%------------------------------------------------------------------------------
% File : E---3.5.1
% Problem : PUZ026-1 : 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 : n019.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 02:01:35 PM UTC 2026
% Result : Unsatisfiable 0.26s 0.58s
% Output : CNFRefutation 0.26s
% Verified :
% SZS Type : Refutation
% Derivation depth : 13
% Number of leaves : 15
% Syntax : Number of clauses : 59 ( 15 unt; 15 nHn; 55 RR)
% Number of literals : 134 ( 0 equ; 83 neg)
% Maximal clause size : 4 ( 2 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of predicates : 3 ( 2 usr; 1 prp; 0-3 aty)
% Number of functors : 8 ( 8 usr; 3 con; 0-2 aty)
% Number of variables : 67 ( 24 sgn)
% Comments :
%------------------------------------------------------------------------------
cnf(liars_lie,axiom,
( ~ a_truth(X2)
| ~ a_truth(says(X1,X2))
| ~ a_truth(liar(X1)) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ003-0.ax',liars_lie) ).
cnf(c_says_c_not_normal,hypothesis,
a_truth(says(c,not_normal(c))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',c_says_c_not_normal) ).
cnf(not_liar_and_normal,axiom,
( ~ a_truth(normal(X1))
| ~ a_truth(liar(X1)) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ003-0.ax',not_liar_and_normal) ).
cnf(normal_or_not_normal,axiom,
( a_truth(normal(X1))
| a_truth(not_normal(X1)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',normal_or_not_normal) ).
cnf(prove_one_of_each,negated_conjecture,
( ~ a_truth(truthteller(X3))
| ~ a_truth(normal(X2))
| ~ a_truth(liar(X1)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_one_of_each) ).
cnf(person_is_one_type,axiom,
( a_truth(normal(X1))
| a_truth(liar(X1))
| a_truth(truthteller(X1)) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ003-0.ax',person_is_one_type) ).
cnf(liars_and_normal_lie,axiom,
( ~ a_truth(says(X2,X1))
| a_truth(normal(X2))
| a_truth(liar(X2))
| a_truth(X1) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ003-0.ax',liars_and_normal_lie) ).
cnf(not_two_liars2,axiom,
( ~ a_truth(liar(X3))
| ~ a_truth(liar(X1))
| ~ people(X1,X2,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_two_liars2) ).
cnf(not_two_truthtellers1,axiom,
( ~ a_truth(truthteller(X2))
| ~ a_truth(truthteller(X1))
| ~ people(X1,X2,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_two_truthtellers1) ).
cnf(b_says_a_normal,hypothesis,
a_truth(says(b,normal(a))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b_says_a_normal) ).
cnf(a_says_a_normal,hypothesis,
a_truth(says(a,normal(a))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',a_says_a_normal) ).
cnf(b_c_a_are_people,hypothesis,
people(b,c,a),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b_c_a_are_people) ).
cnf(c_b_a_are_people,hypothesis,
people(c,b,a),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',c_b_a_are_people) ).
cnf(not_two_normal2,axiom,
( ~ a_truth(normal(X3))
| ~ a_truth(normal(X1))
| ~ people(X1,X2,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_two_normal2) ).
cnf(not_two_normal1,axiom,
( ~ a_truth(normal(X2))
| ~ a_truth(normal(X1))
| ~ people(X1,X2,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_two_normal1) ).
cnf(c_0_15,plain,
( ~ a_truth(X2)
| ~ a_truth(says(X1,X2))
| ~ a_truth(liar(X1)) ),
inference(fof_simplification,[status(thm)],[liars_lie]) ).
cnf(c_0_16,plain,
( ~ a_truth(X2)
| ~ a_truth(says(X1,X2))
| ~ a_truth(liar(X1)) ),
c_0_15 ).
cnf(c_0_17,hypothesis,
a_truth(says(c,not_normal(c))),
c_says_c_not_normal ).
