%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : CAT002-4 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n010.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 0.21s 1.14s
% Output : Refutation 0.21s
% Verified :
% SZS Type : Refutation
% Derivation depth : 7
% Number of leaves : 5
% Syntax : Number of formulae : 15 ( 8 unt; 0 def)
% Number of atoms : 24 ( 23 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 20 ( 11 ~; 9 |; 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 : 16 ( 16 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f9,axiom,
! [X2,X0,X1] : compose(X0,compose(X1,X2)) = compose(compose(X0,X1),X2),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',associativity_of_compose) ).
fof(f13,axiom,
! [X2,X0,X1] :
( compose(a,X0) != X1
| compose(a,X2) != X1
| X0 = X2 ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',cancellation_for_compose1) ).
fof(f14,axiom,
! [X2,X0,X1] :
( compose(b,X0) != X1
| compose(b,X2) != X1
| X0 = X2 ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',cancellation_for_compose2) ).
fof(f16,axiom,
compose(compose(a,b),h) = compose(compose(a,b),g),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',ab_h_equals_ab_g) ).
fof(f17,negated_conjecture,
g != h,
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_g_equals_h) ).
fof(f18,plain,
h != g,
inference(reorient_equations,[],[f17]) ).
fof(f19,plain,
! [X2,X0] :
( compose(a,X0) != compose(a,X2)
| X0 = X2 ),
inference(equality_resolution,[],[f13]) ).
fof(f20,plain,
! [X2,X0] :
( compose(b,X0) != compose(b,X2)
| X0 = X2 ),
inference(equality_resolution,[],[f14]) ).
fof(f25,plain,
compose(compose(a,b),h) = compose(a,compose(b,g)),
inference(superposition,[],[f9,f16]) ).
fof(f27,plain,
! [X0] :
( compose(a,X0) != compose(compose(a,b),h)
| compose(b,g) = X0 ),
inference(superposition,[],[f19,f25]) ).
fof(f33,plain,
! [X0] :
( compose(a,X0) != compose(a,compose(b,h))
| compose(b,g) = X0 ),
inference(superposition,[],[f27,f9]) ).
fof(f54,plain,
compose(b,g) = compose(b,h),
inference(equality_resolution,[],[f33]) ).
fof(f64,plain,
! [X0] :
( compose(b,X0) != compose(b,h)
| g = X0 ),
inference(superposition,[],[f20,f54]) ).
fof(f68,plain,
h = g,
inference(equality_resolution,[],[f64]) ).
fof(f69,plain,
$false,
inference(forward_subsumption_resolution,[],[f68,f18]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : CAT002-4 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.20 % Computer : n010.cluster.edu
% 0.09/0.20 % Model : x86_64 x86_64
% 0.09/0.20 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.20 % Memory : 8046.5625MB
% 0.09/0.20 % OS : Linux 6.8.0-71-generic
% 0.09/0.20 % CPULimit : 300
% 0.09/0.20 % WCLimit : 300
% 0.09/0.20 % DateTime : Mon Sep 28 21:13:05 UTC 2026
% 0.09/0.20 % CPUTime :
% 0.09/0.20 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.23 Running first-order theorem proving
% 0.09/0.23 Running: /export/starexec/sandbox2/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.21/1.14 % (2343826)Input is clausal, will run a generic CNF schedule.
% 0.21/1.14 % (2343835)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=3851197993:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 0.21/1.14 % (2343835)First to succeed.
% 0.21/1.14 % (2343835)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-2343826"
% 0.21/1.14 % (2343831)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=1864488705:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 0.21/1.14 % (2343833)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1928175654:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 0.21/1.14 % (2343834)lrs+10_1_sil=8000:sp=occurrence:random_seed=2528427465:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 0.21/1.14 % (2343832)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2951897064:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 0.21/1.14 % (2343834)Also succeeded, but the first one will report.
% 0.21/1.14 % (2343836)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=4005291171:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 0.21/1.14 % (2343837)dis-21_1_sil=8000:lcm=predicate:random_seed=1791965345: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)
% 0.21/1.14 % (2343837)Instruction limit reached!
% 0.21/1.14 % (2343837)------------------------------
% 0.21/1.14 % (2343837)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.21/1.14 % (2343837)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.21/1.14 % (2343837)CaDiCaL version: 2.1.3
% 0.21/1.14 % (2343837)Termination reason: Instruction limit
% 0.21/1.14 % (2343837)Termination phase: Saturation
% 0.21/1.14 % (2343837)Time elapsed: 0.057 s
% 0.21/1.14 % (2343837)Peak memory usage: 88 MB
% 0.21/1.14 % (2343837)Instructions burned: 118 (million)
% 0.21/1.14 % (2343835)Refutation found. Thanks to Tanya!
% 0.21/1.14 % SZS status Unsatisfiable for theBenchmark
% 0.21/1.14 % SZS output start Proof for theBenchmark
% See solution above
% 0.21/1.14 % (2343835)------------------------------
% 0.21/1.14 % (2343835)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.21/1.14 % (2343835)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.21/1.14 % (2343835)CaDiCaL version: 2.1.3
% 0.21/1.14 % (2343835)Termination reason: Refutation
% 0.21/1.14 % (2343835)Time elapsed: 0.002 s
% 0.21/1.14 % (2343835)Peak memory usage: 88 MB
% 0.21/1.14 % (2343835)Instructions burned: 3 (million)
% 0.21/1.14 % (2343835)------------------------------
% 0.21/1.14 % (2343835)------------------------------
% 0.21/1.14 % (2343826)Success in time 0.27 s
% 0.21/1.14 % Vampire exiting
%------------------------------------------------------------------------------