%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SEU125+2 : 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 : n018.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 12:52:00 PM UTC 2026
% Result : Theorem 0.17s 0.49s
% Output : Refutation 0.17s
% 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(f6,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(f7,axiom,
! [X0,X1] :
( subset(X0,X1)
<=> ! [X2] :
( in(X2,X0)
=> in(X2,X1) ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',d3_tarski) ).
fof(f32,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(f33,negated_conjecture,
~ ! [X0,X1,X2] :
( ( subset(X0,X1)
& subset(X2,X1) )
=> subset(set_union2(X0,X2),X1) ),
inference(negated_conjecture,[status(cth)],[f32]) ).
fof(f40,plain,
! [X0,X1] :
( subset(X0,X1)
<=> ! [X2] :
( in(X2,X1)
| ~ in(X2,X0) ) ),
inference(ennf_transformation,[],[f7]) ).
fof(f52,plain,
? [X0,X1,X2] :
( ~ subset(set_union2(X0,X2),X1)
& subset(X0,X1)
& subset(X2,X1) ),
inference(ennf_transformation,[],[f33]) ).
fof(f53,plain,
? [X0,X1,X2] :
( ~ subset(set_union2(X0,X2),X1)
& subset(X0,X1)
& subset(X2,X1) ),
inference(flattening,[],[f52]) ).
fof(f65,plain,
! [X2,X3,X0,X1] :
( in(X3,X1)
| in(X3,X0)
| ~ in(X3,X2)
| set_union2(X0,X1) != X2 ),
inference(cnf_transformation,[],[f6]) ).
fof(f68,plain,
! [X2,X0,X1] :
( ~ subset(X0,X1)
| in(X2,X1)
| ~ in(X2,X0) ),
inference(cnf_transformation,[],[f40]) ).
fof(f69,plain,
! [X0,X1] :
( subset(X0,X1)
| in(sK2(X0,X1),X0) ),
inference(cnf_transformation,[],[f40]) ).
fof(f70,plain,
! [X0,X1] :
( subset(X0,X1)
| ~ in(sK2(X0,X1),X1) ),
inference(cnf_transformation,[],[f40]) ).
fof(f101,plain,
subset(sK10,sK9),
inference(cnf_transformation,[],[f53]) ).
fof(f102,plain,
subset(sK8,sK9),
inference(cnf_transformation,[],[f53]) ).
fof(f103,plain,
~ subset(set_union2(sK8,sK10),sK9),
inference(cnf_transformation,[],[f53]) ).
fof(f109,plain,
! [X3,X0,X1] :
( ~ in(X3,set_union2(X0,X1))
| in(X3,X0)
| in(X3,X1) ),
inference(equality_resolution,[],[f65]) ).
fof(f165,plain,
in(sK2(set_union2(sK8,sK10),sK9),set_union2(sK8,sK10)),
inference(resolution,[],[f69,f103]) ).
fof(f169,plain,
~ in(sK2(set_union2(sK8,sK10),sK9),sK9),
inference(resolution,[],[f70,f103]) ).
fof(f283,plain,
! [X0] :
( ~ in(X0,sK10)
| in(X0,sK9) ),
inference(resolution,[],[f68,f101]) ).
fof(f284,plain,
! [X0] :
( ~ in(X0,sK8)
| in(X0,sK9) ),
inference(resolution,[],[f68,f102]) ).
fof(f293,plain,
( in(sK2(set_union2(sK8,sK10),sK9),sK8)
| in(sK2(set_union2(sK8,sK10),sK9),sK10) ),
inference(resolution,[],[f109,f165]) ).
fof(f303,definition,
( spl11_5
<=> in(sK2(set_union2(sK8,sK10),sK9),sK10) ),
introduced(definition,[new_symbols(definition,[spl11_5])],[avatar_definition]) ).
fof(f305,plain,
( in(sK2(set_union2(sK8,sK10),sK9),sK10)
| ~ spl11_5 ),
inference(avatar_component_clause,[],[f303]) ).
fof(f307,definition,
( spl11_6
<=> in(sK2(set_union2(sK8,sK10),sK9),sK8) ),
introduced(definition,[new_symbols(definition,[spl11_6])],[avatar_definition]) ).
fof(f309,plain,
( in(sK2(set_union2(sK8,sK10),sK9),sK8)
| ~ spl11_6 ),
inference(avatar_component_clause,[],[f307]) ).
fof(f310,plain,
( spl11_5
| spl11_6 ),
inference(avatar_split_clause,[],[f293,f307,f303]) ).
