%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : NUM533+2 : TPTP v9.3.1. Released v4.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n002.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 12:24:42 PM UTC 2026
% Result : Theorem 0.10s 0.45s
% Output : Refutation 0.10s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 1
% Syntax : Number of formulae : 12 ( 5 unt; 0 def)
% Number of atoms : 54 ( 0 equ)
% Maximal formula atoms : 9 ( 4 avg)
% Number of connectives : 57 ( 15 ~; 9 |; 21 &)
% ( 0 <=>; 12 =>; 0 <=; 0 <~>)
% Maximal formula depth : 9 ( 5 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 3 ( 2 usr; 1 prp; 0-2 aty)
% Number of functors : 4 ( 4 usr; 4 con; 0-0 aty)
% Number of variables : 17 ( 15 !; 2 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f15,conjecture,
( ( ! [X0] :
( aElementOf0(X0,xA)
=> aElementOf0(X0,xB) )
& aSubsetOf0(xA,xB)
& ! [X0] :
( aElementOf0(X0,xB)
=> aElementOf0(X0,xC) )
& aSubsetOf0(xB,xC) )
=> ( ! [X0] :
( aElementOf0(X0,xA)
=> aElementOf0(X0,xC) )
| aSubsetOf0(xA,xC) ) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',m__) ).
fof(f16,negated_conjecture,
~ ( ( ! [X0] :
( aElementOf0(X0,xA)
=> aElementOf0(X0,xB) )
& aSubsetOf0(xA,xB)
& ! [X0] :
( aElementOf0(X0,xB)
=> aElementOf0(X0,xC) )
& aSubsetOf0(xB,xC) )
=> ( ! [X0] :
( aElementOf0(X0,xA)
=> aElementOf0(X0,xC) )
| aSubsetOf0(xA,xC) ) ),
inference(negated_conjecture,[status(cth)],[f15]) ).
fof(f17,plain,
~ ( ( ! [X0] :
( aElementOf0(X0,xA)
=> aElementOf0(X0,xB) )
& aSubsetOf0(xA,xB)
& ! [X1] :
( aElementOf0(X1,xB)
=> aElementOf0(X1,xC) )
& aSubsetOf0(xB,xC) )
=> ( ! [X2] :
( aElementOf0(X2,xA)
=> aElementOf0(X2,xC) )
| aSubsetOf0(xA,xC) ) ),
inference(rectify,[],[f16]) ).
fof(f33,plain,
( ? [X2] :
( ~ aElementOf0(X2,xC)
& aElementOf0(X2,xA) )
& ~ aSubsetOf0(xA,xC)
& ! [X0] :
( aElementOf0(X0,xB)
| ~ aElementOf0(X0,xA) )
& aSubsetOf0(xA,xB)
& ! [X1] :
( aElementOf0(X1,xC)
| ~ aElementOf0(X1,xB) )
& aSubsetOf0(xB,xC) ),
inference(ennf_transformation,[],[f17]) ).
fof(f34,plain,
( ? [X2] :
( ~ aElementOf0(X2,xC)
& aElementOf0(X2,xA) )
& ~ aSubsetOf0(xA,xC)
& ! [X0] :
( aElementOf0(X0,xB)
| ~ aElementOf0(X0,xA) )
& aSubsetOf0(xA,xB)
& ! [X1] :
( aElementOf0(X1,xC)
| ~ aElementOf0(X1,xB) )
& aSubsetOf0(xB,xC) ),
inference(flattening,[],[f33]) ).
fof(f50,plain,
aElementOf0(sK2,xA),
inference(cnf_transformation,[],[f34]) ).
fof(f51,plain,
~ aElementOf0(sK2,xC),
inference(cnf_transformation,[],[f34]) ).
fof(f52,plain,
! [X0] :
( aElementOf0(X0,xB)
| ~ aElementOf0(X0,xA) ),
inference(cnf_transformation,[],[f34]) ).
fof(f53,plain,
! [X1] :
( aElementOf0(X1,xC)
| ~ aElementOf0(X1,xB) ),
inference(cnf_transformation,[],[f34]) ).
fof(f59,plain,
~ aElementOf0(sK2,xB),
inference(resolution,[],[f53,f51]) ).
fof(f60,plain,
~ aElementOf0(sK2,xA),
inference(resolution,[],[f59,f52]) ).
fof(f61,plain,
$false,
inference(forward_subsumption_resolution,[],[f60,f50]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : NUM533+2 : TPTP v9.3.1. Released v4.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.10/0.38 % Computer : n002.cluster.edu
% 0.10/0.38 % Model : x86_64 x86_64
% 0.10/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.38 % Memory : 8046.5625MB
% 0.10/0.38 % OS : Linux 6.8.0-71-generic
% 0.10/0.38 % CPULimit : 300
% 0.10/0.38 % WCLimit : 300
% 0.10/0.38 % DateTime : Sun Sep 27 20:25:07 UTC 2026
% 0.10/0.38 % CPUTime :
% 0.10/0.38 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.10/0.40 Running first-order model finding
% 0.10/0.40 Running: /export/starexec/sandbox2/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.10/0.45 % (3851637)Will run a generic schedule for satisfiability detection.
% 0.10/0.45 % (3851646)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=1070357741:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.10/0.45 % (3851646) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-3851637-3851646"...
% 0.10/0.45 % (3851646)...printing done.
% 0.10/0.45 % (3851646)Refutation found. Thanks to Tanya!
% 0.10/0.45 % SZS status Theorem for theBenchmark
% 0.10/0.45 % SZS output start Proof for theBenchmark
% See solution above
% 0.10/0.45 % (3851646)------------------------------
% 0.10/0.45 % (3851646)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.10/0.45 % (3851646)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.10/0.45 % (3851646)CaDiCaL version: 2.1.3
% 0.10/0.45 % (3851646)Termination reason: Refutation
% 0.10/0.45 % (3851646)Time elapsed: 0.001 s
% 0.10/0.45 % (3851646)Peak memory usage: 11 MB
% 0.10/0.45 % (3851646)Instructions burned: 1 (million)
% 0.10/0.45 % (3851637)Success in time 0.032 s
% 0.10/0.45 % Vampire exiting
%------------------------------------------------------------------------------