%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : GRP708-1 : TPTP v9.3.1. Released v4.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n011.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 10:16:01 AM UTC 2026
% Result : Unsatisfiable 0.18s 1.21s
% Output : Refutation 0.18s
% Verified :
% SZS Type : Refutation
% Derivation depth : 12
% Number of leaves : 9
% Syntax : Number of formulae : 29 ( 29 unt; 1 def)
% Number of atoms : 29 ( 23 equ)
% Maximal formula atoms : 1 ( 1 avg)
% Number of connectives : 2 ( 2 ~; 0 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 4 ( 3 avg)
% Maximal term depth : 6 ( 2 avg)
% Number of predicates : 3 ( 1 usr; 1 prp; 0-2 aty)
% Number of functors : 7 ( 7 usr; 4 con; 0-2 aty)
% Number of variables : 42 ( 42 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f2,axiom,
! [X0,X1] : ld(X0,mult(X0,X1)) = X1,
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c02) ).
fof(f3,axiom,
! [X0,X1] : mult(rd(X0,X1),X1) = X0,
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c03) ).
fof(f4,axiom,
! [X0,X1] : rd(mult(X0,X1),X1) = X0,
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c04) ).
fof(f6,axiom,
! [X0] : mult(unit,X0) = X0,
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c06) ).
fof(f7,axiom,
! [X2,X0,X1] : mult(X0,mult(X1,mult(X0,X2))) = mult(mult(X0,mult(X1,X0)),X2),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c07) ).
fof(f8,axiom,
! [X0] : mult(op_c,X0) = mult(X0,op_c),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c08) ).
fof(f9,axiom,
! [X0,X1] : mult(mult(op_c,op_c),mult(X0,X1)) = mult(mult(mult(op_c,op_c),X0),X1),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c09) ).
fof(f10,negated_conjecture,
mult(a,mult(b,op_c)) != mult(mult(a,b),op_c),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',goals) ).
fof(f11,definition,
~ sP0(mult(a,mult(b,op_c))),
introduced(definition,[new_symbols(definition,[sP0])],[inequality_splitting_name_introduction]) ).
fof(f12,plain,
sP0(mult(mult(a,b),op_c)),
inference(inequality_splitting,[],[f10,f11]) ).
fof(f30,plain,
! [X0] : unit = rd(X0,X0),
inference(superposition,[],[f4,f6]) ).
fof(f40,plain,
! [X0] : rd(mult(op_c,X0),op_c) = X0,
inference(superposition,[],[f4,f8]) ).
fof(f42,plain,
sP0(mult(op_c,mult(a,b))),
inference(superposition,[],[f12,f8]) ).
fof(f48,plain,
! [X2,X0,X1] : mult(X1,mult(rd(X0,X1),mult(X1,X2))) = mult(mult(X1,X0),X2),
inference(superposition,[],[f7,f3]) ).
fof(f49,plain,
! [X0,X1] : mult(X0,mult(unit,mult(X0,X1))) = mult(mult(X0,X0),X1),
inference(superposition,[],[f7,f6]) ).
fof(f63,plain,
! [X0,X1] : mult(mult(X0,X0),X1) = mult(X0,mult(X0,X1)),
inference(forward_demodulation,[],[f49,f6]) ).
fof(f64,plain,
! [X0,X1] : mult(mult(op_c,op_c),mult(X0,X1)) = mult(mult(op_c,mult(rd(op_c,op_c),mult(op_c,X0))),X1),
inference(backward_demodulation,[],[f9,f48]) ).
fof(f74,plain,
! [X0,X1] : mult(X0,mult(X0,X1)) = mult(X0,mult(rd(X0,X0),mult(X0,X1))),
inference(forward_demodulation,[],[f63,f48]) ).
fof(f75,plain,
! [X0,X1] : mult(mult(op_c,op_c),mult(X0,X1)) = mult(op_c,mult(rd(mult(rd(op_c,op_c),mult(op_c,X0)),op_c),mult(op_c,X1))),
inference(forward_demodulation,[],[f64,f48]) ).
