From 5439462bdf79b82095c0c14e7121c6d20fde85a1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Aleksandra=20Grudzi=C4=85=C5=BC?= <oll.dabrowska@gmail.com>
Date: Thu, 25 Oct 2018 11:39:32 +0200
Subject: [PATCH] update paper.md

---
 misc/img/breakdown.png       | Bin 10965 -> 10493 bytes
 misc/img/ceteris_paribus.png | Bin 11645 -> 11414 bytes
 misc/paper.bib               |  43 ++++++++++++++----------------
 misc/paper.md                |  49 ++++++++++++++++++-----------------
 4 files changed, 45 insertions(+), 47 deletions(-)

diff --git a/misc/img/breakdown.png b/misc/img/breakdown.png
index e0ce1709c6dec5a1ce662f022d96791aa58013f3..91914e233279618a421b69dd3f79516a3a628b5e 100644
GIT binary patch
literal 10493
zcmbt)c|6qH|NpxbZ6tg4+orOml*t;66eg+cj8G&Z8Dyuf8e_Xf*{Qd!EHjmT7?N;h
zyF(}pMR+qI%-EOj8R~ZL=lA%2|M>j$?){ked7pFM=bYDap0C&QgkCtW!?{g(8w5d|
z=gy)pLJ%7QK^s1AVFM)_UKKwA_dhS_U)BbX;2o$1K~fNef*@N6T7}r;plxE%HVnjx
zfu#H)6beGwLMQ@c3oa6<%?5F9f}l+rOm+xj*I<IioDe4`B*h0oe0&hUKNIvN1#wD&
z9|cU%DQJ&^Y+2o)z@31ywME&2I|)SqS1X1S!m$3FF&F~IITJ&u!W1yUIKU@uAyAdo
z5;U+y5m@cOAEDKjM6xA;I}@~V#yC4;2+q#n%5=`Ga?b4bmxBBYF#b#?0R<7(zDHQ=
znt&k?Y$4DKfz=?BKtO?K0)Yhn5lF3sDkh<oL}+a#v@#Q*>P%-$CaXt6CIORKm6_Sy
zo!QMK*+L{+6p4T$fkvcO(1_H^Br!=OCbK|_tpLMbfZ;4)78Ed<RRl~Gv#N^8tcOBd
z38+?rZ7T^}p!-(PqLm5m%<fF*Ze~?ClZikVzR#^P{rQ;wQp}Lu;4`2*W&sBD!fXW>
ziB-KjlgR{gVtop9&t$SXU^1DjKwzt@_7gr}#h|UX&YHPH5LY$p|Aso(=T{*}5;}+0
zynH8VEIA@@-#N27i~4?%V)n_+*4+7ZV!AFfAtB7cm>w}F>65c}w}_`X8QXCDVaK1`
z6mc+Jsm!)~$Ix4Q;T0=-hP8uFW?5DadB}TocDZM){OW<qeaHK}v$L~u?mD!j)bLpL
z^TayKr*2k&f>gN0pq)VoG<WKIBhvtaUUH#1-mpn3L*hXS;094Qe2$7Yn?3h*ZrRIN
z4e6ipoc|)9=QqbAH%k&1bUD9@P=)(8K`loP``o(r*ke1)QH5Q6ev&FBy>|n&?KCV+
zldF8y+H)6K__F#c-=orl56y9fGrW;3MaFn}hTyxSKfhO*j2ch(pPumFv!!T7ao6%~
zYgNU<X~mEHtM7FxzMr@Kj_%!G@t}m6XYf4hketgz%J?Sv9s})`l)dE5W$XbPpg6k=
zj0RW2HviJqXUU&OCviHSP1kBt(kZw@<nK$#<vXMu4cc_he@)Y=D)Onmux&VbF|0ea
zhZ=QQjRR);YsWEI%Fe|of>~*i8aA-nbFMvw;G~6fEB==2uslY6tkXZ48r^rQLg`N>
zwv){oM%!E^!pfq1D@p<v=cW>?ig?rlxya*?;#=fukAx__qIC3K-3#g}Gq19DYYehi
z?VvnCu5aVl!o0=T{RSj|ZPly$te!;G-)9OIxBqELQTVg?cg9I>v7j?TN#S9Yv6n4R
zE_7_+_mIMdrp)9wz&XA1FJ=}Q@4Z|mLN|C%-F$b&O5=z^z#cscak<_dh>G*bNqUM=
z4~%F{7_5wG1g;kG`P1FA&&Spxn;mOb_fpIHo_J~EpdGg780Z=l<w-czjy59KOco@6
zX-n4V?u(EzsXSCsE=jHkC8|L5E0-A)n{VIBd)%{dLv;1JbwpLvAoXQVUH0Lquc|(t
zqE@?;F}YUbfk;9wJ@sRxp!QC6BemVdwa@NAOVvoO?;kUzZ54|yN#as^Xp@XmMt#Y*
z?+HsM-ufwI_T_LdpH^9j_8L5Wd&=U=cVVb7j&C{R8=EYgA0V|wecvc?#ks*mI}00?
zKPY9(s4jjKRcpX}U~M};{zpK1rfs;~*Cz&N@3W7%%Z>k8eG3X|{|hCdwmK&RUE#c*
zl(~(%0ojD+2+}|s2ZtaKE*OtML2{>XkY7-3t_t*&_lLUQ2?|wMFsM@AL=1%f+Q8P!
z(A9``Q(HA#h_Fz)NzqV?=!?)Y?{hmp;@FYwv0V$7;K)r=&9&fmRBV$Zdz%(ZwqDQl
z-tS|OKmH$unz-qgE}HtaRQ+jv2KFMTiOz~=r#4lSH~*&Gq)0;7<(8Ex;>S;L!if(&
zw(p6s7e*`Xqzj;h*I%l%`eE)NLpHR#XVXBtW6gai!oct>yOP1{?Nz4Ocrh-E^j{y~
zw^kA9L0vqfQ{1|}YMvJDCX`CM5&d@kTlkbC6)VRLsi_j8_3u+G@ns?XhA7|fFEQKb
z0>2}QZRI@v%-k|X3%>7j^A<a!!%!~}!&gr`<?ALj2R>SBy;C-|xqsA?qIjNyI4C{-
zQXf)o5>8DORjp9kl314>_#`!V`JQgdP+Z{f^UNlB2mEZn-Ys{n=Vnt{Z+uR=Pe?H|
zqwY5p3YpLIX~bje+qU%{XEs^kSE{X-icJD$+Wa%x-<)icrqUf~g0;v-H#=45WBM&<
z`Pbu7mQg3EVmQGSBR)pzJS9Ve$AKwHR=c5{Dt6zeLoGZ%*n1z5WJC@7$VWNJ-rC_$
zxg55#;<~)#x-v+5MsJpHmUR-<>7>jT)*{+61Z;aUsrKDs&?mFmRW5ZI-35}&Sed)=
zPPn_8=0KAr^p<a?_i{95K7O&%Ryq4HHEeaZx?yoVsr?=@^WBmm{C?2CzAV^`x~hX(
z>D9U0XEr0#JgSLvLaF*T_2(uf3pguGxuTh=D`mm`CX357KYbuTvw5kEJqtV?M5I01
zO=IbeU`3dMavdt`6r))&bv`l8oFP#;)jjuSM+2(Z`Hf@tJ8kRL@8--&oVTdj+#5mt
ztUQikMZAkR9;>OGVJ)ysi6USZ7bO-;MhcjplYm0yn=^ECYj!(~na#eJTdG9rORSZW
zi^P-KRCy_}F*AV|CC~<P4e;vR<EVy~GQ03*xn@~z$}y*~6jA#`ku*>)X*z!LA<**#
z6WH}_uJ3+ze2V1>Wo@E+m(Q*9U<$#AbP(dw3iMraVVfj55h$<HQM!v=M#}s6J0hCn
zUtY>Q3B+|~TA%p*-P}&t#M|6s3qK7bd>AzF*&G+{o;VbbP|{B^K;!Q9xokjtB@R7C
zL{#Y5&FG0gSi}9*J!`fV8}Z`@fKn*Xd&ThQj{zg$fJskjkvj_liZQG~DeUuUYioBb
zS8X%AG=SNc@NL>wNI3AEu$#*>#WV7sGms3$)7@HmqpG+$S_d24%?5jA<|7d!k2<*U
z%{wmUk8d{i>Ss0ASZ>QSFfHg6=1$&yS-a(#w2!VGRnM_@=HYYwV5IT7<ifnuJrSK6
zj6mJg`){{C?y1d0GEJU1M~F}{8>q`qJv)}?DK?@s)rYq9o6#*3DdE*~-;A54bs0-i
zAxP5;;y8D*NFkh~_NdQiZt3&c30Q_d>g}g{Ly2j1-2VGrwB;X(?4*`bFEhUGIe*ya
zvJ65LTr>@;y{M>pd;Y_Sfgz_c<wZ3dZTws;Er+<seBhvTi8?5>TwgWdd+(+9w!=P~
z^Bia@8HH^8$s!R423D3dpTT<Yk!{l!OxBVwsB+VUo481!8+_EybQafDpQy&+u^Z5-
z9I!<i7H3vcgZJ|ks{Qmvm8a8?dTCC-cJLI=Uhz5Nz~%v|X+#o-hmV{w2u3o4keR2r
z8FM>H9}`Jsr8|UP`tX1x`4BKjQvz||gcVM|wuy~8rn!>-WYCS<-yc+xBtI*dxe6;~
z>Y1xZDj!2qGs&t%lADhSRU}_4unm0YmVnjkdRRm^zh4dQz>Zdm@8IxowEz79(sM<X
zE;nhw;KNrqy14`+>}?AWd?~_xJ6b8OBa(Rr!<~F1$)Y5R>T7Dq1t)F<M*KT#<*wIf
z=4$YM&`4*ab>vlTJLVzuJ=371g>3TWoVM%qp`^_hsPP-9H?!hval+`?jd&N8CdFE9
zQZ7qMjSjS&AfzD(@e4+twCS@^U(}XvhAqxpMAGU@JpNq#4(bS{f#>F-&=fXm=?1E7
zmMjO{l5Z%_i@nl8^X$3}mRp2*^h-!AEV3daqq7^#+K*3-4VK>wyH{76&F(m@ot(A<
z^rIdoo_J_f^jZ+o6NIQ`KCZgjqbjm^)F!CKjv)lgv%&6Z)D=W2l8`79Ir#X~mzUb_
zYm1(SG7o|!KQVJnEA@W&fxdt19E~^Z!gWnN7J`of!4~RFRXv=OR}UOG+w&XWPmNPF
zf9XY4I>`yDxM`bIRPG-$=2tr`fa}azh_kt59M`qwWz1!<nWTc#%eiIZNvSk_?N~d8
z6i3tq=i8w}e7)I*)a_5f*o+y|of5SUN|93pxzM)<8(rH^Kik}im3gu@xk6YfLscSe
z`@4wAmrX~KZMT~XibcCkU+{~+@GRiyc@xGb8zBd_>9dv&Ce-0zgp!f5_G+cw^MsIP
zps8vkQL6t_#IIM}RrLH$<F-3VTvUwa<Tb5L_zIpJn8bn35*`K$!h`SCGvC%8yLGdw
zhHu{eGj-jl_Yg}wB5c%~)&19AKRd;!jT2xE;pLrp=Yv9NO6+j={hEfWr-PA*V5G=q
z^5`f1BlKQTyo-o{e00+$Sjpi_ZfxpDeTy>&utr{u*5R<&di#x3l{aRLE=BzL?Tuv8
zPPEdF7EpRc3)dOuUvhUcL6Irls5<r~>*H0jQ=9yAgx>ZFZc7P2t(~>G7NJM$*K6V~
zefNuZX6L3zbJK*9tPez1<@!2Ek`+*u`l4)9mHZ-vz5!_6$<44AJ1lZ<y5ZgNIFE^K
zXeIXH*ia{6d3OldsF2Ie^1Pj=7{r%J;l9NJU^L;>vbPr*3#@_Rd-?IbrxW=7c*OF@
zlY<epbh8bx$OHH7uam-a4DKQ6LCAV(l@x2oO$)wi`qB5M45^Xpf$T+8@s)0?Cn_6R
zil0IKQkb78b<vrUIQj!oWcyy+)gk*FxauZF=~Il8U)k&DR}ihqgU<OUeHzO*ck+WJ
zZfeW@9E)&@@0Bj?I&3zEC;s$lAGdVLEAg7n9a=~W;1upPouUeJqD=zAdVTkhMbk7+
z-f0X7WIS<vj+|)AJ$1f=OEKOfHd62~dEd6QBb7z~8tJ30HJQ^-Rz~_(X$GAc%*|*A
zEnaHfYuvCM&VLOxIMD7EI*u(x4OGsV;d?o_DZdN&{PJyOnX<c<m!mdwQw05ZC}8FH
z-~vRgyap7`Oe7Sc84@e4z7ipbKSYfHAdNFjyiO5K(ui)~x4d$DM=;Xd`Xn;pI=)w)
z^;qRVOU|GQQ2H{`4~D5zJOfv5d?8i@fl87-(~8pmzpqG>Rj6(=2>{~tsx|=^3}n8s
zE86X=cCo_VTcwrKE6JALinOhFuPCKd%ng2iUmVgtGUjBx^=?j`E~8;tvSjMd&#nbL
z_;I<LBODHrK0C{u_Pgwn5h$|m>DBY=Gagi_^k>f94z%dqFaM$1cVqr|b6c0cZos7g
zB|J7nroDf4Ri&ddOU2i%{pMufi`=16&ZiQR<Y`4bHq~BS1#YM)JKUB9=TvxDN7S@y
z)Q<@k()x+#o_;*OdhGHgzUBUzCmAO<vQWnja}VXl{s#j}gI>N}k&%u=ulD-*`7k-&
zdR%)%>^aw|R%*pfsl=ASs%Io#yx2GmHXU<=DCZbt?D~As%OMeM5t-0{$@t=s#;ok;
z!~Fg$Mdb~~hE{Kva>n|LBE~nNNpGa6Wtk6mS$%kaa}cLWJA_Z^l{;U%b$&6QV%uSr
z?c&oV0h>V7#4PHrWyL?HonWVOrdM_tu@3n(M%omdf;V~4xsWru9X9x|^XQHCU@uB`
zlzf489)XiSGZ!0J=cTfOJ|O!o_%$+xIny+oDl9kh969j41SZuJiXjVr|4WBj$lVL+
zTxg{YXeE3fY;kB<0j<P_R@#DofT(5I9Bsa4KG9%_IuKa6U!r~M2j?UkfNZ#F*SaqC
z9rpP`rWo{UvCvI}Vhg(NlhZiBN)3vx+Jb|Y0hiC*Ramgk)WqGpBTY7vByW`@Yc4Eb
zrTE@TIGkKyzgR95GGg6&F3I93wJkt}Jg(R(sa%LEehRDT(Tfrfqq78t1;VMx86JF;
zSasEi%6$>QNIPg|3D1_PzbQXNWhs8bFmK&jwsDKDc~yQ?MYISHVg~MH5KhP+69*pJ
zApN6H_t)t%sevQvWk$2*dvY!QauY^N@eIeDqz;-t)|_{L*|IaTHEdextI@MNe505)
z5upE8Vc1u9(<zEMF9YJQf0+71kJPTJ7oHc*ZzDI`KB`!+&8wR~&P(aQIX0C{m#ywA
z8^2+IE4)O`X2lL(mN{&3?*^`2_sNLIPA3iVUK!J_?CA@WS_sdlrkDpEExoQa=9oQ9
z;>_rVXH)QUb%+6%c%R7c5gYk(`?8g!Ie|<DHl@jyp2_VnUQ+R&4};lcM;VWGMpN%B
zw2FBc#W?!c)i_kjxFGcYGYgj9vX$4-6oecz%x}dLVi?z#4Pq+gl<>rAXTg+O>)X-&
z*(L)m2iqq{nu)o8PE}BeG99<21kH+Tk{2Swx=o@&qUtTG8|o%&9L95;tYci+>$Ugl
zl8Ul#+NP{V90hw>-HkWu;zheN-LGp7IC`Q1AW9U-Iv7T5D4R1_kRF{@%$cnhyI9+x
z#H`(!9Sf$^%l-RIy>{B?w{DF662W2sx_vvc9<ijsUYLBDg{da2OnQ7UvjLs2&*=X2
z1k=^?m1~fB-Srim<1{Z;sE8_`S?c{<YdDD_k2l$c_a1KoLBuJXmmA?4Os9H2gQe1L
zJ##arZntA-7~hu?#N2jE$hHOns#TJ0C~`YICA?!$$jWk5Mb5=FYgS4HWuHI(Iw?xn
ziw1HDV_lQGOl#LGn<sd5D#^{Zy_mVmTYI&`YGpBA<DuZxE;k=hEA@lP4=QP<9sRjw
zcj~xZrA`<}+R^UD01YoI@wom`!S&73m*X_MBaEhFAjZuoC~9+$0T4aPg2NXMQ-C@=
zCZw8buJ-KVrtJjl`S5kmTY)hUD#M9)nGNq0+!JNSYxj!ymcDk;?1xF;YTM@YTJi4N
zxJadX-8-mZr*K85aOnV$7JW#Ka@o`&`==BqJe@J)huaH+Uv<Z@G!OO4#6{M=bv4}x
z?D;lpn=$wPTgz;@5dFgkn~QJNpQ}mGwg9!7ZzK=1u*-@cju*6k0(aW|_85#p7F9kZ
zcQaa>w7xx_wUFn8Nx`Z+%WbcyUYs47HkN+!d!DJh=W7eo#gmJ~`Hjc7H-@S|RP&nF
z>AX|?G}V!tqBdn&Fj81!5EpfEURp4qITqhc+?qIDn3_M4U8(wFMzD_hu*f(eqDqAx
z8~XV&A)W}CnC5vivSsS^4wJEae8#)5NhImVew~a4y^f$-H(Yu=X4;aGwLPX1i>g)?
zw2~Dt;<NHcA0Hc($I%{t%?SA|`uN`VSe?f@O_Jn%MX<H#O@bKp>sDBJ>@|6R`{j^|
zFG5zjDWv73K$GRc(F)&@_WML%Fj(3tb3su&_K|cB(pS=V9(Tz56`a*q_zH;&ryq;R
zLFhYs%qsQw-L4BsDyI`?92|Q+OddJdF_y}R++q(pdomRGDLi<&L%u1;x*~^bk-;pZ
z2r8KB^aR;99Lr<X{INS2BsB8G@pAEqG6nT&<;Lrd>D$!&{V<bvW}B0S!Rt{CD|I@S
zhgO@_bDWhoVV=UJ<#rW5qq^ay8?<h)(ki3Dh`pJud-;;uQ@=Z$QiYODy25BL%nR6r
zhm-wwY>nSfcXt-JySVV2tWS=&asi-v5m*@Um<mwK&8Z)##e6yUC`;qKHo~)7HExWl
z@SbnMUF^&ARfc{mwGT@U0C4=ZHxp<CzIQ7?4J|h`c1w}J-K)AV5xVlEz`}^}-1ILi
z(&*_J3|2Q=2TwF_e~`@nLb=>{C3kV2zVn)qMp-=JZx_~NXIg2rH;?x@;(tM&Y^&NR
z{R_dM&7~xL<YVk<27^UTMpA|059Wo`jM-+^P%>-HcmX!aj!cW?%4kqu{3a1)|G*}R
zvvIGR7{8d~nIMGn7lK+~K5+YjBB#Vv3sIbe?P>g=$*q}$d__DFRDi%%p@{=AHCs~D
zxEv=e?Z>l>YY*M`SnmySK_KIJYQEFd)#;jJ7Lv-XqFKj3^3^t19N`j3;XX{S+4ID|
zu&MZ9-h7gE;-67Pa!E9H>cca?MLa+rz3t-p#Iq|~H|&w$py6x5dnGGxC3>UUtseJj
zVPiV{nu!=|a=uC70{R3!lG6D{QK=&i9q1K2)w!Ktt<VsA{=<!nH{{u$(XX5MXI_gT
z3K*Gd$<d0R6%4uij7>FFn$Xd*xl%@fcbYbFi#aB@BKV4gk!E8upKnEv`|CKT3dtmM
z-tnfzsg;`6q=2xggqD%QdLowF<=F%mn6S-JqPMUhHAm?dx0olzKI!?p*QaI0p1=*~
zXFB@1&X;z9QS2@@3B{KGrn3bh&pu`cSYmP)<*yfV#`H^tW?`z`XzV_IwMCy&I<ZpQ
zyJ`4q*S@g>xqKi4-Qh2yhh}Z=0N07bv7RP}`ur2d->1*$HP#_n?hUA+KDd0yebT&L
z$p6c?Lc+vNh!tJCrqrIsmA=&L(vgQ3=x_g$e!ZvimV-fa`07;RjSl~3!|L@u(?A>z
zb<}~7XUlhyeya_>q~C6~wdRWI_aO$g?Gi?=g+uQ1sD-m;y*^Y25Mn?YAD<Uq?>f{P
z*|7ZnT#2`N-n?akN37VgVKlzzDZDq&H^GFT2DXj+iiaJW)MdJtqVu_FC;&Y5Yt4Xf
z+dWv1+OBdydJVex2%}pL%FmX+%r5(Fy`XCpOEG}ulPD){DE4&<ux8;EKU9X?-4&U(
zH^M(*0*-R_`ydAI1%m{+B~`jhR-gE3T>4E*^9lMVRAxD`>~VaF5O~klrb<LQuCVMf
zEgs~4M)(bz+uGBQ?C#V9Hk>&00x@34C<(k&=BNI=`sQmn*nYF*x{Cg*CvrE^k8;9g
z823F3SMv<glQSvbM)#*MV`Ebr1>}>Wu*-jeV7O$q%M@!kd;I=d<}_hDwcWO{y+N(6
zezf^hE9qofUU78RWx2^DKW{g&`i(6Kew$7R?|A&tN2&b>5GtH283Y!ePSwxno!z;e
zuOd#aHaFg4{G{Phe}13gY-~qpg9$#*wEyJt)LWhw?I8!6G*?Dy;EG-~s!zh|pm@m5
z6FO1e1(L0C8KtJWH<TpO<Yi`)h~uhT1ynjhk#;@RENkp1FA}Q!#O$t*pYD;uZV-!f
zjaA?rf;j(nGQCC}LXvB53wmG#?K&D|Sxse39$4PV6rkJ=9lj$=71Y=${l1uc`J4UW
z_3$Ws8K7hUMQ@s~@~c^dn;k3earbd&jP{Sqgb=W=I4|v`hACyMZ<O9PmwWkV#&tdK
zT%_=z^U+{RG=E%{{OaeXkVjadG!xm$o~z;5672l0kJlx)PAia4^$6|k-qB{ZmZ~1o
zXY6lKqqipyvIz)UrVizg8|kSUbT^UZRpR8O7ygN5?jbI12Lp~0+rc^sba;?##{poe
zwF{3_>~iGOb}fGA9$Y$r49#AruCMssLknFo2A68i$)24)&}2;=t0HfHc!rhZ1E9_J
zXrz6D11v~PqxU+kX$uKSAaEwB{GB)_DNBegrp-pPQ)vKJ<7f|uG!tgws0&oq4-?o#
zOsDRN{@Ll@{<of8kwTh9OHC>E+r5LqbO{J|MYj7uhQW(;Jw>8wl&Z}_e_BYs#s2xO
zmNqeFUXAvkR{mg!RM9~FW1VTI3&KH6i{pnu2A_kUl3t)1qAy$CbAgdv1~$OK7g_x(
z?+vOh=V>1gOc)(pIl)C@#;}ITlwZieDj%@kqH8Td$tK)#qz;ehd0l-W&~jnFdGGv9
z%7@>V`WvkE-+S5|KST-Yc~MZ&pKOQ4&2zDVS)EQuF4-yfM<7P5<GpdPk(G<tBOQQP
za|g9kL3}rL(`I36_FAa%vL`d;sYznjCrk>q@Z!}$2a93jxKC;{AhGY6U;es#*6vA1
zpmwbPXai2O<WgSz^NQC{)Xe)Zb-f&^vU+9S1<xsaN%5ziS1x*}T2GpJ(ApommB#e!
z$uRSx>U}Jl^xoYoi&so=jI^h<1uz|p@>-R~bA0u})akSjAC5k}p<P=3yrFj~%w5cL
zKKWgn#(s&4tCjmjv8NNV93!>m!>O~agTm9=sfDesm3}hP9`^HE+AVd+NHL%P%6n7%
zxD02sn@ih*pp|EV{OaNM+qVY|kJ2k-uO(YB%(|p!oeeKqmsyLaIl#lx>J4OK-AwzZ
zkC=9|H63{h8!(Jz&TUo4M5R?`t9xQC8D<)1#H4szyuUQ}4hFb&sPR%>&g9Rz^mnC~
zjGf-a`W$dF)1%RDA0=p3tWMU+nZFegFfu@!>^j68D}b7@$Q<A-K;n4~ZmhYr!YGu;
z4i`~=B{R_m=^FzzwJZq1%2mhykqGM)$NVeqdI#bzZn#Y!<b?qY*P0pT(0M;^dRROp
zpQA}hCo292KP1SVVLA3M*ui#c;^QP$7=zXb99saX<)7}r&z1W`l+Chn1P}?<h}G%a
z@8v%ezduJC#zGiYk}ly7Zr&eZAuT{#`GlsosH^N4aK0iQN`H=6wH?_#e4^<X)k$I(
zCp$oJD3E;{Is$Sc>juV}IhYm5#jmF`{x`<zlhfJh<NrZsy}K&f1VZA8{UQJ4&em1|
z*GMkYV|k9hX|%r=d0H2@H-8-Da-pYQtV9}XLo;Z*u*RJ!?AAF3#_D_SXOPR{%+^UP
zkndsz-fIj)$C{@8P1TjNl41Y9!($u;@hW?Df3K6B_cc$H^Df|#fVQkNSA&@^hDjPR
zwshL%e^3BF#jrnyTC+^85i|T~@6L$xUT6EPPhIvXG<w~&%W55A%Fk%VykYKyl&{q5
zI4Q=5pE@od0S;@lu+9P`iV=tlO_y;e&jjB7F0`2Dg{jUh>sD+z?6Z72rEj~Dn1Qw+
z+J<kac=X4{Y62?(XfRC&((n6+S7)c{U2id(RTGKR=~q6i+<HArlfgqhbyNn>WVAcs
z0Pd-*30nBy>?4b{{J&N{>jn9Lmt`Y)Z&N3W_W7q!qTLkN2r9k~*)3GZ9|pFrW)VO$
zu<Z{Hn(7jcvX_tWvOEY0qy>L)p@24u^Uwh$e@k~=gY0RJncfF{<PWXe*}A2IJjj|6
z|Cbg{VNtAWCf$-&q}RM===s$)VLwI<h~H?l+5D=Az59!LPs}fk*Q3H)T-w$0wyf)<
zq)+@LlN3r=0kn^a=Ziah&EkrEqH6ZN>zwZJ!@D_Z)V@ca|9}KydRpdb^|@tyzxI8W
zp&R@%^ji3zIgT~nICZ#O@r)o|WWXlTMwu?~!|GhW3muyK&wU#36Yh0X4<&Is1`({_
zO|Uux-;R5+e*WU0|CSXtG%~;Qk0G!R|D>kZU)7@$98*Gj^?ne@>jD7$_L^+GVt+Y~
zzg;FEv407UBKym@pM#v~nghxw{MY^cn~^^-04VwYUJ)3&Q-4!^z-_H9FiDG$SBz1w
z^gYTokZ<A9au6`<KkPw7eSE&^VXwN`|KrMYF8IQg%p*TIJrm|{x}O&~AhDO9VT^DK
z`QOZn0!U970z2?FqKbs2nBdOwov{hX`Drl}f?qh%^&dXGoQG1A>$^^&=xFN*kAbZ2
zxgWXgwWl>>`#+?F@@@L>_Pk#f!2)Zn^AJEs%)EXmkZaf)t`!64D9#!1i$R}b0_<rU
zp!2~9bO&OcCpvOw{ZP?T6*z>!I#l#MNF6PoE79=KbMgJf{-r`-OPw0O@BbjaxnEH9
z*3EM7Z!P5E#g|k2`WMU}ZlBfB?}J;uTEs1FZn1VPv^Z$>EezW=5F#<0y2^8j+CH@m
zPYN9chaDyfmn{OL;){A!XSC%fx@sc;0CyiFyAu(!kuQtyld4yQC@*(PpN9XK5K5l@
zs=J5W<Jh?KTUaw04zrHTLvGLc)OwsaAGWfTBA+sQgx>5EF3!16)mk>U%(gyPrEM0`
z_Ti=!fF3ST5AD&O{nK4kXM)RuI*?!WS-I^l5#32sAm%A?G-KJ;4^gqE3MGBm7{me2
zpv>KCy9^%jT&$-XOGxq^pRo#h>c$If`QrsaU$4kYDuc^(JN`Uj<UIGcZJ)9_dyPBa
zY52PNl}c<f5iec&^ya`l1!dW*+OhD2rCOv^@Y3-6w1(v|R0^IB$*{p~dwBf~p3JIw
z)Pc;uVDYTws`C|hu;vOEse>2PmK}HwdRnoHf{}O6`NSxm7ue8JXC5P27IC2*$FFoG
z3*0`aF268Xad70NSnfuc*N)G*C5*^Ls&aq1jWz5m;cH_DGcogmR3Vt{^9FFBM&iv+
zsY0>~`DicJ@iH0td#So9YQFdNEc+i#46d@h`rW!g?zl-d>louX?el1&)|I>e0~UuD
AEC2ui

