%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SYO013_8 : TPTP v9.3.1. Released v8.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n001.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 02:29:33 PM UTC 2026
% Result : Theorem 0.24s 0.32s
% Output : Refutation 0.24s
% Verified :
% SZS Type : Refutation
% Derivation depth : 12
% Number of leaves : 7
% Syntax : Number of formulae : 46 ( 13 unt; 0 typ; 6 def)
% Number of atoms : 130 ( 13 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 73 ( 29 ~; 21 |; 12 &)
% ( 6 <=>; 5 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 3 avg)
% Maximal term depth : 0 ( 0 avg)
% Number of FOOLs : 40 ( 40 fml; 0 var)
% Number of types : 1 ( 0 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 12 ( 9 usr; 10 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 0 ( 0 sgn 0 !; 0 ?; 0 :)
% Comments :
%------------------------------------------------------------------------------
tff(func_def_0,type,
bG0: $o ).
tff(func_def_3,type,
bG1: $o ).
tff(pred_def_3,type,
p: $o > $o ).
tff(f1,conjecture,
( ( a
& b
& p(a) )
=> p(b) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',conj) ).
tff(f2,negated_conjecture,
~ ( ( a
& b
& p(a) )
=> p(b) ),
inference(negated_conjecture,[status(cth)],[f1]) ).
tff(f3,definition,
( a
<=> ( bG0 = $true ) ),
introduced(definition,[new_symbols(definition,[bG0])],[fool_formula_definition]) ).
tff(f4,definition,
( b
<=> ( $true = bG1 ) ),
introduced(definition,[new_symbols(definition,[bG1])],[fool_formula_definition]) ).
tff(f5,plain,
~ ( ( a
& b
& p(bG0) )
=> p(bG1) ),
inference(fool_elimination,[],[f2,f4,f3]) ).
tff(f6,plain,
( b
=> ( $true = bG1 ) ),
inference(unused_predicate_definition_removal,[],[f4]) ).
tff(f7,plain,
( a
=> ( bG0 = $true ) ),
inference(unused_predicate_definition_removal,[],[f3]) ).
tff(f8,plain,
( ( $true = bG1 )
| ~ b ),
inference(ennf_transformation,[],[f6]) ).
tff(f9,plain,
( ( bG0 = $true )
| ~ a ),
inference(ennf_transformation,[],[f7]) ).
tff(f10,plain,
( ~ p(bG1)
& a
& b
& p(bG0) ),
inference(ennf_transformation,[],[f5]) ).
tff(f11,plain,
( ~ p(bG1)
& a
& b
& p(bG0) ),
inference(flattening,[],[f10]) ).
tff(f12,plain,
( ( $true = bG1 )
| ~ b ),
inference(cnf_transformation,[],[f8]) ).
tff(f13,plain,
( ( bG0 = $true )
| ~ a ),
inference(cnf_transformation,[],[f9]) ).
tff(f14,plain,
p(bG0),
inference(cnf_transformation,[],[f11]) ).
tff(f15,plain,
b,
inference(cnf_transformation,[],[f11]) ).
tff(f16,plain,
a,
inference(cnf_transformation,[],[f11]) ).
tff(f17,plain,
~ p(bG1),
inference(cnf_transformation,[],[f11]) ).
tff(f20,plain,
( ( bG0 = $true )
| a ),
inference(consistent_polarity_flipping,[],[f13]) ).
tff(f21,plain,
~ a,
inference(consistent_polarity_flipping,[],[f16]) ).
tff(f23,definition,
( spl2_1
<=> a ),
introduced(definition,[new_symbols(definition,[spl2_1])],[avatar_definition]) ).
tff(f25,plain,
( a
| ~ spl2_1 ),
inference(avatar_component_clause,[],[f23]) ).
tff(f27,definition,
( spl2_2
<=> ( bG0 = $true ) ),
introduced(definition,[new_symbols(definition,[spl2_2])],[avatar_definition]) ).
tff(f29,plain,
( ( bG0 = $true )
| ~ spl2_2 ),
inference(avatar_component_clause,[],[f27]) ).
tff(f30,plain,
( spl2_1
| spl2_2 ),
inference(avatar_split_clause,[],[f20,f27,f23]) ).
tff(f32,definition,
( spl2_3
<=> b ),
introduced(definition,[new_symbols(definition,[spl2_3])],[avatar_definition]) ).
tff(f34,plain,
( ~ b
| spl2_3 ),
inference(avatar_component_clause,[],[f32]) ).