cnf(c_0_18,plain,
( ~ a_truth(normal(X1))
| ~ a_truth(liar(X1)) ),
inference(fof_simplification,[status(thm)],[not_liar_and_normal]) ).
cnf(c_0_19,hypothesis,
( ~ a_truth(not_normal(c))
| ~ a_truth(liar(c)) ),
inference(spm,[status(thm)],[c_0_16,c_0_17]) ).
cnf(c_0_20,axiom,
( a_truth(normal(X1))
| a_truth(not_normal(X1)) ),
normal_or_not_normal ).
cnf(c_0_21,plain,
( ~ a_truth(normal(X1))
| ~ a_truth(liar(X1)) ),
c_0_18 ).
cnf(c_0_22,negated_conjecture,
( ~ a_truth(truthteller(X3))
| ~ a_truth(normal(X2))
| ~ a_truth(liar(X1)) ),
inference(fof_simplification,[status(thm)],[prove_one_of_each]) ).
cnf(c_0_23,hypothesis,
~ a_truth(liar(c)),
inference(csr,[status(thm)],[inference(spm,[status(thm)],[c_0_19,c_0_20]),c_0_21]) ).
cnf(c_0_24,axiom,
( a_truth(normal(X1))
| a_truth(liar(X1))
| a_truth(truthteller(X1)) ),
person_is_one_type ).
cnf(c_0_25,plain,
( ~ a_truth(says(X2,X1))
| a_truth(normal(X2))
| a_truth(liar(X2))
| a_truth(X1) ),
inference(fof_simplification,[status(thm)],[liars_and_normal_lie]) ).
cnf(c_0_26,plain,
( ~ a_truth(liar(X3))
| ~ a_truth(liar(X1))
| ~ people(X1,X2,X3) ),
inference(fof_simplification,[status(thm)],[not_two_liars2]) ).
cnf(c_0_27,plain,
( ~ a_truth(truthteller(X2))
| ~ a_truth(truthteller(X1))
| ~ people(X1,X2,X3) ),
inference(fof_simplification,[status(thm)],[not_two_truthtellers1]) ).
cnf(c_0_28,hypothesis,
a_truth(says(b,normal(a))),
b_says_a_normal ).
cnf(c_0_29,negated_conjecture,
( ~ a_truth(truthteller(X3))
| ~ a_truth(normal(X2))
| ~ a_truth(liar(X1)) ),
c_0_22 ).
cnf(c_0_30,hypothesis,
( a_truth(normal(c))
| a_truth(truthteller(c)) ),
inference(spm,[status(thm)],[c_0_23,c_0_24]) ).
cnf(c_0_31,plain,
( ~ a_truth(says(X2,X1))
| a_truth(normal(X2))
| a_truth(liar(X2))
| a_truth(X1) ),
c_0_25 ).
cnf(c_0_32,hypothesis,
a_truth(says(a,normal(a))),
a_says_a_normal ).
cnf(c_0_33,plain,
( ~ a_truth(liar(X3))
| ~ a_truth(liar(X1))
| ~ people(X1,X2,X3) ),
c_0_26 ).
cnf(c_0_34,hypothesis,
people(b,c,a),
b_c_a_are_people ).
cnf(c_0_35,plain,
( ~ a_truth(truthteller(X2))
| ~ a_truth(truthteller(X1))
| ~ people(X1,X2,X3) ),
c_0_27 ).
cnf(c_0_36,hypothesis,
people(c,b,a),
c_b_a_are_people ).
cnf(c_0_37,hypothesis,
( ~ a_truth(normal(a))
| ~ a_truth(liar(b)) ),
inference(spm,[status(thm)],[c_0_16,c_0_28]) ).
cnf(c_0_38,negated_conjecture,
( ~ a_truth(normal(X2))
| ~ a_truth(liar(X1))
| a_truth(normal(c)) ),
inference(spm,[status(thm)],[c_0_29,c_0_30]) ).
