%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : CSR124_8 : TPTP v9.3.1. Released v8.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n008.cluster.edu
% Model : x86_64 x86_64
% CPU : Intel(R) Xeon(R) CPU E5-2620 v4 2.10GHz
% Memory : 8046.5625MB
% OS : Linux 6.8.0-71-generic
% CPULimit : 300s
% WCLimit : 300s
% DateTime : Tue Sep 29 09:43:47 AM UTC 2026
% Result : Theorem 3.59s 1.28s
% Output : Refutation 3.59s
% Verified :
% SZS Type : Refutation
% Derivation depth : 15
% Number of leaves : 10
% Syntax : Number of formulae : 56 ( 17 unt; 0 typ; 6 def)
% Number of atoms : 249 ( 23 equ)
% Maximal formula atoms : 6 ( 4 avg)
% Number of connectives : 102 ( 44 ~; 44 |; 8 &)
% ( 6 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of FOOLs : 139 ( 135 fml; 4 var)
% Number of types : 3 ( 1 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 16 ( 13 usr; 12 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 2 ( 0 sgn 2 !; 0 ?; 2 :)
% Comments :
%------------------------------------------------------------------------------
tff(type_def_5,type,
num: $tType ).
tff(func_def_5,type,
bG0: $o ).
tff(func_def_8,type,
bG1: $o ).
tff(pred_def_1,type,
holdsDuring_THFTYPE_IiooI: ( $i * $o ) > $o ).
tff(f1,axiom,
likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ax) ).
tff(f2,axiom,
holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ax_001) ).
tff(f3,conjecture,
holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),
( likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
& likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) )),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',con) ).
tff(f4,negated_conjecture,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),
( likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
& likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) )),
inference(negated_conjecture,[status(cth)],[f3]) ).
tff(f5,definition,
( likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
<=> ( bG0 = $true ) ),
introduced(definition,[new_symbols(definition,[bG0])],[fool_formula_definition]) ).
tff(f6,plain,
holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG0),
inference(fool_elimination,[],[f2,f5]) ).
tff(f7,definition,
( ( likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
& likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) )
<=> ( $true = bG1 ) ),
introduced(definition,[new_symbols(definition,[bG1])],[fool_formula_definition]) ).
tff(f8,plain,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG1),
inference(fool_elimination,[],[f4,f7]) ).
tff(f9,plain,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG1),
inference(flattening,[],[f8]) ).
tff(f10,plain,
( ( ( likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
& likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) )
| ( $true != bG1 ) )
& ( ( $true = bG1 )
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
| ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) ) ),
inference(nnf_transformation,[],[f7]) ).
tff(f11,plain,
( ( ( likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
& likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) )
| ( $true != bG1 ) )
& ( ( $true = bG1 )
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
| ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) ) ),
inference(flattening,[],[f10]) ).
tff(f12,plain,
( ( likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
| ( bG0 != $true ) )
& ( ( bG0 = $true )
| ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) ) ),
inference(nnf_transformation,[],[f5]) ).
tff(f13,plain,
( ( $true = bG1 )
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
| ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) ),
inference(cnf_transformation,[],[f11]) ).
tff(f14,plain,
( likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
| ( $true != bG1 ) ),
inference(cnf_transformation,[],[f11]) ).
tff(f16,plain,
( ( bG0 = $true )
| ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) ),
inference(cnf_transformation,[],[f12]) ).
tff(f17,plain,
( likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
| ( bG0 != $true ) ),
inference(cnf_transformation,[],[f12]) ).
tff(f18,plain,
likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i),
inference(cnf_transformation,[],[f1]) ).
tff(f19,plain,
holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG0),
inference(cnf_transformation,[],[f6]) ).
tff(f20,plain,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG1),
inference(cnf_transformation,[],[f9]) ).
tff(f22,plain,
! [X0: $o] :
( ( $false = (X0) )
| ( $true = (X0) ) ),
introduced(definition,[],[fool_exhaustiveness_axiom]) ).
tff(f24,definition,
( spl2_1
<=> likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) ),
introduced(definition,[new_symbols(definition,[spl2_1])],[avatar_definition]) ).
tff(f28,definition,
( spl2_2
<=> ( bG0 = $true ) ),
introduced(definition,[new_symbols(definition,[spl2_2])],[avatar_definition]) ).
