%------------------------------------------------------------------------------
% File : E-SAT---3.5.1
% Problem : PUZ012-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% Transfm : none
% Format : tptp:raw
% Command : run_E /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 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 : Thu Sep 24 02:02:15 PM UTC 2026
% Result : Unsatisfiable 0.12s 0.45s
% Output : CNFRefutation 0.12s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 11
% Syntax : Number of clauses : 38 ( 21 unt; 5 nHn; 34 RR)
% Number of literals : 62 ( 0 equ; 31 neg)
% Maximal clause size : 3 ( 1 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 4 ( 3 usr; 1 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 6 con; 0-0 aty)
% Number of variables : 21 ( 0 sgn)
% Comments :
%------------------------------------------------------------------------------
cnf(label_is_wrong,axiom,
( ~ contains(X1,X2)
| ~ label(X1,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',label_is_wrong) ).
cnf(prove_boxa_contains_bananas_and_boxc_oranges,negated_conjecture,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_boxa_contains_bananas_and_boxc_oranges) ).
cnf(boxb_labelled_oranges,hypothesis,
label(boxb,oranges),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxb_labelled_oranges) ).
cnf(each_thing_is_in_a_box,axiom,
( contains(boxc,X1)
| contains(boxb,X1)
| contains(boxa,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',each_thing_is_in_a_box) ).
cnf(boxa_labelled_apples,hypothesis,
label(boxa,apples),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxa_labelled_apples) ).
cnf(contains_is_well_defined1,axiom,
( ~ contains(X1,X3)
| ~ contains(X1,X2)
| equal_fruits(X2,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',contains_is_well_defined1) ).
cnf(each_box_contains_something,axiom,
( contains(X1,oranges)
| contains(X1,bananas)
| contains(X1,apples) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',each_box_contains_something) ).
cnf(boxc_labelled_bananas,hypothesis,
label(boxc,bananas),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxc_labelled_bananas) ).
cnf(bananas_not_oranges,axiom,
~ equal_fruits(bananas,oranges),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',bananas_not_oranges) ).
cnf(apples_not_bananas,axiom,
~ equal_fruits(apples,bananas),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',apples_not_bananas) ).
cnf(boxb_contains_apples,hypothesis,
contains(boxb,apples),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxb_contains_apples) ).
cnf(c_0_11,plain,
( ~ contains(X1,X2)
| ~ label(X1,X2) ),
inference(fof_simplification,[status(thm)],[label_is_wrong]) ).
cnf(c_0_12,negated_conjecture,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
inference(fof_simplification,[status(thm)],[prove_boxa_contains_bananas_and_boxc_oranges]) ).
cnf(c_0_13,plain,
( ~ contains(X1,X2)
| ~ label(X1,X2) ),
c_0_11 ).
cnf(c_0_14,hypothesis,
label(boxb,oranges),
boxb_labelled_oranges ).
cnf(c_0_15,negated_conjecture,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
c_0_12 ).
cnf(c_0_16,axiom,
( contains(boxc,X1)
| contains(boxb,X1)
| contains(boxa,X1) ),
each_thing_is_in_a_box ).
cnf(c_0_17,hypothesis,
~ contains(boxb,oranges),
inference(spm,[status(thm)],[c_0_13,c_0_14]) ).
cnf(c_0_18,hypothesis,
label(boxa,apples),
boxa_labelled_apples ).
cnf(c_0_19,plain,
( ~ contains(X1,X3)
| ~ contains(X1,X2)
| equal_fruits(X2,X3) ),
inference(fof_simplification,[status(thm)],[contains_is_well_defined1]) ).
cnf(c_0_20,negated_conjecture,
( ~ contains(boxa,bananas)
| contains(boxa,oranges) ),
inference(sr,[status(thm)],[inference(spm,[status(thm)],[c_0_15,c_0_16]),c_0_17]) ).
cnf(c_0_21,axiom,
( contains(X1,oranges)
| contains(X1,bananas)
| contains(X1,apples) ),
each_box_contains_something ).
cnf(c_0_22,hypothesis,
~ contains(boxa,apples),
inference(spm,[status(thm)],[c_0_13,c_0_18]) ).
cnf(c_0_23,hypothesis,
label(boxc,bananas),
boxc_labelled_bananas ).
cnf(c_0_24,plain,
~ equal_fruits(bananas,oranges),
inference(fof_simplification,[status(thm)],[bananas_not_oranges]) ).
cnf(c_0_25,plain,
( ~ contains(X1,X3)
| ~ contains(X1,X2)
| equal_fruits(X2,X3) ),
c_0_19 ).
cnf(c_0_26,negated_conjecture,
contains(boxa,oranges),
inference(sr,[status(thm)],[inference(spm,[status(thm)],[c_0_20,c_0_21]),c_0_22]) ).
