%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : CSR126_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 : n026.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 09:43:48 AM UTC 2026
% Result : Theorem 3.51s 1.28s
% Output : Refutation 3.51s
% Verified :
% SZS Type : Refutation
% Derivation depth : 18
% Number of leaves : 7
% Syntax : Number of formulae : 46 ( 17 unt; 0 typ; 3 def)
% Number of atoms : 280 ( 40 equ)
% Maximal formula atoms : 6 ( 6 avg)
% Number of connectives : 89 ( 36 ~; 41 |; 6 &)
% ( 4 <=>; 2 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of FOOLs : 185 ( 181 fml; 4 var)
% Number of types : 3 ( 1 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 13 ( 10 usr; 8 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 22 ( 22 !; 0 ?; 22 :)
% Comments :
%------------------------------------------------------------------------------
tff(type_def_5,type,
num: $tType ).
tff(func_def_5,type,
bG0: $o ).
tff(func_def_8,type,
bG1: $i > $o ).
tff(func_def_9,type,
bG2: $o ).
tff(pred_def_1,type,
holdsDuring_THFTYPE_IiooI: ( $i * $o ) > $o ).
tff(f1,axiom,
! [X0: $i] : holdsDuring_THFTYPE_IiooI(X0,likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ax) ).
tff(f2,axiom,
! [X0: $i] :
holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),
( likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0)
=> likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0) )),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ax_001) ).
tff(f3,conjecture,
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',con) ).
tff(f4,negated_conjecture,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)),
inference(negated_conjecture,[status(cth)],[f3]) ).
tff(f5,definition,
( likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
<=> ( bG0 = $true ) ),
introduced(definition,[new_symbols(definition,[bG0])],[fool_formula_definition]) ).
tff(f6,plain,
! [X0: $i] : holdsDuring_THFTYPE_IiooI(X0,bG0),
inference(fool_elimination,[],[f1,f5]) ).
tff(f7,definition,
! [X0: $i] :
( ( likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0)
=> likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0) )
<=> ( $true = bG1(X0) ) ),
introduced(definition,[new_symbols(definition,[bG1])],[fool_formula_definition]) ).
tff(f8,plain,
! [X0: $i] : holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG1(X0)),
inference(fool_elimination,[],[f2,f7]) ).
tff(f9,definition,
( likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
<=> ( $true = bG2 ) ),
introduced(definition,[new_symbols(definition,[bG2])],[fool_formula_definition]) ).
tff(f10,plain,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG2),
inference(fool_elimination,[],[f4,f9]) ).
tff(f11,plain,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG2),
inference(flattening,[],[f10]) ).
tff(f12,plain,
! [X0: $i] :
( ( likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0) )
<=> ( $true = bG1(X0) ) ),
inference(ennf_transformation,[],[f7]) ).
tff(f13,plain,
( ( likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
| ( $true != bG2 ) )
& ( ( $true = bG2 )
| ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) ) ),
inference(nnf_transformation,[],[f9]) ).
tff(f14,plain,
! [X0: $i] :
( ( likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0)
| ( $true != bG1(X0) ) )
& ( ( $true = bG1(X0) )
| ( ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
& likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0) ) ) ),
inference(nnf_transformation,[],[f12]) ).
tff(f15,plain,
! [X0: $i] :
( ( likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0)
| ( $true != bG1(X0) ) )
& ( ( $true = bG1(X0) )
| ( ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
& likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0) ) ) ),
inference(flattening,[],[f14]) ).
tff(f16,plain,
( ( likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
| ( bG0 != $true ) )
& ( ( bG0 = $true )
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i) ) ),
inference(nnf_transformation,[],[f5]) ).
tff(f17,plain,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG2),
inference(cnf_transformation,[],[f11]) ).
tff(f18,plain,
! [X0: $i] : holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),bG1(X0)),
inference(cnf_transformation,[],[f8]) ).
tff(f19,plain,
( ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
| ( $true = bG2 ) ),
inference(cnf_transformation,[],[f13]) ).