tff(f29,plain,
( ( bG0 != $true )
| spl2_2 ),
inference(avatar_component_clause,[],[f28]) ).
tff(f30,plain,
( ( bG0 = $true )
| ~ spl2_2 ),
inference(avatar_component_clause,[],[f28]) ).
tff(f31,plain,
( ~ spl2_1
| spl2_2 ),
inference(avatar_split_clause,[],[f16,f28,f24]) ).
tff(f32,plain,
( ~ spl2_2
| spl2_1 ),
inference(avatar_split_clause,[],[f17,f24,f28]) ).
tff(f34,definition,
( spl2_3
<=> likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i) ),
introduced(definition,[new_symbols(definition,[spl2_3])],[avatar_definition]) ).
tff(f38,definition,
( spl2_4
<=> ( $true = bG1 ) ),
introduced(definition,[new_symbols(definition,[spl2_4])],[avatar_definition]) ).
tff(f39,plain,
( ( $true != bG1 )
| spl2_4 ),
inference(avatar_component_clause,[],[f38]) ).
tff(f40,plain,
( ( $true = bG1 )
| ~ spl2_4 ),
inference(avatar_component_clause,[],[f38]) ).
tff(f41,plain,
( ~ spl2_1
| ~ spl2_3
| spl2_4 ),
inference(avatar_split_clause,[],[f13,f38,f34,f24]) ).
tff(f42,plain,
( ~ spl2_4
| spl2_1 ),
inference(avatar_split_clause,[],[f14,f24,f38]) ).
tff(f44,plain,
spl2_3,
inference(avatar_split_clause,[],[f18,f34]) ).
tff(f49,plain,
( ~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),$false)
| ( $true = bG1 ) ),
inference(superposition,[],[f20,f22]) ).
tff(f51,plain,
( ~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),$false)
| spl2_4 ),
inference(forward_subsumption_resolution,[],[f49,f39]) ).
tff(f53,plain,
( ! [X0: $o] :
( ~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),(X0))
| ( $true = (X0) ) )
| spl2_4 ),
inference(superposition,[],[f51,f22]) ).
tff(f54,plain,
( ( bG0 = $true )
| spl2_4 ),
inference(resolution,[],[f53,f19]) ).
tff(f55,plain,
( $false
| spl2_2
| spl2_4 ),
inference(forward_subsumption_resolution,[],[f54,f29]) ).
tff(f56,plain,
( spl2_2
| spl2_4 ),
inference(avatar_contradiction_clause,[],[f55]) ).
tff(f64,plain,
( ~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),$true)
| ~ spl2_4 ),
inference(superposition,[],[f20,f40]) ).
tff(f67,plain,
( holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),$true)
| ~ spl2_2 ),
inference(superposition,[],[f19,f30]) ).
tff(f69,plain,
( $false
| ~ spl2_2
| ~ spl2_4 ),
inference(forward_subsumption_resolution,[],[f67,f64]) ).
tff(f70,plain,
( ~ spl2_2
| ~ spl2_4 ),
inference(avatar_contradiction_clause,[],[f69]) ).
cnf(s1,plain,
( ~ spl2_1
| spl2_2 ),
inference(sat_conversion,[],[f31]) ).
cnf(s2,plain,
( spl2_1
| ~ spl2_2 ),
inference(sat_conversion,[],[f32]) ).
cnf(s3,plain,
( ~ spl2_1
| ~ spl2_3
| spl2_4 ),
inference(sat_conversion,[],[f41]) ).
cnf(s4,plain,
( spl2_1
| ~ spl2_4 ),
inference(sat_conversion,[],[f42]) ).
cnf(s6,plain,
spl2_3,
inference(sat_conversion,[],[f44]) ).
cnf(s7,plain,
( spl2_2
| spl2_4 ),
inference(sat_conversion,[],[f56]) ).
cnf(s10,plain,
( ~ spl2_2
| ~ spl2_4 ),
inference(sat_conversion,[],[f70]) ).
cnf(s11,plain,
( ~ spl2_1
| spl2_4 ),
inference(rat,[],[s3,s6]) ).
cnf(s12,plain,
spl2_1,
inference(rat,[],[s7,s2,s4]) ).
cnf(s13,plain,
spl2_4,
inference(rat,[],[s11,s12]) ).
cnf(s14,plain,
spl2_2,
inference(rat,[],[s1,s12]) ).
