%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN347-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n008.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 01:50:19 PM UTC 2026
% Result : Unsatisfiable 2.85s 1.19s
% Output : Refutation 2.85s
% Verified :
% SZS Type : Refutation
% Derivation depth : 12
% Number of leaves : 11
% Syntax : Number of formulae : 40 ( 5 unt; 5 def)
% Number of atoms : 93 ( 0 equ)
% Maximal formula atoms : 3 ( 2 avg)
% Number of connectives : 100 ( 47 ~; 48 |; 0 &)
% ( 5 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 4 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 7 ( 6 usr; 6 prp; 0-2 aty)
% Number of functors : 3 ( 3 usr; 2 con; 0-2 aty)
% Number of variables : 31 ( 0 sgn 31 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,negated_conjecture,
! [X0,X1] :
( f(X0,y(X0,X1))
| ~ f(X1,y(X0,X1))
| f(a,b) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause1) ).
fof(f2,negated_conjecture,
! [X0,X1] :
( ~ f(X0,y(X0,X1))
| f(X1,y(X0,X1))
| f(a,b) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause2) ).
fof(f3,negated_conjecture,
! [X0,X1] :
( ~ f(X0,y(X0,X1))
| ~ f(X1,y(X0,X1))
| ~ f(a,b) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause3) ).
fof(f4,negated_conjecture,
! [X0,X1] :
( f(X0,y(X0,X1))
| f(X1,y(X0,X1))
| ~ f(a,b) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause4) ).
fof(f5,negated_conjecture,
! [X0,X1] :
( f(b,y(X0,X1))
| f(a,y(X0,X1)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause5) ).
fof(f6,negated_conjecture,
! [X0,X1] :
( ~ f(b,y(X0,X1))
| ~ f(a,y(X0,X1)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause6) ).
fof(f8,definition,
( spl0_1
<=> f(a,b) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f12,definition,
( spl0_2
<=> ! [X0,X1] :
( f(X0,y(X0,X1))
| f(X1,y(X0,X1)) ) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f13,plain,
( ! [X0,X1] :
( f(X0,y(X0,X1))
| f(X1,y(X0,X1)) )
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f12]) ).
fof(f14,plain,
( ~ spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f4,f12,f8]) ).
fof(f16,definition,
( spl0_3
<=> ! [X0,X1] :
( ~ f(X0,y(X0,X1))
| ~ f(X1,y(X0,X1)) ) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f17,plain,
( ! [X0,X1] :
( ~ f(X1,y(X0,X1))
| ~ f(X0,y(X0,X1)) )
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f16]) ).
fof(f18,plain,
( ~ spl0_1
| spl0_3 ),
inference(avatar_split_clause,[],[f3,f16,f8]) ).
fof(f20,definition,
( spl0_4
<=> ! [X0,X1] :
( ~ f(X0,y(X0,X1))
| f(X1,y(X0,X1)) ) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f21,plain,
( ! [X0,X1] :
( ~ f(X0,y(X0,X1))
| f(X1,y(X0,X1)) )
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f20]) ).
fof(f22,plain,
( spl0_1
| spl0_4 ),
inference(avatar_split_clause,[],[f2,f20,f8]) ).
fof(f24,definition,
( spl0_5
<=> ! [X0,X1] :
( f(X0,y(X0,X1))
| ~ f(X1,y(X0,X1)) ) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f25,plain,
( ! [X0,X1] :
( ~ f(X1,y(X0,X1))
| f(X0,y(X0,X1)) )
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f24]) ).
fof(f26,plain,
( spl0_1
| spl0_5 ),
inference(avatar_split_clause,[],[f1,f24,f8]) ).
fof(f28,plain,
( ! [X0] :
( f(X0,y(b,X0))
| f(a,y(b,X0)) )
| ~ spl0_4 ),
inference(resolution,[],[f21,f5]) ).
fof(f33,plain,
( f(a,y(b,a))
| ~ spl0_4 ),
inference(factoring,[],[f28]) ).
fof(f34,plain,
( f(b,y(b,a))
| ~ spl0_4
| ~ spl0_5 ),
inference(resolution,[],[f33,f25]) ).
fof(f40,plain,
( ~ f(a,y(b,a))
| ~ spl0_4
| ~ spl0_5 ),
inference(resolution,[],[f34,f6]) ).
fof(f42,plain,
( $false
| ~ spl0_4
| ~ spl0_5 ),
inference(forward_subsumption_resolution,[],[f40,f33]) ).
