%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN713-1 : TPTP v9.3.1. Released v2.5.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n002.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 02:01:19 PM UTC 2026
% Result : Unsatisfiable 2.61s 1.05s
% Output : Refutation 2.61s
% Verified :
% SZS Type : Refutation
% Derivation depth : 11
% Number of leaves : 18
% Syntax : Number of formulae : 50 ( 16 unt; 4 def)
% Number of atoms : 102 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 107 ( 55 ~; 48 |; 0 &)
% ( 4 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 10 ( 4 avg)
% Maximal term depth : 4 ( 1 avg)
% Number of predicates : 15 ( 14 usr; 5 prp; 0-2 aty)
% Number of functors : 28 ( 28 usr; 15 con; 0-2 aty)
% Number of variables : 57 ( 0 sgn 57 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f2,negated_conjecture,
! [X0] : p9(X0,X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p9_2) ).
fof(f14,negated_conjecture,
! [X0] : p40(X0,X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p40_14) ).
fof(f34,negated_conjecture,
! [X0] : p12(X0,X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p12_34) ).
fof(f35,negated_conjecture,
p59(f38(c72,c77),f35(c73,c68)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p59_35) ).
fof(f38,negated_conjecture,
p56(f11(c65,f14(f17(c66,c67),c68)),c64),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p56_38) ).
fof(f39,negated_conjecture,
~ p57(f26(f28(c71,f41(c78,c64)),c67),c77),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_p57_39) ).
fof(f41,negated_conjecture,
! [X2,X0,X1] :
( p9(X0,X1)
| ~ p9(X2,X0)
| ~ p9(X2,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p9_41) ).
fof(f74,negated_conjecture,
! [X2,X0,X1] :
( p57(f26(f28(c71,X0),X1),X2)
| ~ p57(f26(X0,X1),X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p57_74) ).
fof(f76,negated_conjecture,
! [X2,X3,X0,X1] :
( p56(X0,X1)
| ~ p40(X2,X1)
| ~ p56(X3,X2)
| ~ p4(X3,X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p56_76) ).
fof(f80,negated_conjecture,
~ p58(f31(f33(c75,c76),f23(c69,c77)),f19(f22(c70,c69),c68)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_p58_80) ).
fof(f81,negated_conjecture,
! [X2,X3,X0,X1] :
( ~ p12(X0,X2)
| p10(f14(X0,X1),f14(X2,X3))
| ~ p13(X1,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p10_81) ).
fof(f87,negated_conjecture,
! [X2,X3,X0,X1] :
( ~ p9(X0,X2)
| ~ p10(X1,X3)
| p4(f11(X0,X1),f11(X2,X3)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p4_87) ).
fof(f101,negated_conjecture,
! [X2,X0,X1] :
( ~ p56(f11(c65,f14(f17(c66,X1),f23(c74,X2))),X0)
| p57(f26(f41(c78,X0),X1),X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p57_101) ).
fof(f105,negated_conjecture,
! [X0,X1] :
( p58(f31(f33(c75,c76),f23(c69,X1)),f19(f22(c70,c69),X0))
| p13(X0,f23(c74,X1))
| ~ p59(f38(c72,X1),f35(c73,X0)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',p13_105) ).
fof(f106,plain,
~ p57(f26(f41(c78,c64),c67),c77),
inference(resolution,[],[f74,f39]) ).
fof(f110,plain,
! [X2,X0,X1] :
( p10(f14(X0,X1),f14(X0,X2))
| ~ p13(X1,X2) ),
inference(resolution,[],[f81,f34]) ).
fof(f124,plain,
! [X2,X3,X0,X1,X4] :
( p4(f11(X2,X0),f11(X3,X1))
| ~ p10(X0,X1)
| ~ p9(X4,X2)
| ~ p9(X4,X3) ),
inference(resolution,[],[f87,f41]) ).