tff(f20,plain,
( ( $true != bG2 )
| likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i) ),
inference(cnf_transformation,[],[f13]) ).
tff(f22,plain,
! [X0: $i] :
( ( $true = bG1(X0) )
| ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0) ),
inference(cnf_transformation,[],[f15]) ).
tff(f23,plain,
! [X0: $i] :
( ( $true != bG1(X0) )
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0)
| likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0) ),
inference(cnf_transformation,[],[f15]) ).
tff(f25,plain,
( ( bG0 != $true )
| likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i) ),
inference(cnf_transformation,[],[f16]) ).
tff(f26,plain,
! [X0: $i] : holdsDuring_THFTYPE_IiooI(X0,bG0),
inference(cnf_transformation,[],[f6]) ).
tff(f28,plain,
! [X0: $o] :
( ( $true = (X0) )
| ( $false = (X0) ) ),
introduced(definition,[],[fool_exhaustiveness_axiom]) ).
tff(f31,plain,
( ( $true != $true )
| likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
| ( bG0 = $false ) ),
inference(superposition,[],[f25,f28]) ).
tff(f34,plain,
( ( $true != $true )
| likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
| ( bG2 = $false ) ),
inference(superposition,[],[f20,f28]) ).
tff(f35,plain,
( ~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),$true)
| ( bG2 = $false ) ),
inference(superposition,[],[f17,f28]) ).
tff(f37,plain,
( likes_THFTYPE_IiioI(lSue_THFTYPE_i,lBill_THFTYPE_i)
| ( bG2 = $false ) ),
inference(trivial_inequality_removal,[],[f34]) ).
tff(f38,plain,
( likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
| ( bG0 = $false ) ),
inference(trivial_inequality_removal,[],[f31]) ).
tff(f39,plain,
! [X0: $o] :
( ~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),(X0))
| ( bG2 = $false )
| ( $false = (X0) ) ),
inference(superposition,[],[f35,f28]) ).
tff(f40,plain,
! [X0: $i] :
( ( bG1(X0) = $false )
| ( bG2 = $false ) ),
inference(resolution,[],[f39,f18]) ).
tff(f51,plain,
! [X0: $i] :
( ( $true = $false )
| ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ( bG2 = $false ) ),
inference(superposition,[],[f22,f40]) ).
tff(f55,plain,
! [X0: $i] :
( ~ likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ( bG2 = $false ) ),
inference(trivial_inequality_removal,[],[f51]) ).
tff(f63,plain,
! [X0: $i] :
( ( $true != $true )
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0)
| likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ( bG1(X0) = $false ) ),
inference(superposition,[],[f23,f28]) ).
tff(f64,plain,
! [X0: $i] :
( ( bG1(X0) = $false )
| likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0) ),
inference(trivial_inequality_removal,[],[f63]) ).
tff(f69,plain,
bG2 = $false,
inference(forward_subsumption_resolution,[],[f37,f55]) ).
tff(f72,plain,
~ holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),$false),
inference(superposition,[],[f17,f69]) ).
tff(f140,plain,
! [X0: $i] :
( holdsDuring_THFTYPE_IiooI(lYearFn_THFTYPE_IiiI(n2009_THFTYPE_i),$false)
| likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0) ),
inference(superposition,[],[f18,f64]) ).
tff(f149,plain,
! [X0: $i] :
( likes_THFTYPE_IiioI(lSue_THFTYPE_i,X0)
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,X0) ),
inference(forward_subsumption_resolution,[],[f140,f72]) ).
tff(f150,plain,
( ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i)
| ( $true = bG2 ) ),
inference(resolution,[],[f149,f19]) ).
tff(f152,plain,
( ( $true = $false )
| ~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i) ),
inference(forward_demodulation,[],[f150,f69]) ).
tff(f153,plain,
~ likes_THFTYPE_IiioI(lMary_THFTYPE_i,lBill_THFTYPE_i),
inference(trivial_inequality_removal,[],[f152]) ).
