%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SET583+3 : TPTP v9.3.1. Released v2.2.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 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 12:41:13 PM UTC 2026
% Result : Theorem 3.52s 1.47s
% Output : Refutation 3.52s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 2
% Syntax : Number of formulae : 15 ( 5 unt; 0 def)
% Number of atoms : 40 ( 14 equ)
% Maximal formula atoms : 6 ( 2 avg)
% Number of connectives : 39 ( 14 ~; 9 |; 13 &)
% ( 1 <=>; 2 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 4 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 3 ( 1 usr; 1 prp; 0-2 aty)
% Number of functors : 2 ( 2 usr; 2 con; 0-0 aty)
% Number of variables : 16 ( 12 !; 4 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0,X1] :
( X0 = X1
<=> ( subset(X0,X1)
& subset(X1,X0) ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',equal_defn) ).
fof(f4,conjecture,
! [X0,X1] :
( ( subset(X0,X1)
& subset(X1,X0) )
=> X0 = X1 ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_extensionality) ).
fof(f5,negated_conjecture,
~ ! [X0,X1] :
( ( subset(X0,X1)
& subset(X1,X0) )
=> X0 = X1 ),
inference(negated_conjecture,[status(cth)],[f4]) ).
fof(f6,plain,
? [X0,X1] :
( X0 != X1
& subset(X0,X1)
& subset(X1,X0) ),
inference(ennf_transformation,[],[f5]) ).
fof(f7,plain,
? [X0,X1] :
( X0 != X1
& subset(X0,X1)
& subset(X1,X0) ),
inference(flattening,[],[f6]) ).
fof(f8,plain,
( sK0 != sK1
& subset(sK0,sK1)
& subset(sK1,sK0) ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK0,sK1]),skolemize(X0,sK0),skolemize(X1,sK1)],[f7]) ).
fof(f9,plain,
! [X0,X1] :
( ( X0 = X1
| ~ subset(X0,X1)
| ~ subset(X1,X0) )
& ( ( subset(X0,X1)
& subset(X1,X0) )
| X0 != X1 ) ),
inference(nnf_transformation,[],[f1]) ).
fof(f10,plain,
! [X0,X1] :
( ( X0 = X1
| ~ subset(X0,X1)
| ~ subset(X1,X0) )
& ( ( subset(X0,X1)
& subset(X1,X0) )
| X0 != X1 ) ),
inference(flattening,[],[f9]) ).
fof(f11,plain,
subset(sK1,sK0),
inference(cnf_transformation,[],[f8]) ).
fof(f12,plain,
subset(sK0,sK1),
inference(cnf_transformation,[],[f8]) ).
fof(f13,plain,
sK0 != sK1,
inference(cnf_transformation,[],[f8]) ).
fof(f16,plain,
! [X0,X1] :
( ~ subset(X1,X0)
| ~ subset(X0,X1)
| X0 = X1 ),
inference(cnf_transformation,[],[f10]) ).
fof(f21,plain,
( ~ subset(sK1,sK0)
| sK0 = sK1 ),
inference(resolution,[],[f16,f12]) ).
fof(f24,plain,
sK0 = sK1,
inference(forward_subsumption_resolution,[],[f21,f11]) ).
fof(f26,plain,
$false,
inference(forward_subsumption_resolution,[],[f24,f13]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : SET583+3 : TPTP v9.3.1. Released v2.2.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 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 02:14:57 UTC 2026
% 0.11/0.39 % CPUTime :
% 0.11/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.11/0.42 Running first-order theorem proving
% 0.11/0.42 Running: /export/starexec/sandbox/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 3.52/1.47 % (1122584)Detected formulas, will run a generic FOF schedule.
% 3.52/1.47 % (1122590)lrs+11_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:lma=off:spb=units:urr=ec_only:bce=on:s2agt=64:updr=off:random_seed=2113702377:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.52/1.47 % (1122593)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=1336480801:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.52/1.47 % (1122595)dis-21_1_sil=8000:lcm=predicate:random_seed=2031075100:st=5:avsq=on:i=129:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/129Mi)
% 3.52/1.47 % (1122592)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=3602431115:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.52/1.47 % (1122591)lrs+1010_1_anc=all:sfv=off:to=kbo:ncem=casc2026/models/loop7.pt:sil=128000:npcc=on:prc=on:sos=all:bsr=unit_only:sac=on:random_seed=2837019219:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.52/1.47 % (1122589)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=full:npcc=on:drc=off:sp=weighted_frequency:spb=goal:fd=preordered:foolp=on:random_seed=233970995:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.52/1.47 % (1122594)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3913149104:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.52/1.47 % (1122592)Also succeeded, but the first one will report.
% 3.52/1.47 % (1122593)First to succeed.
% 3.52/1.47 % (1122594)Also succeeded, but the first one will report.
% 3.52/1.47 % (1122595)Also succeeded, but the first one will report.
% 3.52/1.47 % (1122593)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-1122584"
% 3.52/1.47 % (1122593)Refutation found. Thanks to Tanya!
% 3.52/1.47 % SZS status Theorem for theBenchmark
% 3.52/1.47 % SZS output start Proof for theBenchmark
% See solution above
% 3.52/1.47 % (1122593)------------------------------
% 3.52/1.47 % (1122593)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.52/1.47 % (1122593)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.52/1.47 % (1122593)CaDiCaL version: 2.1.3
% 3.52/1.47 % (1122593)Termination reason: Refutation
% 3.52/1.47 % (1122593)Time elapsed: 0.002 s
% 3.52/1.47 % (1122593)Peak memory usage: 88 MB
% 3.52/1.47 % (1122593)------------------------------
% 3.52/1.47 % (1122593)------------------------------
% 3.52/1.47 % (1122584)Success in time 0.414 s
% 3.52/1.47 % Vampire exiting
%------------------------------------------------------------------------------