%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SEU125+1 : TPTP v9.3.1. Released v3.3.0.
% 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 12:51:59 PM UTC 2026
% Result : Theorem 0.18s 0.47s
% Output : Refutation 0.18s
% Verified :
% SZS Type : Refutation
% Derivation depth : 11
% Number of leaves : 5
% Syntax : Number of formulae : 36 ( 11 unt; 2 def)
% Number of atoms : 73 ( 2 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 61 ( 24 ~; 22 |; 6 &)
% ( 6 <=>; 3 =>; 0 <=; 0 <~>)
% Maximal formula depth : 8 ( 4 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of predicates : 6 ( 4 usr; 3 prp; 0-2 aty)
% Number of functors : 5 ( 5 usr; 3 con; 0-2 aty)
% Number of variables : 38 ( 0 sgn 32 !; 6 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f3,axiom,
! [X0,X1,X2] :
( X2 = set_union2(X0,X1)
<=> ! [X3] :
( in(X3,X2)
<=> ( in(X3,X0)
| in(X3,X1) ) ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',d2_xboole_0) ).
fof(f4,axiom,
! [X0,X1] :
( subset(X0,X1)
<=> ! [X2] :
( in(X2,X0)
=> in(X2,X1) ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',d3_tarski) ).
fof(f18,conjecture,
! [X0,X1,X2] :
( ( subset(X0,X1)
& subset(X2,X1) )
=> subset(set_union2(X0,X2),X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t8_xboole_1) ).
fof(f19,negated_conjecture,
~ ! [X0,X1,X2] :
( ( subset(X0,X1)
& subset(X2,X1) )
=> subset(set_union2(X0,X2),X1) ),
inference(negated_conjecture,[status(cth)],[f18]) ).
fof(f23,plain,
! [X0,X1] :
( subset(X0,X1)
<=> ! [X2] :
( in(X2,X1)
| ~ in(X2,X0) ) ),
inference(ennf_transformation,[],[f4]) ).
fof(f29,plain,
? [X0,X1,X2] :
( ~ subset(set_union2(X0,X2),X1)
& subset(X0,X1)
& subset(X2,X1) ),
inference(ennf_transformation,[],[f19]) ).
fof(f30,plain,
? [X0,X1,X2] :
( ~ subset(set_union2(X0,X2),X1)
& subset(X0,X1)
& subset(X2,X1) ),
inference(flattening,[],[f29]) ).
fof(f36,plain,
! [X2,X3,X0,X1] :
( in(X3,X1)
| in(X3,X0)
| ~ in(X3,X2)
| set_union2(X0,X1) != X2 ),
inference(cnf_transformation,[],[f3]) ).
fof(f39,plain,
! [X2,X0,X1] :
( ~ subset(X0,X1)
| in(X2,X1)
| ~ in(X2,X0) ),
inference(cnf_transformation,[],[f23]) ).
fof(f40,plain,
! [X0,X1] :
( subset(X0,X1)
| in(sK1(X0,X1),X0) ),
inference(cnf_transformation,[],[f23]) ).
fof(f41,plain,
! [X0,X1] :
( subset(X0,X1)
| ~ in(sK1(X0,X1),X1) ),
inference(cnf_transformation,[],[f23]) ).
fof(f53,plain,
subset(sK6,sK5),
inference(cnf_transformation,[],[f30]) ).
fof(f54,plain,
subset(sK4,sK5),
inference(cnf_transformation,[],[f30]) ).
fof(f55,plain,
~ subset(set_union2(sK4,sK6),sK5),
inference(cnf_transformation,[],[f30]) ).
fof(f58,plain,
! [X3,X0,X1] :
( ~ in(X3,set_union2(X0,X1))
| in(X3,X0)
| in(X3,X1) ),
inference(equality_resolution,[],[f36]) ).
fof(f89,plain,
in(sK1(set_union2(sK4,sK6),sK5),set_union2(sK4,sK6)),
inference(resolution,[],[f40,f55]) ).
fof(f92,plain,
~ in(sK1(set_union2(sK4,sK6),sK5),sK5),
inference(resolution,[],[f41,f55]) ).
fof(f114,plain,
! [X0] :
( ~ in(X0,sK6)
| in(X0,sK5) ),
inference(resolution,[],[f39,f53]) ).
