA7B+p8@8)+!CVmeMZSZ^*6Yye51`Le|43K@gDsHo>
ze(moQylOtu%gfWAHr|;G4i5H;pVYR_`0=wO)w?=prW<b7Vn4I{3RRJ==u#z416maD
zK1<{a@zW9a2ojzFi+{H{P$v{7Qk~KMd!SJusZxFWr{$tqSl?%oaUeRpJGagOw$c|L
zYu2*$C;|ci0Sz&&V5eYj*QHZA9nn?3rPldb$c*1*x|Y(NeNu?xNNqmcQvr})3bE;8
zMNFnPEX4EA$X&5Wq5OOI^I(g4SYZ@*%e6DbsOQV!ep2MTXkP^|=H6n`14bP5H!IL}
z8fJR-)eIr>$N|PbRJJAv7<C4m*zj>AJgjh_7q7(8_%Cc`;J9Jq-L$r3F(V|YF*X0x
zsRGl;MILreE6cT+H1!2wml%-4^64c!!Q63w8Hm5GB$sqR4leX&XyyUm%1jqcDcXYy
zIr4}>W4y*`+5SpSL|8bm8yz9PH1aldPE^Uy-|QV|zP}+w(yDg5g#hnuIgikEvIkH6
z)!F*PxiFh#8g<Db&6Vz<91{{XwAb8NNO<Z}XkY9r&~ZpbHhD+yvZj1Zh7{nJyI_@N
z8_Ki0&{A3CEU5Q@btP!Ioxt`I=6_Ed{s3Y62bh+0w6Ba*l>5>(G{4wARqD!L`Spv{
zao>BrvZJPBnn4LhkM^$}S8GSt+sfK)ggWF^->*sRqj8BDznJxDni7Y~x;Dontdp$s
z_R|z=fzc}uzV8mCt0i54B6zvt=cU0#sFLIW3t@~TL(E!GQ7(Ywm)JAU2E<<YlZL@x
z!ttIvjCY{rQhhieOx8<Ku%?qRB_2wq*%&0P`N`8KIZz;B5FY6#Gq0x4U;m-n9>zCb
z3QVk;>FL$Rr#iW=o#I=BIE;%NU4B95adh)QFKVsC*uWEkYcq5OfIVy>q;|$|dGxA&
z9C!jWU*fTk?(Xd|!af_i6GOygb|^-n&pOqap~4gc2<XbAq#v{_NQByAAwL^Q9a51w
zfT!4%sy3EI&xT?TT_(W0dc-L;2h3u0$P)Wr;?^i;n^#(oF~g!aK@SqJ*(kulS^sn-
z&0Bp1a`F!_!i^T%ZM27f{VvoSaXL0uB9#h$uScN9;fkPD3H6XvgNd4GinX|fBQ5_T
zH1rNZ<TfXn3De6Bo!U2XGeyNuhG4B4-d$sP?RX+*;AeOQFmpSvAm{S*0AGvL{Gyxd
z*$;_+bXqRf{&ovkHyjeW_SV%a5PyCcTE12d6<aC`lidPizn?TeE?`z0dUhXm05!9H
zys%8NR$DK5Yx0ACk$;Z}R^|oc5K?o?K~A;N1iO5j6I}~iUhCRagZI}|S4R=Qf6`{d
zuk}9PPKF7^>at+3Hnc7{uD5?1EbhGqJmMhiSb8l}+q6X?ja1FVe7h@!Onf@V^q(~c
zpbC*uO?2x-Bqn6M6jaBDNO@AnC)QV0m2GI5O)xg>KCuV&C=OQOLQ$GDXtvtylzj03
z8$vvA$f`G8-T`ZJOP6wi2Eh>bvxd9LbjxdPb=8xt(x&@9GeBeB(V;I$f-d!h?q0Nm
zS&yDKZnCjv7{5)tM=5U*n)S9MCe>j1$*Q)s!LV7VEe_HOy*>&B0^)pLo5mQ11e*?)
zLS+6>F#AJf78?EC+?h>K9TppT(K2PR7!eOR9^|WvIovwZnJ4d$zi#?!*!>U#?R=|k
z58XWe)y>@Q>b3-Z83+b~nR=FLe-;^;7FAFUQwdfT7mIva5-?>iD&~6OsptBE&fFRT
z<*LOZgG_0d?Nf|~z#xPB#%KR~NCl|QgV&Io>~?CtkCRywPaQk(gGGiu#q#bcV}S4X
zfMFTvFQqN@e=W^CJqw9u1fgsJOFgg5*Y_bxfa<g~MX(;J?ZpGi<_V(t=BAYUHi5X4
z*QCCd7KKNV!q~NY2-k&nfLx<G-|ku=(!3idQC}d|GCkeDwD)W4(SE_>w|Kv%=aOf^
zex_}W0@PWHJDm*->BPP~C=t4RFQ&uIsW|X$|77J{9>{puF!PW(7AY`EZvqsG{k=Us
zjd^QH|Hud$_RU}uU`88;ZP^#!`u{<HE`!-D8)@>lfVIa6Xx))lFFbFwL2trQ=XF55
zGkQ~=IsitTZFYhdgF9vp@o~U$h3#x@CeC>>f45Y~hPu58?eC}BWwChkY&AGA1cgGq
zNI-FD!HmPQ&O$dT%AmVI_4onC<dr)F#M)iEuw(#wR6v(vi>5ej3k%AWaC9?+YNd0u
z?E?6)Ya57JcyXJ@D%K$X$UZlEMj^F5GlE+feCpsGImD$82wxRn9@r-WW6?F*xm!|N
zD*4wXqXpKv0&F4ufHS3hT{&o~qw`nedfJBjCc7sLv=3Nq{L8ztUKD{ONz4yszP}X#
z^+cUVqrfLeZeD5Sdt4BNm=dbU`;};EM63;}DBS2d<EQXs{=HEsdh|yR3c6H+r_*;B
zfQ!`vdF(BV!eqh!0-BGPBMqJYbAP}Arp$a7uzgqeQTIYm>dEKaASZ#nh;URXjgakc
zLm%$#8Bn@{X^uR6WCOUst$FO<TqU2W#l;FBVV-~qCL4=iJpXI&+CdhtjXF6u=?(9x
zpsNeZoPk1hoxg$T^Y_5|DwHYWRK_5<$js4w6Ka)R06gKxWmUgH58IOgXg5U+>m&I8
z%YwCUO$iG@&d06JDblzQ7K3eC<v(4}%V<x%e(&-g#6K|jNQGO|HD3&rFrb)~622RC
z8p;7qbInFlfwYtz-j`(epME<hpaCt6s|{uFaK$H3yWY}G8x$%_2z}a-Xan4xvmOC*
zL1ymJ%^cK3H89|KxUZqzt`u4Bz?Cu$i;crBEl(XuNV|>J2J6Raf=PxrVmPnr057Ho
zB21BIR<1iV4{_f*xws6hudgQo#jWk$$H#9~fxTp(e8=}{(SjEX%G(nzNRZ8b)jt&o
z_jIR*IF#q_5BTK%$uC|d8n01-xien+Qw#RPwy)J8ITk0f{Cg%C>}4PCN^J8wyEML=
z;VepnfgHc@x=K3uOG4}6+w5!U2a&0n@x*`=t0f&c2f*J1ICC%{R?~wdtt=R9k%2~6
z<Sb$RQBWHyB?ro=%<DH;{hJdLk{{jDgWs3vcHveNXp?em(|w?qqFT=QZfJOc?-OA#
zR`B1B&kI51$d7EZBVabnJ57_b>z{v`V;7tXCVCa%$zX3=x`gGrf4whqG+u*xRRx-+
zYB~fTyJxAoxnD(J0+h&R6aQnick<v`><(8hYeQ+4Y=0r&I}R|BTQzDJ_MM{CljbH5
zGv;HCabE^27zHfGVn_j(>nC*%hckc%p2%*|kT5;LotFyV6H$ALMZbi4tD#wvfJ-~@
zp16RXr4V2WQKz`3YS~clU25I0CWeP=^nuYNpvZKq1yy5m6C(P?C9a-t2hiR9#<>VC
zh$%RB&Nug~$4zk&iN1|fk1H_im;{nDW?3=se57yJ#vhr@zc(qs%7!Ale&80LSd_$>
zaDT-x<az(Wg0|s4LxMbsoR!~85)9o<t^|<T?Fn=U20#Wd0!f@W1H1>X0n~h4T-^M+
zqIm#9+NI^6KfSLMmtb)o7^Dl}_;d<rc`UQ%&bm3c@b!k$6tn8h;$mLe{_lT1D=^%^
z@_@flGdt_V+3EyAaKR;E5t)0Unons2mryVU*C||xKd{Ds5%1)x<m)sT+o?bFbv(2%
zudy912g(l*=m0B62_Hxp>c9tk8^#gAJ*@#mwojpwnuzCg?D&~B4?tc5>_V4Ni1j#*
zIfR74&FE3a`eV)-7O7n(SDiGrb`=kL48Nn*e<dy@fEEW%mRR>z@O<8b9S#Pkik6=n
zf=YuAxQ`zOmlbcozov!?W5;%IvyL6E^OH$EhO6@*SD@w;SHe;YU?cQe;+i^t8*zSp
zAdUrTw9VZl8+WFef-b=Ef4l%G<k%eiYI{D9KY*3S!DaofrSm=?8=12mSFI9t3ni#j
zq=q>-gV5oeqi`W1YNGDfe&O-hrIgo=d=w7jz@NgG|Lvzx?`~6*LL7@y_XEH+g@ED9
zBG9}SCe-$=T^d#8`Ax|@pvH1`yJX=1c60vw6kc_B=&K}7`X7ELwE!Ce{EmZTk{~C6
z_Cqf#27x3PB$y=JZ_MYkrh=abhSe05uL=IXcuoi*7&J6Ab^sSko~*hW1#amLkU5_M
zDhAMu4T97}flMIC7`*x)-sXg8z~`Y_4Q2<+_=fYRC;o<BO@%DprW&c$Mb~X#LVa9h
zsT#_R`F59g{!33?z9XQR$L8WxCH}0b%0#-&5x#3~eBuFwF-1it@J@{M5hud@@n!@O
z>#OC0MbdaA*4xh!(#pn9IB!itOozXhEI|jJ6V>gftC`^HUI3SJAKLAICINt!SjD&m
z2Eq!*<2!UqB2ep3!E6&m=S4^EMLrN^prIGa76@s~m(p6Wn-8D$ndgy$Mo;U-<68tl
ztoV9y34!fX66f!Z$I|j{2N{AUE7yUmi!~wAOAhAbgl0fVWTNRB@n^GYc0Xvo%lNK*
zuc7>ku=U7N*`dZEC<nOira@n3>I&H4Ig}_Y$b3-^bl}XVdK0)FoRggla9m}`PQ#81
zh=&-B5RUq^XKDZGBL1BXJD+sn4{)fO`jXrOEcFfL_7ED7S;>IBG=9!v$2U);8_rK;
z$%5SamAIAkmb>c~q4T{IIdfuIoi>O`GeK<?;P+@Yj=|yaoT+822!!^7OiMK_FfF$<
zkitMly+Z5hBbxQ~?-CgsemgGB#Z4Xzw>G#1`O=-L!bz^_OE$I-Uqt{q#R8&42Vid@
zj{Ng{%vylrwXbc$Sl9FCzRO%Q9;DoNWwV9;k;7FXb1AijW|76ZQEga)wOOrWRLg}!
zMVY{?O8&<McJJufldl}*EHifsc&#35<2W!0iad7M;INW2zVYJy$1;8UYMGMTxUZ^f
zcsU5(S#3(S$ULl!=Tu3mKWd7f=-=CxoOfQ5nx>hW5IYL!_v=I6a^|XI$8lO2sj5=$
zke+T>$c})RjO$Klkqj@k_xOK~R__TXZ7f(<kj-JBDJ47mDICaA>Oc~*eC#e#|FbUo
zCLemxm0h(=bRbS-&fE`GU4g(3bvTtoflkPB7A4}d)=}oKu;St=B6E!lpBEgIz8b*{
zA<e%sl;Sn<y(PWgoZ!76PX2@G$3nj0)I!9Q%0Uk}i^?WB4G@~-H)6f*TT_l8I+Bm?
z!=j6LMvm>6WKo5oQP@q=NjIy6-iK0QQE$42QJDD)FF8^9aYqlD%-#p|$9sD{PB)nO
zD}?QKyW!sxnYE7Ni%V;C29@R5hHHJ`7ylDio5pE2QEvUXuAUwVN?DE4sL(8zH{2oc
zo#nm$+Baept<Txg#QN9hVNl+|fr`pYdn(cII!D_{(NYp6R_l|{bM2paWSiI!scEnU
z(duU}uL+Mw;huf{(kIQZxk#$)-V<7g+EL)LMQ^zR)>`KRJAz)Tx2xZ33i$WucXd;s
z9I+AsSuggsb)?<L^0k}RD=x=o8Ia1uV2cD8^<B#`d3c{@g<MRkgvaVVx2CCCtcqIV
zP)APwX_A>~oC&Glqj%Q@Mp<c&2p2I>GkcZ$It?@<wz@q{8X@?S@Gf6bX6?$4sYo+z
zZL4p_nP-TOe(d`n3S`f3LJ@|B<HOiUYVp}6DEN&Fp+NJr%f|cB?;Y(n_)BK|kM@VA
zY@HQ}L4ayzMxjLawB<F}l*#6|WkkzdS>od3<L|voVX(iC@&i<TP1oRj?D=z+U23EX
z%-mFWIAu01P0h|GV+WlabS&39`^f%KF)7*I3M|{)*U6|LF0L0p_#>$lLnUCb$eo)|
z`j6xg56FqZJcU6+PsE-INregmP20W{ojSO)JJ4Oo{QS@D>HE*6p?gFbZ<g)m2}W-(
z-J~BkE$#8Bi8^JH@Y+20@b&fOMP_@9gxc<8h`Bv8{pMY{*T_p_gR4R=o!!s+PXA3`
z*al;MUfwS~7cb`#KCqlQi_cPbWz8o<MIcfQm;LM-CUP30uN9Hk&$#mez26hvm64^e
zlPH<I=w?dj<x<PAVru~0U)SS%zMu8-%fj9Z6}jrTq0h=vFHEXW#UWB=cB~Oxh{fBX
zqgr)VX_8g?ZZ>`K*5?!d{<;TL8|H-nob^SB=6s>bu0I`M%tHT%ysm#OqOc^E!NI}6
zu#^H~uxrKov_j;(IJSK&m}df*(^~AeXG)-txiy}GWF`qUZc8!YdKI3oCk+IzZ$J~g
zj<7vkNcPR<=4U-B;VB)H&s}%qpQMhr=wr$?MK(oQ9%kH<<|7|igUtPt4lVh`!!rYa
z@1#{2dX;Cz()$MZ>vq~z4dNG;mcFuDe5RJ2dcxZ>eI;j*MmOeCbAy%NvOQ96!ttnL
z7X24M8XwL#baCNrUGeI#4!ouP3LAVC(mVFT3(C~+XDm>!AazJq$zfycB4(B}rq+FZ
z)M}gFKnQ_NsL`-H-0qN?N0a!|UC6y5-eT)MCcVd|8s=R+XM=G(s_AU4DS}gz+<64?
zKP#e}Vb17il_m9rfa#A-_0|GSq|op|H6Lc-LZ?r{c^S7BmV)&$=VZ?u!3%Sal2jt@
zBTT}XaP$&DzI~zEXu^vr`?4>}g6{@?W-+&QEg<c^H-<iJ;s!)gW_&^;I1QWm@^$E0
zqw1HRxxbEnr@VespLHYt){L;3xv@Cp-zZ`2sRo)XAMJ^pKdx!t+?|cU2vwA5l+YIc
z9liBPj22=#7$3HPFtFn{skGwd*1w~0Bw38hw-|PL8%lTU!jgF<RNuIVIHK&vTA&F=
zn=Am-eID+Mex1Y7zmvn!oeG?<sf^AqlSS7fq9=;?D_Sm-kZ!OW%ng<Nf^Pg!!e0y@
zS6PXXfwuOajX~%lwdm%<r#6X*b8@In#A)o-_FG7{mGR(pBMBDrKz{B1!$)jsRJwhq
zrJu%v7Q|%E=AT=p*b_ji`?w)LW-P}lK3*+4t@sE1bPf`imN*`!Iq8vfrIc__%+Jpc
zf&CN?V1raZTB_1wC17v;5-ZEZ1U-1X)E{tDP@-Ce?lR<!3h#-*YYeR;!$X!Eko+2^
zmU_c&0VpyChI$wlgBOEwCX$O9a^@7&Bt9yAG%$#hr$~jUz2BaYmc8PE_XXpZM`=nL
z8Xqc6d+cCHs<z7t&paZAzSdt>)GEkBzuWiIg7C&DCIf#Sug{$CjE<dxh%TSy8`4BZ
z9AXr<94xx0bS*ft%E!K?FgNG|eaO3E%S)BQ_kKpD<yUtO&YN2rmoGrP_<Mi%1cCI1
zbil@!)-==;$uDhg&dL-fntZW}O~W2=gdKKkpe3))+zLy!&Ne`6@>{!zm2G@){`Nv6
zMyG_Ytn8o#7dpshSbXvO7W_BS%u4jyjRb=26S#l1WHs>_Gc}PgR2W@NaBovf=iuzj
zJM3+ks7lD459#R=bh7?0`~u|Vf4M!}*YCaljR==|W56JW_AG=$BjD$G4%L_b%m;Cz
z(R3Zb9}Eo5f+!$<XGYi~^T0f{P|A-N`kr3x=>GmAFr}Iy`Y;zm$^7!p6MtIZ@O<=-
zXC$sPPJkU-8;^>&kBcT=L#xhisNe8zb^x~r+7j=%o$m8Qa1D~=VMN%@vEv)UDJSWm
zv$tQbRDa-Aa0{H=r1I2Zp9DhQaJRVgEViK7{@7m{)A|~l1dMEj@NV4mY&0%+iV>X+
zRX_V7+)%zIQg2)y0VBc!colC(8amN@e;}7(`tD9;a<hhC%88ZQ&?T>0f)a2>RR)|L
z?xpx(A;FL1QD?@VO7N%n(2_NEq1VC+r6~!)aB)Mw=gS9|;jbG(FW=3c)m2kA=7xhf
zm1jm^Bx!Pl{?lx2c8UQ}gfwld#>m-QZHlqIN5cGWa-gFW%#n3e`{`FnJNj!WqtEKw
z>%)wM<d=lBe8N9~AIe5x56&!30y-s#r#kYoA#d8&9^k101CI{AOP5#CQ~37;*Q^h|
z_am(>Be@#9WAtaJK%FrzF3yzzc@v7nbEZQkG#QU!%>+Q{(6{v+?_p4{Y<+oF<N+Xp
zUy4{wcjLWx)Fv7l77@G57r5ZfxSsJd^qw>bj!t?&h6_j+sa<VW1|6N2ezXYb2hixu
zKx6@V<F>v~8(KZxy+chlP^OiyN+)UF+JJJd^Ke8ga{fGDT9*0$nEDE+sJ`gyH#E|r
z(j|yWcS(ptgNSrV4-HB;2uKS`52;9ZcM5{Q&>&qR-GU(fU4H-nx4w_H#<gSt^X9#K
z&pl_Kz4uwv*VDegh-TIXd@&?Q<}r*(12UMI{b5Uw8M~hME+`mp1xAgCF1z7)HP#xh
zs6!t$V=JgWYcQ=u!+(|oy<!l|0FNOF8MD94T}C#t@<2A~p9&}|G8GGj$TT%o&DQk8
zteynC6Q?j`<qHkBQhP*x-Ui=}3kTwkWUvsmnM9v-H+%m6@yYUUsOHnAB@CU1Kx*9u
z_LU$^n60~ce&sN2N;@M17`%U4b86UQ&JqdZRALQq58qg`dhsmN6rAt9b`+ZUX?>`w
zzOC&fbg6ff-l@i~^$m<}+_Zc8dV59YSDnPap(t@<C$Si^x6f%o4s1ksV3WG+`)00#
zY4jWyAm|IKBIgI0!CXY!adheNjcXxYnw3MhTcD<9ULIa2S7+=+z~|2%oD5_Qo#7Ni
z_}!`#5BZ|r4IiF0>fID!`^o$Qq8nj|h-8EXmueI`U=Nr*AHCBEjG7Q@niYafuL3)a
zbC?yb2wB^CDP`3DgjwmPiLjC1nNTE&H@@_{5k{0^aDR(BM4lCZ?P4Tx_B(Ddg{M^$
ztn0%8qnnh*M>Gq*7ugDnG4=EG=<?_Xr<LdDWQ|RFLY9MR;~;usLTiAw{<rr&>QYH%
zEQ7~nCpcD<7l9unJAO}4V*c8>+Y}OlJO<z7{T`ohl=w1Ga^-iUiab+*SZNP_(MiF%
zC_=u#ZK<at4yV7U4!4TV55FvVQ9kN^Y*IrkMG~MvX28$q3^)fdNbXv44NXJzrTaX&
z{(MKcDY?5Ja|$Gv)0p@_S&!usJji<SeKGkgr<K$I$hWZh%HAsgEi&;)b$ooh5ZFs9
zXS{sWnM3O-sYsEQvjL$+*ShLC0*I(s_lO=Vk^5!N_WAEUEbYQVy6N%pYLfN=ZdL#{
z2ZcW>21cK5rC;MT(<;zD%c9X8C8Y6?Lk5kuFtT)A^(kSI5rD2ddcxO67#GL}g{{49
z0WA*^#F@Mx@ca|B15C)FuPuL?DZ$lblZ?D-TcjTx8d4osY}QCVlZ7hS>Owz@OSzUq
zmYDr;Af&->cjd{|ViIMcz;ESJQfE3i^C>+(KF%pW(6~e5OVADiqLAJy9|=&1dWZO(
zOk+c`Ji}e>YIxgQUY9wUK;)2By3K_q%=`8Uk-VY0`d9)O9a#5Xq6w~bIF<UWIsb|^
zLrcAWQ|Q89W=Ku*?+Zvv(8GZ-t0<_$`0qQenvg@?gmq%!i8sqdu51aCy31qxr#Byw
zMp73Yup$o?9G-@(tY2(+zA1rOk8<GrLfzyeu2;vPuhJ$@Hlg}Pt6Z50cxP!qhnNd}
zvA2jlPzFn4M8;h59&sc5)HEk}w9a=qVVPVx;H1|wL4bLHfP}SxmG!DxQl?Zs9G;(N
zc5!w6^}(kfqB_6`DnN*XW0z8_)SS{=uaDBBvPCMtpksozToC+e80s<#to7QdeF^LQ
z-s$pMS?lsA^(i9GYo}QpzQy>Zka4vM1=nDPxY)dD8?GGATdn~A?&LYnBwJjPzyDtU
z9u`Qu%TC6?^ol%(WLGXk>>n62mX?e!@a7~mIPagwbtg)4lHa}vPH=IXMBQu8f$({w
z;uN*Y{2YOWO@Tww_L9uszc){Zw@<%=0nQ;gxw+RQ?G?CWvnpX$p4=2W?wVh~f{(Jw
z_)^T34F~{f`oMs6)rl5iVu1{?%2;ND1_j54U><%T7{$e1{Z3!p&%8H4eM!jF_-zpT
z$vGNG>u?`M#0Cv^+zs1UGbbt~mjS8<@mLF=%&>0~nU0RG4(zN;e+i$UP?x23+1yd9
zBW-(v2Bn#3?YAYz@xyv1CPft$0%=n~A48?BpI%u07$;WJ>Yb`Aj;*k*QtXznNQ?n-
z9l&-gAMb<dI1G$keO48w1#eO><~3Bev`cGYxsLik0g&{}0sM`&DG(-oda1lrK>z<v
z`@Wey>eARq=Svmei+}{<T-8hopbu?I5dwY3gjX0WVbfKXd1NDZl9M#%X$O^6RWn)j
z;T`dh<5J$mARGP&mYv>*UN(FEjfA@d!J?iNmH3`ZnYm!fs3D;8?}8+JTtN3I8DD}9
z;rLLsufXVRyZ?boX4R>o@MHbxgBFwQ((Rl|86BBpmp^|iUEvLY3U;GW8@9j{Tu&!u
zmtOM#%x{X7@TmUp>Rzd<??1@uG*vD^(JTh=ZBDg#pBk1+oLc&$jxMg``pKoF?O;GV
z$&f`Yw!>0WqvRF$gDx`b5jL!R?EbbfMAUZ=2BH2%y^Eoka_IgSgiX|%h*T9a+sPQt
z@cb<QdStmLEI%0OXPFoZ2vbCST<_;JJ9XwzmpYZ}?0`Ga+>ctV5Ja@vuc46Q93Qve
zKz2#hDX8CTYZ+ariae}maH99pU)p*{<8c58N+{!P$SB715xEa7C9#0&=j197g)-th
zvh<#rp%dsG_+TZeXHT7c76FDdaDMc?Q-FBA;!@SEMQ#C+%sc%2Ck`hbX@S^FB=3R}
z&HvrB1Td-qO!E;t$$4|-7cU06pyE#)*+L-UT1ZGq*+L&4xfGGXIeY}E&&d6CPrF-;
z@eFQG(M{??sCUC-+#YaYZmme(Sh^UNQIo};YOA4H<D+SRdlX_KkxBQ>5w9~&cI)aA
zCMM?FJO)yN?@JF14bj8lZg_UE00YjXV-7t&66xRIxoTO_tlX6mQLn|R3M(bO+xN3V
zD45s{ufAzOT~++A>v6|1=yWk@YO?l^jwiiEE5-nOgO7Ii!w0hl`_0juTC1=bbzsC2
ziF7vKp2DVsa!X8i@IXHg&6xtVOxqdCnyu2eU}bBY8nJONo1j6%ZPXQ^Ap2U&TK270
zF9ly<ivd};GI=3;&q~$v58$Q$&^%Nt8I=F~lGyFIh^Tq}WD!7tqwoDWqA&Y_>aO|P
zKfg30wg_ISh|dyHWX3E|+oEK0Si}m7nqNif{6V?3we|h3)%fWT)|HsaKPD<McS6Y#
zi76gj0c;(QFg6;|jpkheh3!+iQ`s*PX#>WJhtoKa9G`KYcn3GW*pMgjh-Rh0abi{$
z({mgi>RoXPG2xIfhlHGhvR@cFxB*D?jplS>leOu2`*)^t;MPo25w@#>B@$ge`b9sC
z7?0=O`{d923-*dR>sFKz&I1%;YTQ-x>#{NB7ipGjK(6JORHO2b@ZEy>!QueLQ{1)q
z`M<8=#@zLkQkrRJ(Q|WipLmatHPe_+UuP9=#lX7gS^eN+)$ZmSJn#P5tInEGbbCU|
zMeoUn0%vB3U_Ms4F`!ME9)5xtc3bm74!++@c@c<R`zr72dP@j$sOI7w4?=>z-B#<u
zK3|I!DNtKjC`US?hWL=lFqkav?dDaP=LboFc?9cjO;s=&asdK<{IBHgcS$Y&J_hS<
zp$cQSL5lXWf93E;u}cPb7H*!K*g%z#pIuIs{=*kE68?XFe_dD2@TneJ=gZ+t?q59*
zr(AiM{2Z_dh!R(QR(H$%PIj6J=qK(v$Xg+?m=r^X7Dh!JF;QvwnN8lOd-J|o#T^lM
z*{%mrr(H;2;LXK)hb)-P_%E<~DMRDt{3#2s1O7z*4-{TWgENvFsx3S2M<p&C7|;#b
zHxlc+FxJwPZs*3oG+tXlQ3#EIgiYb1@-Xp(1V@p_@xKC=b>`w>D+Xd>DEp`O_8qOE
zGs1_;6A?X@p?zE^!g=#=2MRpv7QQD4ZkzG^92AX_gN2%(U#n#q*PD%dF9If>XK`Tl
z{X$U#(;#aC%aU$x{H6@!NI5S&5;FOS(=OELT3A1^1w+NpfKTPS%c_!BF5HlQwaE-U
zoY}&U`-mT^!l`E-F~ehw{pA<OF4`mwvSa3y1G-eM%az(%!6uCnRhu-ZD0FA0X4?S@
z?MZfFYHa0Vu61V!F2CB+jAzsmeZctI;&bpj;LF!lY!GFBwu9Y&@1y)}G+lMBa~af!
