%------------------------------------------------------------------------------
% File : E-SAT---3.5.1
% Problem : PLA003-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_E /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n004.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 01:58:59 PM UTC 2026
% Result : Unsatisfiable 0.12s 0.44s
% Output : CNFRefutation 0.12s
% Verified :
% SZS Type : Refutation
% Derivation depth : 6
% Number of leaves : 8
% Syntax : Number of clauses : 30 ( 11 unt; 0 nHn; 20 RR)
% Number of literals : 49 ( 0 equ; 24 neg)
% Maximal clause size : 2 ( 1 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 2 ( 1 usr; 1 prp; 0-3 aty)
% Number of functors : 11 ( 11 usr; 8 con; 0-3 aty)
% Number of variables : 79 ( 23 sgn)
% Comments :
%------------------------------------------------------------------------------
cnf(go_holding_ladder,axiom,
( ~ can(monkey(X3,floor,the_ladder),ladder(X3,floor),X2)
| can(monkey(X1,floor,the_ladder),ladder(X1,floor),X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',go_holding_ladder) ).
cnf(grab_ladder,axiom,
( ~ can(monkey(X1,X2,nothing),ladder(X1,X2),X3)
| can(monkey(X1,X2,the_ladder),ladder(X1,X2),X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',grab_ladder) ).
cnf(go_holding_nothing,axiom,
( ~ can(monkey(X4,floor,nothing),X2,X3)
| can(monkey(X1,floor,nothing),X2,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',go_holding_nothing) ).
cnf(grab_bananas,axiom,
( ~ can(monkey(X1,X2,nothing),X3,bananas(X1,X2))
| can(monkey(X1,X2,the_bananas),X3,bananas(X1,X2)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',grab_bananas) ).
cnf(prove_the_monkey_can_get_the_bananas,negated_conjecture,
~ can(monkey(X1,X2,the_bananas),X3,X4),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_the_monkey_can_get_the_bananas) ).
cnf(initial_situation,hypothesis,
can(monkey(l0,floor,nothing),ladder(l1,floor),bananas(l2,ceiling)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',initial_situation) ).
cnf(climb_up,axiom,
( ~ can(monkey(X1,floor,nothing),ladder(X1,floor),X2)
| can(monkey(X1,ceiling,nothing),ladder(X1,floor),X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',climb_up) ).
cnf(drop_ladder,axiom,
( ~ can(monkey(X1,X2,the_ladder),ladder(X1,X4),X3)
| can(monkey(X1,X2,nothing),ladder(X1,floor),X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',drop_ladder) ).
cnf(c_0_8,plain,
( ~ can(monkey(X3,floor,the_ladder),ladder(X3,floor),X2)
| can(monkey(X1,floor,the_ladder),ladder(X1,floor),X2) ),
inference(fof_simplification,[status(thm)],[go_holding_ladder]) ).
cnf(c_0_9,plain,
( ~ can(monkey(X1,X2,nothing),ladder(X1,X2),X3)
| can(monkey(X1,X2,the_ladder),ladder(X1,X2),X3) ),
inference(fof_simplification,[status(thm)],[grab_ladder]) ).
cnf(c_0_10,plain,
( ~ can(monkey(X4,floor,nothing),X2,X3)
| can(monkey(X1,floor,nothing),X2,X3) ),
inference(fof_simplification,[status(thm)],[go_holding_nothing]) ).
cnf(c_0_11,plain,
( ~ can(monkey(X1,X2,nothing),X3,bananas(X1,X2))
| can(monkey(X1,X2,the_bananas),X3,bananas(X1,X2)) ),
inference(fof_simplification,[status(thm)],[grab_bananas]) ).
cnf(c_0_12,negated_conjecture,
~ can(monkey(X1,X2,the_bananas),X3,X4),
inference(fof_simplification,[status(thm)],[prove_the_monkey_can_get_the_bananas]) ).
cnf(c_0_13,plain,
( ~ can(monkey(X3,floor,the_ladder),ladder(X3,floor),X2)
| can(monkey(X1,floor,the_ladder),ladder(X1,floor),X2) ),
c_0_8 ).
cnf(c_0_14,plain,
( ~ can(monkey(X1,X2,nothing),ladder(X1,X2),X3)
| can(monkey(X1,X2,the_ladder),ladder(X1,X2),X3) ),
c_0_9 ).
cnf(c_0_15,plain,
( ~ can(monkey(X4,floor,nothing),X2,X3)
| can(monkey(X1,floor,nothing),X2,X3) ),
c_0_10 ).
cnf(c_0_16,hypothesis,
can(monkey(l0,floor,nothing),ladder(l1,floor),bananas(l2,ceiling)),
initial_situation ).
