%------------------------------------------------------------------------------
% File : SNARK---20120808r022
% Problem : PUZ012-1 : TPTP v8.1.0. Bugfixed v1.2.1.
% 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 18:26:22 EDT 2022
% Result : Unsatisfiable 0.19s 0.50s
% Output : Refutation 0.19s
% Verified :
% SZS Type : Refutation
% Derivation depth : 5
% Number of leaves : 10
% Syntax : Number of clauses : 17 ( 10 unt; 3 nHn; 15 RR)
% Number of literals : 28 ( 0 equ; 13 neg)
% Maximal clause size : 3 ( 1 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 5 ( 4 usr; 1 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 6 con; 0-0 aty)
% Number of variables : 10 ( 0 sgn)
% Comments :
%------------------------------------------------------------------------------
cnf(label_is_wrong,axiom,
( ~ label(X,Y)
| ~ contains(X,Y) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',label_is_wrong) ).
cnf(each_thing_is_in_a_box,axiom,
( contains(boxa,X)
| contains(boxb,X)
| contains(boxc,X) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',each_thing_is_in_a_box) ).
cnf(each_box_contains_something,axiom,
( contains(X,apples)
| contains(X,bananas)
| contains(X,oranges) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',each_box_contains_something) ).
cnf(contains_is_well_defined1,axiom,
( ~ contains(X,Y)
| ~ contains(X,Z)
| equal_fruits(Y,Z) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',contains_is_well_defined1) ).
cnf(contains_is_well_defined2,axiom,
( ~ contains(X,Y)
| ~ contains(Z,Y)
| equal_boxes(X,Z) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',contains_is_well_defined2) ).
cnf(boxb_not_boxc,axiom,
~ equal_boxes(boxb,boxc),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxb_not_boxc) ).
cnf(apples_not_bananas,axiom,
~ equal_fruits(apples,bananas),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',apples_not_bananas) ).
cnf(boxc_labelled_bananas,hypothesis,
label(boxc,bananas),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxc_labelled_bananas) ).
cnf(boxb_contains_apples,hypothesis,
contains(boxb,apples),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxb_contains_apples) ).
cnf(prove_boxa_contains_bananas_and_boxc_oranges,negated_conjecture,
( ~ contains(boxa,bananas)
| ~ contains(boxc,oranges) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_boxa_contains_bananas_and_boxc_oranges) ).
cnf(21,plain,
~ contains(boxc,bananas),
inference('UR-RESOLVE',[status(thm)],[label_is_wrong,boxc_labelled_bananas]) ).
cnf(23,plain,
( contains(boxa,bananas)
| contains(boxb,bananas) ),
inference('HYPERRESOLVE',[status(thm)],[label_is_wrong,each_thing_is_in_a_box,boxc_labelled_bananas]) ).
cnf(24,plain,
~ contains(boxb,bananas),
inference('UR-RESOLVE',[status(thm)],[contains_is_well_defined1,boxb_contains_apples,apples_not_bananas]) ).
cnf(25,plain,
contains(boxa,bananas),
inference('REWRITE',[status(thm)],[23,24]) ).
cnf(26,plain,
~ contains(boxc,oranges),
inference('REWRITE',[status(thm)],[prove_boxa_contains_bananas_and_boxc_oranges,25]) ).
cnf(31,plain,
contains(boxc,apples),
inference('REWRITE',[status(thm)],[inference('HYPERRESOLVE',[status(thm)],[26,each_box_contains_something]),21]) ).
cnf(32,plain,
$false,
inference('REWRITE',[status(thm)],[inference('UR-RESOLVE',[status(thm)],[contains_is_well_defined2,boxb_contains_apples,boxb_not_boxc]),31]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.07/0.12 % Problem : PUZ012-1 : TPTP v8.1.0. Bugfixed v1.2.1.
% 0.07/0.13 % Command : run-snark %s %d
% 0.13/0.33 % Computer : n029.cluster.edu
% 0.13/0.33 % Model : x86_64 x86_64
% 0.13/0.33 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.13/0.33 % Memory : 8042.1875MB
% 0.13/0.33 % OS : Linux 3.10.0-693.el7.x86_64
% 0.13/0.33 % CPULimit : 300
% 0.13/0.33 % WCLimit : 600
% 0.13/0.33 % DateTime : Sun May 29 03:16:58 EDT 2022
% 0.13/0.34 % CPUTime :
% 0.19/0.45 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.19/0.46 *
% 0.19/0.46 *
% 0.19/0.47 #<PACKAGE "SNARK-USER">
% 0.19/0.47 *
% 0.19/0.47 SNARK-TPTP-OPTIONS
% 0.19/0.47 *
% 0.19/0.47 ((AGENDA-LENGTH-LIMIT NIL) (AGENDA-LENGTH-BEFORE-SIMPLIFICATION-LIMIT NIL)
% 0.19/0.47 (USE-HYPERRESOLUTION T) (USE-UR-RESOLUTION T) (USE-PARAMODULATION T)
% 0.19/0.47 (USE-FACTORING :POS)
% 0.19/0.47 (USE-LITERAL-ORDERING-WITH-HYPERRESOLUTION 'LITERAL-ORDERING-P)
% 0.19/0.47 (USE-LITERAL-ORDERING-WITH-PARAMODULATION 'LITERAL-ORDERING-P)
% 0.19/0.47 (ORDERING-FUNCTIONS>CONSTANTS T) (ASSERT-CONTEXT :CURRENT)
% 0.19/0.47 (RUN-TIME-LIMIT 300) (LISTEN-FOR-COMMANDS NIL)
% 0.19/0.47 (USE-CLOSURE-WHEN-SATISFIABLE T) (PRINT-ROWS-WHEN-GIVEN NIL)
% 0.19/0.47 (PRINT-ROWS-WHEN-DERIVED NIL) (PRINT-UNORIENTABLE-ROWS NIL)
% 0.19/0.47 (PRINT-ROW-WFFS-PRETTILY NIL) (PRINT-FINAL-ROWS :TPTP)
% 0.19/0.47 (PRINT-OPTIONS-WHEN-STARTING NIL) (USE-VARIABLE-NAME-SORTS NIL)
% 0.19/0.47 (USE-PURITY-TEST T) (USE-RELEVANCE-TEST T) (DECLARE-TPTP-SYMBOLS1)
% 0.19/0.47 (DECLARE-TPTP-SYMBOLS2))
% 0.19/0.47 *
% 0.19/0.47 "."
