%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN581-1 : 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 : n018.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 02:01:00 PM UTC 2026
% Result : Unsatisfiable 2.86s 1.15s
% Output : Refutation 2.86s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 11
% Syntax : Number of formulae : 30 ( 11 unt; 2 def)
% Number of atoms : 55 ( 0 equ)
% Maximal formula atoms : 4 ( 1 avg)
% Number of connectives : 51 ( 26 ~; 23 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 9 ( 3 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of predicates : 6 ( 5 usr; 3 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 4 con; 0-2 aty)
% Number of variables : 21 ( 0 sgn 21 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f2,negated_conjecture,
! [X0] : p2(X0,X0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p2_2) ).
fof(f3,negated_conjecture,
! [X0] : p5(X0,X0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p5_3) ).
fof(f5,negated_conjecture,
p2(c18,c14),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p2_5) ).
fof(f8,negated_conjecture,
p11(f4(f6(c15,c14)),c16),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p11_8) ).
fof(f9,negated_conjecture,
~ p11(f4(f6(c15,c18)),c16),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',not_p11_9) ).
fof(f14,negated_conjecture,
! [X0,X1] :
( p2(f4(X0),f4(X1))
| ~ p2(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p2_14) ).
fof(f18,negated_conjecture,
! [X2,X0,X1] :
( p2(X0,X1)
| ~ p2(X2,X0)
| ~ p2(X2,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p2_18) ).
fof(f21,negated_conjecture,
! [X2,X3,X0,X1] :
( p11(X0,X1)
| ~ p2(X2,X0)
| ~ p2(X3,X1)
| ~ p11(X2,X3) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p11_21) ).
fof(f23,negated_conjecture,
! [X2,X3,X0,X1] :
( ~ p5(X0,X2)
| ~ p2(X1,X3)
| p2(f6(X0,X1),f6(X2,X3)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',p2_23) ).
fof(f36,plain,
! [X0,X1] :
( ~ p11(X0,X1)
| ~ p2(X1,c16)
| ~ p2(X0,f4(f6(c15,c18))) ),
inference(resolution,[],[f21,f9]) ).
fof(f43,plain,
! [X2,X0,X1] :
( p2(f6(X2,X0),f6(X2,X1))
| ~ p2(X0,X1) ),
inference(resolution,[],[f23,f3]) ).
fof(f178,plain,
( ~ p2(c16,c16)
| ~ p2(f4(f6(c15,c14)),f4(f6(c15,c18))) ),
inference(resolution,[],[f36,f8]) ).
fof(f194,definition,
( spl0_24
<=> p2(c16,c16) ),
introduced(definition,[new_symbols(definition,[spl0_24])],[avatar_definition]) ).
fof(f195,plain,
( ~ p2(c16,c16)
| spl0_24 ),
inference(avatar_component_clause,[],[f194]) ).
fof(f198,definition,
( spl0_25
<=> p2(f4(f6(c15,c14)),f4(f6(c15,c18))) ),
introduced(definition,[new_symbols(definition,[spl0_25])],[avatar_definition]) ).
fof(f199,plain,
( ~ p2(f4(f6(c15,c14)),f4(f6(c15,c18)))
| spl0_25 ),
inference(avatar_component_clause,[],[f198]) ).
fof(f200,plain,
( ~ spl0_25
| ~ spl0_24 ),
inference(avatar_split_clause,[],[f178,f194,f198]) ).
fof(f206,plain,
( $false
| spl0_24 ),
inference(resolution,[],[f195,f2]) ).
fof(f209,plain,
spl0_24,
inference(avatar_contradiction_clause,[],[f206]) ).
fof(f212,plain,
( ~ p2(f6(c15,c14),f6(c15,c18))
| spl0_25 ),
inference(resolution,[],[f199,f14]) ).
fof(f217,plain,
( ~ p2(c14,c18)
| spl0_25 ),
inference(resolution,[],[f212,f43]) ).
fof(f223,plain,
( ! [X0] :
( ~ p2(X0,c14)
| ~ p2(X0,c18) )
| spl0_25 ),
inference(resolution,[],[f217,f18]) ).
fof(f228,plain,
( ~ p2(c18,c18)
| spl0_25 ),
inference(resolution,[],[f223,f5]) ).
fof(f232,plain,
( $false
| spl0_25 ),
inference(resolution,[],[f228,f2]) ).
fof(f235,plain,
spl0_25,
inference(avatar_contradiction_clause,[],[f232]) ).
cnf(s18,plain,
( ~ spl0_24
| ~ spl0_25 ),
inference(sat_conversion,[],[f200]) ).
cnf(s20,plain,
spl0_24,
inference(sat_conversion,[],[f209]) ).
cnf(s21,plain,
spl0_25,
inference(sat_conversion,[],[f235]) ).
cnf(s23,plain,
$false,
inference(rat,[],[s18,s21,s20]) ).
fof(f236,plain,
$false,
inference(avatar_sat_refutation,[],[s23]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : SYN581-1 : TPTP v9.3.1. Released v2.5.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.08/0.17 % Computer : n018.cluster.edu
% 0.08/0.17 % Model : x86_64 x86_64
% 0.08/0.17 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.08/0.17 % Memory : 8046.5625MB
% 0.08/0.17 % OS : Linux 6.8.0-71-generic
% 0.08/0.17 % CPULimit : 300
% 0.08/0.17 % WCLimit : 300
% 0.08/0.17 % DateTime : Mon Sep 28 16:32:25 UTC 2026
% 0.08/0.17 % CPUTime :
% 0.08/0.17 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.08/0.21 Running first-order theorem proving
% 0.08/0.21 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
% 2.86/1.15 % (3525414)Input is clausal, will run a generic CNF schedule.
% 2.86/1.15 % (3525425)dis-21_1_sil=8000:lcm=predicate:random_seed=3071839436: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)
% 2.86/1.15 % (3525425)First to succeed.
% 2.86/1.15 % (3525425)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3525414"
% 2.86/1.15 % (3525420)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2621057414:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.86/1.15 % (3525421)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1501957012:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.86/1.15 % (3525419)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=244945804:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.86/1.15 % (3525422)lrs+10_1_sil=8000:sp=occurrence:random_seed=3917549236:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.86/1.15 % (3525424)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3843692457:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.86/1.15 % (3525423)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2699358185:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.86/1.15 % (3525424)Also succeeded, but the first one will report.
% 2.86/1.15 % (3525423)Also succeeded, but the first one will report.
% 2.86/1.15 % (3525422)Also succeeded, but the first one will report.
% 2.86/1.15 % (3525425)Refutation found. Thanks to Tanya!
% 2.86/1.15 % SZS status Unsatisfiable for theBenchmark
% 2.86/1.15 % SZS output start Proof for theBenchmark
% See solution above
% 2.86/1.15 % (3525425)------------------------------
% 2.86/1.15 % (3525425)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.86/1.15 % (3525425)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.86/1.15 % (3525425)CaDiCaL version: 2.1.3
% 2.86/1.15 % (3525425)Termination reason: Refutation
% 2.86/1.15 % (3525425)Time elapsed: 0.003 s
% 2.86/1.15 % (3525425)Peak memory usage: 89 MB
% 2.86/1.15 % (3525425)Instructions burned: 5 (million)
% 2.86/1.15 % (3525425)------------------------------
% 2.86/1.15 % (3525425)------------------------------
% 2.86/1.15 % (3525414)Success in time 0.31 s
% 2.86/1.15 % Vampire exiting
%------------------------------------------------------------------------------