%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : SYN354-1 : TPTP v9.3.1. Released v1.2.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n011.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 02:07:26 PM UTC 2026
% Result : Unsatisfiable 0.09s 0.23s
% Output : Refutation 0.09s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 6
% Syntax : Number of formulae : 25 ( 6 unt; 2 def)
% Number of atoms : 54 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 55 ( 26 ~; 27 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 5 ( 4 usr; 3 prp; 0-2 aty)
% Number of functors : 3 ( 3 usr; 2 con; 0-2 aty)
% Number of variables : 8 ( 0 sgn 8 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,negated_conjecture,
f(a,b),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',clause1) ).
fof(f3,negated_conjecture,
! [X0,X1] :
( ~ f(X0,X1)
| g(X1,z(X0,X1))
| g(b,z(X0,X1))
| f(b,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',clause3) ).
fof(f4,negated_conjecture,
! [X0,X1] :
( ~ g(b,z(X0,X1))
| ~ g(X1,z(X0,X1))
| ~ f(X0,X1)
| f(b,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',clause4) ).
fof(f7,negated_conjecture,
! [X0,X1] :
( ~ f(b,X0)
| ~ f(a,X0)
| ~ f(X0,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',clause7) ).
fof(f8,plain,
( g(b,z(a,b))
| g(b,z(a,b))
| f(b,b) ),
inference(resolution,[],[f3,f1]) ).
fof(f9,plain,
( g(b,z(a,b))
| f(b,b) ),
inference(duplicate_literal_removal,[],[f8]) ).
fof(f11,definition,
( spl0_1
<=> f(b,b) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f13,plain,
( f(b,b)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f11]) ).
fof(f15,definition,
( spl0_2
<=> g(b,z(a,b)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f17,plain,
( g(b,z(a,b))
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f15]) ).
fof(f18,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f9,f15,f11]) ).
fof(f20,plain,
( ~ g(b,z(a,b))
| ~ f(a,b)
| f(b,b)
| ~ spl0_2 ),
inference(resolution,[],[f4,f17]) ).
fof(f21,plain,
( ~ f(a,b)
| f(b,b)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f20,f17]) ).
fof(f22,plain,
( f(b,b)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f21,f1]) ).
fof(f23,plain,
( spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f22,f15,f11]) ).
fof(f24,plain,
( ! [X0] :
( ~ f(a,b)
| ~ f(b,X0) )
| ~ spl0_1 ),
inference(resolution,[],[f13,f7]) ).
fof(f27,plain,
( ! [X0] : ~ f(b,X0)
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f24,f1]) ).
fof(f28,plain,
( $false
| ~ spl0_1 ),
inference(resolution,[],[f27,f13]) ).
fof(f29,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f28]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f18]) ).
cnf(s2,plain,
( spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f23]) ).
cnf(s3,plain,
~ spl0_1,
inference(sat_conversion,[],[f29]) ).
cnf(s4,plain,
~ spl0_2,
inference(rat,[],[s2,s3]) ).
cnf(s5,plain,
$false,
inference(rat,[],[s1,s4,s3]) ).
fof(f30,plain,
$false,
inference(avatar_sat_refutation,[],[s5]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : SYN354-1 : TPTP v9.3.1. Released v1.2.0.
% 0.00/0.04 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.09/0.16 % Computer : n011.cluster.edu
% 0.09/0.16 % Model : x86_64 x86_64
% 0.09/0.16 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.16 % Memory : 8046.5625MB
% 0.09/0.16 % OS : Linux 6.8.0-71-generic
% 0.09/0.16 % CPULimit : 300
% 0.09/0.16 % WCLimit : 300
% 0.09/0.16 % DateTime : Mon Sep 28 15:48:16 UTC 2026
% 0.09/0.16 % CPUTime :
% 0.09/0.16 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.09/0.19 Running first-order model finding
% 0.09/0.19 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
% 0.09/0.23 % (3490314)Will run a generic schedule for satisfiability detection.
% 0.09/0.23 % (3490324)ott+1_1_to=lpo:sil=16000:sp=reverse_arity:erd=off:random_seed=2077583699:i=131_2999 on theBenchmark for (2999ds/131Mi)
% 0.09/0.23 % (3490324) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-3490314-3490324"...
% 0.09/0.23 % (3490324)...printing done.
% 0.09/0.23 % (3490324)Refutation found. Thanks to Tanya!
% 0.09/0.23 % SZS status Unsatisfiable for theBenchmark
% 0.09/0.23 % SZS output start Proof for theBenchmark
% See solution above
% 0.09/0.23 % (3490324)------------------------------
% 0.09/0.23 % (3490324)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.09/0.23 % (3490324)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.09/0.23 % (3490324)CaDiCaL version: 2.1.3
% 0.09/0.23 % (3490324)Termination reason: Refutation
% 0.09/0.23 % (3490324)Time elapsed: 0.001 s
% 0.09/0.23 % (3490324)Peak memory usage: 12 MB
% 0.09/0.23 % (3490324)Instructions burned: 1 (million)
% 0.09/0.23 % (3490314)Success in time 0.029 s
% 0.09/0.23 % Vampire exiting
%------------------------------------------------------------------------------