TSTP Solution File: PUZ035-2 by SNARK---20120808r022
View Problem
- Process Solution
%------------------------------------------------------------------------------
% File : SNARK---20120808r022
% Problem : PUZ035-2 : TPTP v8.1.0. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run-snark %s %d
% Computer : n029.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 : 600s
% DateTime : Mon Jul 18 18:26:47 EDT 2022
% Result : Unsatisfiable 0.18s 0.50s
% Output : Refutation 0.18s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 12
% Syntax : Number of clauses : 30 ( 8 unt; 16 nHn; 30 RR)
% Number of literals : 60 ( 0 equ; 18 neg)
% Maximal clause size : 4 ( 2 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 : 10 ( 4 sgn)
% Comments :
%------------------------------------------------------------------------------
cnf(everyone_a_knight_or_knave,axiom,
( ~ person(X)
| isa(X,knight)
| isa(X,knave) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',everyone_a_knight_or_knave) ).
cnf(not_both_a_knight_and_knave,axiom,
( ~ isa(X,knight)
| ~ isa(X,knave) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_both_a_knight_and_knave) ).
cnf(knights_make_true_statements,axiom,
( ~ isa(X,knight)
| tell_the_truth(X) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knights_make_true_statements) ).
cnf(knaves_make_false_statements,axiom,
( ~ isa(X,knave)
| lies(X) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knaves_make_false_statements) ).
cnf(statements_are_true_or_false,axiom,
( ~ tell_the_truth(X)
| ~ lies(X) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',statements_are_true_or_false) ).
cnf(statements_are_true_or_false2,axiom,
( ~ person(X)
| tell_the_truth(X)
| lies(X) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',statements_are_true_or_false2) ).
cnf(lie_one_is_a_knight,axiom,
( isa(asked,knight)
| isa(other,knight)
| ~ response(no)
| ~ lies(asked) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',lie_one_is_a_knight) ).
cnf(knight_answers2,axiom,
( ~ response(no)
| ~ tell_the_truth(asked)
| ~ isa(X,knight) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knight_answers2) ).
cnf(two_answers,axiom,
( response(yes)
| response(no) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',two_answers) ).
cnf(asked_person,axiom,
person(asked),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',asked_person) ).
cnf(other_person,axiom,
person(other),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',other_person) ).
cnf(prove_answer,negated_conjecture,
( ~ response(X)
| ~ isa(asked,Y)
| ~ isa(other,Z) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_answer) ).
cnf(18,plain,
( tell_the_truth(asked)
| lies(asked) ),
inference('HYPERRESOLVE',[status(thm)],[statements_are_true_or_false2,asked_person]) ).
cnf(19,plain,
( isa(other,knight)
| isa(other,knave) ),
inference('HYPERRESOLVE',[status(thm)],[everyone_a_knight_or_knave,other_person]) ).
cnf(20,plain,
( isa(asked,knight)
| isa(asked,knave) ),
inference('HYPERRESOLVE',[status(thm)],[everyone_a_knight_or_knave,asked_person]) ).
cnf(24,plain,
( isa(asked,knave)
| tell_the_truth(asked) ),
inference('HYPERRESOLVE',[status(thm)],[knights_make_true_statements,20]) ).
cnf(26,plain,
( isa(asked,knave)
| response(no)
| isa(other,knave) ),
inference('HYPERRESOLVE',[status(thm)],[prove_answer,20,two_answers,19]) ).
cnf(35,plain,
( isa(asked,knave)
| response(no) ),
inference('HYPERRESOLVE',[status(thm)],[prove_answer,26,two_answers,20]) ).
cnf(37,plain,
( response(no)
| lies(asked) ),
inference('HYPERRESOLVE',[status(thm)],[knaves_make_false_statements,35]) ).
cnf(38,plain,
( response(no)
| isa(other,knave) ),
inference('HYPERRESOLVE',[status(thm)],[prove_answer,35,two_answers,19]) ).
cnf(39,plain,
( lies(asked)
| isa(asked,knave) ),
inference('HYPERRESOLVE',[status(thm)],[knight_answers2,37,18,20]) ).
cnf(41,plain,
response(no),
inference('HYPERRESOLVE',[status(thm)],[prove_answer,38,two_answers,35]) ).
