%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SET027+3 : TPTP v9.3.1. Released v2.2.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n020.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 12:42:42 PM UTC 2026
% Result : Theorem 0.12s 0.46s
% Output : Refutation 0.12s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 2
% Syntax : Number of formulae : 19 ( 5 unt; 0 def)
% Number of atoms : 45 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 43 ( 17 ~; 15 |; 6 &)
% ( 2 <=>; 3 =>; 0 <=; 0 <~>)
% Maximal formula depth : 8 ( 5 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 3 ( 2 usr; 1 prp; 0-2 aty)
% Number of functors : 4 ( 4 usr; 3 con; 0-2 aty)
% Number of variables : 38 ( 32 !; 6 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0,X1] :
( subset(X0,X1)
<=> ! [X2] :
( member(X2,X0)
=> member(X2,X1) ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',subset_defn) ).
fof(f3,conjecture,
! [X0,X1,X2] :
( ( subset(X0,X1)
& subset(X1,X2) )
=> subset(X0,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_transitivity_of_subset) ).
fof(f4,negated_conjecture,
~ ! [X0,X1,X2] :
( ( subset(X0,X1)
& subset(X1,X2) )
=> subset(X0,X2) ),
inference(negated_conjecture,[status(cth)],[f3]) ).
fof(f5,plain,
! [X0,X1] :
( subset(X0,X1)
<=> ! [X2] :
( member(X2,X1)
| ~ member(X2,X0) ) ),
inference(ennf_transformation,[],[f1]) ).
fof(f6,plain,
? [X0,X1,X2] :
( ~ subset(X0,X2)
& subset(X0,X1)
& subset(X1,X2) ),
inference(ennf_transformation,[],[f4]) ).
fof(f7,plain,
? [X0,X1,X2] :
( ~ subset(X0,X2)
& subset(X0,X1)
& subset(X1,X2) ),
inference(flattening,[],[f6]) ).
fof(f8,plain,
! [X2,X0,X1] :
( ~ member(X2,X0)
| member(X2,X1)
| ~ subset(X0,X1) ),
inference(cnf_transformation,[],[f5]) ).
fof(f9,plain,
! [X0,X1] :
( member(sK0(X0,X1),X0)
| subset(X0,X1) ),
inference(cnf_transformation,[],[f5]) ).
fof(f10,plain,
! [X0,X1] :
( ~ member(sK0(X0,X1),X1)
| subset(X0,X1) ),
inference(cnf_transformation,[],[f5]) ).
fof(f12,plain,
subset(sK2,sK3),
inference(cnf_transformation,[],[f7]) ).
fof(f13,plain,
subset(sK1,sK2),
inference(cnf_transformation,[],[f7]) ).
fof(f14,plain,
~ subset(sK1,sK3),
inference(cnf_transformation,[],[f7]) ).
fof(f17,plain,
! [X2,X0,X1] :
( member(sK0(X0,X1),X2)
| ~ subset(X0,X2)
| subset(X0,X1) ),
inference(resolution,[],[f8,f9]) ).
fof(f19,plain,
! [X2,X0,X1] :
( ~ member(sK0(X0,X1),X2)
| ~ subset(X2,X1)
| subset(X0,X1) ),
inference(resolution,[],[f8,f10]) ).
fof(f25,plain,
! [X2,X0,X1] :
( ~ subset(X0,X1)
| subset(X2,X1)
| ~ subset(X2,X0)
| subset(X2,X1) ),
inference(resolution,[],[f19,f17]) ).
fof(f27,plain,
! [X2,X0,X1] :
( ~ subset(X0,X1)
| subset(X2,X1)
| ~ subset(X2,X0) ),
inference(duplicate_literal_removal,[],[f25]) ).
fof(f37,plain,
! [X0] :
( subset(X0,sK3)
| ~ subset(X0,sK2) ),
inference(resolution,[],[f27,f12]) ).
fof(f52,plain,
~ subset(sK1,sK2),
inference(resolution,[],[f37,f14]) ).
fof(f55,plain,
$false,
inference(forward_subsumption_resolution,[],[f52,f13]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SET027+3 : TPTP v9.3.1. Released v2.2.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.12/0.38 % Computer : n020.cluster.edu
% 0.12/0.38 % Model : x86_64 x86_64
% 0.12/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.38 % Memory : 8046.5625MB
% 0.12/0.38 % OS : Linux 6.8.0-71-generic
% 0.12/0.38 % CPULimit : 300
% 0.12/0.38 % WCLimit : 300
% 0.12/0.38 % DateTime : Mon Sep 28 00:14:35 UTC 2026
% 0.12/0.39 % CPUTime :
% 0.12/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.12/0.42 Running first-order model finding
% 0.12/0.42 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
% 0.12/0.46 % (3907697)Will run a generic schedule for satisfiability detection.
% 0.12/0.46 % (3907706)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=1789994104:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.12/0.46 % (3907706) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-3907697-3907706"...
% 0.12/0.46 % (3907706)...printing done.
% 0.12/0.46 % (3907703)% WARNING: option uhcvi not known.
% 0.12/0.46 % (3907706)Refutation found. Thanks to Tanya!
% 0.12/0.46 % SZS status Theorem for theBenchmark
% 0.12/0.46 % SZS output start Proof for theBenchmark
% See solution above
% 0.12/0.46 % (3907706)------------------------------
% 0.12/0.46 % (3907706)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.12/0.46 % (3907706)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.12/0.46 % (3907706)CaDiCaL version: 2.1.3
% 0.12/0.46 % (3907706)Termination reason: Refutation
% 0.12/0.46 % (3907706)Time elapsed: 0.001 s
% 0.12/0.46 % (3907706)Peak memory usage: 11 MB
% 0.12/0.46 % (3907706)Instructions burned: 2 (million)
% 0.12/0.46 % (3907697)Success in time 0.026 s
% 0.12/0.46 % Vampire exiting
%------------------------------------------------------------------------------