literal 10965
zcmcI~c|4SD`}dR^-6Tp;vgR%!BRAQ{Izm}mEEPkk$WF%6FoqV!2uUkhnu*FbiIQPR
zLb7#@kTewGvWFS_@;is>xu4(X{XFmc{PAkKK6A}=9>;Z_=dql}aeR-MBUYvYd}4eE
z1VX^v41ElN;DQl|bze7dfnU}Y6yF5brXv<MCg2u41EUZKaRfpRf!K>cXd)0t5eOFq
zq6~ppL2w}ve3l3S0fc}hLJp76)I?~yAT&t`7x1A1N-l)J9|*)B`fTtrzy*vGK*$Mb
zX^G?6fSnvdKn`Cd2fi1v*H{C3O@s@FjV8E~G+kUYUBH#9Ndg~+r2xW`^XFx0NwW0H
zvLsbn7O}xpz$;x4U?_(Y5O9dVABo{YrMghTl?@2IEWNxeNnT#yljW6F>6O)qmqXx-
zEb(l1<jM+36G2*iA8C~}$&y5JL686s4owz`qzUdxBr5nvqB2O8Y!ZV?VlYSyb~2(W
z%gZv0!<3XovdpT?%IfUQ>SR-05L6dUDoK+Hh^P!eL}jq4Y$}z_F0vFTViy&$*_9;A
zN_J%>n_Y*9VURQ#Bo_u1d;ntx7|URTE4wqxtCL;X$!5cdBR^(W*mybiwH<&vyGRZ&
z0xZ}J@S$?Xc4o2JU^SdK0N!jihnmf1uK+o%fF-VMZ_cFwdH(5Vb}|5g*i^;&zpmEz
z$vFf<8ext$v<Z1Ini@wCuRU2Sdg0oiANCyVlX#QzWe@kQslyMpZ$O)SyxhudnpyOS
z*C?vZ<M46brpcoh=yn)1*5qhj=ZBR$_d8}fi#wS2Q&Zf+yRBWAsbj1pwVBqkkulY-
zBspuNO?o}DdN-G5-}0|Re2j#FDxrB_bC=0wRd699f~2((n-I`CKSTrPLfnMFf6S#d
zqbjA!+gXpMQc|iPSA3Xdi6MiO_1`lwi-Sv&&VL|kk0{WBpVrZC!fC}VC=V0XrL%t_
z3^L5H4?C+h#2Oo8BvDKHFV&}YObxLJT*kRpRGW9fi$?U92cdVn_z76W9Vvtv)wJS?
zfdW{xbmVDFs$7@)!d?BTk{OpP1B)`#2R_k#@dwK+{K5kk&eezd=x;{h1$K&fDbB7#
zNXHvN%H?%9IF{*FTvneT;t+PBDRku0--iass?FW?v@<fJ=93Ltgz1OH^2?_;Tq~?x
znrm$KF=<vP;~{fNM~gwdTE%c2g`nXiShe!y&_}0d4i?zy{ZhG)dq=Ad&vZ;V4>(7x
zcz-2qoYh@H?=71nqQn!XJ9<+RkmZBkd{ANgX?Rn_)<dGb%kWV(b<r!c`&H&E%Gt#Z
zX+lf;lWz@}3=r1O=EdQ=dX@9TuA%yFls2R%Sq(S)lJ1wxR=r;N>n|!0gxNzs738AN
zm)^;a;6IM5h`r^9lKg{?VpX*DV;1#FSg9#GUPh9H9qK0&(zfr^AHd*0&eX0FW?XDV
zjrvcKRq6T*Gb{7-6h~HEyNN#L9%bOs`4y?>(9#~l1~ONMkR`cRA*wDfBwq61m9fR_
zP@nDPpXOtkqkiFYDI+brAxi0X8rKKjOfsRpH)+_cE{+=YEg`5{d~vhBSkPP|d|Pl%
z8;29eY)?hzVn*~rugwgncWkUDhY}p=+uM7O=px1*Vq2MqYrfQd!s}SXCsmVU^Gp0(
z9dRLXgdMJWDJ|nR#N`n?Y(Hk=hWN@c%`zSXMFkVW8GW4qZ~ywKwDU_oSf6_PjtsqI
zw<%Q@@?+n(k8704NzO*g?J`=KSuXKS-}{w`k9q1mn|vp#{16eYBd;V;I(QMp2QD4t
z@oO+*<9afefz;vb*G5=G)ae))5g}uMML52Ww+%+Tmj12Z+X7hW5#=FS73)3-b9Y^T
zuNmtvyK<@~Zs*OmrFP%u=9gpcXKQzye`FiXP}%^ET3msLWSE!D3RMNjInh}DU5!m@
zkI_=@t*L9@iTRQYC8C;6i!=>qRxB;jJ7N)F!8&>jd`B1mq%p$kv^>}%ku&BBMwO`j
zFA@fzIE2lm$u_qB;}PzChlA;vSyt2cdH?xHm0pcIye*sLA2|rc`Uhoc?ZH(ISjn}=
zUxg~;zH{}COiwfjTKi(n!AymiO=?6*)zbL`Z4`Z`P7f+{F%s3VRdBJ78H)Kitwwn$
z#hzKxk;^5RULK&lEL4NS-5CGSS?{l#lu<Dmjmda(Jr8Cd(;6kGJBdcsO3hNd;+I3l
zD^p{XrIHp;rPZ}8q}++$$@{3|ev~9C^SSB3AK_o!W<HyTXG--+wp`HdE0$w;#i<@1
z&JJ~tZ#o_9+JbCh*|5a*%|fzncIh8ATNsT|bLeegD9lg3POxJx?N7bOI}${dL|K0>
zUC9{QCM4nhwx@y7tBF%f9zS5(oD}0!o#E7#RxD@7Y|PZ!Grw0pj%+{qY&}tLf1b`Q
z&i2z{oerc$!(1&iV=b^k0VjH!F}CAq8Oqn1=z|2}dwh&_E8E_tv2%(td$3Qw0+s0M
z`QT{VHyo=!A7z?<mueG!J-}ZfV;@%^kg;=gz0CqKP31zX)t|S{XFTA6S}8|a3N@qc
z^7RH<fSubpsCKlyV7r@J@>z1iO|ltFe2f2C_Ry*X^3z-)Mfc^)f0GkhbBtFN054(3
zRCE`n7x*^!)SO6)hJ&&UvFyE~D9WV89INnbZr$-akr&0#_6Y}}oC}hljIodI6IEkL
zw!sp&ae88tJyL4nBJAAPeo>yPNKe0zye%x)Ojg8AB$=!sdHFb9A-Y;qr$t;Cf9qDF
zNkY#MTKT~q{lBtqv<d!Pel*NX$fMT0NHd!`(zsue+<CwM7VKF%<YZzGbv9)<luYN1
z7jv)ayvi=^$9eXIdrY-m+Kh%wFwtBp%-2MD_;YhQZD$nbiCrOGj_Y_mnszmwdvKB%
z>tqrK3)+tvV|(0%Fep1>Iqp!I7d8IZw6^X<J71gmaqR3RqK_MAowvyWlY$1=Q|?wV
zR`^yr-yq3GaVm&tr3iM{G!cF-SNBvH)2|)${_i7JS74K-u6vF;?|q+Zu33Z1dqSpc
zj8jIwjllUGdmn4<#w}zowCJ?#e-++P9skl&uN1F4Rn@XniK>|4#HuN$n_x@$l6KoA
zR9q8c4yh5H3`P<co9K^2O(Eoa$BEa@UAMc%Q6J|ON0GQg_K>3BYt+<64rfEw`T}?&
zdjA-7B`n&fh*2AHOs(v=)Rv_qi#ktE$7y`8el0DQ`q5}u9J7&0?b4yA5t|0!gc->%
z_h%>NwL@7l?S<26RDN>7VumDe1N{u~VaOrff4b(o@_0WEYxR{kJcyc_NXR@JBPsAz
zhL#F81Q{F>XZfK}3x_4BkN$1x><pdPAUx$IJ0$Z!{6FGT8sFXJ4ZmmAz!j8oFd?mq
z2r~_n^ZXAc!jQFG4+0k?jyjd@a90b*v7}*9H<6Tlrz9S-toKq+!+J<KDs6xJR3GMH
zt|Yph*Ami^JSS`>LYAM{KmTn$#z`e${%bp`dEpv?8p?g1Eltz&qCLqx`z3?%V-gj%
z3&+J)&Yxwk{19H5W>{A^F7Uk{GQ{EySlZ`8+25~zns>trFD+S@uf$eNTpU&0o5Kse
zIMaGQTcVeT)RZ{XN>MvcCM*|+Pf?|{D>W%MMCc2;_}fTwdy6}I<=a&HWLf(B(w(A$
zRhv7T%Wb={yVGvq6ya5JQ~4>DV0hm^)ymw*=CFrju}AF$$-`H^XP5pB@n4snClq!q
zUU8lZFa7z1i+s4nnU%a5-<Q-q^GC(0nQG2t*oGLEp=g1~pb}2Nku}*c7%jE1ekW~Z
zvObVXUfq!iuy4ak^9j!L%)5SXHdbpEJ`rMK3lid4dFHB5#4NePzA=SgJmFjHmU@=B
zP`h%<fBTW^>wRmk&S!^iqldDRlg=$H`-R2Dugoj<4@v2*gaXcAYV%t=uZjra5q#)@
zttJBjSfZ6m(_V0&jaL2<5T>>=k)DUDih7RoWUI^YOaKe}7$XTeu!ai16Bcg{;K>)2
zHjy19+(d|ax4Ou3Y7cfh|MBbIkUVu?7_E`ie-EZS%C+UsPlcZwU~_tbu%rJzfpwRr
zwfY~d%w9MxP0QpMr)TTsE7myWze7~4#E3qD4~{x+MRAjhjX0hY;}~ci3FmQaZs=sQ
zh>a>P8otBvRk_~$$s+Vlmj~wr+^-p66<+C@3bqpU&Z)LpRfPMyT22-kVmo^pcD>M_
ze?eK?6RR42_R{{*8_!=VJ<0fC0X(SpVQ|#dc_&e&0tzVJNzFb|&5J)+2Rr$vK7F_>
zL|;#|x*7ykOV)*&j#T^@QEDp;sOBPEvJVeneTWxP+l7<!AXN`vzY3#oj6v7N$Nfr8
z5+uLtU|VeQA3qeov9TywwunmhefF;EdyT4P^LpBcfk%>`?U|Iixj{A>t7l3moB7)G
z_O5loH*5B5N&33XRQ%05PE%2m%$u5pMWpcQe)<pA=c8?ufc5%63PVT1tcG{ZM>mId
z)p}@nM8a(~_cLu-uN0g6;f+CV9J?%j$Q^o@Ahip3sh<T@cVktv{oQ+Yk6Xt^+Li@^
z5#-|!@hZq6=(nvpCX|zmAkPho8h&3xDTE^xsUGs)nLgZT=XNjyscx-Qi~O#7Dboaz
zp1MZJ{-_*Ipq0$OYA2d__9<0HRj>g0@J8lwY1(f8gOPCD1yOqP%-j!*y0<MhGa!&?
z^#`$wxC82*@hJ9vvIT!__6)Jy$KTa|ap;A}qdVVhW0&Wmmdj8AWUA+blhQOb*_h?<
zDno3H8nHaz-!&3uz(RE00FM)XcMn~GhsE4P8lcRhNbM>`Ox<$1989lsVO~;Ox&upV
zZv)iXCIdg53B{`C&bMUG5F+9Jp6i!wgD*+be9X!$+k}b8giVl^5Yqy9d%+lyeHiv+
zVscTIV#i^*T4StdZ^LEVndQA(Fv&h-`|*}f{+Bk9j~iZtvtsf0TuxgiH|>35GxdzM
zf$t;h>?`%&%aU|`J{-$R^|2KScc5<_3WwErEl$^;u#h0<T<-5Yhl+rWBjNWMi|Q&H
z?U=k=&~3vxZ<p;vy?ch_V54hr<M5Bn0b}eg16JjU-MIT<Qi9MRn88B>?D-?%Dff8D
zg4|@qE0djX)r9bS?UZV6N5Vc4TJuM|MCrIQ$mM<L$LrBjq(1UM9WIz?wK10_$g?(n
zzYu=EEVAZy{z==7XgPkgltnvg2k*^AFCpejAl7^uuW*xE@yzGz-6te1bROOCsoX0-
z7K~<fzTJN;y4`Bk9GEu0%^`O3hL52U*==}S(Y@DT9xP!8G{;ldu?$;GydHn9g)=MT
zjwW{D`)`r*1D;FjwZuo+Fnoop-j%h4SR-E^644>YN}}Ecb2c)UyN`4c<gAlXyoyhB
zj%PW>xNd7#Y`HLbbmtZ_e?<q35=m`_q{dOw75X$<QB+eoAt8;NX=?2{%+}wD!{*#L
z88{F>@avS4;6%l?hG0%2J0Q2R;ii5VO6@4BR|E0zrp@%5f`oy-P3}U#o+xHS$v^43
zKdP`UlFvF}D6?fKYb>zY_lri!KAg$KOr-(VqlikYHFB$kC}(v0VdEAL^vaJ*)FfDO
z?-u$tqL1h+i`EmT;$Z#7bG=P<y~M7xtln2U2a99QNYe_`khs2vIzA|;IE;@sZqU5K
za^sZ%W*mrA=G2s~Z!LcHyaJ~>^WlU6_AKysdY1gXGjKn;w$-zrp%#;mWlNA1xyha4
zk3&>^GT=Xjm<C^}$J7^s!v~jL>Zi&^{U!#LL+_S1=30$8&yfZ&;eVkkKC#OV&)g>P
zA27fMtnn1<>2GjxU6^Z3{WN0<;oWAG^=Y4&-vuWGdj@4AZG+FczmRMCBtwhh8kw%J
z46$!qUg<W4MyuPbP6Vbe1-}UmnBYAvE=`*#@^O2Y9}B<OsQJogrSob6(?kRRCTeKs
zf(sJ495YVPex8C-oB5-2s3O{9lAPZC<wMcI(*%BxL%phUmSp>uiG|^bLfiO3%x08s
z$s)d=wqJgzr1xQHn7-V62qnnSKR$f#9lnpo8QknggTiz%V!qbc;_cx34RYk;%{W%;
z!lDc&)k7dB)_*`FaHHIYqKq^(8Je0gh^v=h8T%gBlt8|`NS2$KiuJcxp75fc2pq`H
zahiVo;qoblwgf8z_JFno_e`)4sH=6&@~WT{`r*MPYKT*jkn$#KTzk%4bb74s_h&7L
zF08GT{e`{eyJPRrj+-dt9Dx*dGZ}9-?<F;@yd$!gg{v{z*YsQaTRu>7s?|^O9(4?C
z56s#$C~_6%<`H+4TT)lCIEqzbUIHeNw}sxjPQzAzCt5=Qt&yxg?c%tDIL6bVqoikB
zE1cs`;-o`#iIP-lGoT$wgvWzAQ+KfZMywzY<w$w#^rP-Qu9dBxAS=^GOI@?Twxv!T
zKd*U@LgfUfu_<KFYgqnMNL(+UE--xL@fUKIvG65nZOk!{pX)@8d8UArpeGAH1zyvu
zRAcT9t0CgZhrQ>FI2PLg#bvR(EnAV$&Ip(iVH-?w7m^?+TyF5m=1t0(nM~Q&G#l4f
zS!BGCv$iV{@L6e@c`vavC;fgG)6PBVOue+ZZ-a3!+xq}}S4I)hN&AC(6nqRe3p#;y
z%3&y`@h)J;_s;oEi&WHs^zK3n=a8RN%ged=jYu94`99q8j);73+}7nmu=VB38Jl|2
zhJEPzrDK%v%{aI~j`m3&!-5UVjWsYMRo+`arpl`t?M}Y>o}`wO>wGOaoR)fy|1^&Y
zwakJ&5+@&=64!MWniF4|=(?gK?5xL)qLr($VEm2>Q~fVr54gyBcT~iRR=nf+FraaN
zsVCiU;*FAjz*+t4l9~i|{fHGdbo(gT6m#kK$!fq7n^&&MG+>oqnERIPIg_<@exkZf
zow~76O6SX_ffSkUx;~fSX#MRdzwoI^*?tO15=D6Ik#g@bL2e^Bejna@)|`dO8Wf`Q
z5Ung(A|$dYQ)gj(aa&t-MY68Y<ou7Gb;#c8&IJV%DvCR3Pt;gFm%fEu|GLsRNsLJ{
zAC#hfquc;%`7tJ3mHFI#Vi)zbxc+OrpkQ!REYd$@bTG9JgfRZB3u*~kG?E%OnVMn7
z3cB_EYMfiGLPtqKTHuzY)`dE^UP%-#A~ye#Y3=#!kBpD;VB2rSAa5VUfM_GZZ8$8x
zN$;TGgYGXDl2QkcVhb=jR*^5X1;~oTmRj<&AxUP*C(ApZdo8#3+6FI=D-vq-f4FVj
z*hHl{kN6bo%V{gr8nPgUH0|=M7lsYc?Ps_UB{7w~^F8uH_#(9zu@{Ay`{vQ<zU2G`
zqWh3&?-uF#2+hk|yWFGSToiC9GG>WM(;UUnQt#jIiS7LMFrMxxgA)+KfMi(kkLdP>
ztdsjVu1N^9Qz+Hr)ZBw%y~9{kxH_>szQ{Qt{|{pM9^mE_;-&N2DT?dJRC6)(U6SmE
zmzF^aAO@-4j9xvdPh8iyn0Du)nn}^t#}AL4sS#ftjlv1c+c9$t6Oh|XZ%hwEwg|{`
zJBAfM{6i>pgJzkly0;fp|3s9&QW;3h7a)$|k}pDvk?{I(iID2IvqyAAFvX|*2QQh>
zKh3F2U4A@}?RMLJ=)`7xlj+z{LcSr3ZCQxMN|b6|M`~Ayc>8CDMa`YrMK~WBlZ(dU
zV$B<ek2h#cB{c7>uJ*^)wtyvWy;JDK5=Oe(twSP3t0i%9!K?!)oXsv=Ut4^L|KgX~
z30A%B<z6`cu_5+Fk&^ZI{Qb>n(Q5J}Irg|s($R2t82Oi*ESu$Nk|3onfxH4AY-u~K
zlJCzgNmh(<mKNJwvTw}a*u+#>%XHx8)Z~6evPL|Ue_U-Nv(`#g87E21Pr2;qp0FIZ
z<U<aqQ^a8}K?U12g20v@mffY@9kW|@CoOjA<oD<?qe-uLq^$NP>V3;A@I`kuv@$Nu
z|J9EC1}IiJCz&#(W$=6msbZ>3Y_cC=BcMDphqF-NNY8#6JoO|UshnFO(vHg)MJa8T
zpr4kzo<JFp^mPnWCg%6<o7q70F-blMWxfn^H!pO;p0`O8Z|T#d%|E}fS%^t0nw($Q
z0KDnA;kA#AZZ&!0PE{sKX2Rf{-il)#x?Fd4{P{iaU)i_35Iu^0>Uw<y{P6<eapP6U
zapXeh_rlIvRefDLw3xk%W0{+v+J`-wIDZqLOZHw@mVv+04IL&jT}Zs)i%<5gjWGRY
zK78Nb>z&?x3knMA{ucBzbjg`N(eNqr(YYNDzuR068+`gATkb$qD&JG>GCSS&rIE(a
zGJE}h%d}NsNa=9SQ$GC+qc9~Hs?ES)E4`B0@PpTaiz7}tLaC0)e?p}#vuwvL^jAaS
zZ;CNFv?u4)8~@=<z>sy2RM7HgAynp&Chpr2ZK*=#mAMO-zD5te)jeGd3Z<!8R#^F2
zRhfCjqj-ulU9>-*V#*(IkCJ2N&~7_34N}{~nTD)~Uxy9=hreoR+~l3Bf)v6_zmjBn
zC0CO@HOCG*v68a*%@q#6R>#K}H4e<Sxx^A^VUhf3)8rmdo8Y(CQW7~j*MW2<ADPlB
zuZ}%D;d$h+eX$|-k-SyQUYuK-1=cG6CHj=S5sQ&~xE!nB^(~SaK4v{_JaMG&?pG<k
z1L?gE=7~=)ZYE({B|@n(mgdQNQ0Z9%)}(Vv&p-eQ=OVkJDcbtz?IuBsFIC?DR`q9&
zDP<oqLWbv_0B^j_g8QBy8;x$aK|oCN07sUqh{I0vlQX$r0vsC-C~lDRctcmpRSIsb
zySuk7%*tnX(lq0f1XyZeuu8rNvCFKLXOq`!$=2&<Q7TeL0-{Ucup6n%XHG0_sZMU5
zP%8h{V&1oGaV=OZUFI~b=gP4IiY(6ONa}c=^;=h^MGxU+nK7uPSu}bK;=Cc=Hxm;^
z0Wd+QXsM3&A+!-oY%i&6<=)Ofh`%&vtCXI3(D^N;`&|QANw@!w@AyfAnjaFUW7(&w
z+wBl&YGej{+W=en<!~*0>1{}A32sm?^i4o<(5%J6-7XQ~F~&Q5T6}*j*txnnbJif^
zWBFg&3po+=_8VEiX9s64J;5FCXus17N57eDGD)`-T|js?e;^&0Jb!`jLaup>WulMc
zh#m4x-ZAHQ^d4V>Gp(tDEWz`;XqP3K6X3Yas{D4~QQQq4$dU_02WM2Qka<)%&Nl1I
z7F4i9Z4<niV-d)^ZO2(r^`{+0Ft-BRpEvJ9Q!95sneXe2u->=wopf%U8Xx8Zzis0L
z7H5wH-XD^Qr^tGjsS)*fY*92^vy3(aq^gu7Cj#45eFVYXP@*s@Z|=*V#I$3%!};fT
zBd@|{Ii`oO>(Ek&c*;)8DwhXN(9Rr-lHItAR{{sj56JJUiMzuCy&!c(6p}r;$?XV8
zLO9jlbJP&0<X{^!0Jm6*7Cz+59aJMC3ylN9>;$->0eX{}j`_h3+udnN*6q#>B6spl
zso_JDr<1!wy=#1lwT~iUvz@mNny{+*i-X<_U2Hz%$kb9=O7?#>;j?%%drNcO<NCnA
z0(29#xYh4jT>Aw1WV;n7xP^z{D2rt{X>A5iW{2#&{_S`8$(~U{g8<Y1J*t+JUNJ8*
z5%SQ=(N5;2qtM?=*r#s;(pqh2NXCP1=?e_ChG|nb;BD?ULdL}SqDc2?V%NJcofOL5
z_b9p6)B&eUrzK*YFg;px*xpa{o*$pz%Rj3xb#|kdd{Q_$LPX+N(%lb-6?@l37}z`+
zJn5R1{IJ^X`)JdkSmQHcyHy^SB5N6nvXJ6o-Do;mIemRS&3DiI?{WiT0eA+m!H!~a
zlK8Zsp3Ao{HrFw$+TWKJe#fyU#W7Z_#nkNMr%&>h?_>RTRjX=n(3tgX{>LfDF|GX9
zWg!y_zISP?FXD8Y9<5s`lmQ?6wDmhJG{e<R-Ja<by5DuzMpM_3>oXI#(6hb-*f8(w
zKXmlNC+5-a9@ec*zvCQ8)w$Ok%Ib@h$`YQ6U>;1!-zC5qz8No_dPsLbzBQ2Q(g&*T
z*K5Tk+<P-k$ia{G>aC#C+aXN_7sWA4l1iIFCGiRa=K~+KW_4{<K3)wD2Zwq!0dl)Y
zbmpJP<0i@6?n5R7*e@Ypkm$rE()*nuJ%5B0>%X0r0BS#doV)kqMI?a-AT#%j07o0}
zh_>yNvjo-z2yr-ZidiPSohIwu2!<LcX!sc<#1|bnd<8assu>@zbpOUnANQQnB6G%H
zIDu5vee0szZ@3;#J_dF6URbwkPx;1xhrzd0k=CH`GLgrRdZJS}Ku^l-lPSepZI9#`
z^)D}d+jsjB`fP9Dca>P{Ze<MfbBxQkm_|R4_jw2$;?6Log0e!i+CnJnGGlSe-$z4E
z9%C8S<=lPhG~xr)gXk_qH$Ei@?WCTTz_4PUU@h!6DA4e;$#4h1NxG==mmZVdpA<zL
zMhX`zeN8j>%*r`0x|}cR=dlA=;2EIAZGYztsJ!&R#&ls(4>WUc+eL0OEx1&0x2itj
z-gq^+IW|vX+3n0k&x}(?LhWdeuaS+nhiB=qySL&t*O%7n({l)?13(T{ExAJUKb^YS
zyW}?nZ*i}w84ZKOUmf2!-;kH)TN}8Cyf7ifHT_2c*YVndFyMybwx|a_Q09UXv!okw
z5O>}6#lM(#gF6>`AR}ntg2sWPdyd)Ms@D$GOO{fgse^e&J%+ZRG)%kA-yd)_Ntey+
z#!qafj^8<zpKaRC12iqxUxJY<n%bPByu4>KHheI=Y^c2M1x9|p0o5P+a>G;Vi0A-}
zN87LTg7X6idv&ywR`(}s36yy}rDBhjPO~UJK23Jo>kReMSX)!IPk5^YIfZxymd&j5
ze&+buyF~1)aj@!X0=5twq@H4E>j(gM07Vi8)7t=w@>>CB7Uu(g2abgTaxqX6gVgrb
zxP!x1essL3rSALZqv1)_J1S(<oo?}PoY;#jL)NXfV6pD4s8=#?{{azrD>tmF<f#^E
z+~qIXI!Q}|U5S2r-$}g7llhDNund~YP4)zg|GY>p%y%4#S>9Cau$n!!+f#WXWYo5%
zXXlv8EM&50p9t)Ln!8@%ly(1iaFXb{D{pQjr1PA_)sNXas=C9FR;1Ky2OVJV42wsG
zhXy125Qq&AIlTa^ttC~Sh3@~bZPVnKqW)owG%hWqq5NM(728K=RGMs(1IWdCviB@L
ziKBu+-Tz*dIL1T_t#O+N3S8a%EQYwSg#BtfnFTCu6GspC36O^o01s$fdnVJ^2+&6^
z;3GK(ryT(wIK9R=;pTdd{MP6|^1!qKXxG_Rrq}NmB))WYXU+r_h!Nw}>{}iTLAP^h
zIZwFPN7!y`cXjj&5pa*sdT44dI4JVg<w2@@e2m^9K2FZN3V(q@7XX8jkN;wM7v$8&
zH10%KP7V%8(8(My1Yo$2N&xWjZ;$><Zps&@YtH@MI8Imp2_FG4)g54|9N0*wTa67O
zN)W<owEhZVCu!@~MgaKd4ZOGvk3{~ey{*npxe^yxVEg>j=6|KpF1jt<2smbs)C-xy
z?ZvvMjoHI7a2N+UT{mrNpBQBu9N-?$hDWV0;c7*fLUw7({@~ItZC|Z!aAraSdg1I0
zvfJM!H4bzvjf;F2pb}=imb^;12XO$Y%B!l45~c}J6Za^xjbi|=1eGnbfCK*msn<~E
z-_YAX!E6pd2?)+-{}*`l{|(*7)Mb|rX6uPuId<$N`E`m4C(<cNj*`Tner>b19W$}t
z<6lw*AOv`nGsc0l0h$ZG13+?3#A^r`5IV4YCO8*<DZ(1bs?h$=+}6PHe{i$k+_~HB
zcd6y4+JTL3$X*!y{y9-d=d=3UPxQQqz7Oczs#>yk73MgfMa{R+DNo!6emjAQRc#c)
zZ$rNNB)lZyQw*;Hg0xS(2nxmA%==v~Eda8n%8{qE=6mV9!F$TX_y+Y`LGM80Q%TGz
zR_-sD98`2x8w#iw?e0-jKmDqox~McYsnw$IhHMfI`&Y)1V|E4Z2M3~p;?Fv%0x;o{
zHHrTR0Xov7fHkglC4d%#wKj$m*TGy=Ak*KC0-WvzPM5=K2SN&PaNtd=qW(?7nY}zz
zFvPKKX`H<Uh<Q(AIS4eodgL}aCWDRo|0O<-z5f@=K>e%poPUk)KEW&rPN&1_8f^Xk
z4QW#3l-Bpvble9(+0EuqTJToy^oDJqI|4HYLd2e*Eg!Z-kcpOvuC+y2+OrF`H?uSl
zIC7;)su`7*?qrP~2w>HQ3XWNX&2488vLOn<(rpruO1R$zF7O)A9l-<Ty!(eauXT@%
zKN}kRl}~bvm*`{;;99Yov+?n2r9VaXpBhQlJo$f?)V~Yy|4Ht@gu69Fb&o9QctcRG
z7Y=Pg?B@f0V(U2lGZ9*AO=1~>cFff#u?Vi~GPwNkeI~R~MNeTjUyFQ+`^$UOWTy9?
z*8h6dqc@LCXhn5K-`=yXb%sy*i<HokF#i3@)d{H|BaK$2*FMLFL;Rs-A9_auoOdbE
z_I6j8KL6%wUs2PQ=rTOM18Q?Hser37olgqN76P-4gWscYpV=SqZuuF6_%y&)I?_5g
z-s+P7Zjsb+wSJy?6FDZOP%1tb4x7gv3Os<^vNR}RuPX(@AC@@kp5KLX2Q$Iy9@}6t
zfl_~68h1v@?sA4{@n$5=IIUN6-tQerGR<m_eM}H+#JZq)@CDoMb*txEo7~#+V^1O0
zTI2lgEBx%1Bl_&r$0<8Hc4#bN5S_2HOECr)Kkx(SLP&zOp6pN!u!NWQM`9JnNe(0F
zsr$=TAp}c;@9ES^aV9b(p~<A1wz&5}=wkZe8Ra02D!(Qlt|PqY;#eD&L>GOW$ZHki
z8y+4|%bMY76V0VL9NeXyo-Mc1fU0~sI4+Q@EX4d<!KC(yL=gf~q8wr+3FN-LBJym=
zM>I^KTw%T%Im|eta{)}G=3#M(0u8iXH5&>GNg#M%i-Su9jQGHtGxo0~B0-rN^qP{n
zz9JG~&_Xz|S!yEjyXm;x13Bxoud<+lkeRR|_yQ+Y@!nEdnA4tWZeoSbH#&X!e*m&}
B$p-)c