z@y&{_mj_7*tOGHREOf}afPQv%<|ZMYK`yMYCoZKHzY=EkBF$3)925Ex3`bUR9G@er
z^)`#EYfmsCuH>DEU&3b}GTBFeTr#2*^&`kK45x}iri--EQxy)d?ewEan&>&hV%eRu
z`|Ax#XI%{2Fm8Oyspn>9&LK!9t2nzyw_^(?9rhi1Wv1+{bZ-Z5Cmy^5bL8OONA`V%
zltE2rp{rK6g<MM;JnBrP@njATj=^=#m~0Q#5EJHR+aNn&oODfu*c-<R4?{eOaEfME
z@rALrZ#@JyXoD!S6%^)eipliDKtg7{#Z&(q>ZW|uXgU6|GhXuo2j=Vj#0K@el-S=d
z;5YncbMQ`7=8vBr<pG560OgJgDsd+co)O-r>qf!?9%t{79l?`UN{J#|!5{xjr>ZzR
zA4xNvGjzk@$K|@LITz^QnG<BSEdL^#6|zo2D9++cgYz>Tl87r=k?NW!SMGsAzFcKb
zkB~5_J4m4HHodnPu}JJctv+pHHZ#;xz_Ls*w^KS8?md`p<ND5aw9-ZX@R>V{msOE}
zjCVxow!)XHrr=J{06uI{Ri%FFQEn8H(HcNz>>32pelb{=R--`jS#E3mRO|f(a2N6H
zYR9QZ?r{qRG`vemJxyNz#*J^gs6ON&H&%Ubnu(NvZ`N;+?9;A*+x@!PD?#SfMAx9Q
zXwj|w7>h{mNFdT94LH}K=HvRPyU&Sy8#~t|@8Gak0Xc-%@EonA<hC#>#A+5}bIa6*
zT@8<d@eS58+m(%t3;~~!5`c$U2h7+B($T$|4l9+{u?}c(=t<S3>yCqow~?N1Og+l{
z@aoqQX7{woK$6PhM_mKFj*|)t{V_h4HzLAAkdycC-lfED<@IFD0%`%YfatZM&Ih05
zp@0&9)}1i$nMpdi>7K23op2F!K8nrhc@mbNh@{6bo?H><l08D4)4(-)P=`t<weOJI
z=I3P`b_V9%_1-5tx~Z|Tm3Zw8eBG*$BRI^Nz4WV<_{V?SaZk%|*wGl{GG-5YvH{m$
z`hvnn;`Ve}aM1tUKeZj93n4V@nr7NT^J|l&mdc|ufNKEK>t9fpC6WMi18w+`eorey
z7Hjc|h<jiB4uH3t+qXF~*N+GU`eRHe65Hw=%6-T4)yn$rnP91c8m$hp0p}jk=-PLT
z{Ynxt&avnWk4;{68)lLbM`!~Pl@6s~gUKq2wK!~6Ha1>R`%j8E<2AWQ3R_lFpo|xV
zK;8%paf!N-LNOFP(s4}kgi7XkQ`nh1a}8D3?MW<Yd@vLmw{1*mYHi;a>ltdedH+&k
zSmKX`C%sQ7^%FID-R!k`b@-@!xdcs6@ZsNw9@&^WJ5EBCgZfM%v++UV04G(4*aj$?
z>WJ0yx%fTz0P5=@#CN|7+4CrZS0&;z^LN~GLMc7Hnag^@{Sac)+8wU@Y}Vjn?^V9w
z*u_S0MrZhJRuPW`q8nL=7@_^Eu_M8dAXqwtSbda$6V}zcu%9ema|_aNCE&u-_OYZ>
zIcx(4xiz)b$})X=4-&%gT<amogJ-arTT*hdTJxecgv@w16y&*PVO9=lo}K`xqR+vJ
zg$vXCgv~wDm!t7lQBct3?0l>1d$pV6>Z+lqEeEhtYa7bQTcafCsbg-;o;2KDR>?#D
zJ!K}(0SWr-0L3DARH{i?;d~}_h#I>#nxrh81$8V|^%QL0I^?vL7zVt$ys)q@-V@>M
z@N9kY-Se+`o3xG4-`zXtEnotJ7ZhivY~=YggA7#Fzgq#})dbOMP)k^S>ibl3=6TT&
znf<`A<<x`C^O{c&<f3=E*y;-l6Jhl#wS=JeSH!R4tyfFP_5(O})dM>nLnyTGCz>&s
z)+v$$tUXLPkg>R$n)hM#BHiR9(rJ32?^?>P(i>P6SVKfEgA4>E1vIx{1hk`|^>>d?
zsSMVMI_<+Ry_2VW<_QY3;%_LFF05?w_%qn{ZRq9C-7jcC<)r723v5t<$cM0fl$XIf
z2pM$60%|dkjc|o+Jo%yOu?SQzcdrD1Adl&Z>Dp8Ru$+}-S9wXgjG^OgGMFY(04L9!
zy3PaW!JWr}cGA_f!y3@2*IN>`+py?cd5InXGv{#@;Y->-@L=zi!+9?a1j{z>%Y27r
z;o9s*tp;8J^UwZYK9}r?ID5p!<v8Ygr3mrP);Is0o3o2_qW%AJJLUb?V5d!@bMM~N
z;&BID_Vx8iXph&3-NslrzvRzu)cq$Byqbx*<{h}@C(>Zf9b>?XsWKMdQ1lwpUt2&{
z<Rh_weLRGp_6??smF<<?5CP1o9=F|*x&9|ogjH{KS`cSRk^2s;aZp(jAU(71iOFC;
zbXxqhC;vVcEc`2o);@xt{3@3*<K?4jVyS|=t-lzvzP)^;!O~ebA66T*t%3d_j4p%6
zOg4pCLE#;l@pm5QH53UXN~>yt07Az}7KKV$K!<A~Hl-=P`c?oK!YSsVTvT<$jOb6!
zwf-*`;GQWO9?!GImf6bgb{QF&kX-9A*i-WaRmdAMD6me6Y9AET09A-BMfWsRywmaz
zJEn(k5b^h9fpIt$|GG(&5Xh4l`4%y@sfM=UE{5C`QTt-EjwXnE(sN;h`n7V6^LzhZ
z5fbu%1O9D(p&mLz)ruw4c?wb$JfoXWkNOiqB@@k$zhVtprf!6U=ew*Arn?_cCKR<S
zgSrzGnA}2#zSIG1z!HUC`FO;P(|2jEQ~sb`OFFysO%MxfvxerC1WAeUS~%jIF^d&6
zU23jGPFVrM$QLeewr29M@r)?I7SJ|)JkfxUc;PjblwXuJ5nm?F0GVr8CvLeZ*h2St
zob!y>nHnX4%T_{8?;Z-t$Le}}A;fAh(K=E^41bF?AlK(>5|^v1xA@fsCUu@ZgUT(2
zKigNLNy@0bxF`K|5CC^{dX{TObpVN@E3w%leh!j3fWf!C3-iM?mJbYFl!ZG3a4plZ
zca#jcUfms#iINN$w+-8{2KG8X`FD-N>6*$u0!(_2JL(j)82n2K-b?FN@=sH;wnzLr
zI(s!bHg<!y6ijg>26pz-5+F%pQqryjzu{eMLg5apr)t@M+mIfnIPY*;`R9+5*aRaQ
zgi7aKeHWcQBp9<EikSQc(ml9{h=?}H2rc9{*S}05l}^m`5^QrVwBN{xI=f?Q>7F;w
z_7XMUQ?pBIretRN>wuJd2-N^#ojBFsa36I7xVX~vd&C-igD(hIy#~nEy4$_C3pK4-
zdqISN!`;z^*<hV5XiH$-9$#QYO{{}#SQLu+K9hV#sxtOdKGs}64Kbt!T6Yf5*OwyR
z6HkhDXinzm=l>&aM}e}U3F(Q&XGE|hH&2m;*{%d-fCH&;d;9JT8D^a%<JCiAoTn|o
zZ!$7$g9>^LZO&65s7b^*g7fuSea^hs9;rO#d>+rUjE3Ir20bV_xt#}386d)kK-CZJ
zx~Zab)3z6Ec$ppJ%(TsAf}wXqGa}_%0f09n92kHFjiMEAB%M)#QY{f_nRVrIbl`x0
zC=y^9mfvS>JSQ$2O{3ci5MRt)j!r-oI{pDVraw7A%QOaVUE8VKf%ds@>l3s9oa>mf
zo{-;J{h>B4^iuP$JVL?<=a38`LD&8a&L51Ng?2CwaQXb(QK`UnyQY^AcgOHc`?h#Y
zmZxP97QT)iIpJ)fq%H&T8-L){1gzk6;Vx)1K`|Zh_&$`16<5_EjHCsK%>;qS%a=j>
z?a&X-UY(wHOsIB}Tu_hBc=rP(AA;uBp~s-*ntIrVN45VZy*Wk53-}@_Fe12YCH^&p
zx-6u9^2<H+7D9z+z?6_Ldg%=Ms@U(Oq;CD8^6oIol8uC;e8^|kFQpI*?@ulULZRz!
z6g3+g+oHvKe_2m{p(s|nY}Zp|?xUwFV~W2ED(PPYV1gXpGJIo{Vyq6>?aGa?YG7ky
zQ}fo?p*$O-pG#F2)s`QMOncGLoRj&r`D5}Kk(tc^6gB*+I%oLx=Ba)#_^yw^8%#v&
zEN&?c&CWn!Luy(YB{sGK4&&NZ;~wU)nw{sz{#8B5I0dd-n`KmHEJHTCD7$X(rOoSU
zhWc)@!LBh8IE|3~aNsD|H2<|<tK_`SPKA(Ai`%bI5NU!R96dBSac-1Q(({bdukA()
zm^<2<tpV;<3zI@@$;RY+*|D)PM`;5lK|Z5>3~j=TPACK>Ow|tZ=p;MwtAw4{C|6w;
z$~4elP^nGyL;v5zxi|3_Lng@s*{5hr={nRT9Jm;0SAOpJ8$B>!BP$7Jp%s5XW;!uB
zhN4SXW1<L*9X_ui*2klQf}Xc!gN<xT(LL~XEz@qkabo;Lvsb$918?|-i3=xby*kcv
z{FS>fgN3W>Gw9j0=(*Vc<hOAayAkK&?4=Li6fOrIA;lmF<iV4VBPw|XlXP)Nz_Q!C
zUV!Botr-JRC?Uxe9gm!H_(m<rv_Hdj3IF?2=#fyQ)eM&Y@>C(#?pYgNIcR8l1Mu0A
zbmTG5+Rg1`0cWQ&n#ON)kJT%~t(c%N82X)v&Sgh)Tc<bWfw&764?g~S+f;9VipORt
z!dgPx3KEni7zQ{719;qaEo?BaII(TPA9Vf&VD9=3@JJgwKpz*DTq8F*U{||SPG70m
z^E3n8N|7RFvl=^&D@?ZrYTb1XlFk<C+I!gEpE5FDqcPNORxxDdyp#I8_??pWxJW1i
zAl6pZ{+jG<z)^`yiRAav(y&?BrU#UVF02cFE%bWu*Z0U%;t_j*oJshC3lIS`wLBx1
z1|Xcm4!5$3vQ8q-dYQrynw?$TdhG_)_5U1MH0icf{)f|^S6OpR|Br`>XPo=siyaH$
z$pZ@fpCCQQYR@JF&lRY?0XJTZSusw!t+xYoZF-5N?E=QcdOQC6B6o6jjuF6LF@y?u
z*1msvxgo2YVm`u!#tzyDimIyqWbLYED1TK|Rmthi>)m0)+r&vE_#Y*NZ|YZ>U+R!_
zyHp7Y-JYq%W5W5ly0ghfHbG`=Z=J<F%vFm6mZs%b=Qo&4jU(V@dIiGFNsfG=spZ3Q
z^fzeixaNuGze$!UxcBoP&uOshtNI)JxaE_y6X94H=$8zBEa~aU$j;85oBjFIO(1|o
zEiMw7L_E?kN3Z3Yb$rHrdK)zY2j%2CP;8(;KZ<1*5f)~KU<SCdj8ZQqthOm&OIBEf
zaU5M8t+#DIG;XfJr-H1k>vt%<%tzMI+3RKv?<{?$7;}K?c2}IRL(zZTW9pJtHfDUd
z(c~_6w}kebDCz^CrCi6^JtjPP2y*g!?QEdsq$dn&B^Qy1;yhJHlJl$U5$IP^#r`dd
zjv+$m8;n^~LytE2_{lT{T(|Mr-m~i2k0m*6!!N(SX3-CN{s%~o|4N6|K^|GTogkdL
zVh5a&TIkAVsyGp0pqb9r+LwK8d1Q{QpM1uwGNxy~=_K#xfE0e~Q8?>M4A}viwLVDb
zEx?L?^QQbkVW9+?@r$T}gs>Mtv$NknYJS((4fA#lPm-$Hy}<<SbD%AK@n&_H?H1P&
z9r1yL4JQ3@+N~*>V2;xpW5LnO45#fg-#!#k`W{=4$SNln-sL;u##+$VE|Fl@j|sZE
zo$SKK!txz^30qD54xi+mC8qF7_Ajby#sg_0N8a$`B4KCy+ot#{jNAK9lf>93Wy)bZ
z?x`d@Byzw;<Auiuj<Lu9C3D-i@`M>ae|jCmHwJ}|FxnRP6PSKTpPL7;1V4fuw15Y}
z)F_h(2xFKeE%NQa8HDz?({6l8-r~0@F!O9Fb)5Vu3~I$(_mcz+DB*^0G&D4(lsu-v
zSfAC$ED?V4YVojGV0xX|f4j~_3~>(Sx-eo;J~6r0@2;9r9UY9gz3g<(#l*q|jmGK(
zka;44ow>UNqnX`h@;ITcZOd*^RCp?&#aD=IWF9Qy*Ws1QIjSYbfY8nutP?S~Z|kk7
zsEA}&A@q&W=i^gNPfA$jr>KPi)|~GYiGhXW(>(@L18fM3duu7k-4_O(^$#BGIO2mN
z<*1;z*e4EI0}z8DZE}lv8kx1Ryx6%q$Hff1rDE`1BYF<6wWVR(JIxE!2JH{9j-t`Z
zPHo+q<dRDC{yI)K(gbX!{@nk;+5f{h$RCrGt>4n#0X<--?ZuUfTQ9{k(Yqy$Er*8F
zqH)MW_2*;lKHOxxBzr#`CqpcKALz&3E;`vS{i}W7{M9|M&~$K?cs&bIUx$i~SJ&1E
zE!Qq?I~=jO)_*JcMUDx;HAJFG7>Ppl_$wliXn+aBxn<+*F2=rKmY2gyrtKXePg^`e
zE!ZwA0nDK9b3tP}Y44v{dRZPRBC?gYKh>kLq0D_`yh0qEiukY+Ee&X#wF1`BrYPK{
zAnOsCg*9)S1eq~q$RQLEWTspK>_ZroVxIqT-eyUnF<ScD3S0Va=za1Vy*+TENYZpo
znxeZQr>188-uq6KSPRh|?EAqaB@%>5k&#e<RJ>u@+Zgv{Pq|*rq^Myf<7&vG&BS7m
z8al9;t<$c~$@O<L(XyJZS7M9)$UfY$#xEo!`QLJ3(u>c`TwJdOepCU#F5Mb(T0!N2
zvWEW0@XE(#jP4K4LqIWw1J%!iNz^n15Xz@&Xx$km1#0K4(TO4<`S{IYnZk9!>juz~
zXaL;FqBVzeamYL&deB_@)9?fTes)?h_1bRptS@?p+suSy#M*9C7*?V|p(Ko!pZjaD
zp@**<cgpda`~8_z3xW)BLpw!D42c*{g6G3O$!8BG=qa2-kzqJsL~|*{5i9tXPAqdM
zGc&hCns@1B>LTzWx<H@XGld=j{v_^ND1}ELzFDApg}7${vTeEP!7r>I_pjJGxT#?6
zx8x@zQJQZ)`CEnV^Q|;mF3t7Jh84>oPY(2bG>^9`I%h->+-0)n+p3qlkK2YSS#!Uv
zJlVFf5}-fGLaIG8$qhe1&*^0>v%35_FF{0BKAb$NhGb;im|KTK39K%VB?4Hd4HCv}
zr(+Ur1Z^C3uw+Sz-u=*jdd^Fn{!)L+gB~)!8`DB*K8KgZ^0?XZS^b-;xaN74?lU?i
zBl>F#GLnsN#Y>AYkfg1jN2^Bbw6#8RGI2XthYMH8<Y`jdYUcSFNXmhZ1@XuQ6w;Nf
z4e|hqs=~B!Hl16}hcx`O2T7f_)VC}(mzM53JcmLxfrY#Xgw%Xw3EaaN#^Hl=Pjs__
z6u6UZ*X_M>AJjK`EUS)58Q{F6qBv{vFn+ao-=ad|vVZ>%3Fb$l&#}+?C(F1Z;3YzV
z1x^9&ZJZhBU5v5jqEi@v81o%P)P*eT9T*VTj$j~@-{K_z=_Bm2u8jn$=B<jG+Iu54
z7gCXy%!M8>+q@8Z@8?9zr|aE1)qP6Aoil8Z;=QVsz}}`1=o&je({^DE+eb5*-ugyh
zgf8Xwwp(0zu5xzbawD>?Wu9H%va%f?>v9_^-Y!>3IktL|ldFOTp)Gj6oe;Re3c#y+
zE`sJF8hkxIlh9D66uZL^zP7d&3M#L=5Gz~-w6;3I*cVjm$JkHRsy0A<!b+m%2U5HH
zz(GU^(EoP&OLTSR?jaBhW1sQ~J9Wsf@`iB#F+$`eM)Yq3i>~F)iU;fkjs&%;38}n%
zB0}%O+H-O&={tg@1McAuj~RU|;hEO0S_=_xq!S@TRT0Q4gr)~<Q}~EeXPKn!SGYh2
zXBlsIy_rK>0SvV;oAsk$b91vQ8%L2_fzp_SgfgT8BVBvxn#XGR^S@nbY;1Cm7VQT7
zmFEafss_uURp_Ob(G3-k5gjG>Qa->>^`@z4e}lIZ@cxe@2a(jP!Y|x-a4tQ11duG0
zN&nDTbL3-_$BWBS|H?f7a8uzbU?Tu2ryP$HL)b8gLV#93%BW_~fS*z9_&j)Lm|&$F
zGuA8V`*OQgO6@(VJa2B2`Akqm9!R{7<!83IjSK?NU?jkFIh2w(U2RB3AZQJN$lwJu
z8{qL2?xX$cT|hLM`J;j|e>XMZX8jNeY;Se_^0yphv;+r#^J<$<_#ux-zCq^Ct*-6E
zr+kq;$GzXev?>t;)sBE^NJin4XtIF^8PC-RPzSS73P--9e(jkfj~#%=MG$@Ll|&F*
zG}XZlBoXLKO<4n|r^Pij0-N6C59h}^jyK0bJ)UO#I@!WsJgfv*;Ez%BhyPm-v67Ae
zuPhxVsy-C<7hhgMz9YA!{=a@UHd~o#5LvxNUwr30Jcf*WdaC8Z0Xj_p43QWBg?UeL
zODKw69di!FZ5W8D;JkgxM~}<!0f~Kwu@!bZP!8k39~2%vy?!*42taH~BmTt<^`QNu
z<0FC%E5Zj*mqeZ15^tL3Z^2_9i^Pzbzz<?D_T7KF#17a}kSxiv{^u+BFLBsQH4<vX
zW_c{I;C*IqZ!c-KMo%&#4_QN4WFwQPIr8))e_IC!KUOsn-tEFG|I5A5j!;^RZav~k
z3XekZOgv&Ny4h8yOfeIi4P=Gn6>}XZ$5nk6Do~)n4F=%gG<VcW_{Pgl?$P(eAtn?9
zkOWH>QSzBR*t#tGwpj&*g)^mvThfrbJKzz6f`?IMY~kah5^ZKfBo;UWu-=$OJ^qHu
z1Dgc2Ov1a@k8-l}@@{}XA;c-Qe&_E66WS61Qz6!Y2H-zvvtT(Ko?&s`33XrmbwuD&
zSM7tp^b#`4hCPVf+G?B|e8|PMkJHJW%jbMAU~Hr&^rQb*@h_)B02A@~lApga9{*e$
zR9~hSC%gA4LU=xeaZ2-Z?LidK!ow_4AeaNB-8s`-+5Mmu!h4@;r2}FLAKNwKL%fka
z1}_5l5HHmXpP30f=yk}4ZlNVUBL#R8nlQDL_RPW#LzZ^(nKhzxg1?02Q_5|qm78Ta
zy*&c%tNQ*TPM^KTZ71l)BM{i)y5(L+;3}7LO_pd}$ICBj{W`snLkGeT;MQz2hj~rZ
zPK9_q($jj11*p|m31OyU?9I8>da{)g?GH5r65`^H$QZlyAycI-F8ue>&KA~+%%C>r
z<}<=xLbyoKP8+%~c>#GedwyZzxl-WoX+owfv@-WQe2aujEu)R1n9!Y;1!)AGs`S&B
zuk@Q**~~y@k^x3m>_WL&?)vMQyhlNerAcKv72iZW-5@|Nh?^N7k4OIu8Qug=Q{yjT
zGI=rRbq%}t4E-}Gp}#t!g;>$7WV(Fq258%Ey6!B7|4+A$E?^V#iqk&1OCqiaj~viZ
zOIy+xjGr|SfmE=UmqRqS)FEyOv15sVm1iC`CJ9~(e%KWxfQ^xmk+EmC<_ULEbnIrz
zk_GLRVSam+tm9tbPFDc0<{eBUyYs#<8)u6};jVE(;W=->TfpH0us1#Ev9kKANy(_?
