%------------------------------------------------------------------------------
% File : E---3.5.1
% Problem : PUZ001-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_E /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n001.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 02:01:19 PM UTC 2026
% Result : Unsatisfiable 0.13s 0.42s
% Output : CNFRefutation 0.13s
% Verified :
% SZS Type : Refutation
% Derivation depth : 6
% Number of leaves : 10
% Syntax : Number of clauses : 33 ( 9 unt; 8 nHn; 33 RR)
% Number of literals : 64 ( 0 equ; 32 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 : 3 ( 3 usr; 3 con; 0-0 aty)
% Number of variables : 25 ( 0 sgn)
% Comments :
%------------------------------------------------------------------------------
cnf(killer_hates_victim,hypothesis,
( ~ killed(X1,X2)
| hates(X1,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',killer_hates_victim) ).
cnf(poorer_killer,hypothesis,
( ~ richer(X1,X2)
| ~ killed(X1,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',poorer_killer) ).
cnf(butler_hates_poor,hypothesis,
( ~ lives(X1)
| hates(butler,X1)
| richer(X1,agatha) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',butler_hates_poor) ).
cnf(prove_neither_charles_nor_butler_did_it,negated_conjecture,
( killed(charles,agatha)
| killed(butler,agatha) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_neither_charles_nor_butler_did_it) ).
cnf(different_hates,hypothesis,
( ~ hates(charles,X1)
| ~ hates(agatha,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',different_hates) ).
cnf(butler,hypothesis,
lives(butler),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',butler) ).
cnf(no_one_hates_everyone,hypothesis,
( ~ hates(X1,charles)
| ~ hates(X1,butler)
| ~ hates(X1,agatha) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',no_one_hates_everyone) ).
cnf(same_hates,hypothesis,
( ~ hates(agatha,X1)
| hates(butler,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',same_hates) ).
cnf(agatha_hates_agatha,hypothesis,
hates(agatha,agatha),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',agatha_hates_agatha) ).
cnf(agatha_hates_charles,hypothesis,
hates(agatha,charles),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',agatha_hates_charles) ).
cnf(c_0_10,hypothesis,
( ~ killed(X1,X2)
| hates(X1,X2) ),
inference(fof_simplification,[status(thm)],[killer_hates_victim]) ).
cnf(c_0_11,hypothesis,
( ~ richer(X1,X2)
| ~ killed(X1,X2) ),
inference(fof_simplification,[status(thm)],[poorer_killer]) ).
cnf(c_0_12,hypothesis,
( ~ lives(X1)
| hates(butler,X1)
| richer(X1,agatha) ),
inference(fof_simplification,[status(thm)],[butler_hates_poor]) ).
cnf(c_0_13,hypothesis,
( ~ killed(X1,X2)
| hates(X1,X2) ),
c_0_10 ).
cnf(c_0_14,negated_conjecture,
( killed(charles,agatha)
| killed(butler,agatha) ),
prove_neither_charles_nor_butler_did_it ).
cnf(c_0_15,hypothesis,
( ~ richer(X1,X2)
| ~ killed(X1,X2) ),
c_0_11 ).
cnf(c_0_16,hypothesis,
( ~ lives(X1)
| hates(butler,X1)
| richer(X1,agatha) ),
c_0_12 ).
cnf(c_0_17,hypothesis,
( ~ hates(charles,X1)
| ~ hates(agatha,X1) ),
inference(fof_simplification,[status(thm)],[different_hates]) ).
cnf(c_0_18,negated_conjecture,
( killed(butler,agatha)
| hates(charles,agatha) ),
inference(spm,[status(thm)],[c_0_13,c_0_14]) ).
cnf(c_0_19,hypothesis,
( ~ lives(X1)
| ~ killed(X1,agatha)
| hates(butler,X1) ),
inference(spm,[status(thm)],[c_0_15,c_0_16]) ).
cnf(c_0_20,hypothesis,
lives(butler),
butler ).
cnf(c_0_21,hypothesis,
( ~ hates(X1,charles)
| ~ hates(X1,butler)
| ~ hates(X1,agatha) ),
inference(fof_simplification,[status(thm)],[no_one_hates_everyone]) ).
cnf(c_0_22,hypothesis,
( ~ hates(agatha,X1)
| hates(butler,X1) ),
inference(fof_simplification,[status(thm)],[same_hates]) ).
cnf(c_0_23,hypothesis,
( ~ hates(charles,X1)
| ~ hates(agatha,X1) ),
c_0_17 ).