cnf(c_0_17,plain,
( ~ can(monkey(X1,X2,nothing),X3,bananas(X1,X2))
| can(monkey(X1,X2,the_bananas),X3,bananas(X1,X2)) ),
c_0_11 ).
cnf(c_0_18,negated_conjecture,
~ can(monkey(X1,X2,the_bananas),X3,X4),
c_0_12 ).
cnf(c_0_19,plain,
( ~ can(monkey(X1,floor,nothing),ladder(X1,floor),X2)
| can(monkey(X1,ceiling,nothing),ladder(X1,floor),X2) ),
inference(fof_simplification,[status(thm)],[climb_up]) ).
cnf(c_0_20,plain,
( ~ can(monkey(X1,X2,the_ladder),ladder(X1,X4),X3)
| can(monkey(X1,X2,nothing),ladder(X1,floor),X3) ),
inference(fof_simplification,[status(thm)],[drop_ladder]) ).
cnf(c_0_21,plain,
( ~ can(monkey(X3,floor,nothing),ladder(X3,floor),X2)
| can(monkey(X1,floor,the_ladder),ladder(X1,floor),X2) ),
inference(spm,[status(thm)],[c_0_13,c_0_14]) ).
cnf(c_0_22,hypothesis,
can(monkey(X1,floor,nothing),ladder(l1,floor),bananas(l2,ceiling)),
inference(spm,[status(thm)],[c_0_15,c_0_16]) ).
cnf(c_0_23,plain,
~ can(monkey(X1,X2,nothing),X3,bananas(X1,X2)),
inference(sr,[status(thm)],[c_0_17,c_0_18]) ).
cnf(c_0_24,plain,
( ~ can(monkey(X1,floor,nothing),ladder(X1,floor),X2)
| can(monkey(X1,ceiling,nothing),ladder(X1,floor),X2) ),
c_0_19 ).
cnf(c_0_25,plain,
( ~ can(monkey(X1,X2,the_ladder),ladder(X1,X4),X3)
| can(monkey(X1,X2,nothing),ladder(X1,floor),X3) ),
c_0_20 ).
cnf(c_0_26,hypothesis,
can(monkey(X1,floor,the_ladder),ladder(X1,floor),bananas(l2,ceiling)),
inference(spm,[status(thm)],[c_0_21,c_0_22]) ).
cnf(c_0_27,plain,
~ can(monkey(X1,floor,nothing),ladder(X1,floor),bananas(X1,ceiling)),
inference(spm,[status(thm)],[c_0_23,c_0_24]) ).
cnf(c_0_28,hypothesis,
can(monkey(X1,floor,nothing),ladder(X1,floor),bananas(l2,ceiling)),
inference(spm,[status(thm)],[c_0_25,c_0_26]) ).
cnf(c_0_29,hypothesis,
$false,
inference(spm,[status(thm)],[c_0_27,c_0_28]),
[proof] ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PLA003-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_E /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.37 % Computer : n004.cluster.edu
% 0.12/0.37 % Model : x86_64 x86_64
% 0.12/0.37 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.37 % Memory : 8046.5625MB
% 0.12/0.37 % OS : Linux 6.8.0-71-generic
% 0.12/0.37 % CPULimit : 300
% 0.12/0.37 % WCLimit : 300
% 0.12/0.37 % DateTime : Mon Sep 21 03:31:20 UTC 2026
% 0.12/0.38 % CPUTime :
% 0.12/0.38 Running run_E /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.42 Running first-order theorem proving
% 0.12/0.42 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: FSMSSMSMSSSNFFN.
% 0.12/0.44 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.12/0.44 % Starting G-E--_207_C18_F1_SE_CS_SP_PI_PS_S2SI 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 % sh5l with pid 2153276 completed with status 0
% 0.12/0.44 % Result found by sh5l
% 0.12/0.44 % Preprocessing class: FSMSSMSMSSSNFFN.
% 0.12/0.44 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.12/0.44 % Starting G-E--_207_C18_F1_SE_CS_SP_PI_PS_S2SI 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 % (lift_lambdas = 0, lambda_to_forall = 0,unroll_only_formulas = 0, sine = gf500_gu_R04_F100_L20000)
% 0.12/0.44 % SinE strategy is gf500_gu_R04_F100_L20000
% 0.12/0.44 % Search class: FHUNF-FFSF32-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 2153278 completed with status 0
% 0.12/0.44 % Result found by SubtermCWHack
% 0.12/0.44 % Preprocessing class: FSMSSMSMSSSNFFN.
