%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SEV051^5 : TPTP v9.3.1. Released v4.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n001.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 : Wed Sep 30 08:38:55 AM UTC 2026
% Result : Theorem 0.26s 0.35s
% Output : Refutation 0.26s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 1
% Syntax : Number of formulae : 14 ( 5 unt; 0 typ; 0 def)
% Number of atoms : 35 ( 34 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 34 ( 13 ~; 6 |; 12 &)
% ( 0 <=>; 3 =>; 0 <=; 0 <~>)
% Maximal formula depth : 8 ( 4 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of types : 1 ( 1 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 2 ( 0 usr; 1 prp; 0-2 aty)
% Number of functors : 4 ( 4 usr; 4 con; 0-0 aty)
% Number of variables : 20 ( 12 !; 8 ?; 20 :)
% Comments :
%------------------------------------------------------------------------------
tff(type_def_5,type,
a: $tType ).
tff(func_def_0,type,
sK0: a ).
tff(func_def_1,type,
sK1: a ).
tff(func_def_2,type,
sK2: a ).
tff(func_def_3,type,
sK3: a ).
tff(f1,conjecture,
( ! [X1: a,X2: a,X3: a] :
( ( ( X2 = X3 )
& ( X1 = X3 ) )
=> ( X1 = X2 ) )
& ! [X0: a] : ( X0 = X0 ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',cTHM557_pme) ).
tff(f2,negated_conjecture,
~ ( ! [X1: a,X2: a,X3: a] :
( ( ( X2 = X3 )
& ( X1 = X3 ) )
=> ( X1 = X2 ) )
& ! [X0: a] : ( X0 = X0 ) ),
inference(negated_conjecture,[status(cth)],[f1]) ).
tff(f3,plain,
~ ( ! [X0: a,X1: a,X2: a] :
( ( ( X1 = X2 )
& ( X0 = X2 ) )
=> ( X0 = X1 ) )
& ! [X3: a] : ( X3 = X3 ) ),
inference(rectify,[],[f2]) ).
tff(f4,plain,
( ? [X0: a,X1: a,X2: a] :
( ( X0 != X1 )
& ( X1 = X2 )
& ( X0 = X2 ) )
| ? [X3: a] : ( X3 != X3 ) ),
inference(ennf_transformation,[],[f3]) ).
tff(f5,plain,
( ? [X0: a,X1: a,X2: a] :
( ( X0 != X1 )
& ( X1 = X2 )
& ( X0 = X2 ) )
| ? [X3: a] : ( X3 != X3 ) ),
inference(flattening,[],[f4]) ).
tff(f6,plain,
( ( ( sK0 != sK1 )
& ( sK1 = sK2 )
& ( sK0 = sK2 ) )
| ( sK3 != sK3 ) ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK0,sK1,sK2,sK3]),skolemize(X0,sK0),skolemize(X1,sK1),skolemize(X2,sK2),skolemize(X3,sK3)],[f5]) ).
tff(f7,plain,
( ( sK0 = sK2 )
| ( sK3 != sK3 ) ),
inference(cnf_transformation,[],[f6]) ).
tff(f8,plain,
( ( sK1 = sK2 )
| ( sK3 != sK3 ) ),
inference(cnf_transformation,[],[f6]) ).
tff(f9,plain,
( ( sK0 != sK1 )
| ( sK3 != sK3 ) ),
inference(cnf_transformation,[],[f6]) ).
tff(f10,plain,
sK0 = sK2,
inference(trivial_inequality_removal,[],[f7]) ).
tff(f11,plain,
sK1 = sK2,
inference(trivial_inequality_removal,[],[f8]) ).
tff(f12,plain,
sK0 != sK1,
inference(trivial_inequality_removal,[],[f9]) ).
tff(f13,plain,
sK0 = sK1,
inference(forward_demodulation,[],[f11,f10]) ).
tff(f14,plain,
$false,
inference(forward_subsumption_resolution,[],[f13,f12]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.04 % Problem : SEV051^5 : TPTP v9.3.1. Released v4.0.0.
% 0.00/0.08 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.10/0.26 % Computer : n001.cluster.edu
% 0.10/0.26 % Model : x86_64 x86_64
% 0.10/0.26 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.26 % Memory : 8046.5625MB
% 0.10/0.26 % OS : Linux 6.8.0-71-generic
% 0.10/0.26 % CPULimit : 300
% 0.10/0.26 % WCLimit : 300
% 0.10/0.26 % DateTime : Tue Sep 29 15:11:21 UTC 2026
% 0.10/0.27 % CPUTime :
% 0.10/0.27 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.26/0.31 Running first-order model finding
% 0.26/0.32 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
% 0.26/0.35 % (1364561)Will run a generic schedule for satisfiability detection.
% 0.26/0.35 % (1364568)dis+10_161_sil=256000:plsq=on:plsqr=61199697,1048576:gs=on:alpa=true:sac=on:slsq=on:cn=on:random_seed=3539761986:i=88024:add=on:rawr=on_3000 on theBenchmark for (3000ds/88024Mi)
% 0.26/0.35 % (1364568) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-1364561-1364568"...
% 0.26/0.35 % (1364568)...printing done.
% 0.26/0.35 % (1364568)Refutation found. Thanks to Tanya!
% 0.26/0.35 % SZS status Theorem for theBenchmark
% 0.26/0.35 % SZS output start Proof for theBenchmark
% See solution above
% 0.26/0.35 % (1364568)------------------------------
% 0.26/0.35 % (1364568)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.26/0.35 % (1364568)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.26/0.35 % (1364568)CaDiCaL version: 2.1.3
% 0.26/0.35 % (1364568)Termination reason: Refutation
% 0.26/0.35 % (1364568)Time elapsed: 0.001 s
% 0.26/0.35 % (1364568)Peak memory usage: 11 MB
% 0.26/0.35 % (1364561)Success in time 0.026 s
% 0.26/0.35 % Vampire exiting
%------------------------------------------------------------------------------