fof(f78,plain,
! [X0,X1] : mult(op_c,mult(rd(mult(rd(op_c,op_c),mult(op_c,X0)),op_c),mult(op_c,X1))) = mult(op_c,mult(rd(op_c,op_c),mult(op_c,mult(X0,X1)))),
inference(forward_demodulation,[],[f75,f48]) ).
fof(f81,plain,
! [X0,X1] : mult(op_c,mult(rd(mult(rd(op_c,op_c),mult(op_c,X0)),op_c),mult(op_c,X1))) = mult(op_c,mult(op_c,mult(X0,X1))),
inference(forward_demodulation,[],[f78,f74]) ).
fof(f92,plain,
! [X0,X1] : mult(rd(mult(rd(op_c,op_c),mult(op_c,X0)),op_c),mult(op_c,X1)) = ld(op_c,mult(op_c,mult(op_c,mult(X0,X1)))),
inference(superposition,[],[f2,f81]) ).
fof(f93,plain,
! [X0,X1] : mult(op_c,mult(X0,X1)) = mult(rd(mult(rd(op_c,op_c),mult(op_c,X0)),op_c),mult(op_c,X1)),
inference(forward_demodulation,[],[f92,f2]) ).
fof(f114,plain,
! [X0,X1] : mult(rd(X0,X0),X1) = X1,
inference(superposition,[],[f6,f30]) ).
fof(f118,plain,
! [X0,X1] : mult(op_c,mult(X0,X1)) = mult(rd(mult(op_c,X0),op_c),mult(op_c,X1)),
inference(backward_demodulation,[],[f93,f114]) ).
fof(f122,plain,
! [X0,X1] : mult(X0,mult(op_c,X1)) = mult(op_c,mult(X0,X1)),
inference(forward_demodulation,[],[f118,f40]) ).
fof(f188,plain,
sP0(mult(a,mult(op_c,b))),
inference(superposition,[],[f42,f122]) ).
fof(f194,plain,
sP0(mult(a,mult(b,op_c))),
inference(superposition,[],[f188,f8]) ).
fof(f195,plain,
$false,
inference(forward_subsumption_resolution,[],[f194,f11]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : GRP708-1 : TPTP v9.3.1. Released v4.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.11/0.36 % Computer : n011.cluster.edu
% 0.11/0.36 % Model : x86_64 x86_64
% 0.11/0.36 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.36 % Memory : 8046.5625MB
% 0.11/0.36 % OS : Linux 6.8.0-71-generic
% 0.11/0.36 % CPULimit : 300
% 0.11/0.36 % WCLimit : 300
% 0.11/0.36 % DateTime : Sun Sep 27 10:37:00 UTC 2026
% 0.05/0.36 % CPUTime :
% 0.05/0.36 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.05/0.39 Running first-order theorem proving
% 0.05/0.39 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
% 0.18/1.21 % (2202043)Detected a unit-equality problem, will run specialized UEQ schedule.