cnf(c_0_24,hypothesis,
( hates(butler,agatha)
| hates(charles,agatha) ),
inference(spm,[status(thm)],[c_0_13,c_0_18]) ).
cnf(c_0_25,hypothesis,
hates(agatha,agatha),
agatha_hates_agatha ).
cnf(c_0_26,negated_conjecture,
( hates(butler,butler)
| hates(charles,agatha) ),
inference(cn,[status(thm)],[inference(rw,[status(thm)],[inference(spm,[status(thm)],[c_0_19,c_0_18]),c_0_20])]) ).
cnf(c_0_27,hypothesis,
( ~ hates(X1,charles)
| ~ hates(X1,butler)
| ~ hates(X1,agatha) ),
c_0_21 ).
cnf(c_0_28,hypothesis,
( ~ hates(agatha,X1)
| hates(butler,X1) ),
c_0_22 ).
cnf(c_0_29,hypothesis,
hates(butler,agatha),
inference(cn,[status(thm)],[inference(rw,[status(thm)],[inference(spm,[status(thm)],[c_0_23,c_0_24]),c_0_25])]) ).
cnf(c_0_30,hypothesis,
hates(butler,butler),
inference(cn,[status(thm)],[inference(rw,[status(thm)],[inference(spm,[status(thm)],[c_0_23,c_0_26]),c_0_25])]) ).
cnf(c_0_31,hypothesis,
hates(agatha,charles),
agatha_hates_charles ).
cnf(c_0_32,hypothesis,
$false,
inference(cn,[status(thm)],[inference(rw,[status(thm)],[inference(rw,[status(thm)],[inference(rw,[status(thm)],[inference(spm,[status(thm)],[c_0_27,c_0_28]),c_0_29]),c_0_30]),c_0_31])]),
[proof] ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ001-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.04 % Command : run_E /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.35 % Computer : n001.cluster.edu
% 0.09/0.35 % Model : x86_64 x86_64
% 0.09/0.35 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.35 % Memory : 8046.5625MB
% 0.09/0.35 % OS : Linux 6.8.0-71-generic
% 0.09/0.35 % CPULimit : 300
% 0.09/0.35 % WCLimit : 300
% 0.09/0.35 % DateTime : Mon Sep 21 03:49:43 UTC 2026
% 0.09/0.36 % CPUTime :
% 0.09/0.36 Running run_E /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.13/0.40 Running first-order theorem proving
% 0.13/0.40 Running: /export/starexec/sandbox/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/sandbox/benchmark/theBenchmark.p
% 0.13/0.42 % Version: 3.5.1
% 0.13/0.42 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.13/0.42 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.13/0.42 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.13/0.42 % Starting new_bool_3 with 300s (1) cores
% 0.13/0.42 % Starting new_bool_1 with 300s (1) cores
% 0.13/0.42 % Starting sh5l with 300s (1) cores
% 0.13/0.42 % new_bool_1 with pid 2118594 completed with status 0
% 0.13/0.42 % Result found by new_bool_1
% 0.13/0.42 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.13/0.42 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.13/0.42 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.13/0.42 % Starting new_bool_3 with 300s (1) cores
% 0.13/0.42 % Starting new_bool_1 with 300s (1) cores
% 0.13/0.42 % (lift_lambdas = 0, lambda_to_forall = 0,unroll_only_formulas = 0, sine = GSinE(CountFormulas,hypos,1.5,,3,20000,1.0))
% 0.13/0.42 % SinE strategy is GSinE(CountFormulas,hypos,1.5,,3,20000,1.0)
% 0.13/0.42 % Search class: FGHNF-FFSM00-SFFFFFNN
% 0.13/0.42 % Scheduled 5 strats onto 1 cores with 300 seconds (300 total)
% 0.13/0.42 % Starting SubtermCWHack with 31s (1) cores
% 0.13/0.42 % SubtermCWHack with pid 2118596 completed with status 0
% 0.13/0.42 % Result found by SubtermCWHack
% 0.13/0.42 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.13/0.42 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.13/0.42 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.13/0.42 % Starting new_bool_3 with 300s (1) cores
% 0.13/0.42 % Starting new_bool_1 with 300s (1) cores
% 0.13/0.42 % (lift_lambdas = 0, lambda_to_forall = 0,unroll_only_formulas = 0, sine = GSinE(CountFormulas,hypos,1.5,,3,20000,1.0))
% 0.13/0.42 % SinE strategy is GSinE(CountFormulas,hypos,1.5,,3,20000,1.0)
% 0.13/0.42 % Search class: FGHNF-FFSM00-SFFFFFNN
% 0.13/0.42 % Scheduled 5 strats onto 1 cores with 300 seconds (300 total)
% 0.13/0.42 % Starting SubtermCWHack with 31s (1) cores
% 0.13/0.42 % Preprocessing time : 0.001 s
% 0.13/0.42
% 0.13/0.42 % Proof found!
