%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SYO217^5 : TPTP v9.3.1. Released v4.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n004.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 : Wed Sep 30 08:49:32 AM UTC 2026
% Result : Theorem 0.19s 0.26s
% Output : Refutation 0.19s
% Verified :
% SZS Type : Refutation
% Derivation depth : 16
% Number of leaves : 5
% Syntax : Number of formulae : 53 ( 13 unt; 0 typ; 4 def)
% Number of atoms : 165 ( 39 equ; 0 cnn)
% Maximal formula atoms : 3 ( 3 avg)
% Number of connectives : 174 ( 44 ~; 41 |; 2 &; 76 @)
% ( 7 <=>; 4 =>; 0 <=; 0 <~>)
% Maximal formula depth : 10 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of types : 3 ( 2 usr)
% Number of type conns : 20 ( 20 >; 0 *; 0 +; 0 <<)
% Number of symbols : 12 ( 9 usr; 8 con; 0-2 aty)
% Number of variables : 28 ( 0 sgn 26 !; 2 ?; 28 :)
% Comments :
%------------------------------------------------------------------------------
thf(type_def_5,type,
b: $tType ).
thf(type_def_6,type,
a: $tType ).
thf(type_def_7,type,
sTfun: ( $tType * $tType ) > $tType ).
thf(func_def_1,type,
sK0: b > a > $o ).
thf(func_def_2,type,
sK1: b > a > $o ).
thf(func_def_5,type,
sK2: b ).
thf(func_def_6,type,
sK3: a ).
thf(f1,conjecture,
! [X0: b > a > $o,X1: b > a > $o] :
( ! [X2: b,X3: a] :
( ( X0 @ X2 @ X3 )
<=> ( X1 @ X2 @ X3 ) )
=> ( X0 = X1 ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',cTHM174) ).
thf(f2,negated_conjecture,
~ ! [X0: b > a > $o,X1: b > a > $o] :
( ! [X2: b,X3: a] :
( ( X0 @ X2 @ X3 )
<=> ( X1 @ X2 @ X3 ) )
=> ( X0 = X1 ) ),
inference(negated_conjecture,[status(cth)],[f1]) ).
thf(f3,plain,
~ ! [X0: b > a > $o,X1: b > a > $o] :
( ! [X2: b,X3: a] :
( ( X0 @ X2 @ X3 )
<=> ( X1 @ X2 @ X3 ) )
=> ( X0 = X1 ) ),
inference(rectify,[],[f2]) ).
thf(f4,plain,
~ ! [X0: b > a > $o,X1: b > a > $o] :
( ! [X2: b,X3: a] :
( ( X0 @ X2 @ X3 )
= ( X1 @ X2 @ X3 ) )
=> ( X0 = X1 ) ),
inference(fool_elimination,[],[f3]) ).
thf(f5,plain,
? [X0: b > a > $o,X1: b > a > $o] :
( ( X0 != X1 )
& ! [X2: b,X3: a] :
( ( X0 @ X2 @ X3 )
= ( X1 @ X2 @ X3 ) ) ),
inference(ennf_transformation,[],[f4]) ).
thf(f6,plain,
( ( sK0 != sK1 )
& ! [X2: b,X3: a] :
( ( sK0 @ X2 @ X3 )
= ( sK1 @ X2 @ X3 ) ) ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK0,sK1]),skolemize(X0,sK0),skolemize(X1,sK1)],[f5]) ).
thf(f7,plain,
! [X2: b,X3: a] :
( ( sK0 @ X2 @ X3 )
= ( sK1 @ X2 @ X3 ) ),
inference(cnf_transformation,[],[f6]) ).
thf(f8,plain,
sK0 != sK1,
inference(cnf_transformation,[],[f6]) ).
thf(f11,plain,
! [X2: b,X3: a] :
( ( ( sK1 @ X2 @ X3 )
= $false )
| ( ( sK0 @ X2 @ X3 )
= $true ) ),
inference(iff_proxy_clausification,[],[f7]) ).
thf(f12,plain,
! [X2: b,X3: a] :
( ( ( sK1 @ X2 @ X3 )
= $true )
| ( ( sK0 @ X2 @ X3 )
= $false ) ),
inference(iff_proxy_clausification,[],[f7]) ).
