%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SYN034-1 : 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 : n014.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 02:06:28 PM UTC 2026
% Result : Unsatisfiable 0.06s 0.25s
% Output : Refutation 0.06s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 5
% Syntax : Number of formulae : 24 ( 5 unt; 2 def)
% Number of atoms : 50 ( 0 equ)
% Maximal formula atoms : 3 ( 2 avg)
% Number of connectives : 53 ( 27 ~; 24 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 4 ( 3 usr; 3 prp; 0-2 aty)
% Number of functors : 2 ( 2 usr; 1 con; 0-1 aty)
% Number of variables : 8 ( 0 sgn 8 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( p(X0,f(X0))
| p(X0,a) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause1) ).
fof(f2,axiom,
! [X0] :
( p(f(X0),X0)
| p(X0,a) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause2) ).
fof(f3,negated_conjecture,
! [X0,X1] :
( ~ p(X1,a)
| ~ p(X1,X0)
| ~ p(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',theorem) ).
fof(f4,plain,
! [X0] :
( p(a,a)
| ~ p(f(a),X0)
| ~ p(X0,f(a)) ),
inference(resolution,[],[f2,f3]) ).
fof(f6,definition,
( spl0_1
<=> ! [X0] :
( ~ p(f(a),X0)
| ~ p(X0,f(a)) ) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f7,plain,
( ! [X0] :
( ~ p(f(a),X0)
| ~ p(X0,f(a)) )
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f6]) ).
fof(f9,definition,
( spl0_2
<=> p(a,a) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f10,plain,
( ~ p(a,a)
| spl0_2 ),
inference(avatar_component_clause,[],[f9]) ).
fof(f11,plain,
( p(a,a)
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f9]) ).
fof(f12,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f4,f9,f6]) ).
fof(f13,plain,
( ! [X0] :
( ~ p(a,X0)
| ~ p(X0,a) )
| ~ spl0_2 ),
inference(resolution,[],[f11,f3]) ).
fof(f14,plain,
( ~ p(a,a)
| ~ spl0_2 ),
inference(resolution,[],[f13,f11]) ).
fof(f17,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f14,f11]) ).
fof(f18,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f17]) ).
fof(f19,plain,
( ~ p(a,f(a))
| p(a,a)
| ~ spl0_1 ),
inference(resolution,[],[f7,f2]) ).
fof(f22,plain,
( p(a,a)
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f19,f1]) ).
fof(f23,plain,
( $false
| ~ spl0_1
| spl0_2 ),
inference(forward_subsumption_resolution,[],[f22,f10]) ).
fof(f24,plain,
( ~ spl0_1
| spl0_2 ),
inference(avatar_contradiction_clause,[],[f23]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f12]) ).
cnf(s2,plain,
~ spl0_2,
inference(sat_conversion,[],[f18]) ).
cnf(s3,plain,
( ~ spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f24]) ).
cnf(s4,plain,
~ spl0_1,
inference(rat,[],[s3,s2]) ).
cnf(s5,plain,
$false,
inference(rat,[],[s1,s2,s4]) ).
fof(f25,plain,
$false,
inference(avatar_sat_refutation,[],[s5]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : SYN034-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.06/0.18 % Computer : n014.cluster.edu
% 0.06/0.18 % Model : x86_64 x86_64
% 0.06/0.18 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.06/0.18 % Memory : 8046.5625MB
% 0.06/0.18 % OS : Linux 6.8.0-71-generic
% 0.06/0.18 % CPULimit : 300
% 0.06/0.18 % WCLimit : 300
% 0.06/0.18 % DateTime : Mon Sep 28 15:20:31 UTC 2026
% 0.06/0.18 % CPUTime :
% 0.06/0.18 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.06/0.21 Running first-order model finding
% 0.06/0.21 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
% 0.06/0.25 % (1850404)Will run a generic schedule for satisfiability detection.
% 0.06/0.25 % (1850412)dis+10_1_sil=32000:sp=arity:random_seed=464942233:i=103:fgj=on_2999 on theBenchmark for (2999ds/103Mi)
% 0.06/0.25 % (1850412) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-1850404-1850412"...
% 0.06/0.25 % (1850412)...printing done.
% 0.06/0.25 % (1850412)Refutation found. Thanks to Tanya!
% 0.06/0.25 % SZS status Unsatisfiable for theBenchmark
% 0.06/0.25 % SZS output start Proof for theBenchmark
% See solution above
% 0.06/0.25 % (1850412)------------------------------
% 0.06/0.25 % (1850412)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.06/0.25 % (1850412)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.06/0.25 % (1850412)CaDiCaL version: 2.1.3
% 0.06/0.25 % (1850412)Termination reason: Refutation
% 0.06/0.25 % (1850412)Time elapsed: 0.001 s
% 0.06/0.25 % (1850412)Peak memory usage: 11 MB
% 0.06/0.25 % (1850404)Success in time 0.032 s
% 0.06/0.25 % Vampire exiting
%------------------------------------------------------------------------------