cnf(c_0_39,hypothesis,
( a_truth(normal(a))
| a_truth(liar(a)) ),
inference(spm,[status(thm)],[c_0_31,c_0_32]) ).
cnf(c_0_40,hypothesis,
( ~ a_truth(liar(b))
| ~ a_truth(liar(a)) ),
inference(spm,[status(thm)],[c_0_33,c_0_34]) ).
cnf(c_0_41,hypothesis,
( a_truth(normal(b))
| a_truth(liar(b))
| a_truth(normal(a)) ),
inference(spm,[status(thm)],[c_0_31,c_0_28]) ).
cnf(c_0_42,plain,
( ~ a_truth(normal(X3))
| ~ a_truth(normal(X1))
| ~ people(X1,X2,X3) ),
inference(fof_simplification,[status(thm)],[not_two_normal2]) ).
cnf(c_0_43,hypothesis,
( ~ a_truth(truthteller(c))
| ~ a_truth(truthteller(b)) ),
inference(spm,[status(thm)],[c_0_35,c_0_36]) ).
cnf(c_0_44,hypothesis,
( ~ a_truth(normal(a))
| a_truth(normal(b))
| a_truth(truthteller(b)) ),
inference(spm,[status(thm)],[c_0_37,c_0_24]) ).
cnf(c_0_45,hypothesis,
( ~ a_truth(normal(X1))
| a_truth(normal(c))
| a_truth(normal(a)) ),
inference(spm,[status(thm)],[c_0_38,c_0_39]) ).
cnf(c_0_46,hypothesis,
( a_truth(normal(a))
| a_truth(normal(b)) ),
inference(csr,[status(thm)],[inference(spm,[status(thm)],[c_0_40,c_0_41]),c_0_39]) ).
cnf(c_0_47,plain,
( ~ a_truth(normal(X3))
| ~ a_truth(normal(X1))
| ~ people(X1,X2,X3) ),
c_0_42 ).
cnf(c_0_48,hypothesis,
( ~ a_truth(normal(a))
| ~ a_truth(truthteller(c))
| a_truth(normal(b)) ),
inference(spm,[status(thm)],[c_0_43,c_0_44]) ).
cnf(c_0_49,hypothesis,
( a_truth(normal(a))
| a_truth(normal(c)) ),
inference(spm,[status(thm)],[c_0_45,c_0_46]) ).
cnf(c_0_50,hypothesis,
( ~ a_truth(normal(b))
| ~ a_truth(normal(a)) ),
inference(spm,[status(thm)],[c_0_47,c_0_34]) ).
cnf(c_0_51,hypothesis,
( a_truth(normal(b))
| a_truth(normal(c)) ),
inference(csr,[status(thm)],[inference(spm,[status(thm)],[c_0_48,c_0_30]),c_0_49]) ).
cnf(c_0_52,hypothesis,
( ~ a_truth(normal(c))
| ~ a_truth(normal(a)) ),
inference(spm,[status(thm)],[c_0_47,c_0_36]) ).
cnf(c_0_53,hypothesis,
a_truth(normal(c)),
inference(csr,[status(thm)],[inference(spm,[status(thm)],[c_0_50,c_0_51]),c_0_49]) ).
cnf(c_0_54,plain,
( ~ a_truth(normal(X2))
| ~ a_truth(normal(X1))
| ~ people(X1,X2,X3) ),
inference(fof_simplification,[status(thm)],[not_two_normal1]) ).
cnf(c_0_55,hypothesis,
~ a_truth(normal(a)),
inference(cn,[status(thm)],[inference(rw,[status(thm)],[c_0_52,c_0_53])]) ).
cnf(c_0_56,plain,
( ~ a_truth(normal(X2))
| ~ a_truth(normal(X1))
| ~ people(X1,X2,X3) ),
c_0_54 ).