tff(f36,definition,
( spl2_4
<=> ( $true = bG1 ) ),
introduced(definition,[new_symbols(definition,[spl2_4])],[avatar_definition]) ).
tff(f38,plain,
( ( $true = bG1 )
| ~ spl2_4 ),
inference(avatar_component_clause,[],[f36]) ).
tff(f39,plain,
( ~ spl2_3
| spl2_4 ),
inference(avatar_split_clause,[],[f12,f36,f32]) ).
tff(f40,plain,
( $false
| spl2_3 ),
inference(resolution,[],[f34,f15]) ).
tff(f41,plain,
spl2_3,
inference(avatar_contradiction_clause,[],[f40]) ).
tff(f42,plain,
( p($true)
| ~ spl2_2 ),
inference(superposition,[],[f14,f29]) ).
tff(f43,plain,
( ~ p($true)
| ~ spl2_4 ),
inference(superposition,[],[f17,f38]) ).
tff(f44,plain,
( $false
| ~ spl2_2
| ~ spl2_4 ),
inference(resolution,[],[f43,f42]) ).
tff(f45,plain,
( ~ spl2_2
| ~ spl2_4 ),
inference(avatar_contradiction_clause,[],[f44]) ).
tff(f46,plain,
( $false
| ~ spl2_1 ),
inference(resolution,[],[f25,f21]) ).
tff(f47,plain,
~ spl2_1,
inference(avatar_contradiction_clause,[],[f46]) ).
cnf(s1,plain,
( spl2_1
| spl2_2 ),
inference(sat_conversion,[],[f30]) ).
cnf(s2,plain,
( ~ spl2_3
| spl2_4 ),
inference(sat_conversion,[],[f39]) ).
cnf(s3,plain,
spl2_3,
inference(sat_conversion,[],[f41]) ).
cnf(s4,plain,
( ~ spl2_2
| ~ spl2_4 ),
inference(sat_conversion,[],[f45]) ).
cnf(s5,plain,
~ spl2_1,
inference(sat_conversion,[],[f47]) ).
cnf(s6,plain,
spl2_4,
inference(rat,[],[s2,s3]) ).
cnf(s7,plain,
~ spl2_2,
inference(rat,[],[s4,s6]) ).
cnf(s8,plain,
$false,
inference(rat,[],[s1,s7,s5]) ).
tff(f48,plain,
$false,
inference(avatar_sat_refutation,[],[s8]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYO013_8 : TPTP v9.3.1. Released v8.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.09/0.22 % Computer : n001.cluster.edu
% 0.09/0.22 % Model : x86_64 x86_64
% 0.09/0.22 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.22 % Memory : 8046.5625MB
% 0.09/0.22 % OS : Linux 6.8.0-71-generic
% 0.09/0.22 % CPULimit : 300
% 0.09/0.22 % WCLimit : 300
% 0.09/0.22 % DateTime : Mon Sep 28 17:26:48 UTC 2026
% 0.09/0.23 % CPUTime :
% 0.09/0.23 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.24/0.28 Running first-order model finding
% 0.24/0.28 Running: /export/starexec/sandbox2/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.24/0.32 % (505320)Will run a generic schedule for satisfiability detection.
% 0.24/0.32 % (505331)ott-3_16_to=lpo:sil=16000:sp=arity:fd=off:rp=on:random_seed=1572106981:i=159:bs=unit_only:nicw=on:fsr=off:amm=off_2999 on theBenchmark for (2999ds/159Mi)
% 0.24/0.32 % (505331) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-505320-505331"...
% 0.24/0.32 % (505331)...printing done.
% 0.24/0.32 % (505331)Refutation found. Thanks to Tanya!
% 0.24/0.32 % SZS status Theorem for theBenchmark
% 0.24/0.32 % SZS output start Proof for theBenchmark
% See solution above
% 0.24/0.32 % (505331)------------------------------
% 0.24/0.32 % (505331)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.24/0.32 % (505331)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.24/0.32 % (505331)CaDiCaL version: 2.1.3
% 0.24/0.32 % (505331)Termination reason: Refutation
% 0.24/0.32 % (505331)Time elapsed: 0.002 s
% 0.24/0.32 % (505331)Peak memory usage: 12 MB
% 0.24/0.32 % (505331)Instructions burned: 1 (million)
% 0.24/0.32 % (505320)Success in time 0.026 s
% 0.24/0.32 % Vampire exiting
%------------------------------------------------------------------------------