diff --git a/misc/img/ceteris_paribus.png b/misc/img/ceteris_paribus.png
index 50067ef7366bf4364657703741ed111c42f61302..bf0426764efa36fe6423d6240475acdba57146f0 100644
GIT binary patch
literal 11414
zcmbt)2|SeR`?sQyQzDXtQ%JH^PL^RX6;sJlwk$(YDQhye8B2{LHDXSL7RzM9v1GE0
zWf+N&eGsyYj;$VKtP@$^d#2@dexKj@|KIoXPESwGJokOw*L_{zYq_uMxoc*E+`47=
z7A`KXt*1_&ILF1s4RLX8_=}Gl{IVghI0oFGnw_yQ0AIPdG`YB(xVYB2G&Q+2owzjd
zTux+hab<CFU2$b_nThLy>%#8cyTMP&;>yb6y2{FC%4S|*8koSIr0JxoiPv;;(sTlM
zvL+r}?YiIQ>*{hQ=z`CMP-FJT-Pjm!?4E9ne`TgDZU$&wFf;QCy`U?8L09=g=!FZR
zp@18}hm$53py-6hJK@`%$lzjuneN8!?#6g`cW|Y<r@wMf@AEQK_6qg#3JnD$LcPqu
zKcS)QZ+J~EJZB}mF(AQ(chbZIV(iK3csv>W!IRtZuUPnY)?=>fba&%)Hbs0o-Z=eL
zdU{`9dLQdK7n$tDMRw98<H6-b29wC`<aThe$gFlUi}ea`{EGGJ6^m8Rb+;X_*^YN=
zCxZ*$-VQD>5PVo*EV#9^Sbgd4eXLh~EY^E2XNb#edU2gab^;_=?cgGV$1FgV1&Fc7
zvRJHjppy0VhLsoUKt=r5Pulo!ac!$+|J_jM_2(rnu3x!Moj_OwBu*wprR>oNuI=`Y
z5imO=z$;R9);2%n7EIaG)+xhSLr&Fiyj|?wBJpkMxzmp+KKe#RUD3h*TFaiFUQ%V6
zmzhn_<!5bb1+8<pKDEFV$BOeSvhQCpe5@0+cu06i(eVqcw>u*CPU@d|kwo*io9}?z
z{;RWx&^#grfntb^Keuk@-0C0^%7%TA$kC9}$G&=B2;?*STPti=hua)OO4eRUw1(y+
zU0dlvS{KcS{rLfPaP7T(tn#FjqSis9?j~xk%7aahEp{4E-Uva+z8#rjilL0q{Rbd}
z8D8(JOFb4hEaW<xIirNp4fp$Ru0ahWHS1BS>miqKP*z-;YoEXA<%g^%bjh)#-Dp}4
zKTOoZ<O*X!UVD~x)$X?@Q^!YVDwYuar-xfS<@H270zzk-R1NyzUj{GT*st9hioX2u
z0(Q0^JG4q3-cb2yDnU;oOr>8i-%9n=)srbf#~v)$pAE{PEuxxiT%SD({WbBE$64mw
z%SC*USe>xTl2JV>e)=l*V|QPkxYz<qr1Ex7!BnDw?UpM?W0l5SZ#k~sB$_ivHqOUN
z*!Z*h4roW|%{laz6jU#ow|bf;ucP|?($wmyRY>cKqNJdGYp+g54HXb_b;^>`TJ^n7
ztLk~1DLWi^Iz!z3rtZ|ptVd@5CzNob5BYWfC_kad;FL>9Au2Jq+Xc1Ma>`GXuJ~x=
zl+mX6m>uYbDEpfZS~T6#y-U6C-M!>8vTH8(zw?hV8Na$*Lm2KVk4sB-4-T50ySw;W
zE&shzsJh?F`=#Pg^VlfiP4>peiv^wL3sonNn1&fQD8!YC%HNyAphuesBvY?9_65Hm
zzDYKGX%a#^vT-6`rNT$(n$(%2vHPx-R;D)a!A1>LY9Ueju(|onzTHKOq23SYm-(UA
zwN6!|%*$>Av9c?l#nwxbeqFz~8G|c6>3Gv2MYrCrHeYNZ!jdjP(%hiXVsLO2KNb5r
zSoUJGaD#t-39gcw6FFsn!geDq@s!qF>bG@T5PBy~LgW>$)m+@{y5i_vrTt}zH}387
zZ2$R?B8avL($2KoP11N~`sTjNJnvDWiy?o?{G@HE-I%Q1Y(b3N1D^dgla>hb6;u{Z
zr(GBtJ%fK{a4Xx=@NClPr7jw@FO<a+MC%hm=1w2ED`#<YcgpXfla6b1>$wLIUMIZ-
zmN2C)`mHi@kj2T;((?FbsvdP;i`CqOaeXG%@BC(X*ZRtF*b}S7MEMkWZ!WGvG)+$q
z+jGs=95ZRYAWH9UY;H-3ja_W$@l}R8bBrwiK=$%sSa0D9FKjQ1blT*SNmF++pGhOz
zGH^}7THcA0JEx`2R0t8wLPI{#l)Pb#oyALpnl!n?NXwflvm%~ByH|p>>~<bab4<Et
zr1wJCxoGo}Yw3+6%+6<pvzP4QP_~WO`_enV38p_jb@_;jDrXs#XR<>h^WKhT4ftID
zeX)Cf`09-V^Qq>&cRB>F-nbnSv->jrWjyti$<UIy&r<s+r7%Dt&^E}-r|qDk3#I@0
zxoe}1ZY(1CG612?v*ol2wivG)ZL-R0TJn^}9~^-WcbbNlB)y*qnLoYsxlM7%$<psU
z%r~L<e)+@Hn0{fIjINPp8NC6;g|+(0L!k%c2SP+cKly*zsx~p!v8GkVEvMjc;G&#b
zm;7*7gYm}=$;+x=RE*y7E!lPjijLg>@G9p@Ohnna3l5igl5P;ETS-s)N5*B~1|B!7
z^wLk$6&lL;U<Of+T-lYvX#A`)7hM6|aVBS<5T^^6|L|phL>^x9Z8({uE|EvExl4@L
zk=<<Q?qPM>t+_r23r!vQEw9)8b=MU+oRrCbj%mnhuK8cbAf{RZMV88bG5$LH8k+cW
zC1!ETE_9kU5*mJXkHy*^vy+|a+fT=#BDhhOYF^3O3*x_1jodtR3Yh#*clX++fu@ON
z<9m;#g`q>1e!*9X0?SdY3!-NtYk8N7Ta&QYXvokn;d;h`c>ky279QPm6(1+P@CgYo
zEnHJHE&U|<&^C_wMFUH?t3Ih8beH85I<_eB523FH5kr~0TB9@TL!nVVvyQhim|JM8
z&!0`5+8(-W7rOSmw?RPVL05d2wY{3xdfR0igm*LTOVw!M#z<<|cw3#?go+8nG32f@
z+WGE>#}#kXgP2BgJJK3*xo;)EwYF9Bj=O7%{aBVzu%&6fOU$8U&w<zZhP+EDsQr*1
z-c;Z55BcPeuP5wYI(jA_09^9U7gk(qE>~(9dcQOzC<|TNwDWYRaFr{XSO;Iyejj)@
zgK34C^U-?)BPF~<>8_s0%%9LFIwr8>Oc*Z}<iqo&;F*=}nb^aKJ!V=ELyK@MR4g+=
zFO;TZsQL?TAh)EgVLkHxmHv>Ii~jGGS;xPx*?wie$xZxW>NMW;A`2pISnV6*x0HnH
zrOj-W&rwjOt$L&VGXe?2v8m_WYQUPB#0(az#b0-hrqPnL{7L$ytSfV&0;`o-xnk~>
zlUNsV&em=Ck+1Y0=RMSMo*w#ocNF(QgRfl+gxuY*AGLo?@_){U(fkUkw47c;wF%u{
z{|AWu2Yl+~AX5dIZ?g-#?5EO~3LVKGhsp!CNGn*#3M%bE6NtPEBD&}PJSlZv6Ouv*
zG8KZJncdfUas4lNU0J3u+SznaCLBL<E1Y{uXr7*2h1?=q&n>_^AOk&xhZ95&#_;ak
zR$g})bM?QEV+`kDuYZ3O#uS?W>jw#j4D{+J5;hC}M!kE>(v0K#sMNYC6V-uMM<?ai
zPdXT-3-8`aoe=e#|IYlhL*K5|>zKh@Sxle;_O9>B(rS$otb9aIox*!IT=MUgx;HKj
zt+WnFt<E%;rMj3p4(Zk1QFY1CD`i;J%33-c^IJiW26U38+=Aur9Q*{Og_u)xP+ATw
z>uB0-{D^^yMBife^WZMjACmrmwGF>~nN)G&8lghTAL^866i~}pXH!2dl32qHAFVqU
zmI6Y^uFs1KGTjN)L1|JJeZ97>qrp!<Ev{Nb)uliO>BYtI>QIE3+~8Q`qMMH4OaHl+
zvJRVNLj7}lxhaH=bZ5F-V@Kugdl}O{6Q|O<F1eK5RueIen|F^aUdvce9Ejaq(<QH-
z#}%*>PNm-{N)$!nk2DbV6eM;N6-_AHvtDFpOm{0u(ltoEy$DB3HyA&4yxif1t_8ib
zfa&Hue}3kblY{md@+R8Z@e)yAy=z~RaDO^%H646{%k@dti*Z#uoyCP3)^Y6W4M6BI
zlH>}Q1qY-bstzwK!7)AA^AK34{C?s22%=k{Os2XT-Pq#E=o^IN%jo39X2m*);vhQD
zi#i&!(}>;-PceuVo{#6*d4zkFWclcW*7sk9(P`8qYWHzdIspGb<et4yupZ5-)YdzD
z?8t38(&I`xSOMqB{Gt>?RJ?2vGI1&K3Sr=SX~%C5ZYEdBL#tw^=yBuX^BKN_JJ4ww
z*B;x{X6;s@%LFDppE_?JxL4ZTgI1EuyA<|VPZ%vpAZlQ@`pW3wJZ;t<7n{Hl<U2&H
zDxf^7qTWN=fyPM@PYz?Ry~s+JVl%rBs%5Wn$Y2{4gkAvi9q5PqQi|-!`dN=*g8riC
zQS|QYWTIO@m`C2lYH@dp)&@o+_uLIjyj_+lJb+s9wrYp;V2MSstIr(kcJZ<B?ymIg
zS5^{Owkfy}wwaF*vpt{!rr`cqic7D3#89{SB9CPHNgI#!j+u)?_T7~TvRfVxs#*rJ
za`2%Dp^eDg(5d2WXKA~?@g>1#^9CQ4u3XbGPO(%y^(!<fg(#loqk4RqbVx(WL+5zl
zmo%e_D{*1b+7l{i8<wbi)aW{iD>>y?=uw>${?lBT;XTi+=|+v!KtSXW)YY6U#HL_c
zm(uJW9q8OsM9Ow_c*2TQLierc5&dnMuG<lgC|=m<+X#rb{MdI&ay~{Dnlzf}UXk_Z
zFNn>U4!%{9F1*l_QkkvH17#~VJt%2iduHRtLwnW`J7(xSkD#3Aqo>&}1Rsb_iqi<7
z@1RUBo56CQ?S&}G3XqQP0wjda)~Ut~#8e*RVY~wpp>?}!?3y2T>k#m7)TSu0T|l6n
zI1@p3@9cW){)woejGfrO2RAStoO=FdxpJ#0J+8R1Y-QWH%|hK&3u&}wdE=)`Q%6hn
zFzA5H&mFo?HX^*H`7oi$sYng3U|RVLV#czZSXpK*@C6jROhX<<)z?+SaJeO=wX!Xi
z*TNh=5md1AmrIY61N&EVB9KsHc6Cv(Np910<#DduxAq=>S&7=PMv8&%ns1!zH4pfB
ztX~;r>3y*Z<#@PDXL_P<LI(4rm$XBZzL@hoR%5DgDt&xd<K=JS{%$o{SBEk4`Lp-;
zVbQ7%5mL0zuDK3M3@kdT(XFmKJ#;zt96_ZpQQ<REdNU-MHIS4s?UB#=1$G)B!jc+O
zm`keTo_D&Jyhrr|r5cU%{G<@12#mr)>f3;~1x)WcNx~abf0whmha79CdPv%{A{7bO
z`KZq|9O$I#%<`KK_DItYA8QX8BCqA~F!}||M*cwXhGL!%#UV7#`otelE()bTX&vCl
zWQ*~kNgw->JQ%n9I4Rnw{DmWj7rn2~h$;m+D#sJ;0x#-MF+I2-WgB%XIKpd=593Vj
zePnXSRidH8O$gyXA%s>m9ex_WpC0F58_2rNL(P31QN}pbfrgpV(*ml`*uikQ_gm=M
zlsz{c<Z&kSh+i;98wG^e(P+oKLxJyxr7S*-3xQ~dHTG{5nzw3o8oXPMJC4(RX5){F
z1Pmxl^3XbcimT2noIj(3%bkppL}z~P8{~%}92LTdZrCk)C){>sVMT5e1$Uyo3YbS5
zowuVU^hBVe`=BI!>9wtDYw>k2+L1$gwu((>_HXVf%5`;?rMXs{7X{(ZQnX^PxXmfm
zY*F*rV&?(>M2PMqNvzi9BSSZ~9Sv8!@ea;rw-Yx|Qia08wi1X7V?t<LuDLFvc!nQC
z?uizi*Iht**}aJ;mbJtau`_&B)EC%C7LVj>8Hk5bw9+pFMHk3H4&_gA19drN@kqL)
zixHg`kmUI=GqC6;(JgI)k9r?T53Ih|s6EU_MZj<a8OZ+>lN^Nk=DlcFw5{kG*e=E!
z8R*L%VMK95EO7^Vp=Sv=3E$+uh|-Qv97^m4Vy^8SNMyDo)f#?V@AxK^b0|8meu!f}
zu{FcpQ>s_m2Ge>?cYN0ci*Ko6lJ_dHQBt(AZ$CSfQn35|??!1fX|{C9K;;)}51L-5
zcSxaTRWwe=!<X{=pOyva4h)Wq*auW)B>(P!*n6TUykA*o=GmZgbX-{OUpf+rKbeTv
z6MOm3kh(4w=v~r_Fc70ZzDVh78w@WqU>k(8OU?brcYM@gciOGB5q_{UwF3|^`a(t3
zS}1QQtft)Wp$R<-g#XQ$*HVll99~w@{yRsx=Ps`#!>LzbaT(KWrFg19ZG&jcn%@@~
z=7>=1;lG~%bv1`zq5!OT7%HZpB(605rbLg@!6joky94-SaI{msi6(a|oR6CKm7p*h
z{sXa+icruQ%RZppBw}BD3YLfAUBttPMA9c4TH!dRrX7x1BXJN)^zHu42Sa?^s@65?
zBIWhaJMlS^pwV=G^b}nN$JFJFQh}8D(W66O0#tMk@9`ewSA43fbFsGkd7TuX`KgT-
zaD1{2s5*(m?m<(Wln_v~Fj_VFI6e3-k(>tN2#5|1vCAYR4<ne(#Yg7tN6frkfuv0+
z)6F$P^ZmnH)vN-A(SpQ@@EE%8sm`@0*NtW*^1O*Iojdo(a~Z%k&}`k{9PiA{4ZrUY
zi5hFu*p1H2>22A3S5E(a5<;xOb#iq<yUuAu2#q2TKMuq;IPz01lUH%Ny*B<hW}6JO
zZB`cAJjRFFPR1~R&j4H8+Af6V0!BUBv#=|e<iar40ivz@W$DJj-&7~x=5O~h@&9Pz
zECcO4br?kNIQiYsu?Vp#ffuo~?vXX1JOE2!^zf{R?&c;Bu*G^c+T%WHAgv>JCq*I|
z7S68|3VNSgl)c`}MNJ*&hZ#n)o=h5ssbFTELeV`W)kaBb<i}wYkmlYR%oarf)2q+j
z&#FdrZYEa5KfT`5`>FHd;N2`tu6mM<f4x7|n5r3F2Q7FGY<O=R2gf)LTymQKB`y0r
zOqTIl3dM_l6_AM(vu&X-fB+mEXbAkG%SN8yy;LUKODl1_bgpA^vfu`vCoY?*o=9?2
z$9@am0W(DRLtoRIx{M@)FO@;!FI@<^u^G2BruSa(oU;dM5L33bYxV&#Ltm`BEw*Fv
zFrm#_N=_*{WoI1^Jnk&z=tyZjQKQTDv1hxzhvDc<ONqT9k!-n^j*~KONk#>FQbtR3
zTetGS1FuqM`&}Eo7iI&<Wx3XHUwKHKlQqCLLOrU}9dXVKAW7L5MGnn2=QdLfC?3B;
zl#lV*@DNmT5XQLA?$JFNNZnyMkfzhs)Penz<*=Pj`aHLEs=~q8Cs~v(jnbNPFe-)h
z?x7!*AI{R-xO3*h#)(!%G7?Fr(AqI*7<_5q((Fo|a*v_`-TDN5EA7U*33zmFec+Ix
z<0D^Cc{|c`O+kMz&eJ}*N|1qD`kY)Cu%XI^WrncEOeA#kjJF28i!pt|NA(WeBApsH
z50VDGfrHR;Y`s;`7BB2ZQ+iaR`QrBH&ya$W=&gHSm!>!DS{<pqbi=Y->&0X{|BrdM
z!g2=(!`2`?OQFp7%OfORIVKt))S*1C(an!h3Q)0OXR_HH0n_<ZdE?uST^}r4y3()j
zOCTmZDrUVS*~v<hfb~UMZw%HeYcy=C?ZFcz5;CTRY)_>~Ar^+?To@fvw8($(DJ5;*
z$pWU{JzI$&l=*mP-`idX`R;>wP>tN*+{jP6l0tNU9sDao^$Me4&M%p&v62K_xU%3L
zv<7hUqY6R4TeX7_KnvhOvE2-+F^ngvfY~dBkcVugG$GFuKZHRbE`xxRi=^{Y<9WAW
zMj`#gQvXuHcn;5dZBG%{JX`9&7bDFft+U)}lb9y0?^V3&3x6`eIv{J+<XY#f$kKP3
zHaC;p^8>yexI{Yd{=E62OoZ679CFknmScYK*s|A#Kg2ukJ0CXkmUiT%UdXCrO=ej?
z!jhSNkdtEh=WX9?{qX6tlB#=lmpiSf(GH;kpJphf7qoS;t?Fi9El>P?QT-MI9EJsQ
z$VXZ`IvADBrm~GLzF_E$fjbXl-`FnTUF*zoYl|szgEhP0G2EZOMTBq2U<>1*^E_$t
zvE2o+*|$GOhA^F@L3ga$Nl5x?z-79r=cmN}5-RmZ|FD0C7&D$sl6RTgL(+a@ULA2&
z4vqnSwAe4u!%H3py?A;Mp`ij!y@fHlG@+Xn)T29&CAtx(yu48h7?22fj*M1vzs|oQ
z8Eks4qE(7!0)m2FU~`%3XK|y;U2v&qNNlXy6y;Ltb`BYC%6Z&CbM*#V*;fSR)hx}|
z{(@;{Ht?VnB@xm|8cy`=af$f`p%mb1Zh;MF=&<G>!>_QoXVsGeVDX^NBbEXO{uBi`
z{gpk7{bNRm6yppJqeLg1&~|Wnj*pr$`=FKN_NHcT#y$WSvwN*-$K&y9!T6(e#vM4v
zTu94ft<D6n0xlP1aX4nX07f#{5df%!YDjMeLf!Q|Uk?aXfzaLN`*pqY@+*Ht6A3NA
zpc-T#4kA@(e{{D6jt>ldB>|ggsn^6wy_11L8iq%Yf`G9Do#3DkWR4Cz)|tD~#P<1Y
z$mxxCo~iW};)un$uwhLH?6rLSl6}PGy~>TPASm2N-vj79H_$M8v@F6F_JAE}zk(pG
ze0-E*tDIq;XK9pY-gvBBi;<)q1%f&-UXCa>EFBY8t~B}Vz>bU&39fp-Y@pimNP-+D
zq#?UB+9Bz_k%qCdpLvv!V~cC?xk=$C$LT2tVujH5?Cp{_Vi-x@GYZRS7y-Z9c9~NV
zP)R2EmrS1+Zr@az6QBN9)eai)Atj(*L|LFpzx1=4ACC}Iqu1<O9cb1rDa*`9O6LPV
zVj74Mq$qvhq&FL;2q63Y#NN53ScFJlZYTV0{zGtjIJxbe*j(>L7(%1Lyt?jc+$zXT
zi~=d$ZHfu)HCoGKrc=qxmeimN75Cl?QjrNql%m-(mFgd*jIwha3u<)onWn9Q_f+7x
zZ6G;S9ldtbQ<jfzXK@-y-^+$jxsYypFVIf_N14Ql52t{?Fd`5op2<KY4pIy?4ZUXg
zVCBF*9wdYfT%4k)jJh~*(Ir&!gyxAHHSBU>*p<sGN+BY^j0BKu`XvLbm(3r;g%r{d
z8O&omk^mM!zPTIAd~OW8X2|X1r}`;9)-}xj)XIKf7ktK-V^Sw%5#7-S9p83p8kh~t
z>CqJJ1IU9S1WXIB`dV_wiXH&MRvoI^;Tad^u;0)0+`#3wk55_9Y0+yvqynV>Sa|ux
z{cP*nF=Ix3zIikCh$LbPI7^3yzUfA{26S2l+odK*Av8{Y1V>uWqsedkK4uPn16o>n
zoahzmr-$yAA<V5@^I2@Szyp-kIhx#U<*On3vnBw4giNNfrnt2#$K(c6knj5v?JgM4
z+HXSnYME%5{B3Yn^248DjB#C8dbdSv?yW#@TH&bM>*1K+fTwxLhrzIlA^4qfebu|1
zl+Gwn(9O?vY#%O}eb8ZRy*%3Ui9GPxY&F7_l;wPn+8N_xy>}0UJw{+jeAFVghB6Aa
zd>Uhxm$RXNKh$Se-?YB<7^xlmZMm_V6^Si!@9GEKZiLQ5)8{6U8ocPVI&*(T4!W0g
zFq6tJ>O$vC=l*<WeAF;VE1PkeVgy{QkLGa@O;TnL#(GnVE0fno-VY6wzmrCNh8k}~
zFo(V@9uhEJw3tiXxh>lxh^-q-0gQ#e0-RalOs`?qj~Uj_e8+!Lz^ArB_-CMx?6Ptz
z+9q{orKuvjuC=*b4+C=LLE7v<F%RQW@#dvo<rj^a^qgI!I=tXcjvcfb&}o<pgTDyO
z-?qD8KnS5~N6y~*awMcx3N<K%CbP?%MDp{Eb{TOKQ2jNXI%o@lh-Fn)iHkt;8UbW&
zg!CQWoh?NDkH?jPO)xt_kyCnp7Lg#z;CL3MR$^WtAio8z`*x@uU<Ur;Ivw%RIV)+-
z9pKs;)KYP|z>r!8?=^D^xR?>=-ZIjFUjZx;!yM)wj+0*gb)!`UI4nTf<tEXqeGO8X
z{Wdibfon1M7Xv0Uek(joaA_&!^E*=6G>2>=;#RUrt+?tWkR?d@5tPQuZpY1D3YbpM
z+J4k|q65UmW(AAJ4QRFQ|F)-{P<=16AKQHQ2M0;M@B8qdQ@&ge&6e8{&WBO?%7_`U
zPI9R}>iJnm2cH9$fum8D{8S%7rNpPVRO0=l4@2AFB<W2!W<N(7?aQ$e+Pp3UJLIRk
zKw6gsvMx>)8L%iN>0w#~W2hbnWxnraVHhOg7r3>}eDUPdeL!^E(Z&Q~*zam0-$nJu
z_1i;WyW6N;MfICG2i32|Wl&4R@JPxgJ`MQiq#(MTuq-UmM73X;lZ=e08*c-rfnNuI
zsR1HgBt|M*BqYebtKT14M}F_vlv-^>N!ib?-hHcCOQLBu3%fo$^^NSB8O`x)9RYp{
z{gnx|ZS>(>dnWPVk0a`NK2nP4l|v&hdeu*=*h%1~tsZJs_^tV&0}gYe?zK%Z%GKU@
z#0ve`EQXM)F(I|XVIDfx*mJ{bPwAbgZ<|f@zA2^r0puQ5K`$P5Z|mS^pAYXJGnfU~
z(}l)>uVyMW@P24qgk#ajAIwUFqTb#3j%%PFfkK+@|Db8;Kk~gaZ^%Wx&pBm&rGns1
zG9_>NQN`y$b$k;F`jBlp7uOa7`&|HmpQTC+Ysu)wVZS#4IKcfXh~xC5ARq|0n1K$!
zG{WoD1(1D%QqtF!03S6SNk>$P<3Y_I2F|K~Hw%7x(qee?KaqO93tsYl%ZRBqe$0=K
z!2iQ?<>fp3|5qr%To_^hpWE79zy$TSj=;c-`0xN9s<!`b2?Q^{%K_j(s(DfFd44Os
z9vl4f7asRZ!(rtX%h#}UpGVKC7v(2De3#R0L8>gZ{E6#I1b~^Mr923SFE}9Ol|)B=
z&kanZAH2UQdLYQ6Z*eq@vPlGF2TqM6=!Hw(y9jJ}4F_m+u1I3P&2;$%zBKIbGG<l(
zB^qjcG_l$?=g$Lo2fnwmDvyhC2G!W{$X9G`0>Dh`e3M(m7^iCb)$kTSp9vBEq;IO3
zkTLb`NXdNjU6e#DD3**`Ty+2mL1Hadf@J;dWQ18b>Ibl?ymJp-S5x?57XPhB^dO^q
zeEkglDF@EC7B~g+|JpAa-UToGj)8xS3uAi!437mm!Yk+`!^j%}a?-EuB`WVW%m*Pf
zW-xM3VFY|4IglsGVR0YtWGNS8y<=|JHY&B)RU&T5&4UzUL~m?bo_R;=5O5qJ!lT=c
z{{RC>V<J9(?-fB(KjY+o>VdUT|DH7s+GCU7b^I3`C)N91h?Uqqq<<MlhqqAwrNc&t
zE7M1l-D*sf1!g{={h8WDF-ZDYxatjha&6A?;CvN||0kT;{A7rK!H+_bb9#~3c_)od
zjx$rV?9LOFLS%?lyg^`L-EEuxs#$~bk&f}&=ylUppF#etmtE=yM~T^53B<pPYm2?c
zlrCq2iE7aOu+M0ODhB;@w5e|mqI{*a7u#FF{I8A+u~5kF27Rwk{0t{`c3C1Ix=r$X
zbl4L>FeQiokp2H8#h^ds{tYBEhdckJbx1|h|F-!6LILxq#w3#dF9?{Hs{6Tt`Eet9
zz46lZaB+^9(kQhy3qP$Uu?2FOIE(zVD))zbW=QZs#=)>-qJFIJpqd^ybcMkWqfHxZ
z>-|S}^q)*P|63Q8TKA7df9{U{UvJS=V&2Ipo#VF_r0jZRp!s8BT31c|@2OOpsN3j-
ztgbojlyt~ieW*vzo<-Rce(YzUV-xM2x)vv|Q|s|{ZyxBmb(g5UP+0|3?ZOz{mUV-4
ziBluP09i!rw|Wxwt~ck>mZia(U(koyeM=K^-~NS%a;A)kK@ilLHs1qbAl|t8_|Kvn
z=t%Mfwb^=3<5B*n_zZaX`S>mKy=}}rWdj-$Cc|1kg}}dPPx~jfo!x_|0}k*%{K?i2
zV@K}{@xh`&nEHq0{$c3T17=d@;Rm9L!ywJ5#Pa-$d*Yt*zW1}C|1=J<pgAG+BPJ2C
zCi;S_?yGcm^WN@BoIQAdM5JU-E7e>i`~djB#IKxNben=J_X)a!>&j4$Hh2LAym;bq
z)Bcu&lBA98iF3!<q32R@?I;>XyKb#!GjowNbRxe{hcq+->)z>jHr;I*AK!V!#?3ji
zC|ROUGpo5d2b;IadBz0kR1Xbz$E-TK`n!0Ttz9e_`h8oht(pSU%;I5<^@FkAiqy-L
zp03`LS<k0x)uUZ~xG{OO<CjUizSk4-?>zSN$g!LOlTr`#dDK2DsriypBlj@0Mi$j)
zU6`ZZXe(hvVfDW=Jm=x5Pj-K`tJ8Cm{^v-?4F74rmZ$e+*I#&hj}b^`z4KE&Dx5wG
zzMU7<ws>OjJSwdh<LM6i!Wz!=P6D;<SMFhi?JDma7@pfYDP1vConCV}<>)~ZtEbJ@
zXR<416nm|o82>bh*th;hH>9|5F!GBgqp+lUw*0oAHzUOP$;(t<N>6t$UzYL-XNe$+
z)??pdNp*v|?gq#Ad(a(cJ5tLD56*V>1=XOX3ISCsy9iqe1SR~cdl*?ANffg?WTozG
zQ5PQ}7qVg!nx!of7y2%zWXQhuPfeR}b;q-7>cv3@jjjbblspT&)+moXogY5Ks4L3(
zC2tS3*LbzMrHIH$tE;GJOB_+oMPKgtv#F5yfqd24qlls&?>bSM7e(q_oZtOjyBrlS
znhAXU9_1KxCN5Q7pC^fP!?VVC+u9P|3rKDnJ)7v8!S{vz8YNFKz(^)(vi_3%?Nz8z
zFJ@|J-99QcRwA}uP5O3p)D2mHqaKm~y*OoEvp40=y3X7n$l?$565gAWz)P1~=wv)|
zHEX5%7St?_D%}lJZ@8;DVIoS5e2V#;vU>Ne3H0uO{65Hn8`5!;j^%?{3NF18Z+T5P
z1y~p{3lasdBYG#8^de<&CI)Q-m)u0rfq_wp1Vawjdr042_FSy7@yGXa38BB;c)Yv5
z?h0&;9}+b0|I%Px5k2cWYXJ>bM+A*3I@T>Oty_>k-Gp8lin8A?K4oBXBKOz@-2VY`
C#HK$0