z5|6xs<Q~4!0g7&bcyRy+HY4UY2KvMtgpHK#*3b;Tp`^pI^N{@mrmZb9RnSg)115e!
z1~FZ0%zldSBT(W*U_?*n0sL<z+4J!XdOW;R59jSIAGH=EW;Pr(S`id}_6!m+W-mid
z3R6S8O1!1yT{i`sQ`LLWb9qKdN&lD3q>qi)&Nd8<?+y_nTJwONMEJDa4%d%TVM8f9
zEC`K5SHENqg2-}1)+#!T_QR_~go<1DZ21I^G5%v6_5e~YF5USlu;?l+F21x4?5Uvv
zOmZI=nX;fE;0KA@`%gTR{}w~gCL2+IyH@o4%dle(jw12@@-i!FczP!v9ykJnX7Q3w
z)fhgl@oVDVxqL?r051@MUV@<u7Rtx`0gIH4eiz@?Gq(RE6)x`612L{T+$C8z1y*c|
z00RZZl#f4YfHq4&m?D%s?Y*N9RRO?tU-=jYfgD-5+iEP;#?k-k$ZGg6$xPkfNxbI<
zO*Yq9v&ZlcC-zsgGtRRp)0UnUBv9L3BXtSGq*ijVdOp6h<_wbNnkY==YW)|^@B4DL
z4ayGM{2M}LQLTI3r1U@VXgW1Vl)V;ZggD9o_;5dX_`wl(Bw@mxxJpw69tjer642le
z%f>0s(zo1)2|w*_Rs(}L;#?i?LH}E7V?sSTOD|ZnsKEmrMK`ih1!;;CwEI^Le`W4A
zvjoJ%kw4wkU+)#azEX4V23*iOUgyWfA_^Bmh-;vR*XKB}um!Zuw_&rpeuV9m_Zkd7
zThGvH&9nX&5_Vy2gYB%w8QNlwaU6t8aQauzH}s-49na#!9%6!?4aWf{RL{-l!Aa5r
z)X)KrHu)#BOvAT~h4a1nrcBH?6*8PfPw7-&10SqZnQPMM+sRc9kvuFGrLM2yt&P{3
zMnvi(h)4eR(ii}wrqYCh+C&AArZ^F=LCDyz{9#mv<g*_A2zWfyM@L8E&}XtMs@(>`
zrsNGdprg?+cM+<8rTG_zc#X5Yb`ukpuLg2D-QPorzgJgjm))9#zBK~Zt~IuZ%BWw_
zw5c+?%_>7UVPnZ>Gc(`1&368yKGKqi!)yUW^N*45MuL@<wUfzTM|;~p;T4l4gJ~P5
z$7(RU{pIaTCP|adG9knRkS0R+W@>C{i}3(q4q<C+TQjt-G~;CtKW2j}uxsW(lbT&z
z{QC*pt^F4(uu>B=C7nf{nW&68Bt9zA&M)+04v=LQTr3ouBfayUF7|hm5=d3<fAM8o
zVSvEADnk~C`~@<r-o^JXy6w-)Jk}L}3wWZM8Qv;3eV24Kq*vF}tTBxBw+5#salqoK
zU_o6T_t7hrvC^bveZj)Q*O*HRKRiEQ17^u2|L%~MX!`H5*2S6b8!U*skIH5ojqM73
zF+IZjU0C+<&j(p4U~t;&#9|IhU~C-{_RCp^3$Ut&6iLR>?b-qXK>2*b$L7Epf+;w8
zsQ@V^17yp<1sYiIBeIk~ZupnY@mlmPAF-;^VL^0RbtJwsi1x*|Dhj?WKO>j=nv&MC
zw4CZ^cV7!w4$>59k=Q*0D_=Uy(gO2#x?$B_8MTsw1jDCZ8vl`vtYs_egjbZ=eD?5U
z)CMtL;(DH*e}QX=+s{;+#9k^r5Es9Cs|(t2+|ECNIz0~2!;}GfQ>@6d3E`tGfZ${+
z++H=U@!6Fh{jWqVq^AQfD?aE+h@&kr_wr(ph$8`dmTyiA1)RmP60se4`R_iQF~xby
z2F)4iUx*~rLnA7ixH_-3Z*l9N!>=E`qC)w2f&Ny3GJ#f={cJ6GjMCGhVH;|in*MgR
z^llB&7+;B_q?110*LaaB;fph){m#Pi?guJvW2qmCp-p2}tndEd#yc+gM_;8z1Fj;>
zICsKt#bm7s&=QSmqcezAV2yOU0(4@+qq}ZHam)p?Q-bY%fCfgcA{}j^4kY$*fD{OU
zoAC@~6J<^~;_CZF8Akgd2^*hk96w75%I4*6`ubhP+V{#A)U`1#c`rBoJTTf1Frwmc
zN`Zx%-8572?P&$gG3v|3KZE*8`g&qj6czi*enki>1|h3J-@+!L?XTX8{uvvK>DyPo
zKp%baA3TW9a`2L_E@{6UJuocsmdsWAF#`k#F?com;8S;SYW66RjH}pD8v_U81x#b}
zC<V*4>E4tnIvmi(9ZX1f*c&TWmfro$&36<9Hn8SbJv}W*O3hpDFE*^XzkMerOT~@s
zJqXA|3}T<mPDtOK1e6VtsVLWs4fqy=n4hw_lxmnU$;2Kar-Q%9_a-bJ``d=%yd7oh
zDJF^dIDKu;d*ahCw(~;8zjR#o{9-k#tE=a58ET`=3j0@M8-<58?U29eIE)TBMKe8g
z!A^4k1n9b*uhJzhVH@uO7L3Q{JNVb@M!8)TwqYz$QQdmI4=6bqz;HkYh4UG-7w)!;
zgwxg4!IgxX8T3PS;YBNLxZdI#V8r)r52}Fcq-q=7Th?%^6g%2OVl_X|05tj}FI*Wr
zcLca*z}@h<j=Nq}k&nomrFOO6nKCWS2_LBKRuA$}TSMb1tHP_K^3^+uCKQn)o`HVA
zrc^xkH!}uP<!XT(A|v@W4Px`XvvwM`p#r78?-zg|;4CwX!YKtzbjorQ5GUa-k#+<K
zfS=o!8-f3_I?Ok^{(8r?O*u^zBlhT)T2=gOWQ9+u$1Nw%RQi@0%ACbkd@_4Cxj}X4
zOrDvS`UJ$VC2zp>8MBDocnm%k;PUuK)c`;xY`#vy{=Tuy>84moKDYBTpn*?{W&WGe
z+}!*X(rLXrscFDDDWG-ER#4Vf2&(j`(Z<HANLw3a4w@d+D4EJ>=X((T<bD7W#t6nX
z`?ToEd*W}^B187}tU+CRA9dJ%?OABGqd*e-5R4mV6cQ2|u{XUAbv%887hnM;l61t<
z6kAb+?P?K-86%YTkHVQ7XMDtGsGHs2L>b=a6fM^b0N(gmq-s7+OKWOhWi|VT;~oLp
z6U~WFEH=b_WKk)Q{H&UFIj7Qf2b&}uz7tQK$o-UVh`E|IVU`q;F{*v^&Q4<e%XZ`D
zY3hfXt-%l*fwnJt14jBKda)@LV6#^-)?E(1qu4#Y;4o5CAqT|@Y$;s$C>>P34^G`$
zXu%bLRL)N<K#k`i;2|~<{Z=$!&~Jwc%c{kzX^Et!B0aU=P3phqw&+VooCD<nJnjPj
zgo-ivmT4#-c$!daJ6T$VqL?DiI8C1JK}i_azZUH5X$1rYdPR7i{$^DZ@u%ZhTEs_;
z{mA6$y|$!_@2gIC(ZV>!_<wLmk?ML82HPioa&~fxCXwzsp+n>2DgvFvmDbmB@TqHg
z36c+3<rAcqyQ))?ELnBXoMi^J#OxmHALO(kfi)TKEh&lbhypr%kMFHAU$Wf>G33a+
zU?vqITN5CAK`sd_8qvWt7l$eu<pU1tKKni3sv<R1T%x6{S_~A4>`jY~S*K^&9In+q
zXMct?HLval$ndPO0p9_@<Tl_^nrtl}xO0z0JaDk5p-oXiL1E@eH7(GWgV8Y-+rq@C
zG;&v&MsyO;dV79fn14n#cZe7V0|T<YT5MD_N;`sLO$H;umNpx3S$fBc+3o?YAg48q
zXkS)K77i$coK+Zsj^x>+fENu-sOIdimL=)sG67)nZOiy;t3SZ~$Pdi!xPRfLLdv69
z8&GO&@$8%UrymWRofNHNq#}#v+O_kk%DQ=a|Cb98V-{}*3pWRalVm`PjnOWi`kIf{
z^pta@BCl`}b5NC1kDi{+6n9j1@{u%-`o0hrK5e@kB*FBq40U`rXjjr3LC2#1-0|^~
zClOHn<H5@nV0&%UH(Vu|4Pbqr)^`A^NT(tq8%YJiQ~bWsc==%B=Q}#Kc3k+ieItN+
z-dgixf;jT>_)b!P0=Z~YgbBs-omNdW2yQ-|RtM%^Ml^Jxa<_aKcYwg12XP+8GGnH7
zerkPRKH}^x1ISnVK|hZY(c0W83vUAl2vHKCV?I>ZXCGzl0!Jkt@@#`54$xBn_Rheb
z(sgpbiu>K)T}fv29*HEQ5Dp8V1@vuO6_*73qDO$;^4X36_u*p+cZ8tDV3mUp*2uy_
zkn5Er;@=ce@1N<@0+F(9uU9^M<%hisdw@9(oM{yx(G*D{Yg^kU`T!P{`KG{e$QB$C
z4?v8V6LtnZ!jm~TyfDVDJ#(E7Q$+uhODdGbh~l0jjGLp~bj?tKbWX4z@B#5Vr&gV&
z#fPY*0`+-aUy3=7g+hM-FA9%2%Q5e6vgrDM+4KVrr~A+bR?E4Q${-cr)n;P``6*R0
z|GGsvSczaDW+RkNq__&EE~7Ykg2!pt0bKFOl*xwaoT`2I4>|H%G`bNJJ>punHU$10
zu5g$U_UQ4Nytc`jxu>K8k7VO>(kr@DQ8|O>4}y{#J|gijqmBlSF(DuwgsgaGRUH))
zy-l?N`Rd7oEFx27I9%x~wte;kmEgtwHk<&Vp9qTXbkO{gjAcfmk@zy}Ki6i+;?O!H
zZLeYP!gwCGt?ZV7pD7ObJPrvQOrM?}c9Gq{%GGP5IgR_$hColjMoXc4tvEJnU?Db2
zna^h@)I9l!SX#%et>R;h1s>Qqb9oY{Z-nRiP<7o%)!9bZqMT5rllSpZKY$h>5B|YR
zEui0Nz!yin0^EkX0YkUD4Q{SmDz9KTzilBPKmcC3wdKZZrzjf9XLhPTv5GI4X4FTw
z=Ds?Z{Y+y`lE;1{8Zc%E$4*@~Gs0m68?ml&-a#F`!zJ5ahEp`ez$HrTedNIL1dQ({
z^RAy)_^v-!lhPw{y#Z8uiUgV3A>fd-u_~!!zj7)E=po)Oo8fZeU%9QZfG<e}Q%>M8
zl`JPVjnf=l10LYaDmdCzCL4&1N6c9Sh!5#fvCquvOx9$XM8Q3|>OkRg@d9JzK@RvX
zn}QvMR(i7isXaw%cs{1!3pdNPNx)~DMIDn68ZD^hcJPMflLVB^k|PDyEjm#`vTU2~
zsEcLJq-{D#=!ZIs2_~5K_5g+g7@V^vApB%r#>9-?Mr;r7vp=heC6zgi^JQDoJ_5tL
ze&3ZP!9yg2{DsEk92v7*Z%-4_<}xlh5Ogg0uu4-W|H;~$tnk#l|Ijl&I14zL?x4e#
zWprHoJ)&XxNIZ_0QHfd-y!=Nj5)#Q<CS2$DoFzs99oKuB3H7<M(g}}*BZAKeC`|mH
z$h;({)DI?FY3q3cTbcz5tk%S-g>ZT1O45J=Rl8df4Xb`o_|#cT4Mm9B1N~r1egT0N
zjP~01fygtY#PEts8AXW6x(E@1Fm?AUuF7+y2M1Z10F!LS^fmMum?3gO3pL-gi99z8
z@-oi#fQ$gZYNzN^_spDNI*Oz*?s`-pWxhWAw^&lyw4*_R!UywI4jrMP{+|^@OsLEF
z1VX?k`rHLQ88~4H&POwz<Qf%K8H-)*GOWW1?JR*Z5=+b^HIM>t+zvO?baN=b-@X=p
z;rG`msK0vkjk^I~n#%+5vLuqQ$6+KTA4^P(h(B37FA(0gQkk*>LDR|-ltne{Dv6jn
z5}91@kt<}gH(Q4ubajeB%3(iZ;r)P2*!IC8M_1O`e)j>W?~nSnw(h0w76EnDb401&
ztg0$Q7Vk6_s%zDW1C97o$pbos-vmljWXFjXv~Vfjb3V&UUbQp=Z|INSe!SK#{tl_c
z@pgRtn1k#hc?w&Q-PWPmawx-Ts)~O|4zSg9SoDK$NyXd&NuZ(C{O0_4^VO3n{d>j)
zz<2T<R58GfM3xDOO^<MbADT37Gbk2>PW$hf2ug=}!=`qD^)#>;W7iKx0tVjY&1}=@
zzs5e%#g)ay8SlKhai>peLuy-;;!pT`I`GO?@FJbsf8{9ZzxlEBh+j;hqz|u|#@d)B
zN^N~Az5{RO(0r!FT`7`VX6E7d=$BS^8-9?$MVRheQrvkx{57#wVeH}bw)?ewMAJJ#
zl}b*r>C983`6Anr^&~fo{e8cmRT=A&b1hq~0@%+E8meu>Qju3*3msqeVgvK)*#!9W
z*;+%dgJ_ijq4|n}v)tJxJvzlK6@{5{lg`)fH#V<!KXj~zP979tCT$%sig1;H@kYv2
z@0m%<6FCjfo!sfq&|e!pNoY-iUrb~fa2hdf8qc`Wm?Dfg$?wFl%sXs1tS<~VT8&)w
z-{(~R{nPx*%YOygHd~K(`KnZN4dJBUxa|^-L#wxiyHF17<afkY?97I)=URg3(zrJ|
zaIr0$A5|>GDZZCpo{Vk%C_5`hoHETKL77;S{CQzvA)zqq><4OR?^S_DO&#Y~E%tl<
zdwWH)cGqx;O#gX2I^wTzG_3}MR@qm+-*bHtKU3hd6XqaEjw$k5IHsedppef=9Nr;!
z_pegOW1c|x``=iSk9Eba93TN}PQbDKtzMnOJbm_hiBD#tB`|9epW3sV74hi5D>>zR
z`%la6sC|L&m%ddeqfZ)ll|t$-YC2o~h3gEz6t%wgl*#meJ+jWl`OsP4X{!4J^#!U}
zW@5y4ff}P@R1c>%0SgOjX0FA_&OIIZfhLQ*X$oCSNvVI9#qedrz`Uf;B|*^|DqZYU
zDb_)yA!>mEhpMz`uTcZ*8`fS-@-#Xpi{Rs5Aq3PXAtwKX6#YdaOTk_EP)BU4&VElw
zUN6pxa+MojQsYTNMtIYgqgJn<ZzHwSB>WE}#@4y?JiGlPnpz%g?(ERu1TIM{_$!0a
z3#WfiPJWKx-;(}PK8BhZEA2!{)O!8h>g7JO%NDeoDxXBjE(oLoHphKdUAbadQA>+B
zb;z<1v!=wuvm-D>q$|$62FQr;E-o&p`KyQDQemNX0tIY;W}gVZ?fF?kzp=3;YH#6w
ziXCTn%l#rso?d*^@@`Txg~zNr)Mj@!n;8hzVvy7BV>XK@iB`AW8Ti`cKkwd6_6P1(
z8hbOeu!al9m=B}~G%<6$^isVmvAh=<n)yTpwGiYd^&I``W?H$Tl;SP(chkej*a+)t
z@tq@}4?{Q*M1#BV(*{mdiuAPy7W{lh|H3xDQ<Z}^_=~GhMqhC@sz*8H$J~j|c)#A;
zG>9wouTo<^pqp;TlT-lt@BH3EcJT8=q&Q$--BYfycpI&0X}R7GnkHPsVXQu+OR*A~
zkH}@Cd-Ey5TTAeX8TE!1`wLY$$8HGFY?hYh`qnu*=(%02<yy=N3C*XuT#OE@8#u2I
z8X^$ks@k`E<zA${LY=-!NZXIsS)Gm(8FPz^{+_P{y6%<#IlEM1x$<2V<ZG(XVSjjq
zrJoS8=rX7wO)re7okcC^v)@zC3_kcH6IrU)`o?7akMq#g#mH&&>jDiudW;TJ1qBYX
zKV`9lTRS_&GvPvU<u((A8DKOtCa&KS4R=*!#P?s?q&BLt<X8=Ib1fb7)P2u#pDgU(
zdH>Bmc7gHnr}CA(8`ij9R8c}jh}`JUpMoBLdRhHnzIrujJPk?~@VPky4C26FiD9|>
zqz<XOJ({C*qeQx^Z{W_Bl9E!Iq#@EVdF|BT)7R*_oe`1Kp-}kc3*+tBQ(cA3kzrKT
z+xnq-F7^aP)ozz-o(7-gZ<)z1g$hJ&F79oQOGJT!=JoELP~%0anT@H`tBbh?=Qe&#
zO9J{bABh_tz9!kj669$<(opyk<8cTm2$NE#y%dhjY`(Ghw&dll|H*d5)AE|VX!X22
zo;%)sj`@DuadGalrrJg%yP#mRjHM*e#Xwo*vTt5e!&Y@Y1~epAgSqkPlQbIs9j%#G
zP+Xk1S6~!_J}6(v{e)r~?+HD2Fu1bEJa%Y((HL>Vym^eHdQqHR1gvCQbye`JwUydq
zL%MMRK)C%%Av2DA+8kgLmJj0^m<K8xCQ5-PmF6>IgQ71y(rTM=)!*i|6BTnb=&Xc`
zu8Mbxt%Isq9;XR-`=_Xqwi5FJM{@s)Y(fRD@Plzlf=*yjW;>bNdhb_Y$f&{<`n8xs
z?Dp1d9X|*C>PI*}_FNH*@5@ksi5Fd;v;DXB_uFhbLkPk-IVE%fQNiff-eUe70)h97
zj+4x@ooersr_`%erpUH@;IMgBGx=Iy(~*Co8&wQ0P&`&|U}qP|MfhU1z=kX%8rm|@
z<kT-;lBo)07^4nZwXL%+iVzA;OiU!3yW(}f$<LOgUbi+FJw@4lKj5IG3F_|d_C&bl
zAY1fT_P_gTjZ(R{J^a8UnQ+g@w|kcSJU!MN!I7G@s7bM#%x~ax_`RxfdM8wX|3h~#
zc-N~~(Y3+!rUE@Lo5lH;!X|Ip{g@RHdM&={>Y63l6~NTJtq)P9-FR^pyVdQPauq9>
ztSeWt7(qMmhO@zFl=_KaPlgf`k<OXV^$Nmm%4}orI^$JA{0td9P7Q?DqE7DS;rSt+
zsyg`;!9K>Dht{D;dl8`IubUh$Zuz8FYp3gAY`kQ+*E)q7j6GieO5-Fo+7er9$%~}c
zE_;1Nf2b`YaO?dpX<0Rm*U9aZha4DNj{Mg4(a6RMe?`l^jirRH=+i@`cF}AQAU(DU
z@&@rc53V{VFO8y{etgcRZ@AdqyXFG5zpwB+-n?uUrNp%4UUMqu7X9aDPV3-j_W6%l
z_QYZZ@85av`*u=TlV4D95HD~EyKqB<ziRcpG-EAGKNEot=py?nG#L14gf5z0yH)5k
zFUj{9yMWoAu7C{hsYwxXGcg|{RAn7Y9<uD9pb9=f&t$P~+=+ouPqFJrma~EAV78@L
zV`FWe;m`<}g8sY9PVgdy8{dcyqvNnM6-*GW7sCncshZv)tGU*&qnVkVtpeJ)W48X)
zKeo*26c`=&3Qniu&xkK`+uCkMmSx6^2D9!u`qrRPd%Y^4c|Ga6+ETE{OC1RiwSmq3
zeSZ~V3|6AHMU2?<dEdGwNglv_>uCVyAHe-}sh2hLsR&Nsq`as?rxEv@Z)Wx)0$lLz
z9q-qOO#2POAQoRy8lBbR!PJ4#_mS7xu%dzj>-6kMHo;x@)3)Noj){E234ScR_VJ@q
z_ma%JgH+9mv3+0W8_bkeYO8If&qI3J#S0@cq}|(EHJ<oBiaudV&HVy`02mEWIJdTU
zBLyTF%#Zmj-{dycHG12AKJd>rBr1GfpyAbxy8hw>(k6T04}g4IeP5y7#>(o4yk1Uc
zX2d@s1*7O+m&tl)n-AzP)`OoNj8xmgvTCiq>o3;Vn=M>LimlDJm76VORd2%%Sf}ky
ziel+Xrp#koK~<gcp}FMI3tn&|V(PtDH+&i{dWtND9~Uagxw~t!OW}2O@IGt#_N8Hh
z7s2(SDML@A>|Anh@ECkB-e>>pX8wNma&dDbyxrehdkHK4H?u$xT%-J)R^}7(fTDOg
zkAY78JM(KqZO+R_X+k5vxCJy<_z9#m?v;3KQxDkHFuxzY->AR8r`Yrm3I!sG8RpG~
zG*d*={8bG&$ZljNx`VyTd66hZT8Za2M#LDIDI1<Vt}6YAeRie1L7YHr7M>rp>WY(h
zPoF;8tghb9w;&)8n%Ldj_iSR;{pmJ;vfFKxZAezA)L?K8e;DVPcYR#FcG$U6B|)P}
zO-2<oF*oOvlHE;`s?B|$7-HZM-$Jge&CdIH3sZ2aG|_2f0<OFG>R#x;yVbn`08-wF
z7YcUI2Td$2(1FEi;}ISIJmZafVrPdMQnz>BXl=A?tQ0eB#*^)Ze-3ts9P?v*SLf5a
z?l+HiQ=q3tj*k0%x>X1co~q}OlGr8`r8bU^{z~LUq)}qVARVzSKz>m6!nf<m*K%{s
zX+3yCe1FLN^_O9Nmd9jMT+Afpu|LPECi8~uJ~HE7RaEysbDgPwYi1;oc@v*Ka5q(T
z7DQ)Kg`DsVe}ka8Q0+WF<yWg@ymj{?zq_keGeF6xhqJFlq)KjY^TSQ?yQzNbdu1F6
ziez4Bt_I>dU?8+YXlPN;s?%9zIC<dANaLGj4$gF@&2_e>rXg@M7!<uv*7wo{><=&$
z?pO{kWV(q%(VRGe{olARk=NC0`<V(hamT&kY3?X-9bic7NEo;zp;_#;zi0F)K`}F3
zo-v=6JprBJ1s;_m>tCXO!+Hs&MUIQ3)lXMrU#^0aT9jGyHS6vB4*<rew^j2xjWdzf
z!?;bCQ|0fumcV#iE2<8nX#z(f^_=hjY42L&p=!7I5QkC+^;Sxu8ub>rG`Sl?RHh+a
z6v-eW!pLpLZOmkdiouA%AR?mNnivcQxxBeF8o7>Jgoc@|a?AZ}?|ILM^X+^)U*1pq
zw|{#*xBp&yt^ZojZ$GO!tGCh?g9K?%###4+v32XxqV<`pUu9(D*;DrSToQYK?P+q1
z&o|v2$DUF>OP7$W(WIM$B)$ri?r3oT7*x9JkUol{Ph+xHyGEWrv$!Ei7_DCHbjPs@
zEKjYE{Dvyn4q7tU^vsOct3FGRAI(}6W*!8IVzlb~!oq~cyUuc`GfBbv1TSVBJ{5qG
zHc;esMA}uXvcNBbvnvCFLs-4{#hP9N3yQzX=G&F&mSffp2Q;E1n9p5Z5>Xjz&@#vS
z;E}dRd6k6K4^pk92cy5Gcph5utvt`Udzj>(o5MI1bjPJP*Sam45C0~XE4FeEd8P~R
z)(hJQp3|&z!*-6+>ehV?b+gc>yX*63KT^)rBRx^0@9icZbtZ`uY*yZ{I+Gn>e(@5{
zUqg`aPFbL<RvCUL04F8F7FEVQ@3h<%uZj_mp4_5tXO^gK>%7F<j8Jt!5b^g2BS2b7
z-XktYEujV>2!b4vh0*#39v+h_iPK+NLg{w5%RMuxYk0<4N8mQ>IOcA>SKEdcYrW(U
za4kF&TG_AwGENr&4kZ&sA=0}4MJ_hWQH;Z8%v>8-@Z`M5CQ&kGFP0ncqx0&jh%ywI
z1^}%b^foD~4ovJa0rTQhZB0U8+-lC=Q_85taOkZ}L@rwL{vII-h}z2#oYS1VV$CUm
z?iH@MwW;mQi}O<zerZTH*3aM5VoPOjsvrbLokx%poh@+W5#om!VnkyEU`6vQ$PrVN
zE>U~wQ9Cw#LJ=MBb3j9Yp0z<JrD+5tLKBUdzAZ`3o^HM21IBg25VMmhIwV-zw&7FA
zhx&0Qb?3&mhEu>pcZLN~7hj?!q{_}K4X<2)-9C-XnvVc_m`qO5cEg`rQWtScl3hhY
zQBR%2f+CEsi`;FuOT)s;zS(=VZf-;`h0ci}Pq9OOJbX7}<ayNLh<BmHzG{8(uqu*^
z7^~WUrkGPC7Db`HmxBcxQd$9)1!#r8s!$E8^!~Hz<c{GnPJU&U5#V)cYt3k@!MV(w
zE>2N)lE&FVO9qoQC7|5B#r5YhWC`(D^H*@A0Z|A<>ZRO5yZ4*`Qwu+|llmv9aBI`F
zl*GYxXO(qbferChI%90!Do85Cgwk+D3uo`W6#LhzqB`>StAq?8usDRS&uVK?QMO9;
zz)I~>I>)>1bZn#50V(+{)Ahjh3DL}f1p@Zuaf*j)b+<Si9*kdU{|EAIr@U-esiBFu
zb(Hx98^7g-2<qh9e)dMOIc-C2V1vMLs7I3e`TG+;tTCa&`w9k@?StAL-#H%KlQe-N
z1S_|ko=#rEQrEMX3q_IR1%)?50AIl(dCor6{96ipc5v_)KTEKcSGdA4zo?7ZSdPFw
zujxCN&nq|Cao!w+S(9Y+z0gd?Ku1kGz<Z`4;(UrHPgbVl-UZEIIx5d}W%&($Ri)3~
z9>FG!>O0c|kzJk+4w!+mZQ1>P6L^Ak_0MPvWjmeOVv-TwyK7`<9flmBBXF}Ig+5_=
zP1|>I!+4donHuQZw#^2U+Y~JMwW9f0XHU<*4Byavj~(*5Q`KYLuvSt807%YiC8Ylt
z_L4iX%e?CWyIEod%Hub^WQgpuJK4WR%CbwsEF@2ZNOfr3F4wOC1C-emzj74y!}?oZ
zKfk_HS#2qeR`UY4$cIy=zp@uTk9-1mk5sQK%W7lgil}@-<N*z38}-@CqS%=<-j`VT
zo{i?VexFX}lp+|Adl%deAb*%_dzP@Kq{qenGZ(#L`DNl~kZ64#x(Z7;zWQ?c>C=(m
zmgU8`1~;oq6iGh!2YGHstms=`;jY(;32n9hR#q90$<j)~`y8DC*+D-4iFucYwpmIr
z5V%S!v?$PYc<~Q7UETdlFVq~?mEwcAe&&|Wu>{m{q>Ahc3HkwTJ1$*S^Lip{d1}8r
zWu_R~LE+WxSg(oP7|x+9>M?yvZj4r`EML0no}4RGI;}+YN_t25d^nO%eRs0ihiE$F
z(<F(dt?9LdhHr)hWGI{bVJwewT^EdI<N;BIG7d6A5~WpGZg~xb?0H&~-f<X>_TxJF
zlse7EpXsmCM&;i)!0<wzk{<_pX9xS6Punz-i4lDfy5*9YnYNQX+mEN)jtqNJ$j->L
zPBFSxBiiD0RpD!1FGZl8gx@Aw%~p^WQEtR6*5bK}a9AsbmHvr~V!)55$9N)Uma@&Z
zU%4}t#17fy^+^<5EqX9NdUx@=Cry?>G1P$wN&Il<R{D14$i|k(rl3d46HdHV({XP2
z6zrBRrtO$GWY0ieV}Dvy*I~HE%Lwn={Uv+w_<X&QL5P~0XVp(2SP>rj3>`o`=E4{b
zx>}5+#lA&pyB_&Vxb!V^wS^Lj4QGW0OyFvb!AWUo;b;CJ<aeOkX2*oc$(4r}G{2D3
zwHRtGa=VS|&QXd8Suv9!JU=BG9;Ew)mkB(~y2KsQhOyJdK-_%Tk=A6w&h5t>j;ND>
znT55B`NoNDpfraY(o|#7%Fo#U>-7krqZT8ky?aa9Q~M=imiU6X>|q0uqZjMWIo57j
zG$?+vBnHs4J}7qm5n`)|buazwWuI0O$^AL2TWh4dyYaLQ^a(K{CuR-uf-85uIrE<8
zCEb9&W}>@3Qm=|?pxkAg$hFn4fBaRtB<^?EYg^sC-Y_C2*zAC6iQmWfG*uQ2oPeey
zFKr|(nbraJ2EI{~U8)hjuDnA@&GnzJm-><QP~$mw8aX;60~J5QoX{7<qIL>NJbrDh
z8wqx#vllfL-tQ16rhV<fZL6+g^D1LXgZi7j+f5#W9;9QK;l)Hs8tCA4hZd84Hs1M>
z1r>qIl7YlyiYm8N>5({(`zvk(Wtp1b{3^=R^~9VPAI8XPaXe#By1DYwoUCOfOF!`0
z80@kZr)XQ55)CW#${f_o*q2+LufuA1?!82<k1mOO-EXFF|3Yd$3^evkachW_I+baV
zUkfr_f8b*BEqPN2LtF>~IeGzfQjjQ6(?NIdD54C35Tm3^Ab&sj8<PKzGFWR0gdqy2
zz~VLa<FN>X6CX9tq?oBt+qzr&FGz`Wfr)3A=Ke=19XrDu2CiZcEYJSR1$n(X{-osl
z61!`d_NJJJDIMx`YdwhuHGPARbF^CyF22x{)V7#4#P(Dg&B~<H?BkGA4Mx!%Mz=2J
zs_nd&+W)DD>kXq*qx<}(!#_>|PPz)u*(3K|X5ak&%9tbAb8;*W6f;egYpNtSwoi8`
z_t*#E2=UB&FAR!P@OIbGO*6%)0eOGDt$c+q>$`eu%B?r7?|^|h$As`DHo?!PX$DUL
z^yVAd9a)&j5t*&wYyN0I%EBmB2EUQFgh=g$alv|IWZBstPC)$`I-)p402ESeT5i`x
z`Cjx+y&9uoNxrxn@sw$Qu(vXgvw41}3o4cHtqHn*0IB@*ECeF718HJpY1e7Fatoqh
zKF+%-h^+=GJaKyW<*%bZ<{j|8Lz|9AV}uP8wH;jW-kPI8&6CZiJOh|)G+hWck`3lm
zqkF<r;IiY(iursX*a?$8(jMf588?)9RBFd?>2Y@fFF-B(Pwe2}MnFZ?<Pd(u<e(f|
zVJWYJ|L_y`po;RM{VxS^$JL0XtX0L*%?8@PaTo>Q-sMMlhEgKlgezdqg9P5Wfl)cw
z;~g2md#SI83%1(KJVW=fx3_=O>j?&LETC#;Y$H>cXdN9G2mU7uA(I3D7sJ%IDYp7x
Vf*Y^M6agDSkmoO(6rFPj`xmHTfV=<z

literal 0
HcmV?d00001


From 27a7738e7e074392c9dcf2d7f2eec7d7708ba677 Mon Sep 17 00:00:00 2001
From: Charles Weiss <69219836+weisscharlesj@users.noreply.github.com>
Date: Sat, 24 Jun 2023 15:57:44 -0500
Subject: [PATCH 2/6] Added stochastic tutorial ipynb file

Added tutorial-stochastic-simulation.ipynb file which contains a tutorial demonstrating using NumPy random number generators to stochastically simulate a variety of processes. This tutorial was proposed in issue #184.
---
 content/tutorial-stochastic-simulations.ipynb | 777 ++++++++++++++++++
 1 file changed, 777 insertions(+)
 create mode 100644 content/tutorial-stochastic-simulations.ipynb

diff --git a/content/tutorial-stochastic-simulations.ipynb b/content/tutorial-stochastic-simulations.ipynb
new file mode 100644
index 00000000..2bfd1c8c
--- /dev/null
+++ b/content/tutorial-stochastic-simulations.ipynb
@@ -0,0 +1,777 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2931e270-7884-4521-928c-65fa5ca36d60",
+   "metadata": {},
+   "source": [
+    "# Simulating Using Random Variables\n",
+    "\n",
+    "Randomness, or apparent randomness, is a major part of the world we live from the movement of gas molecules in the air we breath to the outcome of a coin toss. While many events are not truely random, they are often close enough to random or seemingly random enough to be simulated as such. Despite many processes being random, their outcomes often conform to a statistical pattern if enough of these random events occur. For example, if we roll a six-sided die over a large number of rolls, we expect to roll a 5 about $\\frac{1}{6}$ of the time. As a general rule, the larger the number of random events observed, the closer the distribution of these events will *likely* be to the expected disbribution. In this tutorial, we will use a random number generator provided in NumPy to solve a number of problems through stochastic simulations. While the problems demonstrated below all have know solutions or equations, you may face other problems that do not have an analytical model or known solution. The methodology demonstrated below can be used to solve problems when no known solution or model exists. \n",
+    "\n",
+    "## What you'll do\n",
+    "- Generate random values using NumPy to power stochastic simulations\n",
+    "- Perform stochastic simulations to determine the\n",
+    "    - Likelyhood of multiple children in a classroom of 25 having the same birthday\n",
+    "    - Distribution of marbles in a Galton board\n",
+    "    - Value of $\\pi$\n",
+    "    - Amount of radioactive material left versus time\n",
+    "- Compare the above simulations to known values or an analytical model\n",
+    "\n",
+    "## What you'll learn:\n",
+    "- Generating large quantites of random values in a desired distribution\n",
+    "- Using random values to simulation a range of scenarios and solve problems\n",
+    "\n",
+    "## What you'll need:\n",
+    "- [NumPy](https://numpy.org/)\n",
+    "- [Matplotlib](https://matplotlib.org/)\n",
+    "- Python's `math` module\n",
+    "\n",
+    "The above two packages are imported using the following commands:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "50324dde-32fe-44b1-b15f-bce368ce16ca",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "70b2a718-ba0c-4ed3-8a5d-4a7bd90f45c8",
+   "metadata": {},
+   "source": [
+    "## Generating random variables\n",
+    "\n",
+    "NumPy can generate random variables using a Generator from the `np.random` module. While these values are not truely random, they are close enough for the following applications. One of the advantages of using NumPy to generate variables over the standard `random` Python module is that NumPy can generate a large number of random variables efficiently without the use of a `for` loop. These variables can be generated in a variety of probability distribution including normal, poisson, and binomial; but for the following simulations, we will mostly use even distributions where all numbers in the range have an equal likelyhood of being generated. This is accomplished by first creating a Generator using the `np.random.default_rng()` function and then using `random(n)` or `np.integers(low, high=, size=n)` methods with the Generator to produce random values where `n` is the number of random values returned. Below are some common methods for generating random values.\n",
+    "\n",
+    "| Method  | Description |\n",
+    "|-----------|-------------|\n",
+    "|`random(n)`| Generates `n` float values in the [0,1) range with an even distribution |\n",
+    "|`integers(low, high=, size=)`| Generates `size` integers in the requested range [low, high) in a uniform distribution|\n",