cnf(c_0_27,hypothesis,
~ contains(boxc,bananas),
inference(spm,[status(thm)],[c_0_13,c_0_23]) ).
cnf(c_0_28,plain,
~ equal_fruits(bananas,oranges),
c_0_24 ).
cnf(c_0_29,negated_conjecture,
( ~ contains(boxa,X1)
| equal_fruits(X1,oranges) ),
inference(spm,[status(thm)],[c_0_25,c_0_26]) ).
cnf(c_0_30,hypothesis,
( contains(boxb,bananas)
| contains(boxa,bananas) ),
inference(spm,[status(thm)],[c_0_27,c_0_16]) ).
cnf(c_0_31,negated_conjecture,
~ contains(boxa,bananas),
inference(spm,[status(thm)],[c_0_28,c_0_29]) ).
cnf(c_0_32,plain,
~ equal_fruits(apples,bananas),
inference(fof_simplification,[status(thm)],[apples_not_bananas]) ).
cnf(c_0_33,hypothesis,
contains(boxb,bananas),
inference(sr,[status(thm)],[c_0_30,c_0_31]) ).
cnf(c_0_34,plain,
~ equal_fruits(apples,bananas),
c_0_32 ).
cnf(c_0_35,hypothesis,
( ~ contains(boxb,X1)
| equal_fruits(X1,bananas) ),
inference(spm,[status(thm)],[c_0_25,c_0_33]) ).
cnf(c_0_36,hypothesis,
contains(boxb,apples),
boxb_contains_apples ).
cnf(c_0_37,hypothesis,
$false,
inference(cn,[status(thm)],[inference(rw,[status(thm)],[inference(spm,[status(thm)],[c_0_34,c_0_35]),c_0_36])]),
[proof] ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ012-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% 0.00/0.05 % Command : run_E /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.38 % Computer : n016.cluster.edu
% 0.12/0.38 % Model : x86_64 x86_64
% 0.12/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.38 % Memory : 8046.5625MB
% 0.12/0.38 % OS : Linux 6.8.0-71-generic
% 0.12/0.38 % CPULimit : 300
% 0.12/0.38 % WCLimit : 300
% 0.12/0.38 % DateTime : Mon Sep 21 03:49:53 UTC 2026
% 0.12/0.38 % CPUTime :
% 0.12/0.38 Running run_E /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.43 Running first-order theorem proving
% 0.12/0.43 Running: /export/starexec/sandbox2/solver/bin/eprover --delete-bad-limit=2000000000 --definitional-cnf=24 -s --print-statistics -R --print-version --proof-object --auto-schedule=8 --cpu-limit=300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.12/0.44 % Version: 3.5.1
% 0.12/0.44 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.12/0.44 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.12/0.44 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.12/0.44 % Starting new_bool_3 with 300s (1) cores
% 0.12/0.44 % Starting new_bool_1 with 300s (1) cores
% 0.12/0.44 % Starting sh5l with 300s (1) cores
% 0.12/0.44 % new_bool_3 with pid 1481789 completed with status 0
% 0.12/0.44 % Result found by new_bool_3
% 0.12/0.44 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.12/0.44 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.12/0.44 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.12/0.44 % Starting new_bool_3 with 300s (1) cores
% 0.12/0.44 % (lift_lambdas = 0, lambda_to_forall = 0,unroll_only_formulas = 0, sine = GSinE(CountFormulas,hypos,1.5,,3,20000,1.0))
% 0.12/0.44 % SinE strategy is GSinE(CountFormulas,hypos,1.5,,3,20000,1.0)
% 0.12/0.44 % Search class: FGHNS-FFSS00-SFFFFFNN
% 0.12/0.44 % partial match(1): FGHNF-FFSS00-SFFFFFNN
% 0.12/0.44 % Scheduled 5 strats onto 1 cores with 300 seconds (300 total)
% 0.12/0.44 % Starting SubtermCWHack with 31s (1) cores
% 0.12/0.44 % SubtermCWHack with pid 1481793 completed with status 0
% 0.12/0.45 % Result found by SubtermCWHack
% 0.12/0.45 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.12/0.45 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.12/0.45 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.12/0.45 % Starting new_bool_3 with 300s (1) cores
% 0.12/0.45 % (lift_lambdas = 0, lambda_to_forall = 0,unroll_only_formulas = 0, sine = GSinE(CountFormulas,hypos,1.5,,3,20000,1.0))
% 0.12/0.45 % SinE strategy is GSinE(CountFormulas,hypos,1.5,,3,20000,1.0)
% 0.12/0.45 % Search class: FGHNS-FFSS00-SFFFFFNN
% 0.12/0.45 % partial match(1): FGHNF-FFSS00-SFFFFFNN
% 0.12/0.45 % Scheduled 5 strats onto 1 cores with 300 seconds (300 total)
% 0.12/0.45 % Starting SubtermCWHack with 31s (1) cores
% 0.12/0.45 % Preprocessing time : 0.001 s
% 0.12/0.45
% 0.12/0.45 % Proof found!