literal 11645
zcmaia2S8Izw;-aRfR!j16j4Dhh=8JELRG{PkQ+b|>C%)Ygdn{sMNB{tLgxZX6_9}R
zj&wtn-g}iQEp)OM_4~hlZ{O~QA-OYi>YOuY?#vm20(k!rGY2yr9o-?!0~sYcy1f7$
z-JZb%d*POM48z56<&(n0$9Lf>9UY2}PM403Mu$Stp>*j`L^|D6BvJs0ltc=^MFA-Z
zmuDOt9B`8WQa}JHDIlOApkNN8!3euZC|wkah|<+X>B8TsC?Z^%CI8|}O8!QWgg?(*
z<aa-&^72G^(|CDese%Af0jBj#LBZVRnI!U=q`)(mXU|+*U}<1EbWwCLMO`9Mm)NYE
z3YQfa(^THnRGw&R3YU1(_)^pO9&-f&a~E@S7Z;d>i@5^)<KnVgBckYtzc~@*VG?vi
zT@(=}wu>B3B&NcD#MEYD=?bxVC5)~--c&w*mm)EqC?8)MAK%jx-?NfJmzt_em#T|O
zCBj8F6-G*JPHl$EO6p2;>dHzfQNDDgv~*>KLPuyOqMC`i&8cu9HaEis282H=Ff9Dl
zyt2|0Z`!j`+Ox7UK&LlJr|@fywvws~lUQknODf#G0#jXqiS5F!tgO&rlh9~2TWKP&
ziI{K?R4wV~4wvu#@2NKbtWQUGmJTCx`>`!F8{rkjnWOr)x-0$^bFN1AEp;~LdeNc}
zbXB(^@D@hR?L&vHvIQy&dO36p&2p=+PiL9D;EpN@YkFWA{G8|g^^I7&0qx<8O&=eh
zVpWOz-1QGGosqDw$o)lBDKyq*VZ8mr`^*VnUG_b$-&vqrKMKDw?L!{eMjQxZN4@!I
z_vW7myW!ErDCbYSlGMQB^--GvPM~mmVfFnrffmVvVsou`&ixU-G|%YHn>(GMrW365
ztIip={4y$$RRxi!j|WQjSaKB}4J1)VgleKgUtA;2YUtwpKW*U_XY3ccXwPS)%#PnI
z$R;8-zZBu{j{^Gzdh#j;dG4$ajo!9+S|o`cY#Xk=NgQS$;G2H1F5uj`Rb%qQZP<hB
zSD58G`(2B;;s*}a+rNfC+Ah4@S#lU_>j@l~j~74>-5*Gt)=)ljW1gLFZK9~t*)g$Y
zF~J{cckB6%kL{|%%KeV}$xj7|<yzS^%a}_+2N!=8xh>`_PQK`$FH{^|aU+sMp5y#I
z9hb3!<{bmQw8|-yG=B41q8d#texvjD!U9de1hk6%Trv`+Nn3vNK(SrX?xXzX%trO$
zsnrf>vR^wcchW^XcyKgY`>3LeP;9m6eQn#-E~_1v@L8{$qEV}(ueov;bM_DGlI>!6
zx4mvsRd4?0h-)qo$uF!g`AOS;rmeA-SrT+&Rl%`b61_IFX`tDiI-p7YDn$D_$hVfW
zMbheCoD}M~ZvrmQr=HwmPE9xH-my|~xTUYfPJKz$S~r<^$$q!1w|B;%c9yGM0%CPd
z4VX_Xrq7RBo!JO9&)^y$_y4Fm2rhoG0c&bmcgpzrXeHaqnWC;F-|hY*qVwdbW+UZf
z+H@3c@z&8LvwFfuw~~@EnQdo38|9#u^qp0-(UHu0ZB5a3wAu}+&23Y=jf>we8Chl0
z?9L1AIQ&+r&=P-+9Ko!r*rPpdueDPv<W6iXY;jn1TRepC{PI!^1$ZtRCb&e~m3+==
z8*B1#C2ibFSd=AM`7B1Qmu#DgaV`_-EtWGk?R3*#1E;DE#tD^dlenD6IT2uI$-q%f
z6LPk6P_Ss!PPof@)N}@9*gsDoc_s1FgCCzbR~OjQauV$yYT2}vSflw?qFe;Us%8TN
zA8d|(Y@|q%cp|BSF30C@7SB!Lgp23wt+y*rjfp9<JI*?YLd&TIYj1Sw6c!hqXzr`;
zYUfP5qQ<sK#uW)WSt*<B1|5**&PZU+^v&8xd)0~li91P!Hof?=rP2Gf$teR9PR2V<
zDbBPsE+K^X=7RiK%Ekhgd}P2{(K+6j?vqj!NlR*nKiaW8<kRTby0dty_+rvX8V9e0
zsmsgh;?o_0$`5?Dp6Ka$i2oQHZCU*Mo#0zAH86l=58~2J%;(8hIMlAy%3W8l*aR(D
z3~6PHf}&9!0p>@S(hH!YOm_Cg)735(Kg0)CM&E8NbRF7xth{Y9k)NE8T~k$6t&FHh
zQqk&5-=rGl%pS|xbWWVgprt*emee~{Eo@d6M7FMOS5#XP!qm7XohT(XXXl@`-^bon
zadrtw@gY%{Y*T+$x}^B8=rRIG-kqf~5p2A>EiJ!G+K3tY5-t!B|Bdo*B{r>}d0+j1
z;ta1dZJ+Dp@2VqiG3BLEk508<RSiAR&~4rM)$42eH$p}>r}d2Pm&?ek;01E$*DqgQ
zdU6(=<Y$3UCjT9HN=jq{X#YPjal?Oc_|c%2Lnv)?ym2RcEmh*jPIE>%;V8g=SHo!R
z^Mtg+$W&X@({pPw==Ju=eZ@@>`Q{U}MF2{be^@pXHRM@BZ5i@97X!X1oX%?0F4|bk
zm9U$Q8~9L?DaFuU1AP~2FyCT!v74O`%hJnw$DhJxbpm%{E<9?~#q!Js;JmGD$0({6
zb3@*j6t!i)7qhNyC!G2OxVkz`Hg^OaEtsW?7xD%+AYtk+HGX3x4%vOvd8O@Aneg&W
zEqmq2HzKx~z@>$0a)(yG7R_CSZC$DDW3to$I^+Uy{uxpYdF{w%xVCea<le0Qtx>sD
zMxlpG)nL5KVtA?<iIgs>;gpy^nOmbhuoY@H_T3MG#GU9i*<zikkJ_}aB#7@#;ZeLD
zcp5NpSgaQ+DlD27B;RyioL;&4(<EwM%U+*C$w_*>Zq<?cn6o)w;@FFimVIqLv+j@V
zp{?bd{B08T);JWP9KR8z9UGiAF|jjR8zIzm8tu2IR_dC$RL>5RRC~O%L-Y@msNj^Z
zM1+n$g^)}A%;=<LpJl2jW_1Az>VF&9YQ}C+JIGqw6{$sacW8-1C6^j*k)}-CywYyT
z`XEGM(^^P6)(g2u>bL&%wrOh0F4v;Dm8{2Eg&mIj*H!*w@Z=r67#H1?|GURH;?sMA
z{yJC`bp6DOuhZwetTZo;eFuzL_xNa}PPa|i`(M=f+u(|56b!_VB5n}qN(nE5Wzma-
zFqzkS?AxTf|3mv=MTT75>2(?T^S5xrU2#f2j?ov7okcCoDDmBwR3sh1jp`Pfg#N!l
zW};ovzyC%3cmcrD1|{{limjGCxNZo=%`I?AZZt&Djd?kXn*Jknx5eVxWZ>qBqen`f
zmIT;u+?UF?@silleYbd5iZlBkF;h@^HnW?sv4^7iCT59_e6#)^JaZ&B<}?lF?j|z)
zp=cp<>;|EkVO)QRODyry6^A}$5w4kXsUm*u5L4_K>u^#-W{@;*cV^g)>xUg!6z4Nt
zW+s}5nXdY+EhCx`sapFpou5#zz$QRjeL<tPHwiF!RL9jkvXP|3_rKrC(wQc5H_8Pn
z&MWe34pQ|~A0w%hB{JKD{JC#_VvUr~5<~X3(?coLoZE9yU;|o?#v`9Q>nE&Hin*Qe
zihmhf6M~ie%+ot@$*?(<ehKp40OD%2=lYN~iru}wjj|N4j%94KdyiOp4p6K^2{5|=
z<`Re94ht&XxP*NCrfY|Ce<1HdRe{;p_(zLrTdD(*SDIo^*Vc9{S;i|U0hoEJ&%1er
z-4RGB$He7(QA^K;uC$#b&~c)W15(F=b*FYPQuDGeUX1@4tv0_)Q$-RnnMU~$+=UD&
z&PQElNF<Bo^Ql!2m*S7Y#tY&YcfQ=4F^cu?SLQrcYUYk;_kCrfROI-h<iLng^{lLt
z@>yO$X<}mH?t-J}Y^;2TGN&K(uJq&QIImJnn~Gn_jiSvB-2A1>iI>vKmNcuCqqL~X
z4M591*s$cO2kJ=u)+X5;RzUi_Lo<`ZH^K*T2|ndFHzL^ug-VQ-PWI3N(u;DBmX)dT
zE%D<?J~LLDT`Fju=-Y~;(Io@Y=e|9K(wGBfNjA#5QHM=bTw+!BWLFVdF)fdp#_2$g
zU>n7-frf@g;BBkkpZ-QnU$g@65)p#lnQa?p=E{qiDe~?+8Rt?a<EypxMC*0L^dH%F
zz7Iy9PcB$a;=Tk<r2(j)8gJyS=k*Gb>sylcm(-Z3Y^NklCX}~FfCFPZ3A=C{U{ab*
zja;fucOp;`?O8;1tkM&)3YOgXnP!#HVzV=)+83w7*)@IG;fBA>Po$on!gaf341trn
z0ll-#>7fU{TzjB#@Lq8{ucrHF&jpH~&_#!3M!R`Y6<srI%kwhA={0<VtG`J|@%r1-
zZQR(gvxqFwV#K-|5^(Yxtf;jOt}hHu_dM@Bh|O>hd5X|Ftdrw6w=UEuE9|AlIY4kc
z;Z|WCbt)%lZ8SC!b<b?OwIlEJIqUDPJ}}9iNM1D@v)`BI$j3>k#SeQ(Q{DWY)QY)l
zl?N8)zMNUZ{{iD%HXTp+q9`f~L9b$hBu?A`bBBFh?>;S&!{aZ;?>BcPU98i*COwmL
zT0gpdrR1$*k43b7uWj_vJ-vp|6*L=OG9o0`1S-B}dQB_dU7F_&TE`8LUTMsDcwAo(
z`hLpii@nHV;p*MnpV;;d#fq6;)4;pR@O(li-a;dDFXnKGnN`#-8&1bBK8ZteS*uyR
zb~TACmMRPt0+Q5a<h#!SZhpFMt`+uG7cK!Bj=j@`Mvr-0U2j3lJKwtSWsk3+CGh97
zM1Y0%WOI~GA%^U*eBAi<NibI3vN?SA!8ul6$U7_`h%{$feHS|Ll0bUS6eD1vl(@%3
znnx?99e!fZ;s&I{5-w(p#ws;YC;24zCD^1`{`62evPbb<g%GgqdEOIxm&O3ZL>6i;
zv?mERZ32M}Q^$r^=vPP7CYq061)s^B^FOMXj842?99!@KQK@301-*KKeo}Otg1Pi4
zz7LPwpCbY0ibB`%0$S}*+6E?7R#_;HV_g($P?M=HI4CozKa+1MY<ocJFo4yb=wa~a
z#7^hh%(i(uzVt;@#$3)`Cr^dNM-Ay8rS9KwSgxw{s-}3F_vsud`4w|^(<l+8SpO<k
z;ijX7a6b7l*>fV{)z_HF;aHAyPdw!PN$U%Od7s>doYkx^pyz}t&)<9J^#!d{6K5N6
z<E^w~DJoIJptBa$giY7>M3ir5&RB`BMeGzmmMec!kB#A4X*f5Po(O>-nS1aY!D{^%
zZIG5qnl_r(`ml1JkgK-Oq85z!B!#sqt!nPBbebq(d%_b`Qp=j-mEB)%AOBjToOy|V
zd4#rBAhK!HmB$S>G(160E{%weMLW(|4JY#A$#xrPa0Baz>DdcNC*#YKwlij^E$KL4
zhlt~5FB+L1)q{J1_uIF%+bg}wn9N1KthS_Ec|ts2Wd{8<zESo8P69)*>b}xBfUmE{
zYKyQ<IAh#!EGLo?;L%)K9zK@(6uPeFhOiXi#rPuH@zQpD^%wF?JrF@mz(OSZ98Jwe
zi3fOJ(R2`vthYWRR3Uw?_!k5n#OwjCnU!OjOuq*R0D+9j^apJQqK|6hz^7N)v)RFW
z(`jnsxBN*NK_sn=;nk7CTrWJ*=h5-)8}Ilk*ds|C0r5IarI-#Yb%N^yn)`I_S5K28
zFKP&8(0P9FadKyJ%M>cH>TM~8`v!oIkD>W44GY%Yt;H0ba_zt_jjK)Q)(`|uam|Vu
zWR;9yZtctm8gIsG2)SBk@JbT5zc_bF)_<-?q0vnqMZb(TBg4gkvbo0n<emCpgkay{
zrtlG&2M7@qveOBiYJ19S#yP^rj%!B9gS_u;m^N*%)cPrtPH#%s;aEGe8Y=e!HHkhH
zeDulQv{C)FeOEh>J!b);*zy_4dM}d*FNWP``C&)Y5IyjOOr@M&u{HKrRENFo&H#^3
zH6eJ1@{GB&Ii>CGwbM2Q8GUxzEK)k5*L8&apYL$SX-);nykxH?%)Q=@w_@&kX){S8
z#Sgy=K01q`t-rOL_NF*y7;Dtq_V-UF`dp96Ho{tu1qMsb9APx#B#vL_zi<fl8T^Dy
zQNDILre|JG*jNsPBlvpKWuT~HF!pOTG{cBZAFU?fPXv|DhY!W3?g3ajeDuSIW2e?H
zs_JD5qMAB^OExdT=9BZ?R+0LNtAq5wPVKWPwF%*(+V;#t;Pq@GDRR_|57T}!MXZ)E
z(-zN>#ScuSv0DfS+&;{MM)vvb2M$8ZJPv$X^w-tI{GZYEd!u>LO%KBpwDnresF3$9
z)iT0SROrLHs8vxZm6UC>b&J7@daD`+=pbG@L1NEuhN5Gvt_UfUFJZB96b!e4ZeB$N
z*u^CGv5Hr7FZg|CY%;*>8bH!94<p?(217>OX}O$W$Wz_(n&4Zv^5@F02^TJ&x0JRh
zOy)iWw3+$nB7+=J$gKBCnM{^tV`WS#%+S+$u?Z4sWJkD9X?Si+kRR;iWy3Wax+3m!
zRR)n3-XGr&CRydCP$QPU69U3W#v=k99<}0mT1z6s?q!$nPiSmemSue)-9tcitJtKw
zIR%@db#r1l^uUW@CS8l!EI#mFa<aXko8L6FD=O(D26w&(;pH^3g%#vz>>akuNs_2-
zkeIvroL9cHwk?zPh!Fi!VS?LuBIzo;dy1H{o+9ek5oSW3&WN!WOALu7o5zf{M7D<Y
z*6WgHDa+9uJl&)O?V{Q<CHMi|fxHzIUt|9|Zpl-|xGq4f9J5vQCc;wn8%3tGygnxy
zcm5PB%=^i3tQtA|y@<<$*s6zlEq<?prw*&U#dM&9`*q8oDBr3xgXB*U5pGUj?>gvy
zo$nQe0*uB+Q?^i{1Dt${;3c$$QeFUhXtP1Hz$9Z{gAS}R8Tjgr_M->x1YZZnnX4#Z
zSM))&pWfXk>w;Ey#t(sS&BVcXQUh(d#-M19;*?p<6BKgU_z}_Go+}muzFk$Uf|ff%
z)A-fM&@Y#Uuyf_|7Q&}_<u4h(0PD)FNAz`%yu_t{KNNZsg)F#@4#hu$y;fva^;%}}
z4e&gfHSbFBT`0t(NEzIi!k@R6FgOHEEj*6C@w_>re=Jw)g0Ly_vqjmI^7$9d8{<5I
z3*=%S2Q!J83&E3GR`V$z>`n=Ul6U~u`3uT)P)M#U=q^00|3cV<_b!+#Z7F<ag&yd;
zGpO(3Z}<Je6+n6ig(-F^3+sDR$vmMxA|p6las#X@V+5F0%ox)2l3v6d=m_EK2p|Qn