% 0.19/0.47 *
% 0.19/0.47 ; Begin refute-file /export/starexec/sandbox2/benchmark/theBenchmark.p 2022-05-29T03:16:58
% 0.19/0.47 ; Running SNARK from /davis/home/graph/tptp/Systems/SNARK---20120808r022/Source/snark-system.lisp in SBCL 1.0.12 on n029.cluster.edu at 2022-05-29T03:16:58
% 0.19/0.50
% 0.19/0.50
% 0.19/0.50 #||
% 0.19/0.50 % SZS status Unsatisfiable for /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.19/0.50 % SZS output start Refutation
% See solution above
% 0.19/0.50 ||#
% 0.19/0.50
% 0.19/0.50 ; Summary of computation:
% 0.19/0.50 ; 48 formulas have been input or derived (from 20 formulas).
% 0.19/0.50 ; 32 (67%) were retained. Of these,
% 0.19/0.50 ; 4 (12%) were simplified or subsumed later,
% 0.19/0.50 ; 28 (88%) are still being kept.
% 0.19/0.50 ;
% 0.19/0.50 ; Run time in seconds excluding printing time:
% 0.19/0.50 ; 0.003 10% Read assertion file (1 call)
% 0.19/0.50 ; 0.000 0% Assert (18 calls)
% 0.19/0.50 ; 0.004 14% Process new row (41 calls)
% 0.19/0.50 ; 0.002 7% Resolution (38 calls)
% 0.19/0.50 ; 0.000 0% Paramodulation (19 calls)
% 0.19/0.50 ; 0.000 0% Factoring (2 calls)
% 0.19/0.50 ; 0.000 0% Condensing (10 calls)
% 0.19/0.50 ; 0.000 0% Forward subsumption (10 calls)
% 0.19/0.50 ; 0.000 0% Backward subsumption (10 calls)
% 0.19/0.50 ; 0.000 0% Clause clause subsumption (4 calls)
% 0.19/0.50 ; 0.000 0% Forward simplification (41 calls)
% 0.19/0.50 ; 0.000 0% Backward simplification (32 calls)
% 0.19/0.50 ; 0.000 0% Ordering (22 calls)
% 0.19/0.50 ; 0.000 0% Sortal reasoning (32 calls)
% 0.19/0.50 ; 0.000 0% Purity testing (1 call)
% 0.19/0.50 ; 0.020 69% Other
% 0.19/0.50 ; 0.029 Total
% 0.19/0.50 ; 0.032 Real time
% 0.19/0.50 ;
% 0.19/0.50 ; Term-hash-array has 38 terms in all.
% 0.19/0.50 ; Feature-vector-row-index has 6 entries (8 at peak, 10 added, 4 deleted).
% 0.19/0.50 ; Feature-vector-row-index has 19 nodes (27 at peak, 39 added, 20 deleted).
% 0.19/0.50 ; Retrieved 3 possibly forward subsuming rows in 10 calls.
% 0.19/0.50 ; Retrieved 1 possibly backward subsumed row in 10 calls.
% 0.19/0.50 ; Path-index has 42 entries (44 at peak, 45 added, 3 deleted).
% 0.19/0.50 ; Path-index has 47 nodes (48 at peak, 48 added, 1 deleted).
% 0.19/0.50 ; Trie-index has 42 entries (44 at peak, 45 added, 3 deleted).
% 0.19/0.50 ; Trie-index has 54 nodes (57 at peak, 58 added, 4 deleted).
% 0.19/0.50 ; Retrieved 29 generalization terms in 57 calls.
% 0.19/0.50 ; Retrieved 21 instance terms in 21 calls.
% 0.19/0.50 ; Retrieved 295 unifiable terms in 115 calls.
% 0.19/0.50 ;
% 0.19/0.50 ; The agenda of rows to process has 7 entries:
% 0.19/0.50 ; 1 with value 5 3 with value 13 3 with value 21
% 0.19/0.50 ; The agenda of rows to give has 9 entries:
% 0.19/0.50 ; 8 with value (4 5) 1 with value (4 21)
% 0.19/0.50 Evaluation took:
% 0.19/0.50 0.033 seconds of real time
% 0.19/0.50 0.031295 seconds of user run time
% 0.19/0.50 0.001411 seconds of system run time
% 0.19/0.50 0 calls to %EVAL
% 0.19/0.50 0 page faults and
% 0.19/0.50 2,333,944 bytes consed.
% 0.19/0.50 :PROOF-FOUND
% 0.19/0.50 ; End refute-file /export/starexec/sandbox2/benchmark/theBenchmark.p 2022-05-29T03:16:58
% 0.19/0.50 :PROOF-FOUND
% 0.19/0.50 *
%------------------------------------------------------------------------------