thf(f13,plain,
( ( sK0 @ sK2 )
!= ( sK1 @ sK2 ) ),
inference(negative_extensionality,[],[f8]) ).
thf(f14,plain,
( ( sK0 @ sK2 @ sK3 )
!= ( sK1 @ sK2 @ sK3 ) ),
inference(negative_extensionality,[],[f13]) ).
thf(f15,plain,
( ( $true
= ( sK0 @ sK2 @ sK3 ) )
| ( $true
= ( sK1 @ sK2 @ sK3 ) ) ),
inference(xor_proxy_clausification,[],[f14]) ).
thf(f16,plain,
( ( $false
= ( sK0 @ sK2 @ sK3 ) )
| ( $false
= ( sK1 @ sK2 @ sK3 ) ) ),
inference(xor_proxy_clausification,[],[f14]) ).
thf(f18,definition,
( spl4_1
<=> ( $false
= ( sK1 @ sK2 @ sK3 ) ) ),
introduced(definition,[new_symbols(definition,[spl4_1])],[avatar_definition]) ).
thf(f19,plain,
( ( $false
!= ( sK1 @ sK2 @ sK3 ) )
| spl4_1 ),
inference(avatar_component_clause,[],[f18]) ).
thf(f20,plain,
( ( $false
= ( sK1 @ sK2 @ sK3 ) )
| ~ spl4_1 ),
inference(avatar_component_clause,[],[f18]) ).
thf(f22,definition,
( spl4_2
<=> ( $false
= ( sK0 @ sK2 @ sK3 ) ) ),
introduced(definition,[new_symbols(definition,[spl4_2])],[avatar_definition]) ).
thf(f24,plain,
( ( $false
= ( sK0 @ sK2 @ sK3 ) )
| ~ spl4_2 ),
inference(avatar_component_clause,[],[f22]) ).
thf(f25,plain,
( spl4_1
| spl4_2 ),
inference(avatar_split_clause,[],[f16,f22,f18]) ).
thf(f27,definition,
( spl4_3
<=> ( $true
= ( sK1 @ sK2 @ sK3 ) ) ),
introduced(definition,[new_symbols(definition,[spl4_3])],[avatar_definition]) ).
thf(f29,plain,
( ( $true
= ( sK1 @ sK2 @ sK3 ) )
| ~ spl4_3 ),
inference(avatar_component_clause,[],[f27]) ).
thf(f31,definition,
( spl4_4
<=> ( $true
= ( sK0 @ sK2 @ sK3 ) ) ),
introduced(definition,[new_symbols(definition,[spl4_4])],[avatar_definition]) ).
thf(f33,plain,
( ( $true
= ( sK0 @ sK2 @ sK3 ) )
| ~ spl4_4 ),
inference(avatar_component_clause,[],[f31]) ).
thf(f34,plain,
( spl4_3
| spl4_4 ),
inference(avatar_split_clause,[],[f15,f31,f27]) ).
thf(f39,plain,
( ( $false != $false )
| ( $true
= ( sK0 @ sK2 @ sK3 ) )
| spl4_1 ),
inference(constrained_superposition,[],[f19,f11]) ).
thf(f40,plain,
( ( $true
= ( sK0 @ sK2 @ sK3 ) )
| spl4_1 ),
inference(trivial_inequality_removal,[],[f39]) ).
thf(f43,plain,
( spl4_4
| spl4_1 ),
inference(avatar_split_clause,[],[f40,f18,f31]) ).
thf(f45,plain,
( ( $true = $false )
| ~ spl4_2
| ~ spl4_4 ),
inference(constrained_superposition,[],[f33,f24]) ).
thf(f46,plain,
( ( $true = $false )
| ~ spl4_2
| ~ spl4_4 ),
inference(constrained_superposition,[],[f24,f33]) ).
thf(f47,plain,
( $false
| ~ spl4_2
| ~ spl4_4 ),
inference(trivial_inequality_removal,[],[f46]) ).
thf(f48,plain,
( ~ spl4_2
| ~ spl4_4 ),
inference(avatar_contradiction_clause,[],[f47]) ).
thf(f49,plain,
( $false
| ~ spl4_2
| ~ spl4_4 ),
inference(trivial_inequality_removal,[],[f45]) ).