fof(f168,plain,
! [X2,X3,X0,X1,X4] :
( ~ p56(X4,X3)
| ~ p40(X3,X0)
| p57(f26(f41(c78,X0),X1),X2)
| ~ p4(X4,f11(c65,f14(f17(c66,X1),f23(c74,X2)))) ),
inference(resolution,[],[f101,f76]) ).
fof(f174,plain,
( p13(c68,f23(c74,c77))
| ~ p59(f38(c72,c77),f35(c73,c68)) ),
inference(resolution,[],[f105,f80]) ).
fof(f176,definition,
( spl0_1
<=> p59(f38(c72,c77),f35(c73,c68)) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f177,plain,
( ~ p59(f38(c72,c77),f35(c73,c68))
| spl0_1 ),
inference(avatar_component_clause,[],[f176]) ).
fof(f179,definition,
( spl0_2
<=> p13(c68,f23(c74,c77)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f180,plain,
( p13(c68,f23(c74,c77))
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f179]) ).
fof(f181,plain,
( ~ spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f174,f179,f176]) ).
fof(f182,plain,
( $false
| spl0_1 ),
inference(resolution,[],[f177,f35]) ).
fof(f184,plain,
spl0_1,
inference(avatar_contradiction_clause,[],[f182]) ).
fof(f207,plain,
! [X2,X0,X1] :
( ~ p40(c64,X0)
| p57(f26(f41(c78,X0),X1),X2)
| ~ p4(f11(c65,f14(f17(c66,c67),c68)),f11(c65,f14(f17(c66,X1),f23(c74,X2)))) ),
inference(resolution,[],[f168,f38]) ).
fof(f237,plain,
! [X0,X1] :
( ~ p4(f11(c65,f14(f17(c66,c67),c68)),f11(c65,f14(f17(c66,X0),f23(c74,X1))))
| p57(f26(f41(c78,c64),X0),X1) ),
inference(resolution,[],[f207,f14]) ).
fof(f255,plain,
! [X2,X0,X1] :
( p57(f26(f41(c78,c64),X0),X1)
| ~ p10(f14(f17(c66,c67),c68),f14(f17(c66,X0),f23(c74,X1)))
| ~ p9(X2,c65)
| ~ p9(X2,c65) ),
inference(resolution,[],[f237,f124]) ).
fof(f257,plain,
! [X2,X0,X1] :
( p57(f26(f41(c78,c64),X0),X1)
| ~ p10(f14(f17(c66,c67),c68),f14(f17(c66,X0),f23(c74,X1)))
| ~ p9(X2,c65) ),
inference(duplicate_literal_removal,[],[f255]) ).
fof(f259,definition,
( spl0_3
<=> ! [X2] : ~ p9(X2,c65) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f260,plain,
( ! [X2] : ~ p9(X2,c65)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f259]) ).
fof(f262,definition,
( spl0_4
<=> ! [X0,X1] :
( p57(f26(f41(c78,c64),X0),X1)
| ~ p10(f14(f17(c66,c67),c68),f14(f17(c66,X0),f23(c74,X1))) ) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f263,plain,
( ! [X0,X1] :
( ~ p10(f14(f17(c66,c67),c68),f14(f17(c66,X0),f23(c74,X1)))
| p57(f26(f41(c78,c64),X0),X1) )
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f262]) ).
fof(f264,plain,
( spl0_3
| spl0_4 ),
inference(avatar_split_clause,[],[f257,f262,f259]) ).
fof(f267,plain,
( ! [X0] :
( p57(f26(f41(c78,c64),c67),X0)
| ~ p13(c68,f23(c74,X0)) )
| ~ spl0_4 ),
inference(resolution,[],[f263,f110]) ).
fof(f279,plain,
( ~ p13(c68,f23(c74,c77))
| ~ spl0_4 ),
inference(resolution,[],[f267,f106]) ).
fof(f331,plain,
( $false
| ~ spl0_2
| ~ spl0_4 ),
inference(resolution,[],[f279,f180]) ).
