%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : CAT002-3 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n009.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 09:36:33 AM UTC 2026
% Result : Unsatisfiable 3.61s 1.29s
% Output : Refutation 3.61s
% Verified :
% SZS Type : Refutation
% Derivation depth : 7
% Number of leaves : 5
% Syntax : Number of formulae : 15 ( 9 unt; 0 def)
% Number of atoms : 23 ( 22 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 18 ( 10 ~; 8 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of predicates : 2 ( 0 usr; 1 prp; 0-2 aty)
% Number of functors : 5 ( 5 usr; 4 con; 0-2 aty)
% Number of variables : 15 ( 15 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f9,axiom,
! [X2,X0,X1] : compose(X0,compose(X1,X2)) = compose(compose(X0,X1),X2),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',associativity_of_compose) ).
fof(f21,axiom,
! [X2,X0,X1] :
( compose(a,X0) != X1
| compose(a,X2) != X1
| X0 = X2 ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',cancellation_for_compose1) ).
fof(f22,axiom,
! [X2,X0,X1] :
( compose(b,X0) != X1
| compose(b,X2) != X1
| X0 = X2 ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',cancellation_for_compose2) ).
fof(f24,axiom,
compose(compose(a,b),h) = compose(compose(a,b),g),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ab_h_equals_ab_g) ).
fof(f25,negated_conjecture,
g != h,
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_g_equals_h) ).
fof(f26,plain,
h != g,
inference(reorient_equations,[],[f25]) ).
fof(f27,plain,
! [X2,X0] :
( compose(a,X0) != compose(a,X2)
| X0 = X2 ),
inference(equality_resolution,[],[f21]) ).
fof(f28,plain,
! [X2,X0] :
( compose(b,X0) != compose(b,X2)
| X0 = X2 ),
inference(equality_resolution,[],[f22]) ).
fof(f29,plain,
compose(compose(a,b),h) = compose(a,compose(b,g)),
inference(forward_demodulation,[],[f24,f9]) ).
fof(f30,plain,
compose(a,compose(b,g)) = compose(a,compose(b,h)),
inference(forward_demodulation,[],[f29,f9]) ).
fof(f34,plain,
! [X0] :
( compose(a,X0) != compose(a,compose(b,h))
| compose(b,g) = X0 ),
inference(superposition,[],[f27,f30]) ).
fof(f42,plain,
compose(b,g) = compose(b,h),
inference(equality_resolution,[],[f34]) ).
fof(f44,plain,
! [X0] :
( compose(b,X0) != compose(b,h)
| g = X0 ),
inference(superposition,[],[f28,f42]) ).
fof(f59,plain,
h = g,
inference(equality_resolution,[],[f44]) ).
fof(f60,plain,
$false,
inference(forward_subsumption_resolution,[],[f59,f26]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : CAT002-3 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.19 % Computer : n009.cluster.edu
% 0.09/0.19 % Model : x86_64 x86_64
% 0.09/0.19 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.19 % Memory : 8046.5625MB
% 0.09/0.19 % OS : Linux 6.8.0-71-generic
% 0.09/0.19 % CPULimit : 300
% 0.09/0.19 % WCLimit : 300
% 0.09/0.19 % DateTime : Mon Sep 28 21:12:47 UTC 2026
% 0.09/0.19 % CPUTime :
% 0.09/0.19 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.23 Running first-order theorem proving
% 0.09/0.23 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
% 3.61/1.29 % (3482678)Input is clausal, will run a generic CNF schedule.
% 3.61/1.29 % (3482690)dis-21_1_sil=8000:lcm=predicate:random_seed=2054793100:st=5:avsq=on:i=117:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/117Mi)
% 3.61/1.29 % (3482685)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2696806714:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.61/1.29 % (3482686)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=3781218848:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.61/1.29 % (3482684)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=3568049372:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.61/1.29 % (3482688)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=3877223787:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.61/1.29 % (3482689)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=2646728470:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.61/1.29 % (3482687)lrs+10_1_sil=8000:sp=occurrence:random_seed=4016497530:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.61/1.29 % (3482687)First to succeed.
% 3.61/1.29 % (3482687)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3482678"
% 3.61/1.29 % (3482688)Also succeeded, but the first one will report.
% 3.61/1.29 % (3482690)Instruction limit reached!
% 3.61/1.29 % (3482690)------------------------------
% 3.61/1.29 % (3482690)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.61/1.29 % (3482690)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.61/1.29 % (3482690)CaDiCaL version: 2.1.3
% 3.61/1.29 % (3482690)Termination reason: Instruction limit
% 3.61/1.29 % (3482690)Termination phase: Saturation
% 3.61/1.29 % (3482690)Time elapsed: 0.036 s
% 3.61/1.29 % (3482690)Peak memory usage: 90 MB
% 3.61/1.29 % (3482690)Instructions burned: 119 (million)
% 3.61/1.29 % (3482689)Instruction limit reached!
% 3.61/1.29 % (3482689)------------------------------
% 3.61/1.29 % (3482689)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.61/1.29 % (3482689)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.61/1.29 % (3482689)CaDiCaL version: 2.1.3
% 3.61/1.29 % (3482689)Termination reason: Instruction limit
% 3.61/1.29 % (3482689)Termination phase: Saturation
% 3.61/1.29 % (3482689)Time elapsed: 0.111 s
% 3.61/1.29 % (3482689)Peak memory usage: 89 MB
% 3.61/1.29 % (3482689)Instructions burned: 180 (million)
% 3.61/1.29 % (3482698)dis+1010_3_sil=8000:plsq=on:drc=off:fde=none:plsqc=1:bsd=on:plsqr=7,2:sos=on:spb=goal_then_units:random_seed=2519305126:i=143:sd=2:aac=none:ss=axioms:sgt=16_2998 on theBenchmark for (2998ds/143Mi)
% 3.61/1.29 % (3482698)Also succeeded, but the first one will report.
% 3.61/1.29 % (3482687)Refutation found. Thanks to Tanya!
% 3.61/1.29 % SZS status Unsatisfiable for theBenchmark
% 3.61/1.29 % SZS output start Proof for theBenchmark
% See solution above
% 3.61/1.29 % (3482687)------------------------------
% 3.61/1.29 % (3482687)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.61/1.29 % (3482687)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.61/1.29 % (3482687)CaDiCaL version: 2.1.3
% 3.61/1.29 % (3482687)Termination reason: Refutation
% 3.61/1.29 % (3482687)Time elapsed: 0.003 s
% 3.61/1.29 % (3482687)Peak memory usage: 88 MB
% 3.61/1.29 % (3482687)Instructions burned: 2 (million)
% 3.61/1.29 % (3482687)------------------------------
% 3.61/1.29 % (3482687)------------------------------
% 3.61/1.29 % (3482678)Success in time 0.426 s
% 3.61/1.29 % Vampire exiting
%------------------------------------------------------------------------------