%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN637-1 : TPTP v9.3.1. Released v2.5.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n006.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 02:01:08 PM UTC 2026
% Result : Unsatisfiable 2.65s 0.93s
% Output : Refutation 2.65s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 11
% Syntax : Number of formulae : 37 ( 14 unt; 4 def)
% Number of atoms : 67 ( 0 equ)
% Maximal formula atoms : 4 ( 1 avg)
% Number of connectives : 60 ( 30 ~; 26 |; 0 &)
% ( 4 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 9 ( 3 avg)
% Maximal term depth : 7 ( 2 avg)
% Number of predicates : 7 ( 6 usr; 5 prp; 0-2 aty)
% Number of functors : 12 ( 12 usr; 5 con; 0-3 aty)
% Number of variables : 14 ( 0 sgn 14 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f4,negated_conjecture,
! [X0] : p4(X0,X0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p4_4) ).
fof(f12,negated_conjecture,
! [X0,X1] :
( p4(f16(X0),f16(X1))
| ~ p4(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p4_12) ).
fof(f28,negated_conjecture,
! [X2,X3,X0,X1] :
( p22(X0,X1)
| ~ p4(X2,X0)
| ~ p4(X3,X1)
| ~ p22(X2,X3) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p22_28) ).
fof(f32,negated_conjecture,
! [X2,X3,X0,X1] :
( p4(f17(X0,X1),f17(X2,X3))
| ~ p4(X0,X2)
| ~ p4(X1,X3) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p4_32) ).
fof(f39,negated_conjecture,
! [X0] : p4(f5(f8(f11(c25),f9(f10(c25),c28)),X0,c27),f5(f8(f11(c25),f9(f10(c25),c28)),X0,c29)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p4_39) ).
fof(f40,negated_conjecture,
p22(f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c27))),f16(f17(c27,f5(c25,c26,c27)))),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p22_40) ).
fof(f41,negated_conjecture,
~ p22(f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29))),f16(f17(c27,f5(c25,c26,c27)))),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',not_p22_41) ).
fof(f138,plain,
! [X0,X1] :
( ~ p22(X0,X1)
| ~ p4(X1,f16(f17(c27,f5(c25,c26,c27))))
| ~ p4(X0,f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29)))) ),
inference(resolution,[],[f41,f28]) ).
fof(f1378,definition,
( spl0_34
<=> p4(c27,c27) ),
introduced(definition,[new_symbols(definition,[spl0_34])],[avatar_definition]) ).
fof(f1379,plain,
( ~ p4(c27,c27)
| spl0_34 ),
inference(avatar_component_clause,[],[f1378]) ).
fof(f2054,plain,
( $false
| spl0_34 ),
inference(resolution,[],[f1379,f4]) ).
fof(f2057,plain,
spl0_34,
inference(avatar_contradiction_clause,[],[f2054]) ).
fof(f2418,plain,
( ~ p4(f16(f17(c27,f5(c25,c26,c27))),f16(f17(c27,f5(c25,c26,c27))))
| ~ p4(f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c27))),f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29)))) ),
inference(resolution,[],[f138,f40]) ).
fof(f2420,definition,
( spl0_37
<=> p4(f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c27))),f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29)))) ),
introduced(definition,[new_symbols(definition,[spl0_37])],[avatar_definition]) ).
fof(f2421,plain,
( ~ p4(f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c27))),f16(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29))))
| spl0_37 ),
inference(avatar_component_clause,[],[f2420]) ).
fof(f2423,definition,
( spl0_38
<=> p4(f16(f17(c27,f5(c25,c26,c27))),f16(f17(c27,f5(c25,c26,c27)))) ),
introduced(definition,[new_symbols(definition,[spl0_38])],[avatar_definition]) ).
fof(f2424,plain,
( ~ p4(f16(f17(c27,f5(c25,c26,c27))),f16(f17(c27,f5(c25,c26,c27))))
| spl0_38 ),
inference(avatar_component_clause,[],[f2423]) ).
fof(f2425,plain,
( ~ spl0_37
| ~ spl0_38 ),
inference(avatar_split_clause,[],[f2418,f2423,f2420]) ).
fof(f2443,plain,
( ~ p4(f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c27)),f17(c27,f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29)))
| spl0_37 ),
inference(resolution,[],[f2421,f12]) ).
fof(f2450,plain,
( ~ p4(c27,c27)
| ~ p4(f5(f8(f11(c25),f9(f10(c25),c28)),c26,c27),f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29))
| spl0_37 ),
inference(resolution,[],[f2443,f32]) ).
fof(f2453,definition,
( spl0_41
<=> p4(f5(f8(f11(c25),f9(f10(c25),c28)),c26,c27),f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29)) ),
introduced(definition,[new_symbols(definition,[spl0_41])],[avatar_definition]) ).
fof(f2454,plain,
( ~ p4(f5(f8(f11(c25),f9(f10(c25),c28)),c26,c27),f5(f8(f11(c25),f9(f10(c25),c28)),c26,c29))
| spl0_41 ),
inference(avatar_component_clause,[],[f2453]) ).
