%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ020-1 : TPTP v9.3.1. Released v1.0.0.
% 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 12:31:56 PM UTC 2026
% Result : Unsatisfiable 0.12s 0.45s
% Output : Refutation 0.12s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 7
% Syntax : Number of formulae : 20 ( 7 unt; 2 def)
% Number of atoms : 34 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 26 ( 12 ~; 12 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 2 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 6 ( 5 usr; 3 prp; 0-1 aty)
% Number of functors : 3 ( 3 usr; 2 con; 0-1 aty)
% Number of variables : 1 ( 0 sgn 1 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f9,axiom,
! [X0] :
( ~ person(X0)
| ~ a_truth(statement_by(X0))
| knight(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knights_make_true_statements) ).
fof(f13,axiom,
person(husband),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',husband) ).
fof(f19,axiom,
( a_truth(statement_by(husband))
| knight(wife) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knight_wife_or_truthful_husband) ).
fof(f20,axiom,
( ~ knight(wife)
| a_truth(statement_by(husband)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knight_wife_means_truthful_husband) ).
fof(f21,negated_conjecture,
~ knight(husband),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_knight_husband) ).
fof(f25,definition,
( spl0_1
<=> a_truth(statement_by(husband)) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f27,plain,
( a_truth(statement_by(husband))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f25]) ).
fof(f29,definition,
( spl0_2
<=> knight(wife) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f32,plain,
( spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f20,f29,f25]) ).
fof(f33,plain,
( spl0_2
| spl0_1 ),
inference(avatar_split_clause,[],[f19,f25,f29]) ).
fof(f37,plain,
( ~ a_truth(statement_by(husband))
| knight(husband) ),
inference(resolution,[],[f9,f13]) ).
fof(f44,plain,
( knight(husband)
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f37,f27]) ).
fof(f45,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f44,f21]) ).
fof(f46,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f45]) ).
cnf(s1,plain,
( spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f32]) ).
cnf(s2,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f33]) ).
cnf(s4,plain,
~ spl0_1,
inference(sat_conversion,[],[f46]) ).
cnf(s5,plain,
spl0_2,
inference(rat,[],[s2,s4]) ).
cnf(s6,plain,
$false,
inference(rat,[],[s1,s5,s4]) ).
fof(f47,plain,
$false,
inference(avatar_sat_refutation,[],[s6]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ020-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.12/0.37 % Computer : n020.cluster.edu
% 0.12/0.37 % Model : x86_64 x86_64
% 0.12/0.37 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.37 % Memory : 8046.5625MB
% 0.12/0.37 % OS : Linux 6.8.0-71-generic
% 0.12/0.37 % CPULimit : 300
% 0.12/0.37 % WCLimit : 300
% 0.12/0.37 % DateTime : Sun Sep 27 22:31:04 UTC 2026
% 0.12/0.37 % CPUTime :
% 0.12/0.37 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.12/0.40 Running first-order model finding
% 0.12/0.40 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
% 0.12/0.45 % (3831312)Will run a generic schedule for satisfiability detection.
% 0.12/0.45 % (3831321)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=3284823693:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.12/0.45 % (3831321) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-3831312-3831321"...
% 0.12/0.45 % (3831321)...printing done.
% 0.12/0.45 % (3831318)% WARNING: option uhcvi not known.
% 0.12/0.45 % (3831321)Refutation found. Thanks to Tanya!
% 0.12/0.45 % SZS status Unsatisfiable for theBenchmark
% 0.12/0.45 % SZS output start Proof for theBenchmark
% See solution above
% 0.12/0.45 % (3831321)------------------------------
% 0.12/0.45 % (3831321)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.12/0.45 % (3831321)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.12/0.45 % (3831321)CaDiCaL version: 2.1.3
% 0.12/0.45 % (3831321)Termination reason: Refutation
% 0.12/0.45 % (3831321)Time elapsed: 0.001 s
% 0.12/0.45 % (3831321)Peak memory usage: 12 MB
% 0.12/0.45 % (3831321)Instructions burned: 1 (million)
% 0.12/0.45 % (3831312)Success in time 0.035 s
% 0.12/0.45 % Vampire exiting
%------------------------------------------------------------------------------