%------------------------------------------------------------------------------
% File : Prover9---2026-6A
% Problem : PUZ035-2 : TPTP v9.3.1. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : prover9 -casc 300 -f /export/starexec/sandbox/benchmark/theBenchmark.p
% Computer : n016.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 : Sun Sep 27 08:23:10 AM UTC 2026
% Result : Unsatisfiable 0.13s 0.58s
% Output : CNFRefutation 0.13s
% Verified :
% SZS Type : Refutation
% Derivation depth : 17
% Number of leaves : 12
% Syntax : Number of formulae : 55 ( 9 unt; 0 def)
% Number of atoms : 132 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 137 ( 60 ~; 77 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 6 ( 5 usr; 1 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 6 con; 0-0 aty)
% Number of variables : 38 ( 22 sgn 10 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(asked_person,axiom,
person(asked),
file('theBenchmark.p',asked_person) ).
cnf(c_1,plain,
person(asked),
inference(clausify,[status(thm)],[asked_person]) ).
fof(statements_are_true_or_false2,axiom,
! [VAR_0] :
( lies(VAR_0)
| tell_the_truth(VAR_0)
| ~ person(VAR_0) ),
file('theBenchmark.p',statements_are_true_or_false2) ).
cnf(c_2,plain,
( lies(A)
| tell_the_truth(A)
| ~ person(A) ),
inference(clausify,[status(thm)],[statements_are_true_or_false2]) ).
fof(everyone_a_knight_or_knave,axiom,
! [VAR_0] :
( isa(VAR_0,knave)
| isa(VAR_0,knight)
| ~ person(VAR_0) ),
file('theBenchmark.p',everyone_a_knight_or_knave) ).
cnf(c_3,plain,
( isa(A,knave)
| isa(A,knight)
| ~ person(A) ),
inference(clausify,[status(thm)],[everyone_a_knight_or_knave]) ).
fof(other_person,axiom,
person(other),
file('theBenchmark.p',other_person) ).
cnf(c_4,plain,
person(other),
inference(clausify,[status(thm)],[other_person]) ).
cnf(c_6,plain,
( lies(asked)
| tell_the_truth(asked) ),
inference(resolve,[status(thm)],[c_1,c_2]) ).
fof(knight_answers3,axiom,
! [VAR_0] :
( ~ isa(VAR_0,knight)
| ~ tell_the_truth(asked)
| response(yes) ),
file('theBenchmark.p',knight_answers3) ).
cnf(c_8,plain,
( ~ isa(A,knight)
| ~ tell_the_truth(asked)
| response(yes) ),
inference(clausify,[status(thm)],[knight_answers3]) ).
fof(statements_are_true_or_false,axiom,
! [VAR_0] :
( ~ lies(VAR_0)
| ~ tell_the_truth(VAR_0) ),
file('theBenchmark.p',statements_are_true_or_false) ).
cnf(c_11,plain,
( ~ lies(A)
| ~ tell_the_truth(A) ),
inference(clausify,[status(thm)],[statements_are_true_or_false]) ).
fof(knights_make_true_statements,axiom,
! [VAR_0] :
( tell_the_truth(VAR_0)
| ~ isa(VAR_0,knight) ),
file('theBenchmark.p',knights_make_true_statements) ).
cnf(c_12,plain,
( tell_the_truth(A)
| ~ isa(A,knight) ),
inference(clausify,[status(thm)],[knights_make_true_statements]) ).
cnf(c_14,plain,
( ~ lies(A)
| ~ isa(A,knight) ),
inference(resolve,[status(thm)],[c_12,c_11]) ).
cnf(c_16,plain,
( lies(asked)
| ~ isa(A,knight)
| response(yes) ),
inference(resolve,[status(thm)],[c_8,c_6]) ).
fof(knaves_make_false_statements,axiom,
! [VAR_0] :
( lies(VAR_0)
| ~ isa(VAR_0,knave) ),
file('theBenchmark.p',knaves_make_false_statements) ).
cnf(c_18,plain,
( lies(A)
| ~ isa(A,knave) ),
inference(clausify,[status(thm)],[knaves_make_false_statements]) ).
fof(lie_one_is_a_knight,axiom,
( ~ lies(asked)
| ~ response(no)
| isa(other,knight)
| isa(asked,knight) ),
file('theBenchmark.p',lie_one_is_a_knight) ).
cnf(c_19,plain,
( ~ lies(asked)
| ~ response(no)
| isa(other,knight)
| isa(asked,knight) ),
inference(clausify,[status(thm)],[lie_one_is_a_knight]) ).
fof(knight_answers1,axiom,
! [VAR_0] :
( ~ isa(VAR_0,knight)
| ~ lies(asked)
| ~ response(yes) ),
file('theBenchmark.p',knight_answers1) ).
cnf(c_20,plain,
( ~ isa(A,knight)
| ~ lies(asked)
| ~ response(yes) ),
inference(clausify,[status(thm)],[knight_answers1]) ).
cnf(c_24,plain,
( ~ isa(asked,knave)
| ~ isa(A,knight)
| ~ response(yes) ),
inference(resolve,[status(thm)],[c_20,c_18]) ).
cnf(c_29,plain,
( ~ isa(asked,knave)
| ~ response(no)
| isa(other,knight)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_19,c_18]) ).
cnf(c_31,plain,
( ~ isa(asked,knight)
| ~ isa(A,knight)
| response(yes) ),
inference(resolve,[status(thm)],[c_16,c_14]) ).
cnf(c_33,plain,
( isa(other,knave)
| isa(other,knight) ),
inference(resolve,[status(thm)],[c_4,c_3]) ).