thf(f50,plain,
( ~ spl4_2
| ~ spl4_4 ),
inference(avatar_contradiction_clause,[],[f49]) ).
thf(f51,plain,
( ( $true = $false )
| ~ spl4_1
| ~ spl4_3 ),
inference(constrained_superposition,[],[f20,f29]) ).
thf(f55,plain,
( $false
| ~ spl4_1
| ~ spl4_3 ),
inference(trivial_inequality_removal,[],[f51]) ).
thf(f56,plain,
( ~ spl4_1
| ~ spl4_3 ),
inference(avatar_contradiction_clause,[],[f55]) ).
thf(f63,plain,
( ( $true = $false )
| ( $false
= ( sK0 @ sK2 @ sK3 ) )
| ~ spl4_1 ),
inference(constrained_superposition,[],[f20,f12]) ).
thf(f66,plain,
( ( $false
= ( sK0 @ sK2 @ sK3 ) )
| ~ spl4_1 ),
inference(trivial_inequality_removal,[],[f63]) ).
thf(f70,plain,
( spl4_2
| ~ spl4_1 ),
inference(avatar_split_clause,[],[f66,f18,f22]) ).
cnf(s1,plain,
( spl4_1
| spl4_2 ),
inference(sat_conversion,[],[f25]) ).
cnf(s2,plain,
( spl4_3
| spl4_4 ),
inference(sat_conversion,[],[f34]) ).
cnf(s3,plain,
( spl4_1
| spl4_4 ),
inference(sat_conversion,[],[f43]) ).
cnf(s6,plain,
( ~ spl4_2
| ~ spl4_4 ),
inference(sat_conversion,[],[f48]) ).
cnf(s7,plain,
( ~ spl4_2
| ~ spl4_4 ),
inference(sat_conversion,[],[f50]) ).
cnf(s9,plain,
( ~ spl4_1
| ~ spl4_3 ),
inference(sat_conversion,[],[f56]) ).
cnf(s10,plain,
( ~ spl4_1
| spl4_2 ),
inference(sat_conversion,[],[f70]) ).
cnf(s13,plain,
spl4_1,
inference(rat,[],[s6,s1,s3]) ).
cnf(s14,plain,
spl4_2,
inference(rat,[],[s10,s13]) ).
cnf(s15,plain,
~ spl4_3,
inference(rat,[],[s9,s13]) ).
cnf(s16,plain,
~ spl4_4,
inference(rat,[],[s7,s14]) ).
cnf(s17,plain,
$false,
inference(rat,[],[s2,s16,s15]) ).
thf(f72,plain,
$false,
inference(avatar_sat_refutation,[],[s17]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYO217^5 : TPTP v9.3.1. Released v4.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.08/0.19 % Computer : n004.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 : Tue Sep 29 16:39:37 UTC 2026
% 0.08/0.19 % CPUTime :
% 0.08/0.19 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.08/0.22 Running first-order model finding
% 0.08/0.22 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
% 0.19/0.26 % (1530712)Will run a generic schedule for satisfiability detection.
% 0.19/0.26 % (1530723)ott-3_16_to=lpo:sil=16000:sp=arity:fd=off:rp=on:random_seed=4223138333:i=159:bs=unit_only:nicw=on:fsr=off:amm=off_2999 on theBenchmark for (2999ds/159Mi)
% 0.19/0.26 % (1530723) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-1530712-1530723"...
% 0.19/0.26 % (1530723)...printing done.
% 0.19/0.26 % (1530723)Refutation found. Thanks to Tanya!
% 0.19/0.26 % SZS status Theorem for theBenchmark
% 0.19/0.26 % SZS output start Proof for theBenchmark
% See solution above
% 0.19/0.26 % (1530723)------------------------------
% 0.19/0.26 % (1530723)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.19/0.26 % (1530723)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.19/0.26 % (1530723)CaDiCaL version: 2.1.3
% 0.19/0.26 % (1530723)Termination reason: Refutation
% 0.19/0.26 % (1530723)Time elapsed: 0.002 s
% 0.19/0.26 % (1530723)Peak memory usage: 13 MB
% 0.19/0.26 % (1530723)Instructions burned: 3 (million)
% 0.19/0.26 % (1530712)Success in time 0.035 s
% 0.19/0.26 % Vampire exiting
%------------------------------------------------------------------------------