cnf(c_0_57,hypothesis,
a_truth(normal(b)),
inference(sr,[status(thm)],[c_0_46,c_0_55]) ).
cnf(c_0_58,hypothesis,
$false,
inference(cn,[status(thm)],[inference(rw,[status(thm)],[inference(cn,[status(thm)],[inference(rw,[status(thm)],[inference(spm,[status(thm)],[c_0_56,c_0_36]),c_0_53])]),c_0_57])]),
[proof] ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.05 % Problem : PUZ026-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.08 % Command : run_E /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.18/0.44 % Computer : n019.cluster.edu
% 0.18/0.44 % Model : x86_64 x86_64
% 0.18/0.44 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.18/0.44 % Memory : 8046.5625MB
% 0.18/0.44 % OS : Linux 6.8.0-71-generic
% 0.18/0.44 % CPULimit : 300
% 0.18/0.44 % WCLimit : 300
% 0.18/0.44 % DateTime : Mon Sep 21 03:46:04 UTC 2026
% 0.18/0.45 % CPUTime :
% 0.18/0.45 Running run_E /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.26/0.53 Running first-order theorem proving
% 0.26/0.53 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
% 0.26/0.58 % Version: 3.5.1
% 0.26/0.58 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.26/0.58 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.26/0.58 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.26/0.58 % Starting new_bool_3 with 300s (1) cores
% 0.26/0.58 % Starting new_bool_1 with 300s (1) cores
% 0.26/0.58 % Starting sh5l with 300s (1) cores
% 0.26/0.58 % new_bool_1 with pid 1618201 completed with status 0
% 0.26/0.58 % Result found by new_bool_1
% 0.26/0.58 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.26/0.58 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.26/0.58 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.26/0.58 % Starting new_bool_3 with 300s (1) cores
% 0.26/0.58 % Starting new_bool_1 with 300s (1) cores
% 0.26/0.58 % (lift_lambdas = 0, lambda_to_forall = 0,unroll_only_formulas = 0, sine = GSinE(CountFormulas,hypos,1.5,,3,20000,1.0))
% 0.26/0.58 % SinE strategy is GSinE(CountFormulas,hypos,1.5,,3,20000,1.0)
% 0.26/0.58 % Search class: FGHNF-FFSM21-SFFFFFNN
% 0.26/0.58 % Scheduled 5 strats onto 1 cores with 300 seconds (300 total)
% 0.26/0.58 % Starting SubtermCWHack with 31s (1) cores
% 0.26/0.58 % SubtermCWHack with pid 1618206 completed with status 0
% 0.26/0.58 % Result found by SubtermCWHack
% 0.26/0.58 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.26/0.58 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.26/0.58 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.26/0.58 % Starting new_bool_3 with 300s (1) cores
% 0.26/0.58 % Starting new_bool_1 with 300s (1) cores
% 0.26/0.58 % (lift_lambdas = 0, lambda_to_forall = 0,unroll_only_formulas = 0, sine = GSinE(CountFormulas,hypos,1.5,,3,20000,1.0))
% 0.26/0.58 % SinE strategy is GSinE(CountFormulas,hypos,1.5,,3,20000,1.0)
% 0.26/0.58 % Search class: FGHNF-FFSM21-SFFFFFNN
% 0.26/0.58 % Scheduled 5 strats onto 1 cores with 300 seconds (300 total)
% 0.26/0.58 % Starting SubtermCWHack with 31s (1) cores
% 0.26/0.58 % Preprocessing time : 0.002 s
% 0.26/0.58
% 0.26/0.58 % Proof found!
