%------------------------------------------------------------------------------
% File : CSE_E---1.7
% Problem : PUZ020-1 : TPTP v9.2.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : /export/starexec/sandbox/solver/bin/lemma_parallel_prover %s --lemma-prover /export/starexec/sandbox/solver/bin/cse --final-prover /export/starexec/sandbox/solver/bin/eprover --proof-time %d --global-time-limit %d
% Computer : n023.cluster.edu
% Model : x86_64 x86_64
% CPU : Intel(R) Xeon(R) CPU E5-2620 v4 2.10GHz
% Memory : 8042.1875MB
% OS : Linux 3.10.0-693.el7.x86_64
% CPULimit : 300s
% WCLimit : 300s
% DateTime : Tue May 5 05:02:40 PM UTC 2026
% Result : Unsatisfiable 1.26s 1.71s
% Output : CNFRefutation 1.26s
% Verified :
% SZS Type : Refutation
% Derivation depth : 3
% Number of leaves : 7
% Syntax : Number of clauses : 17 ( 9 unt; 4 nHn; 17 RR)
% Number of literals : 29 ( 0 equ; 12 neg)
% Maximal clause size : 3 ( 1 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 6 ( 5 usr; 1 prp; 0-2 aty)
% Number of functors : 3 ( 3 usr; 2 con; 0-1 aty)
% Number of variables : 6 ( 0 sgn)
% Comments :
%------------------------------------------------------------------------------
cnf(knight_wife_means_truthful_husband,hypothesis,
( a_truth(statement_by(husband))
| ~ knight(wife) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knight_wife_means_truthful_husband) ).
cnf(knight_wife_or_truthful_husband,hypothesis,
( a_truth(statement_by(husband))
| knight(wife) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knight_wife_or_truthful_husband) ).
cnf(everyone_a_knight_or_knave,axiom,
( knight(X1)
| knave(X1)
| ~ person(X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',everyone_a_knight_or_knave) ).
cnf(husband,hypothesis,
person(husband),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',husband) ).
cnf(prove_knight_husband,negated_conjecture,
~ knight(husband),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_knight_husband) ).
cnf(knaves_do_not_say_the_truth,axiom,
( ~ knave(X1)
| ~ says(X1,X2)
| ~ a_truth(X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knaves_do_not_say_the_truth) ).
cnf(husband_makes_statements,hypothesis,
says(husband,statement_by(husband)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',husband_makes_statements) ).
cnf(c_0_7,hypothesis,
( a_truth(statement_by(husband))
| ~ knight(wife) ),
knight_wife_means_truthful_husband ).
cnf(c_0_8,hypothesis,
( a_truth(statement_by(husband))
| knight(wife) ),
knight_wife_or_truthful_husband ).
cnf(c_0_9,axiom,
( knight(X1)
| knave(X1)
| ~ person(X1) ),
everyone_a_knight_or_knave ).
cnf(c_0_10,hypothesis,
person(husband),
husband ).
cnf(c_0_11,negated_conjecture,
~ knight(husband),
prove_knight_husband ).
cnf(c_0_12,axiom,
( ~ knave(X1)
| ~ says(X1,X2)
| ~ a_truth(X2) ),
knaves_do_not_say_the_truth ).
cnf(c_0_13,hypothesis,
says(husband,statement_by(husband)),
husband_makes_statements ).
cnf(c_0_14,hypothesis,
a_truth(statement_by(husband)),
inference(csr,[status(thm)],[c_0_7,c_0_8]) ).
cnf(c_0_15,hypothesis,
knave(husband),
inference(sr,[status(thm)],[inference(spm,[status(thm)],[c_0_9,c_0_10]),c_0_11]) ).
cnf(c_0_16,hypothesis,
$false,
inference(cn,[status(thm)],[inference(rw,[status(thm)],[inference(rw,[status(thm)],[inference(spm,[status(thm)],[c_0_12,c_0_13]),c_0_14]),c_0_15])]),
[proof] ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.12 % Problem : PUZ020-1 : TPTP v9.2.1. Released v1.0.0.
% 0.00/0.12 % Command : /export/starexec/sandbox/solver/bin/lemma_parallel_prover %s --lemma-prover /export/starexec/sandbox/solver/bin/cse --final-prover /export/starexec/sandbox/solver/bin/eprover --proof-time %d --global-time-limit %d
% 0.16/0.33 % Computer : n023.cluster.edu
% 0.16/0.33 % Model : x86_64 x86_64
% 0.16/0.33 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.16/0.33 % Memory : 8042.1875MB
% 0.16/0.33 % OS : Linux 3.10.0-693.el7.x86_64
% 0.16/0.33 % CPULimit : 300
% 0.16/0.33 % WCLimit : 300
% 0.16/0.33 % DateTime : Tue May 5 01:34:24 EDT 2026
% 0.16/0.33 % CPUTime :
% 0.16/0.34 % start to proof: theBenchmark
% 1.26/1.71 % Version : CSE_E---1.7
% 1.26/1.71 % Problem : theBenchmark.p
% 1.26/1.71 % SZS status Unsatisfiable for theBenchmark.p
% 1.26/1.71 % SZS output start CNFRefutation
% See solution above
% 1.26/1.71 % Total time : 1.369s
%------------------------------------------------------------------------------