cnf(s15,plain,
$false,
inference(rat,[],[s10,s13,s14]) ).
tff(f71,plain,
$false,
inference(avatar_sat_refutation,[],[s15]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : CSR124_8 : TPTP v9.3.1. Released v8.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.18 % Computer : n008.cluster.edu
% 0.09/0.18 % Model : x86_64 x86_64
% 0.09/0.18 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.18 % Memory : 8046.5625MB
% 0.09/0.18 % OS : Linux 6.8.0-71-generic
% 0.09/0.18 % CPULimit : 300
% 0.09/0.18 % WCLimit : 300
% 0.09/0.18 % DateTime : Mon Sep 28 23:35:40 UTC 2026
% 0.09/0.19 % CPUTime :
% 0.09/0.19 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.22 Running first-order theorem proving
% 0.09/0.22 Running: /export/starexec/sandbox/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 3.59/1.28 % (2760523)Detected formulas, will run a generic FOF schedule.
% 3.59/1.28 % (2760531)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=3294459917:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.59/1.28 % (2760534)dis-21_1_sil=8000:lcm=predicate:random_seed=3649663440:st=5:avsq=on:i=129:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/129Mi)
% 3.59/1.28 % (2760528)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=full:npcc=on:drc=off:sp=weighted_frequency:spb=goal:fd=preordered:foolp=on:random_seed=2097348296:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.59/1.28 % (2760529)lrs+11_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:lma=off:spb=units:urr=ec_only:bce=on:s2agt=64:updr=off:random_seed=1267892272:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.59/1.28 % (2760530)lrs+1010_1_anc=all:sfv=off:to=kbo:ncem=casc2026/models/loop7.pt:sil=128000:npcc=on:prc=on:sos=all:bsr=unit_only:sac=on:random_seed=1568333863:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.59/1.28 % (2760533)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=989548097:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.59/1.28 % (2760531)Refutation not found, incomplete strategy
% 3.59/1.28 % (2760531)------------------------------
% 3.59/1.28 % (2760531)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.59/1.28 % (2760531)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.59/1.28 % (2760531)CaDiCaL version: 2.1.3
% 3.59/1.28 % (2760531)Termination reason: Refutation not found, incomplete strategy
% 3.59/1.28 % (2760531)Time elapsed: 0.001 s
% 3.59/1.28 % (2760531)Peak memory usage: 88 MB
% 3.59/1.28 % (2760534)Refutation not found, incomplete strategy
% 3.59/1.28 % (2760534)------------------------------
% 3.59/1.28 % (2760534)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.59/1.28 % (2760534)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.59/1.28 % (2760534)CaDiCaL version: 2.1.3
% 3.59/1.28 % (2760534)Termination reason: Refutation not found, incomplete strategy
% 3.59/1.28 % (2760534)Time elapsed: 0.001 s
% 3.59/1.28 % (2760534)Peak memory usage: 88 MB
% 3.59/1.28 % (2760533)First to succeed.
% 3.59/1.28 % (2760533)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-2760523"
% 3.59/1.28 % (2760532)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=3943889913:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.59/1.28 % (2760532)Also succeeded, but the first one will report.
% 3.59/1.28 % (2760531)------------------------------
% 3.59/1.28 % (2760531)------------------------------
% 3.59/1.28 % (2760534)------------------------------
% 3.59/1.28 % (2760534)------------------------------
% 3.59/1.28 % (2760533)Refutation found. Thanks to Tanya!
% 3.59/1.28 % SZS status Theorem for theBenchmark
% 3.59/1.28 % SZS output start Proof for theBenchmark
% See solution above
% 3.59/1.29 % (2760533)------------------------------
% 3.59/1.29 % (2760533)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.59/1.29 % (2760533)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.59/1.29 % (2760533)CaDiCaL version: 2.1.3
% 3.59/1.29 % (2760533)Termination reason: Refutation
% 3.59/1.29 % (2760533)Time elapsed: 0.003 s
% 3.59/1.29 % (2760533)Peak memory usage: 90 MB
% 3.59/1.29 % (2760533)Instructions burned: 2 (million)
% 3.59/1.29 % (2760533)------------------------------
% 3.59/1.29 % (2760533)------------------------------
% 3.59/1.29 % (2760523)Success in time 0.42 s
% 3.59/1.29 % Vampire exiting
%------------------------------------------------------------------------------