+    "|`normal(loc, scale=, size=)`| Generates `size` floats in a normal distribution centered on `loc` with a `scale` standard deviation|\n",
+    "|`binomial(t, p, size=)`| Generates `size` integers in a bionimial distribution with `t` trials for each value with a probability `p`|\n",
+    "|`choice(a, size=)`| Selects `size` elements from `a` list, tuple or ndarray with an even probability |\n",
+    "|`shuffle(a)`| Shuffles items in list, tubple, or ndarray `a` |"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8a3c0c28-f9bf-466d-8522-a38e11488499",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0.39930577, 0.71741468, 0.28082333, 0.08272492, 0.96977132,\n",
+       "       0.56392675, 0.64432096, 0.57687146, 0.47536097, 0.12240199])"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rng = np.random.default_rng(seed=18)\n",
+    "rng.random(10)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a59b2279-3f9f-4874-9754-aa1e031634cf",
+   "metadata": {},
+   "source": [
+    "You may have guessed by looking at the returned values that `random()` produces values in the 0 $\\rightarrow$ 1 range, but what happens if we need values in a different range? We can modify these values by mutiplying them by a coefficient to increase the range and using addition or substration to shift the center of the range. For example, if we need random values from -10 $\\rightarrow$ +10, we can accomplish this by the following."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "f6cbfb8d-b153-494b-9532-c657b8fe461b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([-3.72807758,  4.72417165,  8.14778066,  7.7720389 ,  8.96641764,\n",
+       "       -9.49192157,  4.7607717 ,  3.45200153,  2.50375281,  2.75248376])"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "20 * rng.random(10) - 10"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cdc9a16c-6d94-449c-8a41-1dbbb30b649a",
+   "metadata": {},
+   "source": [
+    "It's worth noting that the `random()` method returns values from the [0,1) range which includes the lower end and excludes the upper end. This is close enough to [0,1] for our purposes."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b915dba8-48d1-4dde-b3bd-4f048502f78e",
+   "metadata": {},
+   "source": [
+    "## Solving the birthday problem\n",
+    "\n",
+    "The goal of the [birthday problem](https://en.wikipedia.org/wiki/Birthday_problem) is to determine the probability of multiple children in a classroom of 25 students having the same birthday. For simiplicity, we will ignore leap years (i.e., February 29 birthdays) and assume that the students are equilly likely to be born any day of the year. One method of determining the answer is to repeately simulate a classroom of 25 student birthdays by using a random number generator and see how often all students in the class have unique birthdays. The general steps for this processes are outlined below. \n",
+    "\n",
+    "1. Simulate 25 random birthdays with a random integer generator\n",
+    "2. Check to see if any of the above birthdays match\n",
+    "3. Record the outcome if all birthdays are unique\n",
+    "4. Repeat setps 1-3 a large number of times\n",
+    "\n",
+    "To make things easier, we will just generate integers 0 $\\rightarrow$ 364 representating days of the year instead of actual months and days."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "36e6f902-5218-4975-a625-7a54a05fe03b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def all_unique(class_size, n_classrooms=100):\n",
+    "    '''Randomly generates birthdays for groups of kids of a given group size and outputs the percent of time\n",
+    "   all students have uniquie birthdays. All input and output values are ints or floats.\n",
+    "    \n",
+    "    (classroom size, number of classrooms) -> percentage classrooms with all unique birthdays\n",
+    "    '''\n",
+    "    \n",
+    "    all_unique_class = 0  # number of classrooms with students NOT sharing birthdays\n",
+    "    \n",
+    "    for classroom in range(n_classrooms):\n",
+    "        birthdays = rng.integers(0, high=365, size=class_size)\n",
+    "        if class_size == np.unique(birthdays).size:\n",
+    "            all_unique_class += 1\n",
+    "    \n",
+    "    return 100 * all_unique_class / n_classrooms"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "45763a5f-887f-4a4b-a5d2-a6a04cb52fcc",
+   "metadata": {},
+   "source": [
+    "Below we simulate 50000 classrooms of 25 students and find that only around 43% of the time every student in a classroom has a unique birthday from all the other students."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7c77811a-d825-4f52-8161-f037427c72f9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "43.286"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_unique(25, n_classrooms=50000)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dc951c53-4e08-41e0-b54b-1b88e0ad1061",
+   "metadata": {},
+   "source": [
+    "This problem also has an equation for the probability given below where **p** is the probability of all students having a unique birthday and **n** is the classroom size. Performing this calculation below, we find that 43.13% of the time, students should have all unique birthdays which is quite close to what was found in the simulation above.\n",
+    "\n",
+    "$$ p = \\frac {365!}{365^n(365-n)!} $$"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c95b4fcc-45a0-4925-91fb-39d3469615b9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.4313002960305361"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "n = 25\n",
+    "math.factorial(365)/(365**n * math.factorial(365-n))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5a18ddfb-e49f-44b5-ac98-c1e9512e15ad",
+   "metadata": {},
+   "source": [
+    "## Simulating a Galton board\n",
+    "\n",
+    "Next, we will simulate a [Galton board](https://en.wikipedia.org/wiki/Galton_board) which allows mables to fall down levels of staggered pegs. Each marble starts in the horizontal center of the board, and at each level, the marble hits a peg. To continue falling to the next level, the marble must move around the peg, and it has an equal likeliness of moving to the left as it does to the right. At the bottom of the board, the marbles collect in bins with the height of marbles yielding a normal distribution."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2a0bb53d-71bb-4d70-a308-2f49f1d099ea",
+   "metadata": {},
+   "source": [
+    "![](tutorial-stochastic/galton_board.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "745bf65b-30c0-4ffb-a4ba-5ccae89d9805",
+   "metadata": {},
+   "source": [
+    "**Figure 1.** An example of a Galton board with three marbles with three different potential paths (dotted lines) shown.\n",
+    "\n",
+    "The key operational detail of a Galton board is that every marble moves one increment to the left or right at each level, so our simulation centers around a series of randomly generated +1 and -1 to determine this movement by the following methodolog.\n",
+    "1. Generate a random series of +1 and -1 in an even distribution - one value for every level on the Galton board\n",
+    "2. Sum up the values in step 1 to determine the final location of the mable\n",
+    "3. Repeat steps 1-2 for each simulated marble\n",
+    "4. Visualize the result\n",
+    "\n",
+    "Below is the simulation for a single marble moving down a 10-layered Galton board. Note how the integers 0 and 1 generated by `integers()` and converted to a series of -1 and +1 values, respectively."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "32ce5473-354f-494a-85eb-68054974a2ea",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "moves = 2 * rng.integers(0, high=2, size=10) - 1\n",
+    "final_position = moves.sum()\n",
+    "final_position"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ec34bc52-8270-42bb-8503-cbddfe2d8b25",
+   "metadata": {},
+   "source": [
+    "To simulate additional marbles, we could use a `for` loop, but because we need the same number of integers for each marble, a more efficient way is to generate the random integers in a two-dimensional array with a row for every level on the Galton board and column for every marble simulated. We then sum up the values in each column to obtain the final positions of all marbles."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "5b9fa1dd-d9db-4511-98e3-faa61a0cbff0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def galton(marbles, levels=10):\n",
+    "    '''integer -> ndarray of integers\n",
+    "\n",
+    "    This function takes in an integer number of marbles and number of levels and outputs \n",
+    "    the horizontal position of these marbles at the bottom of a Galton board. \n",
+    "    '''\n",
+    "    moves = 2 * rng.integers(0, high=2, size=(levels, marbles)) - 1\n",
+    "    final_position = moves.sum(axis=0)\n",
+    "    \n",
+    "    return final_position"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d2b772e2-61f8-46f6-90e7-94a553837ac6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([ 0, -2, -2,  2,  4, -4, -4, -2,  2,  2,  0, -2,  4,  0,  4, -4,  0,\n",
+       "       -8,  2,  2])"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sim = galton(1200)\n",
+    "sim[:20]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "693e2121-9fe7-428b-b284-654654a990ac",
+   "metadata": {},
+   "source": [
+    "We visualize the results below using a histogram plot. Being that all values are integers, we set `align='left'` so that each bar resides directly over the integer it represents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "8c5d4ff6-4238-4283-9b49-e2fdfc52dcab",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "bins = np.arange(-10,12)\n",
+    "plt.hist(sim, bins=bins, align='left')\n",
+    "plt.xticks(bins[::2])\n",
+    "plt.xlabel('Horizontal Marble Position')\n",
+    "plt.ylabel('Number of Marbles');"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3b1ed737-e851-4272-b706-67fbb91f5a63",
+   "metadata": {},
+   "source": [
+    "One interesting trend that appears in the above histogram is that all locations are integers. This is because we used whole numbers for our left and right movements of marbles (i.e., +1 and -1) and used ten layers in the above simulation. There is no way to produce an odd integer by totaling a series of ten +1 or -1 integers. If we changed the number of layers to an odd number, we'd only get odd positions in the result, and if we used +1/2 and -1/2 for our horizontal movement, we'd get both even and odd integers."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7152df76-78b5-47fa-9f76-276c7e497cb7",
+   "metadata": {},
+   "source": [
+    "## Calculating pi\n",
+    "\n",
+    "As a second appliation of random number generaters, we will calclate a numerical value for $\\pi$. Imagine a circle with radius = $r$ inscribed inside a square of side length $2r$. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "65166f10-9009-4551-a14f-8205dc3b858c",
+   "metadata": {},
+   "source": [
+    "![](tutorial-stochastic/circle_square.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "88d705e8-b983-4aa2-b35b-ccb13c9aaa6a",
+   "metadata": {
+    "editable": true,
+    "slideshow": {
+     "slide_type": ""
+    },
+    "tags": []
+   },
+   "source": [
+    "**Figure 2.** The circle radius r inscribed in a square with side length of 2r.\n",
+    "\n",
+    "The areas of the circle and square are described by $A\n",
+    "_{circle} = \\pi r^2$ and $A_{square} = 4r^2$, respectively. If we divide the area of the circle by the area of the square, we get $\\pi / 4$.\n",
+    "\n",
+    "$$ \\frac { A_{circle} }{ A_{square} } = \\frac {\\pi r^2} {(2r)^2} = \\frac {\\pi r^2} {4r^2} = \\frac {\\pi}{4} $$\n",
+    "\n",
+    "This means that four times the ratio of the area of the circle and square equals $\\pi$.\n",
+    "\n",
+    "$$ \\frac { A_{circle} }{ A_{square}} \\times 4 = \\pi $$\n",
+    "\n",
+    "The challenge is now finding the ratio between the areas of the two shapes which can be done through a variety of creative means. Our method will be counting randomly placed dots. Imagine we painted the circle inscribed in a square on pavement outside and count the water droplets that fall in the circle and square during a rain storm."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7571b83c-e163-42b0-8329-f494045790a8",
+   "metadata": {},
+   "source": [
+    "![](tutorial-stochastic/circle_square_dots.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c12bceb-c2ad-4cc2-98b9-4148667dc1c7",
+   "metadata": {},
+   "source": [
+    "**Figure 3.** Random dots inside the circle and square used to estimate a value of $\\pi$.\n",
+    "\n",
+    "Because the rain drops fall randomly, the probability of a drop falling in one of the shapes is proportional to the area of that shape, so dividing the number of drops in the circle by the number of drop in the square provides a estimate of $\\frac { A_{circle} }{ A_{square} }$ which then can be used to calculate $\\pi$. Counting rain is a bit tedious and challenging, so we can simulate this using a random number generator to produce random ($x, y$) coordinates of dots inside the square. We then total the number of these that fall inside the circle versus the square and complete the calculation to obtain a value of $\\pi$.\n",
+    "\n",
+    "For smilicity, we will center our circle and square around the origin and give the circle a radius = 1. This requires the coordinates to fall in the [-1, 1) ranges along both the $x$- and $y$-axes. We have no random number generator that produces values in this range, but we can modify the `random()` method which generates floats in the [0, 1) range by multiplying by 2 and substracting 1 as demonstrated below.\n",
+    "\n",
+    "~~~python\n",
+    "rng = np.random.default_rng()\n",
+    "x = 2 * rng.random() - 1\n",
+    "~~~"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "70c285c1-adae-453e-a895-fb515ea562ab",
+   "metadata": {},
+   "source": [
+    "Below is a function that performs this simulation and calculation of $\\pi$ with the only function argument `n_samples` as the number of dots generated. The general proceedure is ouline here.\n",
+    "1. Generate `n_samples` of ($x, y$) coordinates using the `random()` method\n",
+    "2. Calculate the distance from the origin using the `np.hypot()` function to determine if the dot is inside the circle (all dots are inside the square)\n",
+    "3. Calculate $\\pi$"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "e70bfca5-3606-4c3c-ad76-fc715f1f5ef4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def estimate_pi(n_samples):\n",
+    "    '''(integer) -> pi (float)\n",
+    "    \n",
+    "    Estimates the value of pi by finding the ratio of the area of a unit circle/area of a unit square\n",
+    "    and multiplying by 4.\n",
+    "    '''\n",
+    "\n",
+    "    n_samples = int(n_samples)\n",
+    "    \n",
+    "    # Step 1\n",
+    "    rng = np.random.default_rng()\n",
+    "    coords = rng.random(size=(n_samples, 2))\n",
+    "\n",
+    "    # Step 2\n",
+    "    dist_from_origin = np.hypot(coords[:,0], coords[:,1]) # distance from the origion\n",
+    "    in_circle = dist_from_origin[dist_from_origin <= 1] # if <= 1, the point is inside the circle\n",
+    "\n",
+    "    # Step 3\n",
+    "    pi = 4 * (in_circle.size / n_samples)\n",
+    "    \n",
+    "    return pi"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d34736f4-21f4-4e15-a3b3-d68cbf90b782",
+   "metadata": {},
+   "source": [
+    "We can then call this function with 100 dots generated. Because we are using a random number generator, every time we call this function, we likley get a different value for $\\pi$."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "c3bac1dc-e420-4b2d-a0b7-8b3fce9f277b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3.08"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "estimate_pi(100)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "19575a49-311d-4c27-aa34-2cd8a3539265",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3.16"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "estimate_pi(100)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "947f9bfd-9550-440b-820b-eeb746dad01d",
+   "metadata": {},
+   "source": [
+    "We can also generate a value for $\\pi$ using the `np.pi` to compare our answer to."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "9d107cde-6f0a-48ae-9258-0392f41cc37d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3.141592653589793"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "np.pi"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dfdb0029-6ef8-49d9-997a-2b25ad65fe5e",
+   "metadata": {},
+   "source": [
+    "Odds are that the values calculated above for $\\pi$ above is close but not exactly 3.14. If we increase the number of dots, the value for $\\pi$ will on average become closer to the true value. While it may be tempting to just call the function with an extremely large number of dots, this can take substatially longer to computer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "d49d0955-f5e9-4214-abb2-2f0c9c4f470c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3.14157644"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "estimate_pi(1E8)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cbc28bcb-b975-4d82-9f06-6a6378bf09c2",
+   "metadata": {},
+   "source": [
+    "## Simulating radioactive decay\n",
+    "\n",
+    "As a final example, we will simulate the radioactive decay of the radioactive nuclide $^{137m}$Ba to determine the quantity of undecayed material versus time. We will then compare it to an analytical model to see how well the two agree. Radioactive nuclei decay by first-order kinetics, which means that each radioactive nucleus has a fixed probability of decaying at any given time. This is analogous to how each six-sided die in a bucket has a fixed probability of rolling a one each time they are dumped out. This analogy is so good that we can simulate the decay process by generating a large number of random integers with fixed probabilities.\n",