% 0.13/0.42 % SZS status Unsatisfiable
% 0.13/0.42 % SZS output start CNFRefutation
% See solution above
% 0.13/0.42 % Parsed axioms : 12
% 0.13/0.42 % Removed by relevancy pruning/SinE : 0
% 0.13/0.42 % Initial clauses : 12
% 0.13/0.42 % Removed in clause preprocessing : 0
% 0.13/0.42 % Initial clauses in saturation : 12
% 0.13/0.42 % Processed clauses : 20
% 0.13/0.42 % ...of these trivial : 1
% 0.13/0.42 % ...subsumed : 0
% 0.13/0.42 % ...remaining for further processing : 19
% 0.13/0.42 % Other redundant clauses eliminated : 0
% 0.13/0.42 % Clauses deleted for lack of memory : 0
% 0.13/0.42 % Backward-subsumed : 0
% 0.13/0.42 % Backward-rewritten : 2
% 0.13/0.42 % Generated clauses : 11
% 0.13/0.42 % ...of the previous two non-redundant : 8
% 0.13/0.42 % ...aggressively subsumed : 0
% 0.13/0.42 % Contextual simplify-reflections : 0
% 0.13/0.42 % Paramodulations : 11
% 0.13/0.42 % Factorizations : 0
% 0.13/0.42 % NegExts : 0
% 0.13/0.42 % Equation resolutions : 0
% 0.13/0.42 % Disequality decompositions : 0
% 0.13/0.42 % Total rewrite steps : 12
% 0.13/0.42 % ...of those cached : 6
% 0.13/0.42 % Propositional unsat checks : 0
% 0.13/0.42 % Propositional check models : 0
% 0.13/0.42 % Propositional check unsatisfiable : 0
% 0.13/0.42 % Propositional clauses : 0
% 0.13/0.42 % Propositional clauses after purity: 0
% 0.13/0.42 % Propositional unsat core size : 0
% 0.13/0.42 % Propositional preprocessing time : 0.000
% 0.13/0.42 % Propositional encoding time : 0.000
% 0.13/0.42 % Propositional solver time : 0.000
% 0.13/0.42 % Success case prop preproc time : 0.000
% 0.13/0.42 % Success case prop encoding time : 0.000
% 0.13/0.42 % Success case prop solver time : 0.000
% 0.13/0.42 % Current number of processed clauses : 17
% 0.13/0.42 % Positive orientable unit clauses : 7
% 0.13/0.42 % Positive unorientable unit clauses: 0
% 0.13/0.42 % Negative unit clauses : 0
% 0.13/0.42 % Non-unit-clauses : 10
% 0.13/0.42 % Current number of unprocessed clauses: 0
% 0.13/0.42 % ...number of literals in the above : 0
% 0.13/0.42 % Current number of archived formulas : 0
% 0.13/0.42 % Current number of archived clauses : 2
% 0.13/0.42 % Clause-clause subsumption calls (NU) : 11
% 0.13/0.42 % Rec. Clause-clause subsumption calls : 9
% 0.13/0.42 % Non-unit clause-clause subsumptions : 0
% 0.13/0.42 % Unit Clause-clause subsumption calls : 3
% 0.13/0.42 % Rewrite failures with RHS unbound : 0
% 0.13/0.42 % BW rewrite match attempts : 2
% 0.13/0.42 % BW rewrite match successes : 2
% 0.13/0.42 % Condensation attempts : 0
% 0.13/0.42 % Condensation successes : 0
% 0.13/0.42 % Termbank termtop insertions : 365
% 0.13/0.42 % Search garbage collected termcells : 23
% 0.13/0.42
% 0.13/0.42 % -------------------------------------------------
% 0.13/0.42 % User time : 0.002 s
% 0.13/0.42 % System time : 0.002 s
% 0.13/0.42 % Total time : 0.004 s
% 0.13/0.42 % Maximum resident set size: 3632 pages
% 0.13/0.42
% 0.13/0.42 % -------------------------------------------------
% 0.13/0.42 % User time : 0.006 s
% 0.13/0.42 % System time : 0.004 s
% 0.13/0.42 % Total time : 0.010 s
% 0.13/0.42 % Maximum resident set size: 4864 pages
% 0.13/0.42 % E exiting
%------------------------------------------------------------------------------