zhOK_^Vh6{|E>=;V8OyE7e|)@@ZT(^^YHEB-aHdy4zVlqG_I{Oc)4)7+=NPIY=6N~w
z%9~mMkgq%@<kwBg5KS?*V=5c?QZ-jW4scL6!McOZ##qKYH_{bB6w(-8r$@BBn4xmp
z;NvLOPY3()sve|!gRz09ss7Nx?3}Y2dft6}V0+)4o;!jL4q?J@2>R-2jUCkIZNP}J
zhnTQH0drv)<3(dd9}wB6uo%U7%{ol<Hfc)r!66{Rv*^+r#5_5tkliv`!;=AewGZ4d
zDy7J%;e>bD>Gv-(0@Mp%AAT8;5id!<3szaZb!;8)p))~WWj+P*Hk*+UXQ*n)a<+92
z=Kx*F8q@A0Z{>!%oYlfcG&P8`XY{-6Z35KTdbrdJobd}~OzP$**nI7T#@tOJN#ug7
zpsbB6$)~~K@L)yw^i^}5t}5$h#h`u&8+3AXu!7=98yz~<5rNt?k}nw4|FGM7^c{j+
z?FTP+qcVanz{KKcIi`&gHXch5HKd4-&w3)l)5<N%RC;~#qk?=8%Gz47^?nF45~NOj
zuC$$gf<h;jv-vty4!h@YE3USLeZbcQL75j`32GmrCJB=+&M50^IMQ6)uP8bQPEZ_K
z3n=Pr&|_PfKCDSuTQ=}MY+-0BXJRB%u4WKm*Pg}PS2xCrGPgyBc-vUWJZ;_1WV28z
z7_3l-Wr;WjtlE|zvyu|PDaqwH9Yq}@ekTl`n{rk=487v%yNu$~#0d}Go2iyNqdS*y
zqmqLAZW54vhNX)Q*!ELuH26i5I{+RmJ8Vm<P`HZHDZj`7JvL^1cPF3}D|imA_|S46
z&|;Kh*QZ=?Y9!XWl+t-)ES9#MX5YipBitFkT1sfM5B@!rpIahVdY|jcrbCZu<K+~?
zcs2}ZKcd-4*0xh$7r9e899uwPL;WmhMKdk`daeMT6cZr&mZUl+5YAhiX8<3={%|EF
zY7=NAvsZpvELu8WLs7LE@vOHHJ_B4}vpNY@#grccz~sZen*bER-mhHjbniMku`k2<
zJ*<ldMoq5+D>#H!bdj)yPmL94f;+T973~W2P-+)W_~b$uMaL3)3<s34+2~w~OD@h>
z;TwfWJ^>V!Fn#^J%3;@lItlYG&@?}UPpHEPZm)Txj7D9ODTuh~H;9}n{VQ1pZFXuY
zqmyaW+>rb>L6y<1+hJ)cL4EGmj<}Ep6*p6FPN}LtL1gK-x@`h1g85Hps4|nb@e)R@
z{UJGp?b=GBnE*m?j2c@`aoa!&_xstfT7caNGkFc6CK2iiqOh4RmSI{VQC=c|^g6ED
zgt?SZbEs8HHR(F)r}*<IVL&M!dUf&nhcTIw>Y!^tM8W+?6yGU?v!@?_;|}2m@=<HZ
zA&clfc0bwHnxZorXtbh}#77C8Q~7iL!lSWG@hGELW#2H`VFoj$1bEsx_O*H2#5wjU
z=MU<i-;Zk^IB1Z0jwtFG+mYOn`@2b4mIXX+qz>lecdl<X+gVSyJ(IVj17b3*A${Tg
z8?_i4)zohJ5X3p0@T}lCPl5B+Y2f`gf&<dD#SNi6H>hvb5rS|A_CU)mqBwl1PyxiH
z^{I@YYib*ior4<;LM?oijeWV%2|Y|@HEN{n?Z0McT_h#76ElBWv!IrDPVDAT1HLSq
zLO7_t@cKaDXSYmX<&t0ETcZ@TqLhlu{NXmIiHp5<V76Ufn^ht{+Oe#5pc-u<EJbrS
zpZs=`vfG<t5#2w34g*@(uz9cot{+NUR<N|m`86wc82NfL*5pfDS16hH%VN7br+T*7
zl<K`Ab)l(`Ck#(hN4Khu0r?Y8B8#0pV{Tgwpx>LcMH;f%3$I_#X=bo^*@K8y^fbd(
z>1@JBv4@y;=?S7j>)#l*CgK-|v{ha!^x1$TXKZ3Y7SQls1U-N~e7rHGH<?`U8CGq6
z3Wc7&{CR52$V+abkpZ|z-VX|zb7}P#qoE75A@%#Iy*b@BWU2J~0VE&w;|&G-yW;l)
z8So~Se;_NzP8u)l{LMKG0e=5^t^lW*UR=)!y+(8tdRpT^4tbn#zRTh>mxT?@gHQ$T
zrFGXZJy4z*52dv*`|pRNf2ZnU=!%!}48LDdV`uOSuxb@~3f^2;D|8wS6(+Kw2s5sT
zy&VM7(Z;rGI93V+z$l1PEEtp-aV6bWvjhw4q;x7!Kj$rzU=Nv;fmN$n2gai*m|0iS
z8y1k!=;d5g+SsP(l|Q(1iwopgJf4h~U$o-Af6FE}js>Ndd#1`mc?o+t;1Uqgm;Q3e
zinm&HP8`T>L_IXAptxE+s?Jd7eb~k!D`k~DT5*xvsnh+sl!@1zcuKK&M;swd8Ie6D
zWxX>}mgPl_jbfXnT$#<Dk7}Lc0UGxU*LSG@bljEKekis(rpf9l$^c}X6G17Or<(mT
z%Km9N!ZW`Kj1;`L>Q;Q;MGx#%$S$L-`Su-H#j3GGYirk3<FQesLw!=ml<@FS(t{T@
zdzNESO*8a$VTAWdr#Duy>BV!b-3Nh-+^mBY*F8%mZ=+X7JhIDnhrn;TjPkb1!{ZwU
z4?Q-)D8RY1>?Q6Mx872w6E~f}TtkcD9sQ0gtF0*XDR`zeTk(3@^)I7!8u%X^w8VNN
z7{PCp%pP-W;f!7l>*%QC*%n8M;D!>hN({#;GB4UvH%*9I9>ZOHHg?@v?J^p?mlOGo
z5<9JMc&YG?<?wQ@&mLg)(%H+@7Ts9%PcV2tV74wAP%b`y9A$S!>%O$0ocY%%wwO8$
zH_o3Gs41F!GOE9W{=R5GJvr%9@2n;kwv@>@1@>^%_k}_^aYw>GPW3D%=~-XP8ooE1
zdJlb9f_8eeCAEL-C9x9bUrLSL_D{Sgyl8}tjZE&<X(c)|$aEv33g~=yI`5%FB!nF2
zeRcuSpkaH+Ae3hBHd7?g$2g6|mxUcl$AWdV&LSChM<bm!%MYt_PiGP;n@99<v{>FM
z-(%z7DQ9Qzp^&*$h&R}OkX?hzX})-u*j{id>SiS&TG$nFE@KnunCph|{3l{L=jj1a
zgL2BV+d@`qd%-#e@O%DG%k-RtlcyPhQg|%{<w8g`@2e@}<5Ab?fsxEXnQ%4;_XdFz
zj<7C(URjAej$no+GnGNMFGAuC5_`b>xrHC~zNCgj=Wxw7O_3q_>z2)iL`2OhlG`%9
zZ-Gn}8|5k4^nU-1^1~{(acz{YLvy(GJs{$WNFDnzAyG;B#U^|D@6-;Rmb{H17sHzp
z(aJ%0fv$a~$AFj#5A2aHk7;ApLHA-7@GbciaD+PB!G5OE4D&4ViAs4&c6Xw95|jEy
z8sbN*q<YJ>5JQ>SlIO^~eO&XRDQ7LTA`Z+lIkC^e{6k!R&*4(w6N(A?Ve=lvmruT@
zKCb^MeJB>qf47b!LlpQD(T9pKPiw9RsEthgVU+h9nYk`yaYc=}S3%>KUL>_DD0kjb
zxQ-K2up&+9r-~si90uAJHCcj&8~jMmgB%5+Ns$|%J0dX)ja<QkEXyO7W>`@{cx`_I
z1&H=-S@I9+i|#KO!(mQGkRGj87ktC0?e>mCm-8m4#twt5xD_bVMGB|HHM3Rdv7H$(
z7eZ>PxQAo?a$1mZ2iF|>PFU7!6VTuWIo=>5vTHD1A*MP~0&y(hHzxJ|$j1&Z4AP^5
zni&9!#raGQ;9jGRgm^v)_FP$ZD7K2Azyn@yOcCEMFUcnjIIC&0!-4U6QzUPc`ub#n
z3oYW{YRi-{3Y#3*dmwk>XE`W`c$EFvMaostf&3g`#!{Fb^-1%c^7SXdhapq>hS&|G
zp93$B6MLk7O64etaB;14BghALyVO7t`zVWW=xMzaQX;1;$5%=;Kd=wxxcW3NS$r=r
zD3jDk7|%P=AE}=c^#qRbgB8ysgEsO4OSehlFoC>59(k~Jvu6KbY==}{;q2@>xgj<q
z6Kw?cXQK%0Sq5w&FHVKh(Xm+X-UZM?haM2Cv-}|a(~>o-s$xXOEF`7=oc_;Y3nlZA
zl!rYfF2niw;Cvn=F1_Aj2;E_hW-}Nfk@!@ygs6)XXFa|#8L>l8b9LJ1S?PgTO`Pr=
zW0=eNec%K5O|qBMn`I>51b+9O%+vwhBexqCtqAUaF^D?^&u#2(?dB2i_$o)o@V*Ys
z_uXwg-!Px?mmAKr0ttp#Z_8gAKFWPNHHnX-!Pkf`-yE$nlQ^U6d*Y%#$NkXg{Ap-x
znc_Ejk25_o5v6)56CmUnVjpVuN+rG$4=_5M93U9N0`{Vgnb_Jr)qcv$3BHBb(pOHw
zdOB>$miYX}GljqA+?>W7CKy0g%TmHuF<bJ^Vs?3PXFeQNE!d%4d|B`>dSFn$dqva7
zLv_aLc#`4vy0<60O8>Zuwi!LlFBI3@bO}lW_E#2fzPyL?58Gv^%8T=dIqyoM2)_t5
zuV@~2QGHEPh9kw#4MES6%ikzTe<Uf_W}A%qGUZCbbl9M`4EBIetV-diTX1?O{oQxU
zNKA~%ocf#?un&A!(C8^#2U|vI%w0%{_RA}1vw`UisX_x6ZS|g9Ap2y78iCjq2#ITU
za<0@Xem<gUa7Q<1USrMfxy}uAiG|?IEBNPX;^!h|2^J83|Cl9@6<bOhVp%O)%(2Ed
zK?fyz7#=!`!qhPUY8|E;YyF%BP805|<ND%zPC{QE`8-DZv1?evjN@wII3JBbAt#5L
z6uYFp_Sk?2Af9noM2gqu0tr5$VS-RB5YL<|BEoCJBS8~}wE(MZPL*PAu|tzG;qcpC
zdJqfvs+$d%jCu&KsQ_;HGR{Aj1%!`xLSK~<z`+XDK_1uyhPz{C=KXsrpLbs%8`-Es
zaERS&H^j51A8M;4-x<atwm0#j>4lS7p3J|`q7FLWckoa0qU!T5V=uz2AF)EO5^CK@
zuVK0P7~tto`u0ac{`+89SIMA$1pYNC)c+|EKd8jFA7;;P>AFBRfb&|fNf>rW#yT-z
zFZ3{fkS85Ztijg2OZ(@E0q}!!WOM+mF#%4&?c$bV^x-5PymA&W!iT@`+|Bs9o$37t
zYEDZ<5MAeMvtZyJ<-9VNO>GhWP5WfQ8&u-!NwP`_9Jl_!R+*gzbL}^y;1HF9srQI@
zQ!zSF94yyrot3_$7rs2Q9(lN@8(Z7?JC7IN6&ZqC98%9Y+0*W<R`oj}XO#|#J4N`K
zqGuE0`W#L`JhP1TVv69ti**K40zX|zy}cjpfEr3UH(5+@(+E~`beyq1oCmla#U3Px
zqSPM>yNL?L%0;s&Bwl^h_tDOcw4TXhyeE+3P6ynD0bM2c!<#_=@Ke{#al%nSG6El!
z^d|FfFEIj3MwnLmOE=&p=l|K|4?X)QRe1<J*zEtA;j!^S&6|e(gZh#J1hrdnRX?oU
z#^wDHLfeQ`gx+NBm6_fExz?d^Bji%FbyMW7ykY}X{qbw17&EgUg{2fnHP)=xvhP1l
z!yPC9ED&-1n?to)Q_w(_+I9&4POox6Cu1)tvV3kmng8F>VErefE?XuBa7TSECEWg(
z-YKXq;s1j3U%N2)zpgWiuquNdPcw_nBwYA2PV>K@g9abmnBa45t-MAJYK#A$abBI;
z6Nc0MA@wJFIt(vDuoLZS^k_^*!zOPgVeI<Vx5Wp`8|1t0NvKM_L|b%W<=_<rZ|OE3
zA?HwLko_Nwmhp;ztxFoMu+=!ZX~g$CjXPC=E``^!-y<NZ13qK`MTUPH+_v~{!uY>h
zVcJsI`85M%3p*%07~G5pK>shl9l<;p(Z(G*3i^ltNi&m3H>wIkl9FZSc=GZd*Z5&u
z2P@A0YrsR`c+0=G<w2{)xWN0x=l^}=9a<pow}sy$cy9iYP!9}h<dBnnqB9Y*6%%AL
z<`9Vm!-&_$q9rKRu>X0`-Jg>kf%hS!qp%XvudkwiN|^*TW5RI1#l`G9>4)IM`M-f(
zka>?!U)u(tG|00TcCO>}`+&%Q^4kA%?)~2!`!_$YKXKr9dY%b)e*R<ZtAA7XRTHsh
zib|pw#P10QC-AH1y0;Pka1|V^a2m)fogXgaPb9_K{FQ66f#T{k@%F8?iulsy@43In
zi--QzgnntUrEv#tFJ|~3Vtr`UwE5oN!jOHjQ2q#qb#(Wu)~XRr7HUKWF2?0$XZ~N@
z(|J|U<xZQ1viDA+U;fc7-!lE#0Gj0{^=H~217h|~_DjJ8A&*nrul|GkhcBDia*NLN
zKQ{>W0E{(Mo}d3v`k%*$`)1iv*(0-=7M<C@ct`(n70kW^pm@PQ!WF>t3IA93|E>N1
zYXt6&T3eNwyzBgbZ{#denD!Y6;^=QPE_O-1`KZAFo;B1O+~+#}&%<+%1;GPh!R%o7
zg^QwI@`lUHD>2+(U02IvcGpnsMKe;}^Ey%u^x_)1T}AlvtH39klL|WK*NnS$HV0!h
zqYJh%KygS@ODfUeLN!bOkv5*t#*pc+sJ)g*sqxZNZ27Xug0Irja*#J>)0~#E-4}k@
zdkrOeEmm$U1@haiwq1n5zuM>3<ay6)ZaRmOR6pHSv-)($qp1Ef!E@G))X&;yTDaAx
zaQ<!=UHfdfhz_ZOS8rY7YSdLJ#dr@gb}IMBr?UR%trg|eQcQu2&5N&QMQb(wg%1sS
zM3!FuxOkP4D=7&BbH;lFC4h>5WFOW^9f)*Xd-8%4(^C6{<jrNX`GSP(ajE>w%z1t0
z<vsbEGg+I!%+Kk*j}NgClnc{EbE4#ogoex?_yaPElOK2W&xcPM=JVUUFZPBZ6Af8P
zOO8oy^pAEKlImXcW`9^hF16^WO-@ZeQ2mFcL!pb(8xz!GeM^v(R`~Q6WsJ8lxks7g
zEp}%r!>;zAvd7^QRFRl?PLa9lJ0ITsa%BJacGiEcY1K22Xdb;Tg!6ZG-a72Cn3$s%
ztXoSDFdgu&VBY|i8Ngu{=tBp|EgE%M)owAdB*pm>EsxR(pR?Hx^>rHbcz<JZTA;dH
z;(slycDcFImdXl(b5@ZK3Off=&f}!D4*@srM(`QJg0||5GaL0V1`)<+gMOLGZa2C`
zH|xx#zmz#SFMCTC#8I;1zhUT=EbtZ#de8WoA)d4Shmd%@U4f|rU9GV+jb~2;+vXiG
z$wKE@dKi3_^<O1+Z<&3$($8>vi5}S126j(r`1aX&CEAXs=Xl}piPWhM-JBi?`(?wN
ga(=CaB&ThcY;UW4&rcHhyVs~OcR?Al^fTB01z3b-m;e9(