+    "\n",
+    "The first thing we need to is to know the probability of a nucleus decaying in a single second. Because this is a first-order process, the rate (-dA/dt) is described by\n",
+    "\n",
+    "$$ \\frac{-dA}{dt} = kA $$\n",
+    "\n",
+    "where A is the quantity of $^{137m}$Ba, $t$ is time in seconds, and $k$ is the rate constant for this process. We also know that the half-life (t$_{1/2}$) of  $^{137m}$Ba is about 151 seconds which is related to the rate constant by the following equation.\n",
+    "\n",
+    "$$ t_{1/2} = \\frac{ln(2)}{k} $$\n",
+    "\n",
+    "This means that $k$ = 4.59e$^{-3}$ s$^{-1}$. For first-order kinetics, this means that 4.59e$^{-3}$ fraction of the nuclei decays, so this is the probability we need to simulate this process using random numbers. The function below calculates the fraction of radioactive material remaining based on a rate constant `k` and allows the users to choose the number of simulated nuclei `n` and duraction of the simulation `n_final`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "f5ec62ec-f980-43ea-b5ea-19d7a6de8450",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def decay(k, n=1000, t_final=1000):\n",
+    "    '''floats and integers -> ndarray of integers\n",
+    "\n",
+    "    Calculates the fraction of nuclei remaining at each second in the simulation given n initial \n",
+    "    nuclei with a rate constant k of decaying each second and a final simulation time t_final.\n",
+    "    '''\n",
+    "\n",
+    "    n_undecayed = n\n",
+    "    undecayed_array = np.full(t_final + 1, n)\n",
+    "    \n",
+    "    for second in range(1, t_final + 1):\n",
+    "        decays = rng.binomial(1, p=k, size=n_undecayed).sum()\n",
+    "        n_undecayed -= decays\n",
+    "        undecayed_array[second] = n_undecayed\n",
+    "        \n",
+    "    fraction = undecayed_array / n    \n",
+    "    \n",
+    "    \n",
+    "    return fraction"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61e2bc98-4518-4b2b-a33d-b8303ee65a53",
+   "metadata": {},
+   "source": [
+    "Below we simulate the decay of $^{137m}$Ba using a hundred simulated nuclei."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "bd9d6811-2248-4c12-b834-385658b40baa",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1.  , 1.  , 1.  , ..., 0.01, 0.01, 0.01])"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "decay(4.59e-3, n=100)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8320f7c8-31ea-4272-8683-9cd477f943c6",
+   "metadata": {},
+   "source": [
+    "We can plot and compare this simulation to the analytical model for this simulation knowing that the fraction of undecayed nuclei ($\\frac{A}{A_0}$) is described by the following first-order equation where $A_0$ and $A_t$ are the initial quantities and quantities of nuclei at time $t$.\n",
+    "\n",
+    "$$ \\frac{A_t}{A_0} = e^{-kt} $$"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "aff9c2ec-a032-4fc7-8ca0-46502ab1b31c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "seconds = np.arange(1001)\n",
+    "fraction = np.exp(-4.59e-3 * seconds)\n",
+    "\n",
+    "plt.plot(seconds, fraction, linestyle='-', label='Theoretical')\n",
+    "plt.plot(seconds, decay(4.59e-3, n=500), linestyle='--', label='Simulation')\n",
+    "plt.xlabel('Time, s')\n",
+    "plt.ylabel('Fraction of Undecayed Nuclei')\n",
+    "plt.legend();"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "10d2f74f-06d1-418e-a9e0-14265c58171a",
+   "metadata": {},
+   "source": [
+    "The simulation is in good agreement with the theoretical model, but this is some discrepency. If we increase the number of simulated nuclei, the simulation should align better with the theoretical values."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "bae004b9-9cf0-4975-aaa5-b9b410b69cde",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "seconds = np.arange(1001)\n",
+    "fraction = np.exp(-4.59e-3 * seconds)\n",
+    "\n",
+    "plt.plot(seconds, fraction, linestyle='-', label='Theoretical')\n",
+    "plt.plot(seconds, decay(4.59e-3, n=5000), linestyle='--', label='Simulation')\n",
+    "plt.xlabel('Time, s')\n",
+    "plt.ylabel('Fraction of Undecayed Nuclei')\n",
+    "plt.legend();"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7e193e9f-25ca-47fe-9809-16db9141e164",
+   "metadata": {},
+   "source": [
+    "## Further reading\n",
+    "\n",
+    "- To learn more about NumPy random number generators, see [Random Generator](https://numpy.org/doc/stable/reference/random/index.html)\n",
+    "- To learn more about random number distributions and their generation, see [Monte Carlo Simulation Part 5: Randomness & Random Number Generation](https://towardsdatascience.com/monte-carlo-simulation-421110b678c5?gi=f86d4ec9f452)\n",
+    "- For examples of using random variables for chemical simulations, see chapter 9 of [Scientific Computing for Chemists](https://weisscharlesj.github.io/SciCompforChemists/intro.html)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

From d8d5b47e7cbf5095fd4e5c24034bcde0e1d88c77 Mon Sep 17 00:00:00 2001
From: Charles Weiss <69219836+weisscharlesj@users.noreply.github.com>
Date: Sat, 24 Jun 2023 16:00:49 -0500
Subject: [PATCH 3/6] Update README.md

Added tutorial-stochastic-simulations to README file
---
 README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/README.md b/README.md
index b5453a6e..d84f57d9 100644
--- a/README.md
+++ b/README.md
@@ -26,6 +26,7 @@ or navigate to any of the documents listed below and download it individually.
 9. [Tutorial: Plotting Fractals](content/tutorial-plotting-fractals.ipynb)
 10. [Tutorial: NumPy natural language processing from scratch with a focus on ethics](content/tutorial-nlp-from-scratch.md)
 11. [Tutorial: Analysing the impact of the lockdown on air quality in Delhi, India](content/tutorial-air-quality-analysis.md)
+12. [Tutorial: Stochastic Simulations](contant/tutorial-stochastic-simulations.ipynb)
 
 
 ## Contributing

From bc946ee8b6e78347b44f2634bf1716274e2336a2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Brigitta=20Sip=C5=91cz?= <b.sipocz@gmail.com>
Date: Wed, 28 Jun 2023 08:01:55 -0700
Subject: [PATCH 4/6] Update README.md

Co-authored-by: Mukulika <60316606+Mukulikaa@users.noreply.github.com>
---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index d84f57d9..00e7bfc1 100644
--- a/README.md
+++ b/README.md
@@ -26,7 +26,7 @@ or navigate to any of the documents listed below and download it individually.
 9. [Tutorial: Plotting Fractals](content/tutorial-plotting-fractals.ipynb)
 10. [Tutorial: NumPy natural language processing from scratch with a focus on ethics](content/tutorial-nlp-from-scratch.md)
 11. [Tutorial: Analysing the impact of the lockdown on air quality in Delhi, India](content/tutorial-air-quality-analysis.md)
-12. [Tutorial: Stochastic Simulations](contant/tutorial-stochastic-simulations.ipynb)
+12. [Tutorial: Stochastic Simulations](content/tutorial-stochastic-simulations.ipynb)
 
 
 ## Contributing

From 89c3bb7f25c105f4f3a0f3b28d3d0c86cbc34acf Mon Sep 17 00:00:00 2001
From: Ross Barnowski <rossbar@caltech.edu>
Date: Sun, 30 Jul 2023 18:38:40 -0700
Subject: [PATCH 5/6] MAINT: Add stochastic tutorial to toctree.

This is necessary to get the sphinx build working.
---
 site/features.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/site/features.md b/site/features.md
index fb966a8a..e98581c6 100644
--- a/site/features.md
+++ b/site/features.md
@@ -10,4 +10,5 @@ maxdepth: 1
 content/tutorial-svd
 content/save-load-arrays
 content/tutorial-ma
+content/tutorial-stochastic-simulations
 ```

From 39c80ea7f659f19bb20767d8b3eb43b45960811e Mon Sep 17 00:00:00 2001
From: Charles Weiss <69219836+weisscharlesj@users.noreply.github.com>
Date: Sun, 30 Jul 2023 18:40:27 -0700
Subject: [PATCH 6/6] ENH: Convert stochastic tutorial to myst version.

---
 content/tutorial-stochastic-simulations.ipynb | 777 ------------------
 content/tutorial-stochastic-simulations.md    | 483 +++++++++++
 2 files changed, 483 insertions(+), 777 deletions(-)
 delete mode 100644 content/tutorial-stochastic-simulations.ipynb
 create mode 100644 content/tutorial-stochastic-simulations.md

diff --git a/content/tutorial-stochastic-simulations.ipynb b/content/tutorial-stochastic-simulations.ipynb
deleted file mode 100644
index 2bfd1c8c..00000000
--- a/content/tutorial-stochastic-simulations.ipynb
+++ /dev/null
@@ -1,777 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "2931e270-7884-4521-928c-65fa5ca36d60",
-   "metadata": {},
-   "source": [
-    "# Simulating Using Random Variables\n",
-    "\n",
-    "Randomness, or apparent randomness, is a major part of the world we live from the movement of gas molecules in the air we breath to the outcome of a coin toss. While many events are not truely random, they are often close enough to random or seemingly random enough to be simulated as such. Despite many processes being random, their outcomes often conform to a statistical pattern if enough of these random events occur. For example, if we roll a six-sided die over a large number of rolls, we expect to roll a 5 about $\\frac{1}{6}$ of the time. As a general rule, the larger the number of random events observed, the closer the distribution of these events will *likely* be to the expected disbribution. In this tutorial, we will use a random number generator provided in NumPy to solve a number of problems through stochastic simulations. While the problems demonstrated below all have know solutions or equations, you may face other problems that do not have an analytical model or known solution. The methodology demonstrated below can be used to solve problems when no known solution or model exists. \n",
-    "\n",
-    "## What you'll do\n",
-    "- Generate random values using NumPy to power stochastic simulations\n",
-    "- Perform stochastic simulations to determine the\n",
-    "    - Likelyhood of multiple children in a classroom of 25 having the same birthday\n",
-    "    - Distribution of marbles in a Galton board\n",
-    "    - Value of $\\pi$\n",
-    "    - Amount of radioactive material left versus time\n",
-    "- Compare the above simulations to known values or an analytical model\n",
-    "\n",
-    "## What you'll learn:\n",
-    "- Generating large quantites of random values in a desired distribution\n",
-    "- Using random values to simulation a range of scenarios and solve problems\n",
-    "\n",
-    "## What you'll need:\n",
-    "- [NumPy](https://numpy.org/)\n",
-    "- [Matplotlib](https://matplotlib.org/)\n",
-    "- Python's `math` module\n",
-    "\n",
-    "The above two packages are imported using the following commands:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "50324dde-32fe-44b1-b15f-bce368ce16ca",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "import math"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "70b2a718-ba0c-4ed3-8a5d-4a7bd90f45c8",
-   "metadata": {},
-   "source": [
-    "## Generating random variables\n",
-    "\n",
-    "NumPy can generate random variables using a Generator from the `np.random` module. While these values are not truely random, they are close enough for the following applications. One of the advantages of using NumPy to generate variables over the standard `random` Python module is that NumPy can generate a large number of random variables efficiently without the use of a `for` loop. These variables can be generated in a variety of probability distribution including normal, poisson, and binomial; but for the following simulations, we will mostly use even distributions where all numbers in the range have an equal likelyhood of being generated. This is accomplished by first creating a Generator using the `np.random.default_rng()` function and then using `random(n)` or `np.integers(low, high=, size=n)` methods with the Generator to produce random values where `n` is the number of random values returned. Below are some common methods for generating random values.\n",
-    "\n",
-    "| Method  | Description |\n",
-    "|-----------|-------------|\n",
-    "|`random(n)`| Generates `n` float values in the [0,1) range with an even distribution |\n",
-    "|`integers(low, high=, size=)`| Generates `size` integers in the requested range [low, high) in a uniform distribution|\n",
-    "|`normal(loc, scale=, size=)`| Generates `size` floats in a normal distribution centered on `loc` with a `scale` standard deviation|\n",
-    "|`binomial(t, p, size=)`| Generates `size` integers in a bionimial distribution with `t` trials for each value with a probability `p`|\n",
-    "|`choice(a, size=)`| Selects `size` elements from `a` list, tuple or ndarray with an even probability |\n",
-    "|`shuffle(a)`| Shuffles items in list, tubple, or ndarray `a` |"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "8a3c0c28-f9bf-466d-8522-a38e11488499",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([0.39930577, 0.71741468, 0.28082333, 0.08272492, 0.96977132,\n",
-       "       0.56392675, 0.64432096, 0.57687146, 0.47536097, 0.12240199])"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "rng = np.random.default_rng(seed=18)\n",
-    "rng.random(10)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a59b2279-3f9f-4874-9754-aa1e031634cf",
-   "metadata": {},
-   "source": [
-    "You may have guessed by looking at the returned values that `random()` produces values in the 0 $\\rightarrow$ 1 range, but what happens if we need values in a different range? We can modify these values by mutiplying them by a coefficient to increase the range and using addition or substration to shift the center of the range. For example, if we need random values from -10 $\\rightarrow$ +10, we can accomplish this by the following."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "f6cbfb8d-b153-494b-9532-c657b8fe461b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([-3.72807758,  4.72417165,  8.14778066,  7.7720389 ,  8.96641764,\n",
-       "       -9.49192157,  4.7607717 ,  3.45200153,  2.50375281,  2.75248376])"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "20 * rng.random(10) - 10"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cdc9a16c-6d94-449c-8a41-1dbbb30b649a",
-   "metadata": {},
-   "source": [
-    "It's worth noting that the `random()` method returns values from the [0,1) range which includes the lower end and excludes the upper end. This is close enough to [0,1] for our purposes."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b915dba8-48d1-4dde-b3bd-4f048502f78e",
-   "metadata": {},
-   "source": [
-    "## Solving the birthday problem\n",
-    "\n",
-    "The goal of the [birthday problem](https://en.wikipedia.org/wiki/Birthday_problem) is to determine the probability of multiple children in a classroom of 25 students having the same birthday. For simiplicity, we will ignore leap years (i.e., February 29 birthdays) and assume that the students are equilly likely to be born any day of the year. One method of determining the answer is to repeately simulate a classroom of 25 student birthdays by using a random number generator and see how often all students in the class have unique birthdays. The general steps for this processes are outlined below. \n",
-    "\n",
-    "1. Simulate 25 random birthdays with a random integer generator\n",
-    "2. Check to see if any of the above birthdays match\n",
-    "3. Record the outcome if all birthdays are unique\n",
-    "4. Repeat setps 1-3 a large number of times\n",
-    "\n",
-    "To make things easier, we will just generate integers 0 $\\rightarrow$ 364 representating days of the year instead of actual months and days."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "36e6f902-5218-4975-a625-7a54a05fe03b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def all_unique(class_size, n_classrooms=100):\n",
-    "    '''Randomly generates birthdays for groups of kids of a given group size and outputs the percent of time\n",
-    "   all students have uniquie birthdays. All input and output values are ints or floats.\n",
-    "    \n",
-    "    (classroom size, number of classrooms) -> percentage classrooms with all unique birthdays\n",
-    "    '''\n",
-    "    \n",
-    "    all_unique_class = 0  # number of classrooms with students NOT sharing birthdays\n",
-    "    \n",
-    "    for classroom in range(n_classrooms):\n",
-    "        birthdays = rng.integers(0, high=365, size=class_size)\n",
-    "        if class_size == np.unique(birthdays).size:\n",
-    "            all_unique_class += 1\n",
-    "    \n",
-    "    return 100 * all_unique_class / n_classrooms"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "45763a5f-887f-4a4b-a5d2-a6a04cb52fcc",
-   "metadata": {},
-   "source": [
-    "Below we simulate 50000 classrooms of 25 students and find that only around 43% of the time every student in a classroom has a unique birthday from all the other students."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "7c77811a-d825-4f52-8161-f037427c72f9",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "43.286"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "all_unique(25, n_classrooms=50000)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "dc951c53-4e08-41e0-b54b-1b88e0ad1061",
-   "metadata": {},
-   "source": [
-    "This problem also has an equation for the probability given below where **p** is the probability of all students having a unique birthday and **n** is the classroom size. Performing this calculation below, we find that 43.13% of the time, students should have all unique birthdays which is quite close to what was found in the simulation above.\n",
-    "\n",
-    "$$ p = \\frac {365!}{365^n(365-n)!} $$"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "c95b4fcc-45a0-4925-91fb-39d3469615b9",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "0.4313002960305361"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "n = 25\n",
-    "math.factorial(365)/(365**n * math.factorial(365-n))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5a18ddfb-e49f-44b5-ac98-c1e9512e15ad",
-   "metadata": {},
-   "source": [
-    "## Simulating a Galton board\n",
-    "\n",