fof(f333,plain,
( ~ spl0_2
| ~ spl0_4 ),
inference(avatar_contradiction_clause,[],[f331]) ).
fof(f334,plain,
( $false
| ~ spl0_3 ),
inference(resolution,[],[f260,f2]) ).
fof(f336,plain,
~ spl0_3,
inference(avatar_contradiction_clause,[],[f334]) ).
cnf(s1,plain,
( ~ spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f181]) ).
cnf(s2,plain,
spl0_1,
inference(sat_conversion,[],[f184]) ).
cnf(s3,plain,
( spl0_3
| spl0_4 ),
inference(sat_conversion,[],[f264]) ).
cnf(s15,plain,
( ~ spl0_2
| ~ spl0_4 ),
inference(sat_conversion,[],[f333]) ).
cnf(s16,plain,
~ spl0_3,
inference(sat_conversion,[],[f336]) ).
cnf(s17,plain,
spl0_4,
inference(rat,[],[s3,s16]) ).
cnf(s18,plain,
~ spl0_2,
inference(rat,[],[s15,s17]) ).
cnf(s20,plain,
$false,
inference(rat,[],[s1,s18,s2]) ).
fof(f337,plain,
$false,
inference(avatar_sat_refutation,[],[s20]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYN713-1 : TPTP v9.3.1. Released v2.5.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.20 % Computer : n002.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 16:51:22 UTC 2026
% 0.09/0.21 % CPUTime :
% 0.09/0.21 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.25 Running first-order theorem proving
% 0.09/0.25 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
% 2.61/1.05 % (508266)Input is clausal, will run a generic CNF schedule.
% 2.61/1.05 % (508279)dis-21_1_sil=8000:lcm=predicate:random_seed=1574351744: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)
% 2.61/1.05 % (508279)First to succeed.
% 2.61/1.05 % (508279)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-508266"
% 2.61/1.05 % (508276)lrs+10_1_sil=8000:sp=occurrence:random_seed=2027456775:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.61/1.05 % (508278)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=2809634612:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.61/1.05 % (508277)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2125189601:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.61/1.05 % (508278)Also succeeded, but the first one will report.
% 2.61/1.05 % (508274)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=3413373130:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.61/1.05 % (508273)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=32325198:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.61/1.05 % (508275)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=705875000:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.61/1.05 % (508277)Also succeeded, but the first one will report.
% 2.61/1.05 % (508276)Instruction limit reached!
% 2.61/1.05 % (508276)------------------------------
% 2.61/1.05 % (508276)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.61/1.05 % (508276)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.61/1.05 % (508276)CaDiCaL version: 2.1.3
% 2.61/1.05 % (508276)Termination reason: Instruction limit
% 2.61/1.05 % (508276)Termination phase: Saturation
% 2.61/1.05 % (508276)Time elapsed: 0.068 s
% 2.61/1.05 % (508276)Peak memory usage: 89 MB
% 2.61/1.05 % (508276)Instructions burned: 108 (million)
% 2.61/1.05 % (508279)Refutation found. Thanks to Tanya!
% 2.61/1.05 % SZS status Unsatisfiable for theBenchmark
% 2.61/1.05 % SZS output start Proof for theBenchmark
% See solution above
% 2.61/1.05 % (508279)------------------------------
% 2.61/1.05 % (508279)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.61/1.05 % (508279)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.61/1.05 % (508279)CaDiCaL version: 2.1.3
% 2.61/1.05 % (508279)Termination reason: Refutation
% 2.61/1.05 % (508279)Time elapsed: 0.005 s
% 2.61/1.05 % (508279)Peak memory usage: 89 MB
% 2.61/1.05 % (508279)Instructions burned: 12 (million)
% 2.61/1.05 % (508279)------------------------------
% 2.61/1.05 % (508279)------------------------------
% 2.61/1.05 % (508266)Success in time 0.277 s
% 2.61/1.05 % Vampire exiting
%------------------------------------------------------------------------------