% 0.12/0.44 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.12/0.44 % Starting G-E--_207_C18_F1_SE_CS_SP_PI_PS_S2SI 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 % (lift_lambdas = 0, lambda_to_forall = 0,unroll_only_formulas = 0, sine = gf500_gu_R04_F100_L20000)
% 0.12/0.44 % SinE strategy is gf500_gu_R04_F100_L20000
% 0.12/0.44 % Search class: FHUNF-FFSF32-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 % Preprocessing time : 0.001 s
% 0.12/0.44
% 0.12/0.44 % Proof found!
% 0.12/0.44 % SZS status Unsatisfiable
% 0.12/0.44 % SZS output start CNFRefutation
% See solution above
% 0.12/0.44 % Parsed axioms : 11
% 0.12/0.44 % Removed by relevancy pruning/SinE : 0
% 0.12/0.44 % Initial clauses : 11
% 0.12/0.44 % Removed in clause preprocessing : 0
% 0.12/0.44 % Initial clauses in saturation : 11
% 0.12/0.44 % Processed clauses : 16
% 0.12/0.44 % ...of these trivial : 0
% 0.12/0.44 % ...subsumed : 2
% 0.12/0.44 % ...remaining for further processing : 14
% 0.12/0.44 % Other redundant clauses eliminated : 0
% 0.12/0.44 % Clauses deleted for lack of memory : 0
% 0.12/0.44 % Backward-subsumed : 0
% 0.12/0.44 % Backward-rewritten : 1
% 0.12/0.44 % Generated clauses : 12
% 0.12/0.44 % ...of the previous two non-redundant : 7
% 0.12/0.44 % ...aggressively subsumed : 0
% 0.12/0.44 % Contextual simplify-reflections : 0
% 0.12/0.44 % Paramodulations : 12
% 0.12/0.44 % Factorizations : 0
% 0.12/0.44 % NegExts : 0
% 0.12/0.44 % Equation resolutions : 0
% 0.12/0.44 % Disequality decompositions : 0
% 0.12/0.44 % Total rewrite steps : 3
% 0.12/0.44 % ...of those cached : 0
% 0.12/0.44 % Propositional unsat checks : 0
% 0.12/0.44 % Propositional check models : 0
% 0.12/0.44 % Propositional check unsatisfiable : 0
% 0.12/0.44 % Propositional clauses : 0
% 0.12/0.44 % Propositional clauses after purity: 0
% 0.12/0.44 % Propositional unsat core size : 0
% 0.12/0.44 % Propositional preprocessing time : 0.000
% 0.12/0.44 % Propositional encoding time : 0.000
% 0.12/0.44 % Propositional solver time : 0.000
% 0.12/0.44 % Success case prop preproc time : 0.000
% 0.12/0.44 % Success case prop encoding time : 0.000
% 0.12/0.44 % Success case prop solver time : 0.000
% 0.12/0.44 % Current number of processed clauses : 13
% 0.12/0.44 % Positive orientable unit clauses : 3
% 0.12/0.44 % Positive unorientable unit clauses: 0
% 0.12/0.44 % Negative unit clauses : 3
% 0.12/0.44 % Non-unit-clauses : 7
% 0.12/0.44 % Current number of unprocessed clauses: 1
% 0.12/0.44 % ...number of literals in the above : 2
% 0.12/0.44 % Current number of archived formulas : 0
% 0.12/0.44 % Current number of archived clauses : 1
% 0.12/0.44 % Clause-clause subsumption calls (NU) : 8
% 0.12/0.44 % Rec. Clause-clause subsumption calls : 8
% 0.12/0.44 % Non-unit clause-clause subsumptions : 0
% 0.12/0.44 % Unit Clause-clause subsumption calls : 0
% 0.12/0.44 % Rewrite failures with RHS unbound : 0
% 0.12/0.44 % BW rewrite match attempts : 14
% 0.12/0.44 % BW rewrite match successes : 1
% 0.12/0.44 % Condensation attempts : 0
% 0.12/0.44 % Condensation successes : 0
% 0.12/0.44 % Termbank termtop insertions : 667
% 0.12/0.44 % Search garbage collected termcells : 26
% 0.12/0.44
% 0.12/0.44 % -------------------------------------------------
% 0.12/0.44 % User time : 0.002 s
% 0.12/0.44 % System time : 0.003 s
% 0.12/0.44 % Total time : 0.005 s
% 0.12/0.44 % Maximum resident set size: 3588 pages
% 0.12/0.44
% 0.12/0.44 % -------------------------------------------------
% 0.12/0.44 % User time : 0.004 s
% 0.12/0.44 % System time : 0.007 s
% 0.12/0.44 % Total time : 0.011 s
% 0.12/0.44 % Maximum resident set size: 4864 pages
% 0.12/0.44 % E exiting
%------------------------------------------------------------------------------