diff --git a/misc/paper.bib b/misc/paper.bib
index 91ea0b9..06547bc 100644
--- a/misc/paper.bib
+++ b/misc/paper.bib
@@ -3,21 +3,19 @@ @Manual{ceterisParibus
     author = {Biecek, Przemysław},
     year = {2018},
     note = {R package version 0.2.1},
-    url = {https://CRAN.R-project.org/package=ceterisParibus}
+    url = {http://CRAN.R-project.org/package=ceterisParibus}
   }
 
 @article{2018arXiv180608915B,
-   author = {{Biecek}, Przemysław},
+	author = {{Biecek}, Przemysław},
     title = "{DALEX: explainers for complex predictive models}",
-  journal = {ArXiv e-prints},
-archivePrefix = "arXiv",
-   eprint = {1806.08915},
- primaryClass = "stat.ML",
- keywords = {Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Statistics - Applications},
-     year = 2018,
-    month = jun,
-   adsurl = {http://adsabs.harvard.edu/abs/2018arXiv180608915B},
-  adsnote = {Provided by the SAO/NASA Astrophysics Data System}
+    url = {http://arxiv.org/abs/1806.08915},
+	eprint = {1806.08915},
+	primaryClass = "stat.ML",
+	keywords = {Statistics - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Statistics - Applications},
+    year = 2018,
+	adsurl = {http://adsabs.harvard.edu/abs/2018arXiv180608915B},
+	adsnote = {Provided by the SAO/NASA Astrophysics Data System}
 }
 