% 0.18/1.21 % (2202054)lrs+10_3_to=lpo:sil=64000:drc=off:fde=unused:sp=reverse_frequency:acc=on:bsr=on:fd=preordered:nwc=1:random_seed=1491729920:avsq=on:i=257:avsqr=16,3:bd=preordered:fsr=off_2999 on theBenchmark for (2999ds/257Mi)
% 0.18/1.21 % (2202055)dis-1010_7_sil=8000:fde=unused:flr=on:random_seed=1535158397:i=1187:sd=4:av=off:ss=axioms:sgt=32_2999 on theBenchmark for (2999ds/1187Mi)
% 0.18/1.21 % (2202051)lrs+10_1_ncem=casc2026/models/loop5.pt:sil=128000:tgt=ground:npcc=on:spb=goal_then_units:urr=ec_only:random_seed=4101389386:i=130716:gtgl=4:add=on:doe=on:bd=all:gtg=exists_sym_2999 on theBenchmark for (2999ds/130716Mi)
% 0.18/1.21 % (2202053)dis+10_14_to=lpo:sil=8000:tgt=full:drc=off:sp=const_frequency:sos=all:random_seed=3343346391:i=181:gtgl=5:bs=unit_only:fsr=off:gtg=exists_all_2999 on theBenchmark for (2999ds/181Mi)
% 0.18/1.21 % (2202050)lrs+11_1_ncem=casc2026/models/loop6.pt:sil=128000:npcc=on:lma=off:spb=units:urr=ec_only:bce=on:s2agt=64:updr=off:random_seed=3963627570:i=130792:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/130792Mi)
% 0.18/1.21 % (2202052)ott-1010_1_sfv=off:to=lpo:sil=8000:fdtod=off:sp=reverse_frequency:spb=goal_then_units:fd=preordered:random_seed=1917513164:i=136:bd=preordered:ins=2:av=off_2999 on theBenchmark for (2999ds/136Mi)
% 0.18/1.21 % (2202049)lrs+1002_1_ncem=casc2026/models/loop7.pt:sil=128000:tgt=ground:npcc=on:drc=off:sp=reverse_frequency:spb=goal:acc=on:s2agt=16:kmz=on:sac=on:random_seed=1546413961:i=138329:kws=inv_arity_squared:fgj=on:bd=preordered_2999 on theBenchmark for (2999ds/138329Mi)
% 0.18/1.21 % (2202052)First to succeed.
% 0.18/1.21 % (2202054)Also succeeded, but the first one will report.
% 0.18/1.21 % (2202052)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-2202043"
% 0.18/1.21 % (2202053)Instruction limit reached!
% 0.18/1.21 % (2202053)------------------------------
% 0.18/1.21 % (2202053)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.18/1.21 % (2202053)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.18/1.21 % (2202053)CaDiCaL version: 2.1.3
% 0.18/1.21 % (2202053)Termination reason: Instruction limit
% 0.18/1.21 % (2202053)Termination phase: Saturation
% 0.18/1.21 % (2202053)Time elapsed: 0.102 s
% 0.18/1.21 % (2202053)Peak memory usage: 89 MB
% 0.18/1.21 % (2202053)Instructions burned: 182 (million)
% 0.18/1.21 % (2202055)Also succeeded, but the first one will report.
% 0.18/1.21 % (2202063)lrs-1011_1_ncem=casc2026/models/loop8.pt:sil=32000:npcc=on:prc=on:fde=unused:lcm=predicate:bsr=on:flr=on:random_seed=2134698377:i=2051:gtgl=2:fgj=on:bd=all:gtg=exists_top_2997 on theBenchmark for (2997ds/2051Mi)
% 0.18/1.21 % (2202064)lrs-1002_1_ncem=casc2026/models/all5champsBiggishL14.pt:sil=16000:npcc=on:random_seed=3396167869:i=4948:ss=axioms:sgt=16_2996 on theBenchmark for (2996ds/4948Mi)
% 0.18/1.21 % (2202052)Refutation found. Thanks to Tanya!
% 0.18/1.21 % SZS status Unsatisfiable for theBenchmark
% 0.18/1.21 % SZS output start Proof for theBenchmark
% See solution above
% 0.18/1.21 % (2202052)------------------------------
% 0.18/1.21 % (2202052)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.18/1.21 % (2202052)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.18/1.21 % (2202052)CaDiCaL version: 2.1.3
% 0.18/1.21 % (2202052)Termination reason: Refutation
% 0.18/1.21 % (2202052)Time elapsed: 0.009 s
% 0.18/1.21 % (2202052)Peak memory usage: 88 MB
% 0.18/1.21 % (2202052)Instructions burned: 12 (million)
% 0.18/1.21 % (2202052)------------------------------
% 0.18/1.21 % (2202052)------------------------------
% 0.18/1.21 % (2202043)Success in time 0.412 s
% 0.18/1.21 % Vampire exiting
%------------------------------------------------------------------------------