% 0.26/0.58 % SZS status Unsatisfiable
% 0.26/0.58 % SZS output start CNFRefutation
% See solution above
% 0.26/0.58 % Parsed axioms : 23
% 0.26/0.58 % Removed by relevancy pruning/SinE : 0
% 0.26/0.58 % Initial clauses : 23
% 0.26/0.58 % Removed in clause preprocessing : 0
% 0.26/0.58 % Initial clauses in saturation : 23
% 0.26/0.58 % Processed clauses : 69
% 0.26/0.58 % ...of these trivial : 0
% 0.26/0.58 % ...subsumed : 20
% 0.26/0.58 % ...remaining for further processing : 48
% 0.26/0.58 % Other redundant clauses eliminated : 0
% 0.26/0.58 % Clauses deleted for lack of memory : 0
% 0.26/0.58 % Backward-subsumed : 8
% 0.26/0.58 % Backward-rewritten : 6
% 0.26/0.58 % Generated clauses : 65
% 0.26/0.58 % ...of the previous two non-redundant : 56
% 0.26/0.58 % ...aggressively subsumed : 0
% 0.26/0.58 % Contextual simplify-reflections : 5
% 0.26/0.58 % Paramodulations : 63
% 0.26/0.58 % Factorizations : 0
% 0.26/0.58 % NegExts : 0
% 0.26/0.58 % Equation resolutions : 0
% 0.26/0.58 % Disequality decompositions : 0
% 0.26/0.58 % Total rewrite steps : 9
% 0.26/0.58 % ...of those cached : 6
% 0.26/0.58 % Propositional unsat checks : 0
% 0.26/0.58 % Propositional check models : 0
% 0.26/0.58 % Propositional check unsatisfiable : 0
% 0.26/0.58 % Propositional clauses : 0
% 0.26/0.58 % Propositional clauses after purity: 0
% 0.26/0.58 % Propositional unsat core size : 0
% 0.26/0.58 % Propositional preprocessing time : 0.000
% 0.26/0.58 % Propositional encoding time : 0.000
% 0.26/0.58 % Propositional solver time : 0.000
% 0.26/0.58 % Success case prop preproc time : 0.000
% 0.26/0.58 % Success case prop encoding time : 0.000
% 0.26/0.58 % Success case prop solver time : 0.000
% 0.26/0.58 % Current number of processed clauses : 32
% 0.26/0.58 % Positive orientable unit clauses : 9
% 0.26/0.58 % Positive unorientable unit clauses: 0
% 0.26/0.58 % Negative unit clauses : 3
% 0.26/0.58 % Non-unit-clauses : 20
% 0.26/0.58 % Current number of unprocessed clauses: 9
% 0.26/0.58 % ...number of literals in the above : 20
% 0.26/0.58 % Current number of archived formulas : 0
% 0.26/0.58 % Current number of archived clauses : 16
% 0.26/0.58 % Clause-clause subsumption calls (NU) : 152
% 0.26/0.58 % Rec. Clause-clause subsumption calls : 108
% 0.26/0.58 % Non-unit clause-clause subsumptions : 18
% 0.26/0.58 % Unit Clause-clause subsumption calls : 23
% 0.26/0.58 % Rewrite failures with RHS unbound : 0
% 0.26/0.58 % BW rewrite match attempts : 2
% 0.26/0.58 % BW rewrite match successes : 2
% 0.26/0.58 % Condensation attempts : 0
% 0.26/0.58 % Condensation successes : 0
% 0.26/0.58 % Termbank termtop insertions : 1467
% 0.26/0.58 % Search garbage collected termcells : 43
% 0.26/0.58
% 0.26/0.58 % -------------------------------------------------
% 0.26/0.58 % User time : 0.008 s
% 0.26/0.58 % System time : 0.002 s
% 0.26/0.58 % Total time : 0.011 s
% 0.26/0.58 % Maximum resident set size: 3648 pages
% 0.26/0.58
% 0.26/0.58 % -------------------------------------------------
% 0.26/0.58 % User time : 0.011 s
% 0.26/0.58 % System time : 0.008 s
% 0.26/0.58 % Total time : 0.019 s
% 0.26/0.58 % Maximum resident set size: 4608 pages
% 0.26/0.58 % E exiting
%------------------------------------------------------------------------------