fof(f920,plain,
( in(sK2(set_union2(sK8,sK10),sK9),sK9)
| ~ spl11_5 ),
inference(resolution,[],[f305,f283]) ).
fof(f923,plain,
( $false
| ~ spl11_5 ),
inference(forward_subsumption_resolution,[],[f920,f169]) ).
fof(f924,plain,
~ spl11_5,
inference(avatar_contradiction_clause,[],[f923]) ).
fof(f1019,plain,
( in(sK2(set_union2(sK8,sK10),sK9),sK9)
| ~ spl11_6 ),
inference(resolution,[],[f309,f284]) ).
fof(f1022,plain,
( $false
| ~ spl11_6 ),
inference(forward_subsumption_resolution,[],[f1019,f169]) ).
fof(f1023,plain,
~ spl11_6,
inference(avatar_contradiction_clause,[],[f1022]) ).
cnf(s5,plain,
( spl11_5
| spl11_6 ),
inference(sat_conversion,[],[f310]) ).
cnf(s16,plain,
~ spl11_5,
inference(sat_conversion,[],[f924]) ).
cnf(s17,plain,
~ spl11_6,
inference(sat_conversion,[],[f1023]) ).
cnf(s21,plain,
$false,
inference(rat,[],[s5,s17,s16]) ).
fof(f1024,plain,
$false,
inference(avatar_sat_refutation,[],[s21]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SEU125+2 : 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 : n018.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 03:40:54 UTC 2026
% 0.11/0.38 % CPUTime :
% 0.11/0.38 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.11/0.41 Running first-order model finding
% 0.11/0.41 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
% 0.17/0.49 % (2972652)Will run a generic schedule for satisfiability detection.
% 0.17/0.49 % (2972659)dis+10_161_sil=256000:plsq=on:plsqr=61199697,1048576:gs=on:alpa=true:sac=on:slsq=on:cn=on:random_seed=2935599360:i=88024:add=on:rawr=on_2999 on theBenchmark for (2999ds/88024Mi)
% 0.17/0.49 % (2972658)% WARNING: option uhcvi not known.
% 0.17/0.49 % (2972657)fmb+10_1_sas=cadical:bce=on:rp=on:random_seed=3154039214_2999 on theBenchmark for (2999ds/0Mi)
% 0.17/0.49 % (2972661)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=2175393690:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.17/0.49 % (2972658)dis+11_61:31_drc=ordering:lsd=5:bsr=unit_only:rp=on:newcnf=on:random_seed=4181268051:i=135531:add=off:rawr=on_2999 on theBenchmark for (2999ds/135531Mi)
% 0.17/0.49 % (2972660)dis+10_1_sil=32000:sp=arity:random_seed=151925940:i=103:fgj=on_2999 on theBenchmark for (2999ds/103Mi)
% 0.17/0.49 % (2972662)ott+1_1_to=lpo:sil=16000:sp=reverse_arity:erd=off:random_seed=1912864111:i=131_2999 on theBenchmark for (2999ds/131Mi)
% 0.17/0.49 % (2972663)ott-3_16_to=lpo:sil=16000:sp=arity:fd=off:rp=on:random_seed=3781865539:i=159:bs=unit_only:nicw=on:fsr=off:amm=off_2999 on theBenchmark for (2999ds/159Mi)
% 0.17/0.49 % TRYING [1]
% 0.17/0.49 % TRYING [2]
% 0.17/0.49 % TRYING [3]
% 0.17/0.49 % TRYING [4]
% 0.17/0.49 % (2972661) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-2972652-2972661"...
% 0.17/0.49 % (2972661)...printing done.
% 0.17/0.49 % TRYING [5]
% 0.17/0.49 % (2972661)Refutation found. Thanks to Tanya!
% 0.17/0.49 % SZS status Theorem for theBenchmark
% 0.17/0.49 % SZS output start Proof for theBenchmark
% See solution above
% 0.17/0.49 % (2972661)------------------------------
% 0.17/0.49 % (2972661)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.17/0.49 % (2972661)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.17/0.49 % (2972661)CaDiCaL version: 2.1.3
% 0.17/0.49 % (2972661)Termination reason: Refutation
% 0.17/0.49 % (2972661)Time elapsed: 0.027 s
% 0.17/0.49 % (2972661)Peak memory usage: 13 MB
% 0.17/0.49 % (2972661)Instructions burned: 39 (million)
% 0.17/0.49 % (2972652)Success in time 0.063 s
% 0.17/0.49 % Vampire exiting
%------------------------------------------------------------------------------