fof(f2455,plain,
( ~ spl0_41
| ~ spl0_34
| spl0_37 ),
inference(avatar_split_clause,[],[f2450,f2420,f1378,f2453]) ).
fof(f2497,plain,
( $false
| spl0_41 ),
inference(resolution,[],[f2454,f39]) ).
fof(f2501,plain,
spl0_41,
inference(avatar_contradiction_clause,[],[f2497]) ).
fof(f2515,plain,
( $false
| spl0_38 ),
inference(resolution,[],[f2424,f4]) ).
fof(f2518,plain,
spl0_38,
inference(avatar_contradiction_clause,[],[f2515]) ).
cnf(s24,plain,
spl0_34,
inference(sat_conversion,[],[f2057]) ).
cnf(s27,plain,
( ~ spl0_37
| ~ spl0_38 ),
inference(sat_conversion,[],[f2425]) ).
cnf(s29,plain,
( ~ spl0_34
| spl0_37
| ~ spl0_41 ),
inference(sat_conversion,[],[f2455]) ).
cnf(s30,plain,
spl0_41,
inference(sat_conversion,[],[f2501]) ).
cnf(s32,plain,
spl0_38,
inference(sat_conversion,[],[f2518]) ).
cnf(s33,plain,
( ~ spl0_34
| spl0_37 ),
inference(rat,[],[s29,s30]) ).
cnf(s34,plain,
~ spl0_37,
inference(rat,[],[s27,s32]) ).
cnf(s35,plain,
~ spl0_34,
inference(rat,[],[s33,s34]) ).
cnf(s36,plain,
$false,
inference(rat,[],[s24,s35]) ).
fof(f2519,plain,
$false,
inference(avatar_sat_refutation,[],[s36]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYN637-1 : TPTP v9.3.1. Released v2.5.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.07/0.18 % Computer : n006.cluster.edu
% 0.07/0.18 % Model : x86_64 x86_64
% 0.07/0.18 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.07/0.18 % Memory : 8046.5625MB
% 0.07/0.18 % OS : Linux 6.8.0-71-generic
% 0.07/0.18 % CPULimit : 300
% 0.07/0.18 % WCLimit : 300
% 0.07/0.18 % DateTime : Mon Sep 28 16:37:40 UTC 2026
% 0.07/0.19 % CPUTime :
% 0.07/0.19 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.07/0.22 Running first-order theorem proving
% 0.07/0.22 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
% 2.65/0.93 % (4103227)Input is clausal, will run a generic CNF schedule.
% 2.65/0.93 % (4103238)dis-21_1_sil=8000:lcm=predicate:random_seed=2779485552: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)
% 2.65/0.93 % (4103238)First to succeed.
% 2.65/0.93 % (4103238)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-4103227"
% 2.65/0.93 % (4103234)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1840090166:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.65/0.93 % (4103233)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2533897484:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.65/0.93 % (4103232)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=2190291650:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.65/0.93 % (4103235)lrs+10_1_sil=8000:sp=occurrence:random_seed=978758186:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.65/0.93 % (4103237)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=4215669751:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.65/0.93 % (4103236)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=4156185110:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.65/0.93 % (4103237)Also succeeded, but the first one will report.
% 2.65/0.93 % (4103236)Also succeeded, but the first one will report.
% 2.65/0.93 % (4103235)Instruction limit reached!
% 2.65/0.93 % (4103235)------------------------------
% 2.65/0.93 % (4103235)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.65/0.93 % (4103235)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.65/0.93 % (4103235)CaDiCaL version: 2.1.3
% 2.65/0.93 % (4103235)Termination reason: Instruction limit
% 2.65/0.93 % (4103235)Termination phase: Saturation
% 2.65/0.93 % (4103235)Time elapsed: 0.059 s
% 2.65/0.93 % (4103235)Peak memory usage: 88 MB
% 2.65/0.93 % (4103235)Instructions burned: 109 (million)
% 2.65/0.93 % (4103238)Refutation found. Thanks to Tanya!
% 2.65/0.93 % SZS status Unsatisfiable for theBenchmark
% 2.65/0.93 % SZS output start Proof for theBenchmark
% See solution above
% 2.65/0.93 % (4103238)------------------------------
% 2.65/0.93 % (4103238)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.65/0.93 % (4103238)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.65/0.93 % (4103238)CaDiCaL version: 2.1.3
% 2.65/0.93 % (4103238)Termination reason: Refutation
% 2.65/0.93 % (4103238)Time elapsed: 0.031 s
% 2.65/0.93 % (4103238)Peak memory usage: 90 MB
% 2.65/0.93 % (4103238)Instructions burned: 90 (million)
% 2.65/0.93 % (4103238)------------------------------
% 2.65/0.93 % (4103238)------------------------------
% 2.65/0.93 % (4103227)Success in time 0.315 s
% 2.65/0.93 % Vampire exiting
%------------------------------------------------------------------------------