tff(f154,plain,
bG0 = $false,
inference(resolution,[],[f153,f38]) ).
tff(f164,plain,
! [X0: $i] : holdsDuring_THFTYPE_IiooI(X0,$false),
inference(superposition,[],[f26,f154]) ).
tff(f168,plain,
$false,
inference(resolution,[],[f164,f72]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : CSR126_8 : TPTP v9.3.1. Released v8.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.20 % Computer : n026.cluster.edu
% 0.10/0.20 % Model : x86_64 x86_64
% 0.10/0.20 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.20 % Memory : 8046.5625MB
% 0.10/0.20 % OS : Linux 6.8.0-71-generic
% 0.10/0.20 % CPULimit : 300
% 0.10/0.20 % WCLimit : 300
% 0.10/0.20 % DateTime : Mon Sep 28 23:37:57 UTC 2026
% 0.10/0.21 % CPUTime :
% 0.10/0.21 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.24 Running first-order theorem proving
% 0.10/0.24 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
% 3.51/1.28 % (194051)Detected formulas, will run a generic FOF schedule.
% 3.51/1.28 % (194156)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=2712080624:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.51/1.28 % (194163)dis-21_1_sil=8000:lcm=predicate:random_seed=2128723155: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)
% 3.51/1.28 % (194155)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=1965023380:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.51/1.28 % (194161)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1419617596:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.51/1.28 % (194154)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=1072126403:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.51/1.28 % (194159)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=332522342:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.51/1.28 % (194158)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=292497265:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.51/1.28 % (194158)Refutation not found, incomplete strategy
% 3.51/1.28 % (194158)------------------------------
% 3.51/1.28 % (194158)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.51/1.28 % (194158)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.51/1.28 % (194163)Refutation not found, incomplete strategy
% 3.51/1.28 % (194163)------------------------------
% 3.51/1.28 % (194163)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.51/1.28 % (194158)CaDiCaL version: 2.1.3
% 3.51/1.28 % (194158)Termination reason: Refutation not found, incomplete strategy
% 3.51/1.28 % (194158)Time elapsed: 0.001 s
% 3.51/1.28 % (194163)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.51/1.28 % (194158)Peak memory usage: 88 MB
% 3.51/1.28 % (194163)CaDiCaL version: 2.1.3
% 3.51/1.28 % (194163)Termination reason: Refutation not found, incomplete strategy
% 3.51/1.28 % (194163)Time elapsed: 0.001 s
% 3.51/1.28 % (194163)Peak memory usage: 88 MB
% 3.51/1.28 % (194163)Instructions burned: 1 (million)
% 3.51/1.28 % (194159)First to succeed.
% 3.51/1.28 % (194161)Also succeeded, but the first one will report.
% 3.51/1.28 % (194159)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-194051"
% 3.51/1.28 % (194158)------------------------------
% 3.51/1.28 % (194158)------------------------------
% 3.51/1.28 % (194163)------------------------------
% 3.51/1.28 % (194163)------------------------------
% 3.51/1.28 % (194159)Refutation found. Thanks to Tanya!
% 3.51/1.28 % SZS status Theorem for theBenchmark
% 3.51/1.28 % SZS output start Proof for theBenchmark
% See solution above
% 3.51/1.28 % (194159)------------------------------
% 3.51/1.28 % (194159)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.51/1.28 % (194159)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.51/1.28 % (194159)CaDiCaL version: 2.1.3
% 3.51/1.28 % (194159)Termination reason: Refutation
% 3.51/1.28 % (194159)Time elapsed: 0.004 s
% 3.51/1.28 % (194159)Peak memory usage: 88 MB
% 3.51/1.28 % (194159)Instructions burned: 5 (million)
% 3.51/1.28 % (194159)------------------------------
% 3.51/1.28 % (194159)------------------------------
% 3.51/1.28 % (194051)Success in time 0.404 s
% 3.51/1.28 % Vampire exiting
%------------------------------------------------------------------------------