cnf(42,plain,
( isa(asked,knight)
| isa(other,knight)
| ~ lies(asked) ),
inference('REWRITE',[status(thm)],[lie_one_is_a_knight,41]) ).
cnf(48,plain,
lies(asked),
inference('HYPERRESOLVE',[status(thm)],[knaves_make_false_statements,39]) ).
cnf(50,plain,
( isa(asked,knight)
| isa(other,knight) ),
inference('REWRITE',[status(thm)],[42,48]) ).
cnf(52,plain,
( isa(asked,knight)
| tell_the_truth(asked) ),
inference('HYPERRESOLVE',[status(thm)],[prove_answer,50,41,24]) ).
cnf(54,plain,
~ tell_the_truth(asked),
inference('UR-RESOLVE',[status(thm)],[statements_are_true_or_false,48]) ).
cnf(55,plain,
isa(asked,knave),
inference('REWRITE',[status(thm)],[24,54]) ).
cnf(57,plain,
isa(asked,knight),
inference('REWRITE',[status(thm)],[52,54]) ).
cnf(58,plain,
$false,
inference('REWRITE',[status(thm)],[inference('UR-RESOLVE',[status(thm)],[not_both_a_knight_and_knave,55]),57]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.12 % Problem : PUZ035-2 : TPTP v8.1.0. Released v2.0.0.
% 0.12/0.12 % Command : run-snark %s %d
% 0.12/0.34 % Computer : n029.cluster.edu
% 0.12/0.34 % Model : x86_64 x86_64
% 0.12/0.34 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.34 % Memory : 8042.1875MB
% 0.12/0.34 % OS : Linux 3.10.0-693.el7.x86_64
% 0.12/0.34 % CPULimit : 300
% 0.12/0.34 % WCLimit : 600
% 0.12/0.34 % DateTime : Sun May 29 02:24:58 EDT 2022
% 0.12/0.34 % CPUTime :
% 0.18/0.45 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.18/0.46 *
% 0.18/0.46 *
% 0.18/0.46 #<PACKAGE "SNARK-USER">
% 0.18/0.46 *
% 0.18/0.46 SNARK-TPTP-OPTIONS
% 0.18/0.46 *
% 0.18/0.46 ((AGENDA-LENGTH-LIMIT NIL) (AGENDA-LENGTH-BEFORE-SIMPLIFICATION-LIMIT NIL)
% 0.18/0.46 (USE-HYPERRESOLUTION T) (USE-UR-RESOLUTION T) (USE-PARAMODULATION T)
% 0.18/0.46 (USE-FACTORING :POS)
% 0.18/0.46 (USE-LITERAL-ORDERING-WITH-HYPERRESOLUTION 'LITERAL-ORDERING-P)
% 0.18/0.46 (USE-LITERAL-ORDERING-WITH-PARAMODULATION 'LITERAL-ORDERING-P)
% 0.18/0.46 (ORDERING-FUNCTIONS>CONSTANTS T) (ASSERT-CONTEXT :CURRENT)
% 0.18/0.46 (RUN-TIME-LIMIT 300) (LISTEN-FOR-COMMANDS NIL)
% 0.18/0.46 (USE-CLOSURE-WHEN-SATISFIABLE T) (PRINT-ROWS-WHEN-GIVEN NIL)
% 0.18/0.46 (PRINT-ROWS-WHEN-DERIVED NIL) (PRINT-UNORIENTABLE-ROWS NIL)
% 0.18/0.46 (PRINT-ROW-WFFS-PRETTILY NIL) (PRINT-FINAL-ROWS :TPTP)
% 0.18/0.46 (PRINT-OPTIONS-WHEN-STARTING NIL) (USE-VARIABLE-NAME-SORTS NIL)
% 0.18/0.46 (USE-PURITY-TEST T) (USE-RELEVANCE-TEST T) (DECLARE-TPTP-SYMBOLS1)
% 0.18/0.46 (DECLARE-TPTP-SYMBOLS2))
% 0.18/0.46 *
% 0.18/0.47 "."