-    "Next, we will simulate a [Galton board](https://en.wikipedia.org/wiki/Galton_board) which allows mables to fall down levels of staggered pegs. Each marble starts in the horizontal center of the board, and at each level, the marble hits a peg. To continue falling to the next level, the marble must move around the peg, and it has an equal likeliness of moving to the left as it does to the right. At the bottom of the board, the marbles collect in bins with the height of marbles yielding a normal distribution."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2a0bb53d-71bb-4d70-a308-2f49f1d099ea",
-   "metadata": {},
-   "source": [
-    "![](tutorial-stochastic/galton_board.png)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "745bf65b-30c0-4ffb-a4ba-5ccae89d9805",
-   "metadata": {},
-   "source": [
-    "**Figure 1.** An example of a Galton board with three marbles with three different potential paths (dotted lines) shown.\n",
-    "\n",
-    "The key operational detail of a Galton board is that every marble moves one increment to the left or right at each level, so our simulation centers around a series of randomly generated +1 and -1 to determine this movement by the following methodolog.\n",
-    "1. Generate a random series of +1 and -1 in an even distribution - one value for every level on the Galton board\n",
-    "2. Sum up the values in step 1 to determine the final location of the mable\n",
-    "3. Repeat steps 1-2 for each simulated marble\n",
-    "4. Visualize the result\n",
-    "\n",
-    "Below is the simulation for a single marble moving down a 10-layered Galton board. Note how the integers 0 and 1 generated by `integers()` and converted to a series of -1 and +1 values, respectively."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "32ce5473-354f-494a-85eb-68054974a2ea",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "4"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "moves = 2 * rng.integers(0, high=2, size=10) - 1\n",
-    "final_position = moves.sum()\n",
-    "final_position"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ec34bc52-8270-42bb-8503-cbddfe2d8b25",
-   "metadata": {},
-   "source": [
-    "To simulate additional marbles, we could use a `for` loop, but because we need the same number of integers for each marble, a more efficient way is to generate the random integers in a two-dimensional array with a row for every level on the Galton board and column for every marble simulated. We then sum up the values in each column to obtain the final positions of all marbles."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "5b9fa1dd-d9db-4511-98e3-faa61a0cbff0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def galton(marbles, levels=10):\n",
-    "    '''integer -> ndarray of integers\n",
-    "\n",
-    "    This function takes in an integer number of marbles and number of levels and outputs \n",
-    "    the horizontal position of these marbles at the bottom of a Galton board. \n",
-    "    '''\n",
-    "    moves = 2 * rng.integers(0, high=2, size=(levels, marbles)) - 1\n",
-    "    final_position = moves.sum(axis=0)\n",
-    "    \n",
-    "    return final_position"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "d2b772e2-61f8-46f6-90e7-94a553837ac6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([ 0, -2, -2,  2,  4, -4, -4, -2,  2,  2,  0, -2,  4,  0,  4, -4,  0,\n",
-       "       -8,  2,  2])"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "sim = galton(1200)\n",
-    "sim[:20]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "693e2121-9fe7-428b-b284-654654a990ac",
-   "metadata": {},
-   "source": [
-    "We visualize the results below using a histogram plot. Being that all values are integers, we set `align='left'` so that each bar resides directly over the integer it represents."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "8c5d4ff6-4238-4283-9b49-e2fdfc52dcab",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjsAAAGwCAYAAABPSaTdAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAA4T0lEQVR4nO3deVgW9eL//9cNKIKyiAqIC+KSey5YhFrHjiailaaf1LJySzuJiUuWlrunY5mZaaR1KrCOW37SOnkKI0w9Kq6Je7iE4gJYbrh8BYT5/dHP+9N9QOXG+/bGOc/Hdc11OTPve+Y1LPFqZu65LYZhGAIAADApN1cHAAAAcCbKDgAAMDXKDgAAMDXKDgAAMDXKDgAAMDXKDgAAMDXKDgAAMDUPVwcoCwoLC3Xq1Cn5+PjIYrG4Og4AACgBwzB08eJFhYSEyM3txudvKDuSTp06pVq1ark6BgAAKIXjx4+rZs2aN1xP2ZHk4+Mj6fcvlq+vr4vTAACAksjJyVGtWrWsf8dvhLIjWS9d+fr6UnYAALjL3OoWFG5QBgAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApkbZAQAApubh6gAAUBp1xv3L4ds8+mY3h28TgOtxZgcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJgaZQcAAJiah6sDAIDZ1Rn3L4dv8+ib3Ry+TcCsXHpmZ8aMGbrvvvvk4+OjwMBA9ejRQ2lpaTZjOnToIIvFYjP95S9/sRmTkZGhbt26ydvbW4GBgRo7dqyuXbt2Jw8FAACUUS49s7Nu3TrFxMTovvvu07Vr1/Taa6+pc+fO2r9/vypWrGgdN2TIEE2bNs067+3tbf13QUGBunXrpuDgYG3atEmZmZl67rnnVK5cOf3tb3+7o8cDAADKHpeWncTERJv5hIQEBQYGaseOHXrooYesy729vRUcHFzsNr7//nvt379fP/zwg4KCgtSyZUtNnz5dr776qqZMmaLy5cs79RgAAEDZVqZuUL5w4YIkKSAgwGb5okWLVLVqVTVr1kzjx4/XlStXrOtSUlLUvHlzBQUFWZdFRUUpJydH+/btK3Y/ubm5ysnJsZkAAIA5lZkblAsLCzVy5Ei1a9dOzZo1sy5/+umnFRoaqpCQEO3evVuvvvqq0tLStGLFCklSVlaWTdGRZJ3Pysoqdl8zZszQ1KlTnXQkAACgLCkzZScmJkZ79+7Vhg0bbJYPHTrU+u/mzZurevXq6tixo44cOaJ69eqVal/jx4/X6NGjrfM5OTmqVatW6YIDAIAyrUxcxho+fLhWrVqlH3/8UTVr1rzp2IiICEnS4cOHJUnBwcHKzs62GXN9/kb3+Xh6esrX19dmAgAA5uTSsmMYhoYPH66VK1dqzZo1CgsLu+VrUlNTJUnVq1eXJEVGRmrPnj06ffq0dUxSUpJ8fX3VpEkTp+QGAAB3D5dexoqJidHixYv19ddfy8fHx3qPjZ+fn7y8vHTkyBEtXrxYXbt2VZUqVbR7926NGjVKDz30kO69915JUufOndWkSRM9++yzmjlzprKysjRhwgTFxMTI09PTlYcHAADKAJeWnfnz50v6/cGBfxQfH68BAwaofPny+uGHHzRnzhxdvnxZtWrVUq9evTRhwgTrWHd3d61atUovvviiIiMjVbFiRfXv39/muTwASoYn/QIwI5eWHcMwbrq+Vq1aWrdu3S23Exoaqm+//dZRsQAAgImUiRuUAQAAnIWyAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATI2yAwAATM2lZWfGjBm677775OPjo8DAQPXo0UNpaWk2Y65evaqYmBhVqVJFlSpVUq9evZSdnW0zJiMjQ926dZO3t7cCAwM1duxYXbt27U4eCgAAKKMcUnbOnz9fqtetW7dOMTEx2rx5s5KSkpSfn6/OnTvr8uXL1jGjRo3SN998o+XLl2vdunU6deqUevbsaV1fUFCgbt26KS8vT5s2bdLChQuVkJCgSZMm3e5hAQAAE7C77Lz11ltatmyZdb53796qUqWKatSooV27dtm1rcTERA0YMEBNmzZVixYtlJCQoIyMDO3YsUOSdOHCBX3yySeaPXu2/vznPys8PFzx8fHatGmTNm/eLEn6/vvvtX//fv3jH/9Qy5YtFR0drenTpysuLk55eXn2Hh4AADAZu8vOggULVKtWLUlSUlKSkpKS9N133yk6Olpjx469rTAXLlyQJAUEBEiSduzYofz8fHXq1Mk6plGjRqpdu7ZSUlIkSSkpKWrevLmCgoKsY6KiopSTk6N9+/YVu5/c3Fzl5OTYTAAAwJw87H1BVlaWteysWrVKvXv3VufOnVWnTh1FRESUOkhhYaFGjhypdu3aqVmzZtZ9lS9fXv7+/jZjg4KClJWVZR3zx6Jzff31dcWZMWOGpk6dWuqsAADg7mH3mZ3KlSvr+PHjkn6/DHX9rIthGCooKCh1kJiYGO3du1dLly4t9TZKavz48bpw4YJ1un48AADAfOw+s9OzZ089/fTTatCggc6cOaPo6GhJ0s6dO1W/fv1ShRg+fLhWrVql9evXq2bNmtblwcHBysvL0/nz523O7mRnZys4ONg6ZuvWrTbbu/5uretj/pOnp6c8PT1LlRUAANxd7D6z8+6772r48OFq0qSJkpKSVKlSJUlSZmamhg0bZte2DMPQ8OHDtXLlSq1Zs0ZhYWE268PDw1WuXDklJydbl6WlpSkjI0ORkZGSpMjISO3Zs0enT5+2jklKSpKvr6+aNGli7+EBAACTsfvMTrly5fTyyy8XWT5q1Ci7dx4TE6PFixfr66+/lo+Pj/UeGz8/P3l5ecnPz0+DBw/W6NGjFRAQIF9fX7300kuKjIzUAw88IEnq3LmzmjRpomeffVYzZ85UVlaWJkyYoJiYGM7eAACA0j1n5/PPP1f79u0VEhKiY8eOSZLmzJmjr7/+2q7tzJ8/XxcuXFCHDh1UvXp16/THt7a/++67evTRR9WrVy899NBDCg4O1ooVK6zr3d3dtWrVKrm7uysyMlLPPPOMnnvuOU2bNq00hwYAAEzG7jM78+fP16RJkzRy5Ei98cYb1puS/f39NWfOHHXv3r3E2zIM45ZjKlSooLi4OMXFxd1wTGhoqL799tsS7xcAAPz3sPvMzrx58/T3v/9dr7/+utzd3a3L27Rpoz179jg0HAAAwO2yu+ykp6erVatWRZZ7enrafMwDAABAWWB32QkLC1NqamqR5YmJiWrcuLEjMgEAADiM3ffsjB49WjExMbp69aoMw9DWrVu1ZMkSzZgxQx9//LEzMgIAAJSa3WXn+eefl5eXlyZMmKArV67o6aefVkhIiN577z317dvXGRkBAABKze6yI0n9+vVTv379dOXKFV26dEmBgYGOzgUAAOAQpSo713l7e8vb29tRWQAAAByuRGWnVatWslgsJdrgTz/9dFuBAAAAHKlEZadHjx5OjgEAAOAcJSo7kydPdnYOAAAApyj1PTvbt2/XgQMHJElNmjRReHi4w0IBAAA4it1l58SJE3rqqae0ceNG+fv7S5LOnz+vtm3baunSpapZs6ajMwIAAJSa3U9Qfv7555Wfn68DBw7o7NmzOnv2rA4cOKDCwkI9//zzzsgIAABQanaf2Vm3bp02bdqkhg0bWpc1bNhQ8+bN04MPPujQcAAAALfL7jM7tWrVUn5+fpHlBQUFCgkJcUgoAAAAR7G77Lz99tt66aWXtH37duuy7du3KzY2VrNmzXJoOAAAgNtVostYlStXtnmo4OXLlxURESEPj99ffu3aNXl4eGjQoEE8kwcAAJQpJSo7c+bMcXIMAAAA5yhR2enfv7+k38/gLF68WFFRUQoKCnJqMAAAAEew654dDw8P/eUvf9HVq1edlQcAAMCh7L5B+f7779fOnTudkQUAAMDh7H7OzrBhwzRmzBidOHFC4eHhqlixos36e++912HhAAAAbpfdZadv376SpBEjRliXWSwWGYYhi8WigoICx6UDAAC4TXaXnfT0dGfkAAAAcAq7y05oaKgzcgAAADiF3WXnuv379ysjI0N5eXk2yx9//PHbDgUAAOAodpedX375RU888YT27NljvVdHkvUJy9yzAwAAyhK733oeGxursLAwnT59Wt7e3tq3b5/Wr1+vNm3aaO3atU6ICAAAUHp2n9lJSUnRmjVrVLVqVbm5ucnNzU3t27fXjBkzNGLECJ7BAwAAyhS7z+wUFBTIx8dHklS1alWdOnVK0u83LqelpTk2HQAAwG2y+8xOs2bNtGvXLoWFhSkiIkIzZ85U+fLl9dFHH6lu3brOyAgAAFBqdpedCRMm6PLly5KkadOm6dFHH9WDDz6oKlWqaNmyZQ4PCAAAcDvsLjtRUVHWf9evX18///yzzp49q8qVK1vfkQUAAFBWlPo5O38UEBDgiM0AAAA4XInLzqBBg0o07tNPPy11GAAAAEcrcdlJSEhQaGioWrVqZX2QIAAAQFlX4rLz4osvasmSJUpPT9fAgQP1zDPPcPkKAACUeSV+zk5cXJwyMzP1yiuv6JtvvlGtWrXUu3dvrV69mjM9AACgzLLroYKenp566qmnlJSUpP3796tp06YaNmyY6tSpo0uXLjkrIwAAQKnZ/QRl6wvd3KwfBMqHfwIAgLLKrrKTm5urJUuW6JFHHtE999yjPXv26P3331dGRoYqVarkrIwAAAClVuIblIcNG6alS5eqVq1aGjRokJYsWaKqVas6MxsAAMBtK3HZWbBggWrXrq26detq3bp1WrduXbHjVqxY4bBwAAAAt6vEZee5557j4yAAAMBdx66HCgIAANxtSv1uLAAAgLsBZQcAAJgaZQcAAJgaZQcAAJhaicpO69atde7cOUnStGnTdOXKFaeGAgAAcJQSlZ0DBw7o8uXLkqSpU6fyOVgAAOCuUaK3nrds2VIDBw5U+/btZRiGZs2adcOPh5g0aVKJd75+/Xq9/fbb2rFjhzIzM7Vy5Ur16NHDun7AgAFauHChzWuioqKUmJhonT979qxeeuklffPNN3Jzc1OvXr303nvv8fEVAABAUgnLTkJCgiZPnqxVq1bJYrHou+++k4dH0ZdaLBa7ys7ly5fVokULDRo0SD179ix2TJcuXRQfH2+d9/T0tFnfr18/ZWZmKikpSfn5+Ro4cKCGDh2qxYsXlzgHAAAwrxKVnYYNG2rp0qWSfv+08+TkZAUGBt72zqOjoxUdHX3TMZ6engoODi523YEDB5SYmKht27apTZs2kqR58+apa9eumjVrlkJCQop9XW5urnJzc63zOTk5pTwCAABQ1tn9bqzCwkKHFJ2SWrt2rQIDA9WwYUO9+OKLOnPmjHVdSkqK/P39rUVHkjp16iQ3Nzdt2bLlhtucMWOG/Pz8rFOtWrWcegwAAMB1SvXW8yNHjuill15Sp06d1KlTJ40YMUJHjhxxdDZ16dJFn332mZKTk/XWW29p3bp1io6OVkFBgSQpKyurSPHy8PBQQECAsrKybrjd8ePH68KFC9bp+PHjDs8OAADKhhJ/NtZ1q1ev1uOPP66WLVuqXbt2kqSNGzeqadOm+uabb/TII484LFzfvn2t/27evLnuvfde1atXT2vXrlXHjh1LvV1PT88i9/4AAABzsrvsjBs3TqNGjdKbb75ZZPmrr77q0LLzn+rWrauqVavq8OHD6tixo4KDg3X69GmbMdeuXdPZs2dveJ8PAAD472L3ZawDBw5o8ODBRZYPGjRI+/fvd0ioGzlx4oTOnDmj6tWrS5IiIyN1/vx57dixwzpmzZo1KiwsVEREhFOzAACAu4PdZadatWpKTU0tsjw1NdXuG5cvXbqk1NRU6/bS09OVmpqqjIwMXbp0SWPHjtXmzZt19OhRJScnq3v37qpfv76ioqIkSY0bN1aXLl00ZMgQbd26VRs3btTw4cPVt2/fG74TCwAA/Hex+zLWkCFDNHToUP3yyy9q27atpN/v2Xnrrbc0evRou7a1fft2Pfzww9b566/v37+/5s+fr927d2vhwoU6f/68QkJC1LlzZ02fPt3mfptFixZp+PDh6tixo/WhgnPnzrX3sAAAgEnZXXYmTpwoHx8fvfPOOxo/frwkKSQkRFOmTNGIESPs2laHDh1kGMYN169evfqW2wgICOABggAA4IbsLjsWi0WjRo3SqFGjdPHiRUmSj4+Pw4MBAAA4gt1l548oOQAAoKwr1UMFAQAA7haUHQAAYGqUHQAAYGp2lZ38/Hx17NhRhw4dclYeAAAAh7LrBuVy5cpp9+7dzsoCAHCxOuP+5fBtHn2zm8O3CdjD7stYzzzzjD755BNnZAEAAHA4u996fu3aNX366af64YcfFB4erooVK9qsnz17tsPCAQAA3C67y87evXvVunVrSdLBgwdt1lksFsekAgAAcBC7y86PP/7ojBwAAABOUeonKB8+fFhHjhzRQw89JC8vLxmGwZkdoBjOuOFT4qZPACgpu29QPnPmjDp27Kh77rlHXbt2VWZmpiRp8ODBGjNmjMMDAgAA3A67y86oUaNUrlw5ZWRkyNvb27q8T58+SkxMdGg4AACA22X3Zazvv/9eq1evVs2aNW2WN2jQQMeOHXNYMAAAAEew+8zO5cuXbc7oXHf27Fl5eno6JBQAAICj2F12HnzwQX322WfWeYvFosLCQs2cOVMPP/ywQ8MBAADcLrsvY82cOVMdO3bU9u3blZeXp1deeUX79u3T2bNntXHjRmdkBAAAKDW7z+w0a9ZMBw8eVPv27dW9e3ddvnxZPXv21M6dO1WvXj1nZAQAACi1Uj1nx8/PT6+//rqjswAAADhcqcrOuXPn9Mknn+jAgQOSpCZNmmjgwIEKCAhwaDgAAIDbZfdlrPXr16tOnTqaO3euzp07p3Pnzmnu3LkKCwvT+vXrnZERAACg1Ow+sxMTE6M+ffpo/vz5cnd3lyQVFBRo2LBhiomJ0Z49exweEgAAoLTsPrNz+PBhjRkzxlp0JMnd3V2jR4/W4cOHHRoOAADgdtlddlq3bm29V+ePDhw4oBYtWjgkFAAAgKOU6DLW7t27rf8eMWKEYmNjdfjwYT3wwAOSpM2bNysuLk5vvvmmc1ICAACUUonKTsuWLWWxWGQYhnXZK6+8UmTc008/rT59+jguHQAAwG0qUdlJT093dg4AAACnKFHZCQ0NdXYOAAAApyjVQwVPnTqlDRs26PTp0yosLLRZN2LECIcEAwAAcAS7y05CQoJeeOEFlS9fXlWqVJHFYrGus1gslB0AAFCm2F12Jk6cqEmTJmn8+PFyc7P7nesAAAB3lN1t5cqVK+rbty9FBwAA3BXsbiyDBw/W8uXLnZEFAADA4ey+jDVjxgw9+uijSkxMVPPmzVWuXDmb9bNnz3ZYOAAAgNtVqrKzevVqNWzYUJKK3KAMAABQlthddt555x19+umnGjBggBPiAAAAOJbd9+x4enqqXbt2zsgCAADgcHaXndjYWM2bN88ZWQAAABzO7stYW7du1Zo1a7Rq1So1bdq0yA3KK1ascFg4AACA22V32fH391fPnj2dkQUAAMDh7C478fHxzsgBAADgFDwGGQAAmJrdZ3bCwsJu+jydX3755bYCAQAAOJLdZWfkyJE28/n5+dq5c6cSExM1duxYR+UCAABwCLvLTmxsbLHL4+LitH379tsOBAAA4EgOu2cnOjpaX375paM2BwAA4BAOKzv/+7//q4CAAEdtDgAAwCHsvozVqlUrmxuUDcNQVlaWfv31V33wwQcODQcAAHC77C47PXr0sJl3c3NTtWrV1KFDBzVq1MhRuQAAABzC7rIzefJkZ+QAAABwCpc+VHD9+vV67LHHFBISIovFoq+++spmvWEYmjRpkqpXry4vLy916tRJhw4dshlz9uxZ9evXT76+vvL399fgwYN16dKlO3gUAACgLCtx2XFzc5O7u/tNJw8P+04UXb58WS1atFBcXFyx62fOnKm5c+dqwYIF2rJliypWrKioqChdvXrVOqZfv37at2+fkpKStGrVKq1fv15Dhw61KwcAADCvEreTlStX3nBdSkqK5s6dq8LCQrt2Hh0drejo6GLXGYahOXPmaMKECerevbsk6bPPPlNQUJC++uor9e3bVwcOHFBiYqK2bdumNm3aSJLmzZunrl27atasWQoJCSl227m5ucrNzbXO5+Tk2JUbAADcPUpcdq4Xjj9KS0vTuHHj9M0336hfv36aNm2aw4Klp6crKytLnTp1si7z8/NTRESEUlJS1LdvX6WkpMjf399adCSpU6dOcnNz05YtW/TEE08Uu+0ZM2Zo6tSpDssKAADKrlLds3Pq1CkNGTJEzZs317Vr15SamqqFCxcqNDTUYcGysrIkSUFBQTbLg4KCrOuysrIUGBhos97Dw0MBAQHWMcUZP368Lly4YJ2OHz/usNwAAKBssesmmwsXLuhvf/ub5s2bp5YtWyo5OVkPPvigs7I5jaenpzw9PV0dAwAA3AElPrMzc+ZM1a1bV6tWrdKSJUu0adMmpxad4OBgSVJ2drbN8uzsbOu64OBgnT592mb9tWvXdPbsWesYAADw363EZ3bGjRsnLy8v1a9fXwsXLtTChQuLHbdixQqHBAsLC1NwcLCSk5PVsmVLSb/fSLxlyxa9+OKLkqTIyEidP39eO3bsUHh4uCRpzZo1KiwsVEREhENyAACAu1uJy85zzz1n8zERjnDp0iUdPnzYOp+enq7U1FQFBASodu3aGjlypP7617+qQYMGCgsL08SJExUSEmJ9inPjxo3VpUsXDRkyRAsWLFB+fr6GDx+uvn373vCdWAAA4L9LictOQkKCw3e+fft2Pfzww9b50aNHS5L69++vhIQEvfLKK7p8+bKGDh2q8+fPq3379kpMTFSFChWsr1m0aJGGDx+ujh07ys3NTb169dLcuXMdnhUAANyd7P64CEfq0KGDDMO44XqLxaJp06bd9C3tAQEBWrx4sTPiAQAAE3Dpx0UAAAA4G2UHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYGmUHAACYmoerAwClUWfcv5yy3aNvdnPKdgEArsOZHQAAYGqUHQAAYGqUHQAAYGqUHQAAYGqUHQAAYGqUHQAAYGqUHQAAYGpluuxMmTJFFovFZmrUqJF1/dWrVxUTE6MqVaqoUqVK6tWrl7Kzs12YGAAAlDVl/qGCTZs21Q8//GCd9/D4v8ijRo3Sv/71Ly1fvlx+fn4aPny4evbsqY0bN7oiKgDgDnLGw0V5sKg5lfmy4+HhoeDg4CLLL1y4oE8++USLFy/Wn//8Z0lSfHy8GjdurM2bN+uBBx6401EBAEAZVKYvY0nSoUOHFBISorp166pfv37KyMiQJO3YsUP5+fnq1KmTdWyjRo1Uu3ZtpaSk3HSbubm5ysnJsZkAAIA5lemyExERoYSEBCUmJmr+/PlKT0/Xgw8+qIsXLyorK0vly5eXv7+/zWuCgoKUlZV10+3OmDFDfn5+1qlWrVpOPAoAAOBKZfoyVnR0tPXf9957ryIiIhQaGqovvvhCXl5epd7u+PHjNXr0aOt8Tk4OhQcAAJMq02d2/pO/v7/uueceHT58WMHBwcrLy9P58+dtxmRnZxd7j88feXp6ytfX12YCAADmdFeVnUuXLunIkSOqXr26wsPDVa5cOSUnJ1vXp6WlKSMjQ5GRkS5MCQAAypIyfRnr5Zdf1mOPPabQ0FCdOnVKkydPlru7u5566in5+flp8ODBGj16tAICAuTr66uXXnpJkZGRvBMLAABYlemyc+LECT311FM6c+aMqlWrpvbt22vz5s2qVq2aJOndd9+Vm5ubevXqpdzcXEVFRemDDz5wcWoAAFCWlOmys3Tp0puur1ChguLi4hQXF3eHEgEAgLvNXXXPDgAAgL0oOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQoOwAAwNQ8XB0AAACzqzPuXw7f5tE3uzl8m2bFmR0AAGBqlB0AAGBqlB0AAGBq3LMDK2dcU5a4rgwAcC3O7AAAAFOj7AAAAFOj7AAAAFOj7AAAAFOj7AAAAFOj7AAAAFOj7AAAAFOj7AAAAFOj7AAAAFMzTdmJi4tTnTp1VKFCBUVERGjr1q2ujgQAAMoAU3xcxLJlyzR69GgtWLBAERERmjNnjqKiopSWlqbAwECXZuMjGAAAdxNn/N1y9d8sU5zZmT17toYMGaKBAweqSZMmWrBggby9vfXpp5+6OhoAAHCxu/7MTl5ennbs2KHx48dbl7m5ualTp05KSUkp9jW5ubnKzc21zl+4cEGSlJOT4/B8hblXHL5NiaxkvXuyOiOnRFaykpWs/7ddwzBuPtC4y508edKQZGzatMlm+dixY43777+/2NdMnjzZkMTExMTExMRkgun48eM37Qp3/Zmd0hg/frxGjx5tnS8sLNTZs2dVpUoVWSwWl2TKyclRrVq1dPz4cfn6+rokQ0mR1TnI6hxkdY67JevdklMia2kYhqGLFy8qJCTkpuPu+rJTtWpVubu7Kzs722Z5dna2goODi32Np6enPD09bZb5+/s7K6JdfH19y/wP+XVkdQ6yOgdZneNuyXq35JTIai8/P79bjrnrb1AuX768wsPDlZycbF1WWFio5ORkRUZGujAZAAAoC+76MzuSNHr0aPXv319t2rTR/fffrzlz5ujy5csaOHCgq6MBAAAXM0XZ6dOnj3799VdNmjRJWVlZatmypRITExUUFOTqaCXm6empyZMnF7m8VhaR1TnI6hxkdY67JevdklMiqzNZDONW79cCAAC4e9319+wAAADcDGUHAACYGmUHAACYGmUHAACYGmWnDHjjjTfUtm1beXt73/DhhhkZGerWrZu8vb0VGBiosWPH6tq1a3c2aDEOHjyo7t27q2rVqvL19VX79u31448/ujrWDf3rX/9SRESEvLy8VLlyZfXo0cPVkW4qNzdXLVu2lMViUWpqqqvjFHH06FENHjxYYWFh8vLyUr169TR58mTl5eW5OpokKS4uTnXq1FGFChUUERGhrVu3ujpSETNmzNB9990nHx8fBQYGqkePHkpLS3N1rBJ58803ZbFYNHLkSFdHKdbJkyf1zDPPqEqVKvLy8lLz5s21fft2V8cqoqCgQBMnTrT5PZo+ffqtP+/pDli/fr0ee+wxhYSEyGKx6KuvvrJZbxiGJk2apOrVq8vLy0udOnXSoUOHXBP2Jig7ZUBeXp6efPJJvfjii8WuLygoULdu3ZSXl6dNmzZp4cKFSkhI0KRJk+5w0qIeffRRXbt2TWvWrNGOHTvUokULPfroo8rKynJ1tCK+/PJLPfvssxo4cKB27dqljRs36umnn3Z1rJt65ZVXbvkYdFf6+eefVVhYqA8//FD79u3Tu+++qwULFui1115zdTQtW7ZMo0eP1uTJk/XTTz+pRYsWioqK0unTp10dzca6desUExOjzZs3KykpSfn5+ercubMuX77s6mg3tW3bNn344Ye69957XR2lWOfOnVO7du1Urlw5fffdd9q/f7/eeecdVa5c2dXRinjrrbc0f/58vf/++zpw4IDeeustzZw5U/PmzXN1NF2+fFktWrRQXFxcsetnzpypuXPnasGCBdqyZYsqVqyoqKgoXb169Q4nvQVHfBgnHCM+Pt7w8/Mrsvzbb7813NzcjKysLOuy+fPnG76+vkZubu4dTGjr119/NSQZ69evty7LyckxJBlJSUkuy1Wc/Px8o0aNGsbHH3/s6igl9u233xqNGjUy9u3bZ0gydu7c6epIJTJz5kwjLCzM1TGM+++/34iJibHOFxQUGCEhIcaMGTNcmOrWTp8+bUgy1q1b5+ooN3Tx4kWjQYMGRlJSkvGnP/3JiI2NdXWkIl599VWjffv2ro5RIt26dTMGDRpks6xnz55Gv379XJSoeJKMlStXWucLCwuN4OBg4+2337YuO3/+vOHp6WksWbLEBQlvjDM7d4GUlBQ1b97c5iGJUVFRysnJ0b59+1yWq0qVKmrYsKE+++wzXb58WdeuXdOHH36owMBAhYeHuyxXcX766SedPHlSbm5uatWqlapXr67o6Gjt3bvX1dGKlZ2drSFDhujzzz+Xt7e3q+PY5cKFCwoICHBphry8PO3YsUOdOnWyLnNzc1OnTp2UkpLiwmS3duHCBUly+dfwZmJiYtStWzebr29Z889//lNt2rTRk08+qcDAQLVq1Up///vfXR2rWG3btlVycrIOHjwoSdq1a5c2bNig6OhoFye7ufT0dGVlZdn8HPj5+SkiIqLM/Z6Z4gnKZpeVlVXkadDX5115uchiseiHH35Qjx495OPjIzc3NwUGBioxMbHMnSr+5ZdfJElTpkzR7NmzVadOHb3zzjvq0KGDDh48WKb+sBiGoQEDBugvf/mL2rRpo6NHj7o6UokdPnxY8+bN06xZs1ya47ffflNBQUGxvzc///yzi1LdWmFhoUaOHKl27dqpWbNmro5TrKVLl+qnn37Stm3bXB3lpn755RfNnz9fo0eP1muvvaZt27ZpxIgRKl++vPr37+/qeDbGjRunnJwcNWrUSO7u7iooKNAbb7yhfv36uTraTV3/+1Pc71lZu5WBMztOMm7cOFkslptOZfU/uiXNbhiGYmJiFBgYqH//+9/aunWrevTooccee0yZmZllKmthYaEk6fXXX1evXr0UHh6u+Ph4WSwWLV++vExlnTdvni5evKjx48ffkVy3k/WPTp48qS5duujJJ5/UkCFDXJT87hYTE6O9e/dq6dKlro5SrOPHjys2NlaLFi1ShQoVXB3npgoLC9W6dWv97W9/U6tWrTR06FANGTJECxYscHW0Ir744gstWrRIixcv1k8//aSFCxdq1qxZWrhwoaujmQZndpxkzJgxGjBgwE3H1K1bt0TbCg4OLvIukuzsbOs6Rytp9jVr1mjVqlU6d+6cfH19JUkffPCBkpKStHDhQo0bN87h2Uqb9Xr5atKkiXW5p6en6tatq4yMDGdGtLLn65qSklLkM2fatGmjfv363ZH/ANr783vq1Ck9/PDDatu2rT766CMnp7u1qlWryt3d3fp7cl12drZTfmccYfjw4Vq1apXWr1+vmjVrujpOsXbs2KHTp0+rdevW1mUFBQVav3693n//feXm5srd3d2FCf9P9erVbX7fJalx48b68ssvXZToxsaOHatx48apb9++kqTmzZvr2LFjmjFjRpk7C/VH13+XsrOzVb16devy7OxstWzZ0kWpikfZcZJq1aqpWrVqDtlWZGSk3njjDZ0+fVqBgYGSpKSkJPn6+hb5ZXaEkma/cuWKpN/vhfgjNzc365kUZytp1vDwcHl6eiotLU3t27eXJOXn5+vo0aMKDQ11dkxJJc86d+5c/fWvf7XOnzp1SlFRUVq2bJkiIiKcGdHKnp/fkydP6uGHH7aeLfvPnwdXKF++vMLDw5WcnGx9vEBhYaGSk5M1fPhw14b7D4Zh6KWXXtLKlSu1du1ahYWFuTrSDXXs2FF79uyxWTZw4EA1atRIr776apkpOpLUrl27Im/hP3jw4B37fbfHlStXivzeuLu737H/jpZWWFiYgoODlZycbC03OTk52rJlyw3fXewyLr5BGoZhHDt2zNi5c6cxdepUo1KlSsbOnTuNnTt3GhcvXjQMwzCuXbtmNGvWzOjcubORmppqJCYmGtWqVTPGjx/v0ty//vqrUaVKFaNnz55GamqqkZaWZrz88stGuXLljNTUVJdmK05sbKxRo0YNY/Xq1cbPP/9sDB482AgMDDTOnj3r6mg3lZ6eXmbfjXXixAmjfv36RseOHY0TJ04YmZmZ1snVli5danh6ehoJCQnG/v37jaFDhxr+/v4272osC1588UXDz8/PWLt2rc3X78qVK66OViJl9d1YW7duNTw8PIw33njDOHTokLFo0SLD29vb+Mc//uHqaEX079/fqFGjhrFq1SojPT3dWLFihVG1alXjlVdecXU04+LFi9a/SZKM2bNnGzt37jSOHTtmGIZhvPnmm4a/v7/x9ddfG7t37za6d+9uhIWFGf/v//0/Fye3RdkpA/r3729IKjL9+OOP1jFHjx41oqOjDS8vL6Nq1arGmDFjjPz8fNeF/v9t27bN6Ny5sxEQEGD4+PgYDzzwgPHtt9+6Olax8vLyjDFjxhiBgYGGj4+P0alTJ2Pv3r2ujnVLZbnsxMfHF/uzW1b+P2revHlG7dq1jfLlyxv333+/sXnzZldHKuJGX7/4+HhXRyuRslp2DMMwvvnmG