%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : COM002-2 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n026.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 09:40:04 AM UTC 2026
% Result : Unsatisfiable 0.24s 0.34s
% Output : Refutation 0.24s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 11
% Syntax : Number of formulae : 31 ( 16 unt; 2 def)
% Number of atoms : 50 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 39 ( 20 ~; 17 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 7 ( 6 usr; 3 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 5 con; 0-1 aty)
% Number of variables : 13 ( 0 sgn 13 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0,X1] :
( ~ follows(X0,X1)
| ~ fails(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',direct_success) ).
fof(f2,axiom,
! [X2,X0,X1] :
( ~ fails(X0,X1)
| fails(X0,X2)
| fails(X2,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',transitivity_of_success) ).
fof(f3,axiom,
! [X2,X0,X1] :
( ~ has(X1,goto(X2))
| ~ fails(X0,X1)
| ~ labels(X2,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',goto_success) ).
fof(f8,axiom,
labels(loop,p3),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',label_state_3) ).
fof(f13,axiom,
follows(p6,p3),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',transition_3_to_6) ).
fof(f15,axiom,
follows(p7,p6),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',transition_6_to_7) ).
fof(f17,axiom,
follows(p8,p7),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',transition_7_to_8) ).
fof(f18,axiom,
has(p8,goto(loop)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',state_8) ).
fof(f19,negated_conjecture,
fails(p3,p3),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_there_is_a_loop_through_p3) ).
fof(f23,plain,
~ fails(p6,p3),
inference(resolution,[],[f1,f13]) ).
fof(f24,plain,
~ fails(p7,p6),
inference(resolution,[],[f1,f15]) ).
fof(f25,plain,
~ fails(p8,p7),
inference(resolution,[],[f1,f17]) ).
fof(f27,plain,
! [X0] :
( fails(p3,X0)
| fails(X0,p3) ),
inference(resolution,[],[f2,f19]) ).
fof(f29,plain,
! [X0,X1] :
( fails(X0,p3)
| fails(p3,X1)
| fails(X1,X0) ),
inference(resolution,[],[f27,f2]) ).
fof(f34,plain,
! [X0] :
( ~ labels(loop,X0)
| ~ fails(X0,p8) ),
inference(resolution,[],[f3,f18]) ).
fof(f45,plain,
~ fails(p3,p8),
inference(resolution,[],[f34,f8]) ).
fof(f57,plain,
( fails(p7,p3)
| fails(p3,p8) ),
inference(resolution,[],[f29,f25]) ).
fof(f65,definition,
( spl0_1
<=> fails(p3,p8) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f69,definition,
( spl0_2
<=> fails(p7,p3) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f71,plain,
( fails(p7,p3)
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f69]) ).
fof(f72,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f57,f69,f65]) ).
fof(f75,plain,
( ! [X0] :
( fails(p7,X0)
| fails(X0,p3) )
| ~ spl0_2 ),
inference(resolution,[],[f71,f2]) ).
fof(f77,plain,
~ spl0_1,
inference(avatar_split_clause,[],[f45,f65]) ).
fof(f117,plain,
( fails(p6,p3)
| ~ spl0_2 ),
inference(resolution,[],[f75,f24]) ).
fof(f120,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f117,f23]) ).
fof(f121,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f120]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f72]) ).
cnf(s2,plain,
~ spl0_1,
inference(sat_conversion,[],[f77]) ).
cnf(s3,plain,
~ spl0_2,
inference(sat_conversion,[],[f121]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s3,s2]) ).
fof(f122,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : COM002-2 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.10/0.25 % Computer : n026.cluster.edu
% 0.10/0.25 % Model : x86_64 x86_64
% 0.10/0.25 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.25 % Memory : 8046.5625MB
% 0.10/0.25 % OS : Linux 6.8.0-71-generic
% 0.10/0.25 % CPULimit : 300
% 0.10/0.25 % WCLimit : 300
% 0.10/0.25 % DateTime : Mon Sep 28 21:45:27 UTC 2026
% 0.10/0.25 % CPUTime :
% 0.10/0.25 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.24/0.30 Running first-order model finding
% 0.24/0.30 Running: /export/starexec/sandbox/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 0.24/0.34 % (110784)Will run a generic schedule for satisfiability detection.
% 0.24/0.34 % (110792)dis+10_1_sil=32000:sp=arity:random_seed=3110233070:i=103:fgj=on_2999 on theBenchmark for (2999ds/103Mi)
% 0.24/0.34 % (110792) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-110784-110792"...
% 0.24/0.34 % (110794)ott+1_1_to=lpo:sil=16000:sp=reverse_arity:erd=off:random_seed=3116994547:i=131_2999 on theBenchmark for (2999ds/131Mi)
% 0.24/0.34 % (110792)...printing done.
% 0.24/0.34 % (110792)Refutation found. Thanks to Tanya!
% 0.24/0.34 % SZS status Unsatisfiable for theBenchmark
% 0.24/0.34 % SZS output start Proof for theBenchmark
% See solution above
% 0.24/0.34 % (110792)------------------------------
% 0.24/0.34 % (110792)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.24/0.34 % (110792)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.24/0.34 % (110792)CaDiCaL version: 2.1.3
% 0.24/0.34 % (110792)Termination reason: Refutation
% 0.24/0.34 % (110792)Time elapsed: 0.003 s
% 0.24/0.34 % (110792)Peak memory usage: 12 MB
% 0.24/0.34 % (110792)Instructions burned: 3 (million)
% 0.24/0.34 % (110784)Success in time 0.024 s
% 0.24/0.34 % Vampire exiting
%------------------------------------------------------------------------------