% 0.12/0.45 % SZS status Unsatisfiable
% 0.12/0.45 % SZS output start CNFRefutation
% See solution above
% 0.12/0.45 % Parsed axioms : 18
% 0.12/0.45 % Removed by relevancy pruning/SinE : 0
% 0.12/0.45 % Initial clauses : 18
% 0.12/0.45 % Removed in clause preprocessing : 0
% 0.12/0.45 % Initial clauses in saturation : 18
% 0.12/0.45 % Processed clauses : 31
% 0.12/0.45 % ...of these trivial : 0
% 0.12/0.45 % ...subsumed : 1
% 0.12/0.45 % ...remaining for further processing : 30
% 0.12/0.45 % Other redundant clauses eliminated : 0
% 0.12/0.45 % Clauses deleted for lack of memory : 0
% 0.12/0.45 % Backward-subsumed : 2
% 0.12/0.45 % Backward-rewritten : 1
% 0.12/0.45 % Generated clauses : 21
% 0.12/0.45 % ...of the previous two non-redundant : 19
% 0.12/0.45 % ...aggressively subsumed : 0
% 0.12/0.45 % Contextual simplify-reflections : 0
% 0.12/0.45 % Paramodulations : 20
% 0.12/0.45 % Factorizations : 0
% 0.12/0.45 % NegExts : 0
% 0.12/0.45 % Equation resolutions : 0
% 0.12/0.45 % Disequality decompositions : 0
% 0.12/0.45 % Total rewrite steps : 3
% 0.12/0.45 % ...of those cached : 1
% 0.12/0.45 % Propositional unsat checks : 0
% 0.12/0.45 % Propositional check models : 0
% 0.12/0.45 % Propositional check unsatisfiable : 0
% 0.12/0.45 % Propositional clauses : 0
% 0.12/0.45 % Propositional clauses after purity: 0
% 0.12/0.45 % Propositional unsat core size : 0
% 0.12/0.45 % Propositional preprocessing time : 0.000
% 0.12/0.45 % Propositional encoding time : 0.000
% 0.12/0.45 % Propositional solver time : 0.000
% 0.12/0.45 % Success case prop preproc time : 0.000
% 0.12/0.45 % Success case prop encoding time : 0.000
% 0.12/0.45 % Success case prop solver time : 0.000
% 0.12/0.45 % Current number of processed clauses : 26
% 0.12/0.45 % Positive orientable unit clauses : 8
% 0.12/0.45 % Positive unorientable unit clauses: 0
% 0.12/0.45 % Negative unit clauses : 10
% 0.12/0.45 % Non-unit-clauses : 8
% 0.12/0.45 % Current number of unprocessed clauses: 6
% 0.12/0.45 % ...number of literals in the above : 20
% 0.12/0.45 % Current number of archived formulas : 0
% 0.12/0.45 % Current number of archived clauses : 4
% 0.12/0.45 % Clause-clause subsumption calls (NU) : 15
% 0.12/0.45 % Rec. Clause-clause subsumption calls : 12
% 0.12/0.45 % Non-unit clause-clause subsumptions : 0
% 0.12/0.45 % Unit Clause-clause subsumption calls : 11
% 0.12/0.45 % Rewrite failures with RHS unbound : 0
% 0.12/0.45 % BW rewrite match attempts : 1
% 0.12/0.45 % BW rewrite match successes : 1
% 0.12/0.45 % Condensation attempts : 0
% 0.12/0.45 % Condensation successes : 0
% 0.12/0.45 % Termbank termtop insertions : 482
% 0.12/0.45 % Search garbage collected termcells : 30
% 0.12/0.45
% 0.12/0.45 % -------------------------------------------------
% 0.12/0.45 % User time : 0.004 s
% 0.12/0.45 % System time : 0.000 s
% 0.12/0.45 % Total time : 0.004 s
% 0.12/0.45 % Maximum resident set size: 3636 pages
% 0.12/0.45
% 0.12/0.45 % -------------------------------------------------
% 0.12/0.45 % User time : 0.005 s
% 0.12/0.45 % System time : 0.004 s
% 0.12/0.45 % Total time : 0.010 s
% 0.12/0.45 % Maximum resident set size: 4608 pages
% 0.12/0.45 % E exiting
%------------------------------------------------------------------------------