6NZs2aGp6en0ahRI+Ojjz5ydaRi5eTkGLGxsUbt2rWNChUqGHXr1jVef/11lz5a5Loff/yx2J/P/v37G4bx+9vPJ06caAQFBRmenp5Gx44djbS0NNeGLobFMMrAIxoBAACcxPUX1wEAAJyIsgMAAEyNsgMAAEyNsgMAAEyNsgMAAEyNsgMAAEyNsgMAAEyNsgMAAEyNsgOY2NGjR2WxWJSamurqKLc0ZcqUMvPhgXXq1NGcOXNuOsZiseirr766I3lKo0OHDho5cuRNxyQkJMjf3/+O5AFcibIDuNCAAQOsH1T5R2vXrpXFYtH58+dva/u1atVSZmammjVrdlvbsceNjul2XS9u7u7uOnnypM26zMxMeXh4yGKx6OjRow7ftzNcP57rU5UqVdS5c2ft3LnTIdtfsWKFpk+fbp0vrsD16dNHBw8edMj+gLKMsgOYVF5entzd3RUcHCwPDw9Xx3GYGjVq6LPPPrNZtnDhQtWoUeO2t52Xl3fb27DXDz/8oMzMTK1evVqXLl1SdHT0bZdcSQoICJCPj89Nx3h5eSkwMPC29wWUdZQd4C7x5ZdfqmnTpvL09FSdOnX0zjvv2KyvU6eOpk+frueee06+vr4aOnRokctYAwYMsDmbcH1au3atJOncuXN67rnnVLlyZXl7eys6OlqHDh2y7uP6ZY/Vq1ercePGqlSpkrp06aLMzExJv1+KWrhwob7++usi23711Vd1zz33yNvbW3Xr1tXEiROVn59v99ehf//+io+Pt1kWHx+v/v372ywrKCjQ4MGDFRYWJi8vLzVs2FDvvfeezZjrZ6HeeOMNhYSEqGHDhtZ1Fy9e1FNPPaWKFSuqRo0aiouLu2mu48ePq3fv3vL391dAQIC6d+9eorNMVapUUXBwsNq0aaNZs2YpOztbW7ZskXTr7/kHH3ygBg0aqEKFCgoKCtL//M//WNf98TJWhw4ddOzYMY0aNcr6fZGKv4w1f/581atXT+XLl1fDhg31+eef26y3WCz6+OOP9cQTT8jb21sNGjTQP//5z1seJ+BKlB3gLrBjxw717t1bffv21Z49ezRlyhRNnDhRCQkJNuNmzZqlFi1aaOfOnZo4cWKR7bz33nvKzMy0TrGxsQoMDFSjRo0k/f7Hf/v27frnP/+plJQUGYahrl272pSSK1euaNasWfr888+1fv16ZWRk6OWXX5Ykvfzyy+rdu7e1AGVmZqpt27aSJB8fHyUkJGj//v1677339Pe//13vvvuu3V+Lxx9/XOfOndOGDRskSRs2bNC5c+f02GOP2YwrLCxUzZo1tXz5cu3fv1+TJk3Sa6+9pi+++MJmXHJystLS0pSUlKRVq1ZZl7/99tvWr+W4ceMUGxurpKSkYjPl5+crKipKPj4++ve//62NGzdai6A9Z4u8vLwk/X6G6Vbf8+3bt2vEiBGaNm2a0tLSlJiYqIceeqjY7a5YsUI1a9bUtGnTrN+X4qxcuVKxsbEaM2aM9u7dqxdeeEEDBw7Ujz/+aDNu6tSp6t27t3bv3q2uXbuqX79+Onv2bImPE7jjXPyp68B/tf79+xvu7u5GxYoVbaYKFSoYkoxz584ZhmEYTz/9tPHII4/YvHbs2LFGkyZNrPOhoaFGjx49bMakp6cbkoydO3cW2feXX35pVKhQwdiwYYNhGIZx8OBBQ5KxceNG65jffvvN8PLyMr744gvDMAwjPj7ekGQcPnzYOiYuLs4ICgqyOabu3bvf8tjffvttIzw83Do/efJko0WLFjcc/8djGTlypDFw4EDDMAxj4MCBxqhRo4ydO3cakoz09PQbbiMmJsbo1auXTdagoCAjNzfXZlxoaKjRpUsXm2V9+vQxoqOjrfOSjJUrVxqGYRiff/650bBhQ6OwsNC6Pjc31/Dy8jJWr159y+MxDMM4d+6c8cQTTxiVKlUysrKybvk9//LLLw1fX18jJyen2O3/6U9/MmJjY22O6d1337UZEx8fb/j5+Vnn27ZtawwZMsRmzJNPPml07drV5rgnTJhgnb906ZIhyfjuu++KzQGUBZzZAVzs4YcfVmpqqs308ccf24w5cOCA2rVrZ7OsXbt2OnTokAoKCqzL2rRpU6J97ty5U88++6zef/9963YPHDggDw8PRUREWMdVqVJFDRs21IEDB6zLvL29Va9ePet89erVdfr06Vvuc9myZWrXrp2Cg4NVqVIlTZgwQRkZGSXK+58GDRqk5cuXKysrS8uXL9egQYOKHRcXF6fw8HBVq1ZNlSpV0kcffVRkn82bN1f58uWLvDYyMrLI/B+/Dn+0a9cuHT58WD4+PqpUqZIqVaqkgIAAXb16VUeOHLnpsbRt21aVKlVS5cqVtWvXLi1btkxBQUG3/J4/8sgjCg0NVd26dfXss89q0aJFunLlyk33dSs32ud/Hve9995r/XfFihXl6+tbop8BwFXMc9cicJeqWLGi6tevb7PsxIkTpd7WrWRlZenxxx/X888/r8GDB9u9j3LlytnMWywWGYZx09ekpKSoX79+mjp1qqKiouTn56elS5cWuQelpJo3b65GjRrpqaeeUuPGjdWsWbMib69funSpXn75Zb3zzjuKjIyUj4+P3n77bev9MNeV5Gt2K5cuXVJ4eLgWLVpUZF21atVu+tply5apSZMmqlKlil1vA/fx8dFPP/2ktWvX6vvvv9ekSZM0ZcoUbdu2zelvJy/uZ6CwsNCp+wRuB2d2gLtA48aNtXHjRptlGzdu1D333CN3d/cSb+fq1avq3r27GjVqpNmzZxfZx7Vr12zKwJkzZ5SWlqYmTZqUeB/ly5e3OdskSZs2bVJoaKhef/11tWnTRg0aNNCxY8dKvM3iDBo0SGvXrr3hWZ2NGzeqbdu2GjZsmFq1aqX69evf8izLH23evLnIfOPGjYsd27p1ax06dEiBgYGqX7++zeTn53fT/dSqVUv16tUrUlBK8j338PBQp06dNHPmTO3evVtHjx7VmjVrit1Pcd+X/3Sjfdrz/QfKIsoOcBcYM2aMkpOTNX36dB08eFALFy7U+++/b70xuKReeOEFHT9+XHPnztWvv/6qrKwsZWVlKS8vTw0aNFD37t01ZMgQbdiwQbt27dIzzzyjGjVqqHv37iXeR506dbR7926lpaXpt99+U35+vho0aKCMjAwtXbpUR44c0dy5c7Vy5Up7vww2hgwZol9//VXPP/98sesbNGig7du3a/Xq1Tp48KAmTpyobdu2lXj7Gzdu1MyZM3Xw4EHFxcVp+fLlio2NLXZsv379VLVqVXXv3l3//ve/lZ6errVr12rEiBGlPkt3q+/5qlWrNHfuXKWmpurYsWP67LPPVFhYaPOOsj+qU6eO1q9fr5MnT+q3334rdszYsWOVkJCg+fPn69ChQ5o9e7ZWrFhh988ZUNZQdoC7QOvWrfXFF19o6dKlatasmSZNmqRp06ZpwIABdm1n3bp1yszMVJMmTVS9enXrtGnTJkm/v4U7PDxcjz76qCIjI2UYhr799tsily1uZsiQIWrYsKHatGmjatWqaePGjXr88cc1atQoDR8+XC1bttSmTZuKfbeYPTw8PFS1atUbPkPohRdeUM+ePdWnTx9FRETozJkzGjZsWIm3P2bMGG3fvl2tWrXSX//6V82ePVtRUVHFjvX29tb69etVu3Zt9ezZU40bN9bgwYN19epV+fr6lur4bvU99/f314oVK/TnP/9ZjRs31oIFC7RkyRI1bdq02O1NmzZNR48eVb169W54aa1Hjx567733NGvWLDVt2lQffvih4uPj1aFDh1IdA1BWWIxbXWwHAAC4i3FmBwAAmBplBwAAmBplBwAAmBplBwAAmBplBwAAmBplBwAAmBplBwAAmBplBwAAmBplBwAAmBplBwAAmBplBwAAmNr/B3vHo8SMeMvyAAAAAElFTkSuQmCC\n",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "bins = np.arange(-10,12)\n",
-    "plt.hist(sim, bins=bins, align='left')\n",
-    "plt.xticks(bins[::2])\n",
-    "plt.xlabel('Horizontal Marble Position')\n",
-    "plt.ylabel('Number of Marbles');"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3b1ed737-e851-4272-b706-67fbb91f5a63",
-   "metadata": {},
-   "source": [
-    "One interesting trend that appears in the above histogram is that all locations are integers. This is because we used whole numbers for our left and right movements of marbles (i.e., +1 and -1) and used ten layers in the above simulation. There is no way to produce an odd integer by totaling a series of ten +1 or -1 integers. If we changed the number of layers to an odd number, we'd only get odd positions in the result, and if we used +1/2 and -1/2 for our horizontal movement, we'd get both even and odd integers."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7152df76-78b5-47fa-9f76-276c7e497cb7",
-   "metadata": {},
-   "source": [
-    "## Calculating pi\n",
-    "\n",
-    "As a second appliation of random number generaters, we will calclate a numerical value for $\\pi$. Imagine a circle with radius = $r$ inscribed inside a square of side length $2r$. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "65166f10-9009-4551-a14f-8205dc3b858c",
-   "metadata": {},
-   "source": [
-    "![](tutorial-stochastic/circle_square.png)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "88d705e8-b983-4aa2-b35b-ccb13c9aaa6a",
-   "metadata": {
-    "editable": true,
-    "slideshow": {
-     "slide_type": ""
-    },
-    "tags": []
-   },
-   "source": [
-    "**Figure 2.** The circle radius r inscribed in a square with side length of 2r.\n",
-    "\n",
-    "The areas of the circle and square are described by $A\n",
-    "_{circle} = \\pi r^2$ and $A_{square} = 4r^2$, respectively. If we divide the area of the circle by the area of the square, we get $\\pi / 4$.\n",
-    "\n",
-    "$$ \\frac { A_{circle} }{ A_{square} } = \\frac {\\pi r^2} {(2r)^2} = \\frac {\\pi r^2} {4r^2} = \\frac {\\pi}{4} $$\n",
-    "\n",
-    "This means that four times the ratio of the area of the circle and square equals $\\pi$.\n",
-    "\n",
-    "$$ \\frac { A_{circle} }{ A_{square}} \\times 4 = \\pi $$\n",
-    "\n",
-    "The challenge is now finding the ratio between the areas of the two shapes which can be done through a variety of creative means. Our method will be counting randomly placed dots. Imagine we painted the circle inscribed in a square on pavement outside and count the water droplets that fall in the circle and square during a rain storm."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7571b83c-e163-42b0-8329-f494045790a8",
-   "metadata": {},
-   "source": [
-    "![](tutorial-stochastic/circle_square_dots.png)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5c12bceb-c2ad-4cc2-98b9-4148667dc1c7",
-   "metadata": {},
-   "source": [
-    "**Figure 3.** Random dots inside the circle and square used to estimate a value of $\\pi$.\n",
-    "\n",
-    "Because the rain drops fall randomly, the probability of a drop falling in one of the shapes is proportional to the area of that shape, so dividing the number of drops in the circle by the number of drop in the square provides a estimate of $\\frac { A_{circle} }{ A_{square} }$ which then can be used to calculate $\\pi$. Counting rain is a bit tedious and challenging, so we can simulate this using a random number generator to produce random ($x, y$) coordinates of dots inside the square. We then total the number of these that fall inside the circle versus the square and complete the calculation to obtain a value of $\\pi$.\n",
-    "\n",
-    "For smilicity, we will center our circle and square around the origin and give the circle a radius = 1. This requires the coordinates to fall in the [-1, 1) ranges along both the $x$- and $y$-axes. We have no random number generator that produces values in this range, but we can modify the `random()` method which generates floats in the [0, 1) range by multiplying by 2 and substracting 1 as demonstrated below.\n",
-    "\n",
-    "~~~python\n",
-    "rng = np.random.default_rng()\n",
-    "x = 2 * rng.random() - 1\n",
-    "~~~"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "70c285c1-adae-453e-a895-fb515ea562ab",
-   "metadata": {},
-   "source": [
-    "Below is a function that performs this simulation and calculation of $\\pi$ with the only function argument `n_samples` as the number of dots generated. The general proceedure is ouline here.\n",
-    "1. Generate `n_samples` of ($x, y$) coordinates using the `random()` method\n",
-    "2. Calculate the distance from the origin using the `np.hypot()` function to determine if the dot is inside the circle (all dots are inside the square)\n",
-    "3. Calculate $\\pi$"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "e70bfca5-3606-4c3c-ad76-fc715f1f5ef4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def estimate_pi(n_samples):\n",
-    "    '''(integer) -> pi (float)\n",
-    "    \n",
-    "    Estimates the value of pi by finding the ratio of the area of a unit circle/area of a unit square\n",
-    "    and multiplying by 4.\n",
-    "    '''\n",
-    "\n",
-    "    n_samples = int(n_samples)\n",
-    "    \n",
-    "    # Step 1\n",
-    "    rng = np.random.default_rng()\n",
-    "    coords = rng.random(size=(n_samples, 2))\n",
-    "\n",
-    "    # Step 2\n",
-    "    dist_from_origin = np.hypot(coords[:,0], coords[:,1]) # distance from the origion\n",
-    "    in_circle = dist_from_origin[dist_from_origin <= 1] # if <= 1, the point is inside the circle\n",
-    "\n",
-    "    # Step 3\n",
-    "    pi = 4 * (in_circle.size / n_samples)\n",
-    "    \n",
-    "    return pi"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d34736f4-21f4-4e15-a3b3-d68cbf90b782",
-   "metadata": {},
-   "source": [
-    "We can then call this function with 100 dots generated. Because we are using a random number generator, every time we call this function, we likley get a different value for $\\pi$."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "c3bac1dc-e420-4b2d-a0b7-8b3fce9f277b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "3.08"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "estimate_pi(100)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "19575a49-311d-4c27-aa34-2cd8a3539265",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "3.16"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "estimate_pi(100)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "947f9bfd-9550-440b-820b-eeb746dad01d",
-   "metadata": {},
-   "source": [
-    "We can also generate a value for $\\pi$ using the `np.pi` to compare our answer to."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "9d107cde-6f0a-48ae-9258-0392f41cc37d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "3.141592653589793"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "np.pi"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "dfdb0029-6ef8-49d9-997a-2b25ad65fe5e",
-   "metadata": {},
-   "source": [
-    "Odds are that the values calculated above for $\\pi$ above is close but not exactly 3.14. If we increase the number of dots, the value for $\\pi$ will on average become closer to the true value. While it may be tempting to just call the function with an extremely large number of dots, this can take substatially longer to computer."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "d49d0955-f5e9-4214-abb2-2f0c9c4f470c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "3.14157644"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "estimate_pi(1E8)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cbc28bcb-b975-4d82-9f06-6a6378bf09c2",
-   "metadata": {},
-   "source": [
-    "## Simulating radioactive decay\n",
-    "\n",
-    "As a final example, we will simulate the radioactive decay of the radioactive nuclide $^{137m}$Ba to determine the quantity of undecayed material versus time. We will then compare it to an analytical model to see how well the two agree. Radioactive nuclei decay by first-order kinetics, which means that each radioactive nucleus has a fixed probability of decaying at any given time. This is analogous to how each six-sided die in a bucket has a fixed probability of rolling a one each time they are dumped out. This analogy is so good that we can simulate the decay process by generating a large number of random integers with fixed probabilities.\n",
-    "\n",
-    "The first thing we need to is to know the probability of a nucleus decaying in a single second. Because this is a first-order process, the rate (-dA/dt) is described by\n",
-    "\n",
-    "$$ \\frac{-dA}{dt} = kA $$\n",
-    "\n",
-    "where A is the quantity of $^{137m}$Ba, $t$ is time in seconds, and $k$ is the rate constant for this process. We also know that the half-life (t$_{1/2}$) of  $^{137m}$Ba is about 151 seconds which is related to the rate constant by the following equation.\n",
-    "\n",
-    "$$ t_{1/2} = \\frac{ln(2)}{k} $$\n",
-    "\n",
-    "This means that $k$ = 4.59e$^{-3}$ s$^{-1}$. For first-order kinetics, this means that 4.59e$^{-3}$ fraction of the nuclei decays, so this is the probability we need to simulate this process using random numbers. The function below calculates the fraction of radioactive material remaining based on a rate constant `k` and allows the users to choose the number of simulated nuclei `n` and duraction of the simulation `n_final`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "f5ec62ec-f980-43ea-b5ea-19d7a6de8450",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def decay(k, n=1000, t_final=1000):\n",
-    "    '''floats and integers -> ndarray of integers\n",
-    "\n",
-    "    Calculates the fraction of nuclei remaining at each second in the simulation given n initial \n",
-    "    nuclei with a rate constant k of decaying each second and a final simulation time t_final.\n",
-    "    '''\n",
-    "\n",
-    "    n_undecayed = n\n",
-    "    undecayed_array = np.full(t_final + 1, n)\n",
-    "    \n",
-    "    for second in range(1, t_final + 1):\n",
-    "        decays = rng.binomial(1, p=k, size=n_undecayed).sum()\n",
-    "        n_undecayed -= decays\n",
-    "        undecayed_array[second] = n_undecayed\n",
-    "        \n",
-    "    fraction = undecayed_array / n    \n",
-    "    \n",
-    "    \n",
-    "    return fraction"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "61e2bc98-4518-4b2b-a33d-b8303ee65a53",
-   "metadata": {},
-   "source": [
-    "Below we simulate the decay of $^{137m}$Ba using a hundred simulated nuclei."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "bd9d6811-2248-4c12-b834-385658b40baa",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "array([1.  , 1.  , 1.  , ..., 0.01, 0.01, 0.01])"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "decay(4.59e-3, n=100)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8320f7c8-31ea-4272-8683-9cd477f943c6",
-   "metadata": {},
-   "source": [
-    "We can plot and compare this simulation to the analytical model for this simulation knowing that the fraction of undecayed nuclei ($\\frac{A}{A_0}$) is described by the following first-order equation where $A_0$ and $A_t$ are the initial quantities and quantities of nuclei at time $t$.\n",
-    "\n",
-    "$$ \\frac{A_t}{A_0} = e^{-kt} $$"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "aff9c2ec-a032-4fc7-8ca0-46502ab1b31c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "seconds = np.arange(1001)\n",
-    "fraction = np.exp(-4.59e-3 * seconds)\n",
-    "\n",
-    "plt.plot(seconds, fraction, linestyle='-', label='Theoretical')\n",
-    "plt.plot(seconds, decay(4.59e-3, n=500), linestyle='--', label='Simulation')\n",
-    "plt.xlabel('Time, s')\n",
-    "plt.ylabel('Fraction of Undecayed Nuclei')\n",
-    "plt.legend();"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "10d2f74f-06d1-418e-a9e0-14265c58171a",
-   "metadata": {},
-   "source": [
-    "The simulation is in good agreement with the theoretical model, but this is some discrepency. If we increase the number of simulated nuclei, the simulation should align better with the theoretical values."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "bae004b9-9cf0-4975-aaa5-b9b410b69cde",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 640x480 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "seconds = np.arange(1001)\n",
-    "fraction = np.exp(-4.59e-3 * seconds)\n",
-    "\n",
-    "plt.plot(seconds, fraction, linestyle='-', label='Theoretical')\n",
-    "plt.plot(seconds, decay(4.59e-3, n=5000), linestyle='--', label='Simulation')\n",
-    "plt.xlabel('Time, s')\n",
-    "plt.ylabel('Fraction of Undecayed Nuclei')\n",
-    "plt.legend();"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "7e193e9f-25ca-47fe-9809-16db9141e164",
-   "metadata": {},
-   "source": [
-    "## Further reading\n",
-    "\n",
-    "- To learn more about NumPy random number generators, see [Random Generator](https://numpy.org/doc/stable/reference/random/index.html)\n",
-    "- To learn more about random number distributions and their generation, see [Monte Carlo Simulation Part 5: Randomness & Random Number Generation](https://towardsdatascience.com/monte-carlo-simulation-421110b678c5?gi=f86d4ec9f452)\n",
-    "- For examples of using random variables for chemical simulations, see chapter 9 of [Scientific Computing for Chemists](https://weisscharlesj.github.io/SciCompforChemists/intro.html)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}
diff --git a/content/tutorial-stochastic-simulations.md b/content/tutorial-stochastic-simulations.md
new file mode 100644
index 00000000..ae5fa508
--- /dev/null
+++ b/content/tutorial-stochastic-simulations.md
@@ -0,0 +1,483 @@
+---
+jupytext:
+  text_representation:
+    extension: .md
+    format_name: myst
+    format_version: 0.13
+    jupytext_version: 1.14.7
+kernelspec:
+  display_name: Python 3 (ipykernel)
+  language: python
+  name: python3
+---
+
+# Simulating Using Random Variables
+
+Randomness, or apparent randomness, is a major part of the world we live from
+the movement of gas molecules in the air we breath to the outcome of a coin toss.