cnf(c_34,plain,
( isa(asked,knave)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_1,c_3]) ).
fof(prove_answer,axiom,
! [VAR_0,VAR_1,VAR_2] :
( ~ isa(other,VAR_2)
| ~ isa(asked,VAR_1)
| ~ response(VAR_0) ),
file('theBenchmark.p',prove_answer) ).
cnf(c_35,plain,
( ~ isa(other,C)
| ~ isa(asked,B)
| ~ response(A) ),
inference(clausify,[status(thm)],[prove_answer]) ).
fof(two_answers,axiom,
( response(no)
| response(yes) ),
file('theBenchmark.p',two_answers) ).
cnf(c_36,plain,
( response(no)
| response(yes) ),
inference(clausify,[status(thm)],[two_answers]) ).
cnf(c_38,plain,
( ~ isa(asked,knight)
| response(yes) ),
inference(factor,[status(thm)],[c_31]) ).
cnf(c_65,plain,
( ~ response(no)
| isa(other,knight)
| isa(asked,knight)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_34,c_29]) ).
cnf(c_40,plain,
( ~ response(no)
| isa(other,knight)
| isa(asked,knight) ),
inference(copy,[status(thm)],[c_65]) ).
cnf(c_41,plain,
( ~ isa(A,knight)
| ~ response(yes)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_34,c_24]) ).
cnf(c_42,plain,
( isa(asked,knight)
| ~ isa(other,B)
| ~ response(A) ),
inference(resolve,[status(thm)],[c_35,c_34]) ).
cnf(c_43,plain,
( isa(other,knight)
| ~ isa(asked,B)
| ~ response(A) ),
inference(resolve,[status(thm)],[c_35,c_33]) ).
cnf(c_44,plain,
( response(yes)
| isa(other,knight)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_40,c_36]) ).
cnf(c_45,plain,
( isa(other,knight)
| isa(asked,knight)
| ~ response(A) ),
inference(resolve,[status(thm)],[c_42,c_33]) ).
cnf(c_66,plain,
( isa(asked,knight)
| ~ response(A)
| response(yes)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_44,c_42]) ).
cnf(c_46,plain,
( ~ response(A)
| response(yes)
| isa(asked,knight) ),
inference(copy,[status(thm)],[c_66]) ).
cnf(c_67,plain,
( response(yes)
| response(yes)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_46,c_36]) ).
cnf(c_47,plain,
( response(yes)
| isa(asked,knight) ),
inference(copy,[status(thm)],[c_67]) ).
cnf(c_68,plain,
( response(yes)
| response(yes) ),
inference(resolve,[status(thm)],[c_47,c_38]) ).
cnf(c_50,plain,
response(yes),
inference(copy,[status(thm)],[c_68]) ).
cnf(c_51,plain,
( ~ isa(A,knight)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_50,c_41]) ).
cnf(c_54,plain,
( isa(other,knight)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_50,c_45]) ).
cnf(c_69,plain,
( isa(asked,knight)
| isa(asked,knight) ),
inference(resolve,[status(thm)],[c_54,c_51]) ).
cnf(c_57,plain,
isa(asked,knight),
inference(copy,[status(thm)],[c_69]) ).
cnf(c_60,plain,
( isa(other,knight)
| ~ response(A) ),
inference(resolve,[status(thm)],[c_57,c_43]) ).
cnf(c_70,plain,
( ~ isa(other,B)
| ~ isa(asked,A) ),
inference(resolve,[status(thm)],[c_35,c_50]) ).
cnf(c_62,plain,
~ isa(other,A),
inference(resolve,[status(thm)],[c_70,c_57]) ).
cnf(c_63,plain,
~ response(A),
inference(resolve,[status(thm)],[c_62,c_60]) ).
cnf(c_64,plain,
$false,
inference(resolve,[status(thm)],[c_63,c_50]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ035-2 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.03 % Command : prover9 -casc 300 -f /export/starexec/sandbox/benchmark/theBenchmark.p
% 0.10/0.55 % Computer : n016.cluster.edu
% 0.10/0.55 % Model : x86_64 x86_64
% 0.10/0.55 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.55 % Memory : 8046.5625MB
% 0.10/0.55 % OS : Linux 6.8.0-71-generic
% 0.10/0.55 % CPULimit : 300
% 0.10/0.55 % WCLimit : 300
% 0.10/0.55 % DateTime : Sat Sep 26 05:11:30 UTC 2026
% 0.10/0.56 % CPUTime :
% 0.10/0.56 % Prover9 (64) version 2026-6A, July 2026, CASC-J13.
% 0.10/0.56 % Process 40553 was started by sandbox on n016,
% 0.10/0.56 % Sat Sep 26 05:11:30 2026
% 0.10/0.56 % The command was "/export/starexec/sandbox/solver/bin/prover9 -casc 300 -f /export/starexec/sandbox/benchmark/theBenchmark.p".
% 0.10/0.56
% 0.10/0.56 % From the command line: assign(max_seconds, 300).
% 0.13/0.58
% 0.13/0.58 % SZS status Unsatisfiable for theBenchmark
% 0.13/0.58
% 0.13/0.58 % Proof 1 at 0.00 (+ 0.00) seconds.
% 0.13/0.58 % Length of proof is 37.
% 0.13/0.58 % Level of proof is 11.
% 0.13/0.58 % Maximum clause weight is 11.000.
% 0.13/0.58 % Given clauses 27.
% 0.13/0.58
% 0.13/0.58 % SZS output start CNFRefutation for theBenchmark
% See solution above
%------------------------------------------------------------------------------