% 0.18/0.47 *
% 0.18/0.47 ; Begin refute-file /export/starexec/sandbox2/benchmark/theBenchmark.p 2022-05-29T02:24:58
% 0.18/0.47 ; Running SNARK from /davis/home/graph/tptp/Systems/SNARK---20120808r022/Source/snark-system.lisp in SBCL 1.0.12 on n029.cluster.edu at 2022-05-29T02:24:58
% 0.18/0.50
% 0.18/0.50
% 0.18/0.50 #||
% 0.18/0.50 % SZS status Unsatisfiable for /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.18/0.50 % SZS output start Refutation
% See solution above
% 0.18/0.51 ||#
% 0.18/0.51
% 0.18/0.51 ; Summary of computation:
% 0.18/0.51 ; 112 formulas have been input or derived (from 41 formulas).
% 0.18/0.51 ; 58 (52%) were retained. Of these,
% 0.18/0.51 ; 40 (69%) were simplified or subsumed later,
% 0.18/0.51 ; 18 (31%) are still being kept.
% 0.18/0.51 ;
% 0.18/0.51 ; Run time in seconds excluding printing time:
% 0.18/0.51 ; 0.003 8% Read assertion file (1 call)
% 0.18/0.51 ; 0.001 3% Assert (16 calls)
% 0.18/0.51 ; 0.003 8% Process new row (104 calls)
% 0.18/0.51 ; 0.002 5% Resolution (80 calls)
% 0.18/0.51 ; 0.000 0% Paramodulation (40 calls)
% 0.18/0.51 ; 0.000 0% Factoring (19 calls)
% 0.18/0.51 ; 0.000 0% Condensing (71 calls)
% 0.18/0.51 ; 0.002 5% Forward subsumption (71 calls)
% 0.18/0.51 ; 0.002 5% Backward subsumption (48 calls)
% 0.18/0.51 ; 0.000 0% Clause clause subsumption (45 calls)
% 0.18/0.51 ; 0.002 5% Forward simplification (82 calls)
% 0.18/0.51 ; 0.000 0% Backward simplification (58 calls)
% 0.18/0.51 ; 0.000 0% Ordering (76 calls)
% 0.18/0.51 ; 0.000 0% Sortal reasoning (32 calls)
% 0.18/0.51 ; 0.000 0% Purity testing (1 call)
% 0.18/0.51 ; 0.024 62% Other
% 0.18/0.51 ; 0.039 Total
% 0.18/0.51 ; 0.043 Real time
% 0.18/0.51 ;
% 0.18/0.51 ; Term-hash-array has 20 terms in all.
% 0.18/0.51 ; Feature-vector-row-index has 8 entries (28 at peak, 48 added, 40 deleted).
% 0.18/0.51 ; Feature-vector-row-index has 27 nodes (143 at peak, 211 added, 184 deleted).
% 0.18/0.51 ; Retrieved 45 possibly forward subsuming rows in 71 calls.
% 0.18/0.51 ; Retrieved 16 possibly backward subsumed rows in 48 calls.
% 0.18/0.51 ; Path-index has 24 entries (26 at peak, 26 added, 2 deleted).
% 0.18/0.51 ; Path-index has 31 nodes (32 at peak, 32 added, 1 deleted).
% 0.18/0.51 ; Trie-index has 24 entries (26 at peak, 26 added, 2 deleted).
% 0.18/0.51 ; Trie-index has 33 nodes (35 at peak, 35 added, 2 deleted).
% 0.18/0.51 ; Retrieved 2 generalization terms in 7 calls.
% 0.18/0.51 ; Retrieved 9 instance terms in 9 calls.
% 0.18/0.51 ; Retrieved 475 unifiable terms in 280 calls.
% 0.18/0.51 ;
% 0.18/0.51 ; The agenda of rows to process has 1 entry:
% 0.18/0.51 ; 1 with value 10
% 0.18/0.51 ; The agenda of rows to give has 4 entries:
% 0.18/0.51 ; 1 with value (4 9) 3 with value (4 10)
% 0.18/0.51 Evaluation took:
% 0.18/0.51 0.043 seconds of real time
% 0.18/0.51 0.03493 seconds of user run time
% 0.18/0.51 0.008072 seconds of system run time
% 0.18/0.51 0 calls to %EVAL
% 0.18/0.51 0 page faults and
% 0.18/0.51 3,493,048 bytes consed.
% 0.18/0.51 :PROOF-FOUND
% 0.18/0.51 ; End refute-file /export/starexec/sandbox2/benchmark/theBenchmark.p 2022-05-29T02:24:58
% 0.18/0.51 :PROOF-FOUND
% 0.18/0.51 *
%------------------------------------------------------------------------------