fof(f43,plain,
( ~ spl0_4
| ~ spl0_5 ),
inference(avatar_contradiction_clause,[],[f42]) ).
fof(f56,plain,
( ! [X0] : f(X0,y(X0,X0))
| ~ spl0_2 ),
inference(factoring,[],[f13]) ).
fof(f59,plain,
( ! [X0] : ~ f(X0,y(X0,X0))
| ~ spl0_2
| ~ spl0_3 ),
inference(resolution,[],[f17,f56]) ).
fof(f61,plain,
( $false
| ~ spl0_2
| ~ spl0_3 ),
inference(forward_subsumption_resolution,[],[f59,f56]) ).
fof(f62,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(avatar_contradiction_clause,[],[f61]) ).
cnf(s1,plain,
( ~ spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f14]) ).
cnf(s2,plain,
( ~ spl0_1
| spl0_3 ),
inference(sat_conversion,[],[f18]) ).
cnf(s3,plain,
( spl0_1
| spl0_4 ),
inference(sat_conversion,[],[f22]) ).
cnf(s4,plain,
( spl0_1
| spl0_5 ),
inference(sat_conversion,[],[f26]) ).
cnf(s5,plain,
( ~ spl0_4
| ~ spl0_5 ),
inference(sat_conversion,[],[f43]) ).
cnf(s8,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(sat_conversion,[],[f62]) ).
cnf(s9,plain,
spl0_1,
inference(rat,[],[s5,s3,s4]) ).
cnf(s10,plain,
spl0_3,
inference(rat,[],[s2,s9]) ).
cnf(s11,plain,
spl0_2,
inference(rat,[],[s1,s9]) ).
cnf(s12,plain,
$false,
inference(rat,[],[s8,s10,s11]) ).
fof(f63,plain,
$false,
inference(avatar_sat_refutation,[],[s12]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYN347-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.08/0.19 % Computer : n008.cluster.edu
% 0.08/0.19 % Model : x86_64 x86_64
% 0.08/0.19 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.08/0.19 % Memory : 8046.5625MB
% 0.08/0.19 % OS : Linux 6.8.0-71-generic
% 0.08/0.19 % CPULimit : 300
% 0.08/0.19 % WCLimit : 300
% 0.08/0.19 % DateTime : Mon Sep 28 15:48:24 UTC 2026
% 0.08/0.20 % CPUTime :
% 0.08/0.20 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.08/0.23 Running first-order theorem proving
% 0.08/0.23 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
% 2.85/1.19 % (2362418)Input is clausal, will run a generic CNF schedule.
% 2.85/1.19 % (2362426)lrs+10_1_sil=8000:sp=occurrence:random_seed=647096415:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.85/1.19 % (2362426)First to succeed.
% 2.85/1.19 % (2362426)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-2362418"
% 2.85/1.19 % (2362429)dis-21_1_sil=8000:lcm=predicate:random_seed=4008364567: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)
% 2.85/1.19 % (2362424)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=1464148478:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.85/1.19 % (2362425)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=2908460223:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.85/1.19 % (2362428)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=217344676:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.85/1.19 % (2362423)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=2210984119:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.85/1.19 % (2362427)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=3428362521:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.85/1.19 % (2362427)Also succeeded, but the first one will report.
% 2.85/1.19 % (2362428)Also succeeded, but the first one will report.
% 2.85/1.19 % (2362429)Also succeeded, but the first one will report.
% 2.85/1.19 % (2362426)Refutation found. Thanks to Tanya!
% 2.85/1.19 % SZS status Unsatisfiable for theBenchmark
% 2.85/1.19 % SZS output start Proof for theBenchmark
% See solution above
% 2.85/1.19 % (2362426)------------------------------
% 2.85/1.19 % (2362426)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.85/1.19 % (2362426)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.85/1.19 % (2362426)CaDiCaL version: 2.1.3
% 2.85/1.19 % (2362426)Termination reason: Refutation
% 2.85/1.19 % (2362426)Time elapsed: 0.002 s
% 2.85/1.19 % (2362426)Peak memory usage: 89 MB
% 2.85/1.19 % (2362426)Instructions burned: 2 (million)
% 2.85/1.19 % (2362426)------------------------------
% 2.85/1.19 % (2362426)------------------------------
% 2.85/1.19 % (2362418)Success in time 0.316 s
% 2.85/1.19 % Vampire exiting
%------------------------------------------------------------------------------