+While many events are not truely random, they are often close enough to random
+or seemingly random enough to be simulated as such.
+Despite many processes being random, their outcomes often conform to a
+statistical pattern if enough of these random events occur.
+For example, if we roll a six-sided die over a large number of rolls, we expect
+to roll a 5 about $\frac{1}{6}$ of the time.
+As a general rule, the larger the number of random events observed, the closer
+the distribution of these events will *likely* be to the expected disbribution.
+In this tutorial, we will use a random number generator provided in NumPy to
+solve a number of problems through stochastic simulations.
+While the problems demonstrated below all have know solutions or equations, you
+may face other problems that do not have an analytical model or known solution.
+The methodology demonstrated below can be used to solve problems when no known
+solution or model exists. 
+
+## What you'll do
+- Generate random values using NumPy to power stochastic simulations
+- Perform stochastic simulations to determine the
+    - Likelyhood of multiple children in a classroom of 25 having the same birthday
+    - Distribution of marbles in a Galton board
+    - Value of $\pi$
+    - Amount of radioactive material left versus time
+- Compare the above simulations to known values or an analytical model
+
+## What you'll learn:
+- Generating large quantites of random values in a desired distribution
+- Using random values to simulation a range of scenarios and solve problems
+
+## What you'll need:
+- [NumPy](https://numpy.org/)
+- [Matplotlib](https://matplotlib.org/)
+- Python's `math` module
+
+The above two packages are imported using the following commands:
+
+```{code-cell} ipython3
+import numpy as np
+import matplotlib.pyplot as plt
+import math
+```
+
+## Generating random variables
+
+NumPy can generate random variables using a Generator from the `np.random` module.
+While these values are not truely random, they are close enough for the following
+applications.
+One of the advantages of using NumPy to generate variables over the standard
+`random` Python module is that NumPy can generate a large number of random
+variables efficiently without the use of a `for` loop.
+These variables can be generated in a variety of probability distribution
+including normal, poisson, and binomial; but for the following simulations, we
+will mostly use even distributions where all numbers in the range have an equal
+likelyhood of being generated.
+This is accomplished by first creating a Generator using the
+`np.random.default_rng()` function and then using `random(n)` or
+`np.integers(low, high=, size=n)` methods with the Generator to produce random
+values where `n` is the number of random values returned.
+Below are some common methods for generating random values.
+
+| Method  | Description |
+|-----------|-------------|
+|`random(n)`| Generates `n` float values in the [0,1) range with an even distribution |
+|`integers(low, high=, size=)`| Generates `size` integers in the requested range [low, high) in a uniform distribution|
+|`normal(loc, scale=, size=)`| Generates `size` floats in a normal distribution centered on `loc` with a `scale` standard deviation|
+|`binomial(t, p, size=)`| Generates `size` integers in a bionimial distribution with `t` trials for each value with a probability `p`|
+|`choice(a, size=)`| Selects `size` elements from `a` list, tuple or ndarray with an even probability |
+|`shuffle(a)`| Shuffles items in list, tubple, or ndarray `a` |
+
+```{code-cell} ipython3
+rng = np.random.default_rng(seed=18)
+rng.random(10)
+```
+
+You may have guessed by looking at the returned values that `random()` produces
+values in the 0 $\rightarrow$ 1 range, but what happens if we need values in a
+different range?
+We can modify these values by mutiplying them by a coefficient to increase the
+range and using addition or substration to shift the center of the range.
+For example, if we need random values from -10 $\rightarrow$ +10, we can
+accomplish this by the following.
+
+```{code-cell} ipython3
+20 * rng.random(10) - 10
+```
+
+It's worth noting that the `random()` method returns values from the [0,1) range
+which includes the lower end and excludes the upper end.
+This is close enough to [0,1] for our purposes.
+
++++
+
+## Solving the birthday problem
+
+The goal of the [birthday problem](https://en.wikipedia.org/wiki/Birthday_problem)
+is to determine the probability of multiple children in a classroom of 25
+students having the same birthday.
+For simiplicity, we will ignore leap years (i.e., February 29 birthdays) and
+assume that the students are equilly likely to be born any day of the year.
+One method of determining the answer is to repeately simulate a classroom of 25
+student birthdays by using a random number generator and see how often all
+students in the class have unique birthdays.
+The general steps for this processes are outlined below. 
+
+1. Simulate 25 random birthdays with a random integer generator
+2. Check to see if any of the above birthdays match
+3. Record the outcome if all birthdays are unique
+4. Repeat setps 1-3 a large number of times
+
+To make things easier, we will just generate integers 0 $\rightarrow$ 364
+representating days of the year instead of actual months and days.
+
+```{code-cell} ipython3
+def all_unique(class_size, n_classrooms=100):
+    '''Randomly generates birthdays for groups of kids of a given group size and
+    outputs the percent of time all students have uniquie birthdays. All input
+    and output values are ints or floats.
+    
+    (classroom size, number of classrooms) -> percentage classrooms with all unique birthdays
+    '''
+    
+    all_unique_class = 0  # number of classrooms with students NOT sharing birthdays
+    
+    for classroom in range(n_classrooms):
+        birthdays = rng.integers(0, high=365, size=class_size)
+        if class_size == np.unique(birthdays).size:
+            all_unique_class += 1
+    
+    return 100 * all_unique_class / n_classrooms
+```
+
+Below we simulate 50000 classrooms of 25 students and find that only around 43%
+of the time every student in a classroom has a unique birthday from all the other students.
+
+```{code-cell} ipython3
+all_unique(25, n_classrooms=50000)
+```
+
+This problem also has an equation for the probability given below where **p**
+is the probability of all students having a unique birthday and **n** is the
+classroom size.
+Performing this calculation below, we find that 43.13% of the time, students
+should have all unique birthdays which is quite close to what was found in the
+simulation above.
+
+$$ p = \frac {365!}{365^n(365-n)!} $$
+
+```{code-cell} ipython3
+n = 25
+math.factorial(365)/(365**n * math.factorial(365-n))
+```
+
+## Simulating a Galton board
+
+Next, we will simulate a [Galton board](https://en.wikipedia.org/wiki/Galton_board)
+which allows mables to fall down levels of staggered pegs.
+Each marble starts in the horizontal center of the board, and at each level,
+the marble hits a peg. To continue falling to the next level, the marble must
+move around the peg, and it has an equal likeliness of moving to the left as it
+does to the right.
+At the bottom of the board, the marbles collect in bins with the height of
+marbles yielding a normal distribution.
+
++++
+
+![](tutorial-stochastic/galton_board.png)
+
++++
+
+**Figure 1.** An example of a Galton board with three marbles with three
+different potential paths (dotted lines) shown.
+
+The key operational detail of a Galton board is that every marble moves one
+increment to the left or right at each level, so our simulation centers around
+a series of randomly generated +1 and -1 to determine this movement by the
+following methodolog.
+1. Generate a random series of +1 and -1 in an even distribution - one value for
+   every level on the Galton board
+2. Sum up the values in step 1 to determine the final location of the mable
+3. Repeat steps 1-2 for each simulated marble
+4. Visualize the result
+
+Below is the simulation for a single marble moving down a 10-layered Galton board.
+Note how the integers 0 and 1 generated by `integers()` and converted to a
+series of -1 and +1 values, respectively.
+
+```{code-cell} ipython3
+moves = 2 * rng.integers(0, high=2, size=10) - 1
+final_position = moves.sum()
+final_position
+```
+
+To simulate additional marbles, we could use a `for` loop, but because we need
+the same number of integers for each marble, a more efficient way is to generate
+the random integers in a two-dimensional array with a row for every level on the
+Galton board and column for every marble simulated.
+We then sum up the values in each column to obtain the final positions of all marbles.
+
+```{code-cell} ipython3
+def galton(marbles, levels=10):
+    '''integer -> ndarray of integers
+
+    This function takes in an integer number of marbles and number of levels and outputs 
+    the horizontal position of these marbles at the bottom of a Galton board. 
+    '''
+    moves = 2 * rng.integers(0, high=2, size=(levels, marbles)) - 1
+    final_position = moves.sum(axis=0)
+    
+    return final_position
+```
+
+```{code-cell} ipython3
+sim = galton(1200)
+sim[:20]
+```
+
+We visualize the results below using a histogram plot.
+Being that all values are integers, we set `align='left'` so that each bar
+resides directly over the integer it represents.
+
+```{code-cell} ipython3
+bins = np.arange(-10,12)
+plt.hist(sim, bins=bins, align='left')
+plt.xticks(bins[::2])
+plt.xlabel('Horizontal Marble Position')
+plt.ylabel('Number of Marbles');
+```
+
+One interesting trend that appears in the above histogram is that all locations
+are integers.
+This is because we used whole numbers for our left and right movements of
+marbles (i.e., +1 and -1) and used ten layers in the above simulation.
+There is no way to produce an odd integer by totaling a series of ten +1 or -1
+integers.
+If we changed the number of layers to an odd number, we'd only get odd positions
+in the result, and if we used +1/2 and -1/2 for our horizontal movement, we'd get
+both even and odd integers.
+
++++
+
+## Calculating pi
+
+As a second appliation of random number generaters, we will calclate a numerical
+value for $\pi$.
+Imagine a circle with radius = $r$ inscribed inside a square of side length $2r$. 
+
++++
+
+![](tutorial-stochastic/circle_square.png)
+
++++ {"editable": true, "slideshow": {"slide_type": ""}}
+
+**Figure 2.** The circle radius r inscribed in a square with side length of 2r.
+
+The areas of the circle and square are described by $A
+_{circle} = \pi r^2$ and $A_{square} = 4r^2$, respectively.
+If we divide the area of the circle by the area of the square, we get $\pi / 4$.
+
+$$ \frac { A_{circle} }{ A_{square} } = \frac {\pi r^2} {(2r)^2} = \frac {\pi r^2} {4r^2} = \frac {\pi}{4} $$
+
+This means that four times the ratio of the area of the circle and square equals $\pi$.
+
+$$ \frac { A_{circle} }{ A_{square}} \times 4 = \pi $$
+
+The challenge is now finding the ratio between the areas of the two shapes which
+can be done through a variety of creative means.
+Our method will be counting randomly placed dots.
+Imagine we painted the circle inscribed in a square on pavement outside and
+count the water droplets that fall in the circle and square during a rain storm.
+
++++
+
+![](tutorial-stochastic/circle_square_dots.png)
+
++++
+
+**Figure 3.** Random dots inside the circle and square used to estimate a value of $\pi$.
+
+Because the rain drops fall randomly, the probability of a drop falling in one
+of the shapes is proportional to the area of that shape, so dividing the number
+of drops in the circle by the number of drop in the square provides a estimate
+of $\frac { A_{circle} }{ A_{square} }$ which then can be used to calculate $\pi$.
+Counting rain is a bit tedious and challenging, so we can simulate this using a
+random number generator to produce random ($x, y$) coordinates of dots inside
+the square.
+We then total the number of these that fall inside the circle versus the square
+and complete the calculation to obtain a value of $\pi$.
+
+For smilicity, we will center our circle and square around the origin and give
+the circle a radius = 1.
+This requires the coordinates to fall in the [-1, 1) ranges along both the $x$-
+and $y$-axes.
+We have no random number generator that produces values in this range, but we
+can modify the `random()` method which generates floats in the [0, 1) range by
+multiplying by 2 and substracting 1 as demonstrated below.
+
+~~~python
+rng = np.random.default_rng()
+x = 2 * rng.random() - 1
+~~~
+
++++
+
+Below is a function that performs this simulation and calculation of $\pi$ with
+the only function argument `n_samples` as the number of dots generated.
+The general proceedure is ouline here.
+1. Generate `n_samples` of ($x, y$) coordinates using the `random()` method
+2. Calculate the distance from the origin using the `np.hypot()` function to
+   determine if the dot is inside the circle (all dots are inside the square)
+3. Calculate $\pi$
+
+```{code-cell} ipython3
+def estimate_pi(n_samples):
+    '''(integer) -> pi (float)
+    
+    Estimates the value of pi by finding the ratio of the area of a unit circle/area
+    of a unit square and multiplying by 4.
+    '''
+
+    n_samples = int(n_samples)
+    
+    # Step 1
+    rng = np.random.default_rng()
+    coords = rng.random(size=(n_samples, 2))
+
+    # Step 2
+    dist_from_origin = np.hypot(coords[:,0], coords[:,1]) # distance from the origion
+    in_circle = dist_from_origin[dist_from_origin <= 1] # if <= 1, the point is inside the circle
+
+    # Step 3
+    pi = 4 * (in_circle.size / n_samples)
+    
+    return pi
+```
+
+We can then call this function with 100 dots generated.
+Because we are using a random number generator, every time we call this function,
+we likley get a different value for $\pi$.
+
+```{code-cell} ipython3
+estimate_pi(100)
+```
+
+```{code-cell} ipython3
+estimate_pi(100)
+```
+
+We can also generate a value for $\pi$ using the `np.pi` to compare our answer to.
+
+```{code-cell} ipython3
+np.pi
+```
+
+Odds are that the values calculated above for $\pi$ above is close but not
+exactly 3.14.
+If we increase the number of dots, the value for $\pi$ will on average become
+closer to the true value.
+While it may be tempting to just call the function with an extremely large number
+of dots, this can take substatially longer to computer.
+
+```{code-cell} ipython3
+estimate_pi(1E8)
+```
+
+## Simulating radioactive decay
+
+As a final example, we will simulate the radioactive decay of the radioactive
+nuclide $^{137m}$Ba to determine the quantity of undecayed material versus time.
+We will then compare it to an analytical model to see how well the two agree.
+Radioactive nuclei decay by first-order kinetics, which means that each radioactive
+nucleus has a fixed probability of decaying at any given time.
+This is analogous to how each six-sided die in a bucket has a fixed probability
+of rolling a one each time they are dumped out.
+This analogy is so good that we can simulate the decay process by generating a
+large number of random integers with fixed probabilities.
+
+The first thing we need to is to know the probability of a nucleus decaying in
+a single second.
+Because this is a first-order process, the rate (-dA/dt) is described by
+
+$$ \frac{-dA}{dt} = kA $$
+
+where A is the quantity of $^{137m}$Ba, $t$ is time in seconds, and $k$ is the
+rate constant for this process.
+We also know that the half-life (t$_{1/2}$) of  $^{137m}$Ba is about 151 seconds
+which is related to the rate constant by the following equation.
+
+$$ t_{1/2} = \frac{ln(2)}{k} $$
+
+This means that $k$ = 4.59e$^{-3}$ s$^{-1}$.
+For first-order kinetics, this means that 4.59e$^{-3}$ fraction of the nuclei
+decays, so this is the probability we need to simulate this process using random
+numbers.
+The function below calculates the fraction of radioactive material remaining
+based on a rate constant `k` and allows the users to choose the number of
+simulated nuclei `n` and duraction of the simulation `n_final`.
+
+```{code-cell} ipython3
+def decay(k, n=1000, t_final=1000):
+    '''floats and integers -> ndarray of integers
+
+    Calculates the fraction of nuclei remaining at each second in the simulation
+    given n initial nuclei with a rate constant k of decaying each second and
+    a final simulation time t_final.
+    '''
+
+    n_undecayed = n
+    undecayed_array = np.full(t_final + 1, n)
+    
+    for second in range(1, t_final + 1):
+        decays = rng.binomial(1, p=k, size=n_undecayed).sum()
+        n_undecayed -= decays
+        undecayed_array[second] = n_undecayed
+        
+    fraction = undecayed_array / n    
+    
+    
+    return fraction
+```
+
+Below we simulate the decay of $^{137m}$Ba using a hundred simulated nuclei.
+
+```{code-cell} ipython3
+decay(4.59e-3, n=100)
+```
+
+We can plot and compare this simulation to the analytical model for this
+simulation knowing that the fraction of undecayed nuclei ($\frac{A}{A_0}$) is
+described by the following first-order equation where $A_0$ and $A_t$ are the
+initial quantities and quantities of nuclei at time $t$.
+
+$$ \frac{A_t}{A_0} = e^{-kt} $$
+
+```{code-cell} ipython3
+seconds = np.arange(1001)
+fraction = np.exp(-4.59e-3 * seconds)
+
+plt.plot(seconds, fraction, linestyle='-', label='Theoretical')
+plt.plot(seconds, decay(4.59e-3, n=500), linestyle='--', label='Simulation')
+plt.xlabel('Time, s')
+plt.ylabel('Fraction of Undecayed Nuclei')
+plt.legend();
+```
+
+The simulation is in good agreement with the theoretical model, but this is some
+discrepency.
+If we increase the number of simulated nuclei, the simulation should align
+better with the theoretical values.
+
+```{code-cell} ipython3
+seconds = np.arange(1001)
+fraction = np.exp(-4.59e-3 * seconds)
+
+plt.plot(seconds, fraction, linestyle='-', label='Theoretical')
+plt.plot(seconds, decay(4.59e-3, n=5000), linestyle='--', label='Simulation')
+plt.xlabel('Time, s')
+plt.ylabel('Fraction of Undecayed Nuclei')
+plt.legend();
+```
+
+## Further reading
+
+- To learn more about NumPy random number generators, see [Random Generator](https://numpy.org/doc/stable/reference/random/index.html)
+- To learn more about random number distributions and their generation, see
+  [Monte Carlo Simulation Part 5: Randomness & Random Number Generation](https://towardsdatascience.com/monte-carlo-simulation-421110b678c5?gi=f86d4ec9f452)
+- For examples of using random variables for chemical simulations, see chapter
+  9 of [Scientific Computing for Chemists](https://weisscharlesj.github.io/SciCompforChemists/intro.html)