 
@@ -26,7 +24,7 @@ @book{collett2015modelling
   author={Collett, David},
   isbn={9781498731690},
   series={Chapman \& Hall/CRC Texts in Statistical Science},
-  url={https://books.google.pl/books?id=Okf7CAAAQBAJ},
+  url={http://books.google.pl/books?id=Okf7CAAAQBAJ},
   year={2015},
   publisher={CRC Press}
 }
@@ -43,11 +41,12 @@ @article{lu2003modeling
 @Article{randomForestSRC,
   title = {Random survival forests},
   author = {Ishwaran, Hemant and Kogalur, Udaya B. and Blackstone, Eugene H. and Lauer, Michael S.},
-  journal = {Ann. Appl. Statist.},
+  journal = {The Annals of Applied Statistics},
   year = {2008},
   volume = {2},
   number = {3},
   pages = {841--860},
+  doi = {doi:10.1214/08-AOAS169},
   url = {http://arXiv.org/abs/0811.1645v1},
   pdf = {http://arxiv.org/pdf/0811.1645},
 }
@@ -61,8 +60,8 @@ @article{ELEUTERI2003855
   year = {2003}, 
   note = {Advances in Neural Networks Research: IJCNN '03},
   issn = {0893-6080},
-  doi = {https://doi.org/10.1016/S0893-6080(03)00098-4},
-  url = {http://www.sciencedirect.com/science/article/pii/S0893608003000984},
+  doi = {10.1016/S0893-6080(03)00098-4},
+  url = {http://doi.org/10.1016/S0893-6080(03)00098-4},
   author = {Eleuteri, Antonio and Tagliaferri, Roberto and Milano, Leopoldo and De Placido, Sabino and De Laurentiis, Michele},
   keywords = {Survival analysis, Conditioning probability estimation, Neural networks, Bayesian learning, MCMC methods}
 }
@@ -72,7 +71,7 @@ @article{RJ-2017-016
   title = {{pdp: An R Package for Constructing Partial Dependence Plots}},
   year = {2017},
   journal = {{The R Journal}},
-  url = {https://journal.r-project.org/archive/2017/RJ-2017-016/index.html},
+  url = {http://journal.r-project.org/archive/2017/RJ-2017-016/index.html},
   pages = {421--436},
   volume = {9},
   number = {1}
@@ -94,13 +93,11 @@ @Article{BSScore
 @ARTICLE{2018arXiv180401955S,
    author = {Staniak, Mateusz and Biecek, Przemysław},
     title = "{Explanations of model predictions with live and breakDown packages}",
-  journal = {ArXiv e-prints},
-archivePrefix = "arXiv",
    eprint = {1804.01955},
  primaryClass = "stat.ML",
  keywords = {Statistics - Machine Learning, Computer Science - Learning, Statistics - Applications},
      year = 2018,
-    month = apr,
+	url = {http://arxiv.org/abs/1804.01955},
    adsurl = {http://adsabs.harvard.edu/abs/2018arXiv180401955S},
   adsnote = {Provided by the SAO/NASA Astrophysics Data System}
 }
@@ -108,7 +105,7 @@ @ARTICLE{2018arXiv180401955S
 