fof(f115,plain,
! [X0] :
( ~ in(X0,sK4)
| in(X0,sK5) ),
inference(resolution,[],[f39,f54]) ).
fof(f119,plain,
( in(sK1(set_union2(sK4,sK6),sK5),sK4)
| in(sK1(set_union2(sK4,sK6),sK5),sK6) ),
inference(resolution,[],[f58,f89]) ).
fof(f129,definition,
( spl7_1
<=> in(sK1(set_union2(sK4,sK6),sK5),sK6) ),
introduced(definition,[new_symbols(definition,[spl7_1])],[avatar_definition]) ).
fof(f131,plain,
( in(sK1(set_union2(sK4,sK6),sK5),sK6)
| ~ spl7_1 ),
inference(avatar_component_clause,[],[f129]) ).
fof(f133,definition,
( spl7_2
<=> in(sK1(set_union2(sK4,sK6),sK5),sK4) ),
introduced(definition,[new_symbols(definition,[spl7_2])],[avatar_definition]) ).
fof(f135,plain,
( in(sK1(set_union2(sK4,sK6),sK5),sK4)
| ~ spl7_2 ),
inference(avatar_component_clause,[],[f133]) ).
fof(f136,plain,
( spl7_1
| spl7_2 ),
inference(avatar_split_clause,[],[f119,f133,f129]) ).
fof(f141,plain,
( in(sK1(set_union2(sK4,sK6),sK5),sK5)
| ~ spl7_2 ),
inference(resolution,[],[f135,f115]) ).
fof(f144,plain,
( $false
| ~ spl7_2 ),
inference(forward_subsumption_resolution,[],[f141,f92]) ).
fof(f145,plain,
~ spl7_2,
inference(avatar_contradiction_clause,[],[f144]) ).
fof(f150,plain,
( in(sK1(set_union2(sK4,sK6),sK5),sK5)
| ~ spl7_1 ),
inference(resolution,[],[f131,f114]) ).
fof(f153,plain,
( $false
| ~ spl7_1 ),
inference(forward_subsumption_resolution,[],[f150,f92]) ).
fof(f154,plain,
~ spl7_1,
inference(avatar_contradiction_clause,[],[f153]) ).
cnf(s1,plain,
( spl7_1
| spl7_2 ),
inference(sat_conversion,[],[f136]) ).
cnf(s2,plain,
~ spl7_2,
inference(sat_conversion,[],[f145]) ).
cnf(s3,plain,
~ spl7_1,
inference(sat_conversion,[],[f154]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s2,s3]) ).
fof(f155,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : SEU125+1 : TPTP v9.3.1. Released v3.3.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.11/0.38 % Computer : n003.cluster.edu
% 0.11/0.38 % Model : x86_64 x86_64
% 0.11/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.38 % Memory : 8046.5625MB
% 0.11/0.38 % OS : Linux 6.8.0-71-generic
% 0.11/0.38 % CPULimit : 300
% 0.11/0.38 % WCLimit : 300
% 0.11/0.38 % DateTime : Mon Sep 28 03:40:27 UTC 2026
% 0.11/0.39 % CPUTime :
% 0.11/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.11/0.42 Running first-order model finding
% 0.11/0.42 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
% 0.18/0.47 % (1160887)Will run a generic schedule for satisfiability detection.
% 0.18/0.47 % (1160901)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=380794178:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.18/0.47 % (1160901) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-1160887-1160901"...
% 0.18/0.47 % (1160901)...printing done.
% 0.18/0.47 % (1160898)% WARNING: option uhcvi not known.
% 0.18/0.47 % (1160901)Refutation found. Thanks to Tanya!
% 0.18/0.47 % SZS status Theorem for theBenchmark
% 0.18/0.47 % SZS output start Proof for theBenchmark
% See solution above
% 0.18/0.47 % (1160901)------------------------------
% 0.18/0.47 % (1160901)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.18/0.47 % (1160901)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.18/0.47 % (1160901)CaDiCaL version: 2.1.3
% 0.18/0.47 % (1160901)Termination reason: Refutation
% 0.18/0.47 % (1160901)Time elapsed: 0.003 s
% 0.18/0.47 % (1160901)Peak memory usage: 12 MB
% 0.18/0.47 % (1160901)Instructions burned: 5 (million)
% 0.18/0.47 % (1160887)Success in time 0.036 s
% 0.18/0.47 % Vampire exiting
%------------------------------------------------------------------------------