%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SYN721-1 : TPTP v9.3.1. Released v2.5.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n003.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 02:17:58 PM UTC 2026
% Result : Unsatisfiable 0.09s 0.26s
% Output : Refutation 0.09s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 6
% Syntax : Number of formulae : 26 ( 10 unt; 2 def)
% Number of atoms : 42 ( 0 equ)
% Maximal formula atoms : 2 ( 1 avg)
% Number of connectives : 34 ( 18 ~; 14 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 5 ( 4 usr; 3 prp; 0-2 aty)
% Number of functors : 2 ( 2 usr; 2 con; 0-0 aty)
% Number of variables : 21 ( 0 sgn 21 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,negated_conjecture,
r(a,b),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',lx1_1) ).
fof(f2,negated_conjecture,
! [X0,X1] :
( q(X0,X0)
| ~ r(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',lx1_2) ).
fof(f3,negated_conjecture,
! [X2,X0,X1] :
( r(X0,X1)
| ~ q(X2,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',lx1_3) ).
fof(f4,negated_conjecture,
! [X0] :
( ~ q(X0,a)
| ~ r(b,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',lx1_4) ).
fof(f5,plain,
~ r(a,b),
inference(consistent_polarity_flipping,[],[f1]) ).
fof(f6,plain,
! [X0,X1] :
( ~ q(X0,X0)
| r(X0,X1) ),
inference(consistent_polarity_flipping,[],[f2]) ).
fof(f7,plain,
! [X2,X0,X1] :
( q(X2,X1)
| ~ r(X0,X1) ),
inference(consistent_polarity_flipping,[],[f3]) ).
fof(f8,plain,
! [X0] :
( q(X0,a)
| r(b,X0) ),
inference(consistent_polarity_flipping,[],[f4]) ).
fof(f9,plain,
! [X2,X0,X1] :
( r(X1,X2)
| ~ r(X0,X1) ),
inference(resolution,[],[f7,f6]) ).
fof(f10,plain,
! [X0] :
( r(b,a)
| r(a,X0) ),
inference(resolution,[],[f8,f6]) ).
fof(f12,definition,
( spl0_1
<=> ! [X0] : r(a,X0) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f13,plain,
( ! [X0] : r(a,X0)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f12]) ).
fof(f15,definition,
( spl0_2
<=> r(b,a) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f17,plain,
( r(b,a)
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f15]) ).
fof(f18,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f10,f15,f12]) ).
fof(f19,plain,
! [X0] : ~ r(X0,a),
inference(resolution,[],[f9,f5]) ).
fof(f20,plain,
( $false
| ~ spl0_2 ),
inference(resolution,[],[f19,f17]) ).
fof(f21,plain,
! [X0,X1] : ~ r(X0,X1),
inference(resolution,[],[f19,f9]) ).
fof(f22,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f20]) ).
fof(f23,plain,
( $false
| ~ spl0_1 ),
inference(resolution,[],[f13,f21]) ).
fof(f24,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f23]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f18]) ).
cnf(s2,plain,
~ spl0_2,
inference(sat_conversion,[],[f22]) ).
cnf(s3,plain,
~ spl0_1,
inference(sat_conversion,[],[f24]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s2,s3]) ).
fof(f25,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYN721-1 : TPTP v9.3.1. Released v2.5.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.09/0.19 % Computer : n003.cluster.edu
% 0.09/0.19 % Model : x86_64 x86_64
% 0.09/0.19 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.19 % Memory : 8046.5625MB
% 0.09/0.19 % OS : Linux 6.8.0-71-generic
% 0.09/0.19 % CPULimit : 300
% 0.09/0.19 % WCLimit : 300
% 0.09/0.19 % DateTime : Mon Sep 28 16:50:58 UTC 2026
% 0.09/0.19 % CPUTime :
% 0.09/0.19 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.09/0.22 Running first-order model finding
% 0.09/0.23 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
% 0.09/0.26 % (1743316)Will run a generic schedule for satisfiability detection.
% 0.09/0.26 % (1743327)ott-3_16_to=lpo:sil=16000:sp=arity:fd=off:rp=on:random_seed=4218740733:i=159:bs=unit_only:nicw=on:fsr=off:amm=off_2999 on theBenchmark for (2999ds/159Mi)
% 0.09/0.26 % (1743327) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-1743316-1743327"...
% 0.09/0.26 % (1743327)...printing done.
% 0.09/0.26 % (1743327)Refutation found. Thanks to Tanya!
% 0.09/0.26 % SZS status Unsatisfiable for theBenchmark
% 0.09/0.26 % SZS output start Proof for theBenchmark
% See solution above
% 0.09/0.26 % (1743327)------------------------------
% 0.09/0.26 % (1743327)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.09/0.26 % (1743327)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.09/0.26 % (1743327)CaDiCaL version: 2.1.3
% 0.09/0.26 % (1743327)Termination reason: Refutation
% 0.09/0.26 % (1743327)Time elapsed: 0.001 s
% 0.09/0.26 % (1743327)Peak memory usage: 12 MB
% 0.09/0.26 % (1743316)Success in time 0.031 s
% 0.09/0.26 % Vampire exiting
%------------------------------------------------------------------------------