 @article{Molnar2018,
   doi = {10.21105/joss.00786},
-  url = {https://doi.org/10.21105/joss.00786},
+  url = {http://doi.org/10.21105/joss.00786},
   year  = {2018},
   month = {jun},
   publisher = {The Open Journal},
@@ -128,7 +125,7 @@ @misc{pramit_choudhary_2018_1198885
   month        = mar,
   year         = 2018,
   doi          = {10.5281/zenodo.1198885},
-  url          = {https://doi.org/10.5281/zenodo.1198885}
+  url          = {http://doi.org/10.5281/zenodo.1198885}
 }
 
 
@@ -160,8 +157,8 @@ @article{doi:10.4155/fmc.11.23
   year = {2011},
   doi = {10.4155/fmc.11.23},
   note ={PMID: 21554073},
-  URL = {https://doi.org/10.4155/fmc.11.23},
-  eprint = {https://doi.org/10.4155/fmc.11.23}
+  URL = {http://doi.org/10.4155/fmc.11.23},
+  eprint = {http://doi.org/10.4155/fmc.11.23}
 }
 
 
diff --git a/misc/paper.md b/misc/paper.md
index 37197ee..518032c 100644
--- a/misc/paper.md
+++ b/misc/paper.md
@@ -1,5 +1,5 @@
 ---
-title: 'survxai: an R package for model agnostic explanations of survival models'
+title: 'survxai: an R package for model-agnostic explanations of survival models'
 authors:
 - affiliation: 1, 2
   name: Aleksandra Grudziaz
@@ -10,7 +10,7 @@ authors:
 - affiliation: 1, 2
   name: Przemyslaw Biecek
   orcid: 0000-0001-8423-1823
-date: "3 August 2018"
+date: "23 August 2018"
 output: pdf_document
 bibliography: paper.bib
 tags:
@@ -20,63 +20,63 @@ tags:
 - interpretable machine learning
 affiliations:
 - index: 1
-  name: Faculty of Mathematics, Informatics, and Mechanics, University of Warsaw
-- index: 2
   name: Faculty of Mathematics and Information Science, Warsaw University of Technology
+- index: 2
+  name: Faculty of Mathematics, Informatics, and Mechanics, University of Warsaw
 ---
 
 # Introduction
 
 <!-- A summary describing the high-level functionality and purpose of the software for a diverse, non-specialist audience-->
 
-Predictive models are widely used in the supervised machine learning. Three most common classes of such models are: *regression models*, here the target variable is continuous numeric, *classification models* here the target variable is binary or categorical and *survival models* here the target is some censored variable. Common examples of censored variables are time to death (but some cases lived for x years and are still alive), cessation of service by the customer or failure of a machine component.
+Predictive models are widely used in supervised machine learning. Three most common classes of such models are: *regression models*, where the target variable is continuous numeric, *classification models*, where the target variable is binary or categorical and *survival models*, where the target is some censored variable. Common examples of censored variables are times to death (but some cases lived for x years and are still alive), cessation of service by customer, or failure of machine components.
 
-Modern predictive models are often complex in structure. Think about neural networks [@ELEUTERI2003855] or random forest [@randomForestSRC]. Such models may be described by thousands of coefficients. Often such flexibility leads to high performance, but makes these models opaque, hard to understand. It is acceptable in cases in which only the model accuracy is important, but in cases that involve human decisions it may not be enough. To trust model predictions one needs to see which features are important and how model predictions would change if some feature was changed. 
+Modern predictive models are often complex in structure; for example neural networks [@ELEUTERI2003855] or random forest [@randomForestSRC]. Such sophisticated tools are also more and more often used in survival analysis. These models may be described by thousands of coefficients. Often such flexibility leads to high performance, but makes models opaque and hard to understand. This is acceptable in cases where only the model accuracy is important, but in cases that involve human decisions, it may not be informative enough. To trust model predictions one needs to see which features are important and how model predictions would change if some feature was changed.
 
-The area of model interpretability or explanability gains quickly attention of machine learning experts. Understanding of complex models leads not only to higher trust in model predictions but also to better models. Better means that they are more robust and maintain high accuracy on validation data. See examples in `DALEX`  [@2018arXiv180608915B] or `iml` [@Molnar2018] R packages. 
+The area of model interpretability or explanability has quickly gained the attention of machine learning experts. Understanding of complex models leads not only to higher trust in model predictions but also better models. Better, means that the models are more robust and obtains higher accuracy on validation data. See examples in the `DALEX`  [@2018arXiv180608915B] or `iml` [@Molnar2018] R packages.
 
-Existing tools for model agnostic explanations are focused on regression models and classification problems as in both cases model predictions may be summarised by a single number. Survival models require different approach as predictions are in a form of survival curves. Demand for such explainers leads to some model specific solutions, like `iSurvive` introduced by [@pmlr-v70-dempsey17a] for continuous time hidden Markov model. Yet, we are lacking of model agnostic tools for survival models.
+Existing tools for model agnostic explanations are focused on regression models and classification problems, as in both cases model predictions that may be summarised by a single number. Survival models require different approaches as predictions are in a form of survival curves. Demand for such explainers has led to some model specific solutions, like `iSurvive` [@pmlr-v70-dempsey17a] for continuous time hidden Markov models. Yet, there is currently a lack of model agnostic tools for survival models.
 
-The `survxai` fills out this gap. This R package is designed to deliver local and global explanations for survival models in a model agnostic fashion. In the package documentation we demonstrate examples for Cox models and for Survival Random Forest models.
-The `survxai` package consists new implementations and visualisations of explainers designed for survival models. Functions are well documented, package is supplemented with unit tests and illustrations. 
-Regardless of the complexity of the model, methods implemented in the `survxai` package maintain a certain level of interpretability, important in medical applications [@collett2015modelling], churn analysis [@lu2003modeling] and others.
+The `survxai` fills this gap. This R package is designed to deliver local and global explanations for survival models, in a model-agnostic fashion. In the package documentation we demonstrate examples for survival random forest models and for Cox models.
+The `survxai` package consists of new implementations and visualisations of explainers, designed for survival models. Functions are well documented and the package is supplemented with unit tests, and illustrations.
+Regardless of the complexity of the model, the methods implemented in the `survxai` package maintain a certain level of interpretability, important in medical applications [@collett2015modelling], churn analysis [@lu2003modeling] and others.
 
 
 <!-- A clear statement of need that illustrates the purpose of the software-->
 # Explanations of survival models
  
-The R package `survxai` is a tool for creating explanations of survival models. It's model agnostic, thus is working with both complex and simple survival models. It also allows to compare two or more models. 
+The R package `survxai` is a tool for creating explanations of survival models. It is model-agnostic, and thus works for both complex and simple survival models. It also allows for comparisons between two or more models.
  
-Currently, four classes of model explainers are implemented. Two for local explanations (for a single prediction), and two for global explanations (for a whole model). 
+Currently, four classes of model explainers are implemented. Two for local explanations (for a single prediction), and two for global explanations (for a whole model).
 
-Package `survxai` is available on CRAN and a development version of the package can be found on [https://github.com/MI2DataLab/survxai](https://github.com/MI2DataLab/survxai).
+The package `survxai` is available on CRAN. It can be install using the command `install.packages('survxai')`. The development version of the package can be found on [https://github.com/MI2DataLab/survxai](https://github.com/MI2DataLab/survxai).
 
 **Local methods** are the explanations of one observation.
  
-- **Ceteris Paribus** plot presents model responses around a single point in the feature space [@ceterisParibus]. See an example in Figure 1. Each panel is related to a single variable. Single panel shows how a model prediction (survival curve) would change if only a single variable will be changed. It if usefull for *what-if* reasoning. Each curve in a panle is realted a different value of the selected variable.
-Ceteris Paribus plot illustrates how may the survival curve change along with the changing values of the variable. 
+- **The Ceteris Paribus** plot presents model responses around a single point in the feature space [@ceterisParibus]. See Figure 1 for an example. Each panel is related to a single variable. Each single panel shows how a model prediction (survival curve) would change if only a single variable were changed. It is useful for *what-if* reasoning. Each curve in a panel is related to a different value of the selected variable.
+The Ceteris Paribus plot illustrates how the survival curve may change with the changing of values of variable.
 
-![Ceteris Paribus plot for Cox Proportional Hazards model with three variables. Black survival curve corresponds to a observation of interest. Middle panel shows that prediction for sex=0 are worse than for sex=1.](img/ceteris_paribus.png)
+![Ceteris Paribus plot for survival random forest model with three variables. The black dashed survival curve corresponds to an observation of interest. The left panel shows the survival curves for different values of bilirubin. Colors correspond to mean survival curves of observations from quintiles. From red which is the first quintile to blue which is the last one. The middle panel shows that prediction for sex=0 is worse than for sex=1 for times less than 7.5. The right panel analogously shows survival curves for different levels of the variable stage.](img/ceteris_paribus.png)
 
-- **break down** plot presents variable contributions in final predictions  [@2018arXiv180401955S]. See an example in Figure 2. The Break Down of prediction  for survival model helps to understand which factors drive survival probability for a single observation.
+- **The break down** plot presents variable contributions in final predictions  [@2018arXiv180401955S]. See Figure 2 for an example. The break down of predictions for survival models help to understand which factors drive survival probabilities for a single observation.
 
-![Break Down plot for Cox Proportional Hazards model. Variables bili and stage have highest impact on final prediction.](img/breakdown.png)
+![Break down plot for survival random forest model. Variables bili and stage have the highest impact on the final prediction.](img/breakdown.png)
  
 **Global methods** are model performance and explanations of the conditional model structure.
  
-- **variable response** plot is designed to better understand the relation between a variable and a model output. See an example in Figure 3. Variable response plot illustrates how the mean survival curve change along with the changing values of the variable. It is inspired by partial dependence plots [@RJ-2017-016]. 
+- **The variable response** plot is designed to better understand the relation between a variable and a model output. See Figure 3 for an example. The variable response plot illustrates how the mean survival curve changes along with the changing values of the variable. It is inspired by partial dependence plots [@RJ-2017-016].
 
-![Variable response plot for three models and variable sex. In survival random forest the sex variable affects model predictions in a different way than in  other models.](img/variable_response.png)
+![Variable response plots for three models and variable sex. In survival random forest, the sex variable affects model predictions in a different way than in  other models.](img/variable_response.png)
  
-- **model performance** curves present prediction error for the chosen survival model depending on time. See an example in Figure 4. For computing prediction error we use the expected Brier Score [@BSScore]. At a given time point t, the Brier score for a single observation is the squared difference between observed survival status and a model-based prediction of surviving time t.
+- **The model performance** curves present prediction error for the chosen survival model, depending on time. See Figure 4 for an example. For computing prediction error, we use the expected Brier Score [@BSScore]. At a given time point t, the Brier score for a single observation is the squared difference between observed survival status and a model-based prediction of surviving time t.
 
-![Model performance plot for three models. In random forest model predictions are less accurate after year 4.](img/model_performance.png)
+![Model performance plots for three models. In random forest model, predictions are less accurate after year 4.](img/model_performance.png)
 
 <!-- Mentions (if applicable) of any ongoing research projects using the software or recent scholarly publications enabled by it -->
 
 # Conclusions and future work
 
-Explainers implemented in the `survxai` package allow exploring one or more models in a feature-by-feature fashion. This approach will miss interactions between variables that may be handled by the models. The main problem with integrations is that number of interactions grows rapidly with the number of features what makes it hard to present in a readable form. 
+Explainers implemented in the `survxai` package allow for exploration of one or more models in a feature-by-feature fashion. This approach will miss interactions between variables that may be handled by the models. The main problem with integrations is that number of interactions grows rapidly with the number of features what makes it hard to present in a readable form.
 
 # Acknowledgments
 
@@ -87,3 +87,4 @@ The work was supported by NCN Opus grant 2016/21/B/ST6/02176.
 # References
 
 
+