%------------------------------------------------------------------------------
% File : E---3.5.1
% Problem : PUZ025-1 : 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 : n005.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 0.16s 0.60s
% Output : CNFRefutation 0.16s
% Verified :
% SZS Type : Refutation
% Derivation depth : 6
% Number of leaves : 7
% Syntax : Number of clauses : 26 ( 8 unt; 8 nHn; 24 RR)
% Number of literals : 70 ( 0 equ; 43 neg)
% Maximal clause size : 4 ( 2 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 4 ( 3 usr; 1 prp; 0-2 aty)
% Number of functors : 8 ( 8 usr; 5 con; 0-2 aty)
% Number of variables : 37 ( 5 sgn)
% Comments :
%------------------------------------------------------------------------------
cnf(liar_supports_lies,axiom,
( ~ a_truth(liar(X1))
| ~ ask_1_if_2(X1,X2)
| answer(yes)
| a_truth(X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',liar_supports_lies) ).
cnf(prove_there_is_an_answer,negated_conjecture,
~ answer(X1),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_there_is_an_answer) ).
cnf(truthteller_denies_lies,axiom,
( ~ a_truth(truthteller(X1))
| ~ ask_1_if_2(X1,X2)
| answer(no)
| a_truth(X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',truthteller_denies_lies) ).
cnf(liar_denies_truths,axiom,
( ~ a_truth(X2)
| ~ a_truth(liar(X1))
| ~ ask_1_if_2(X1,X2)
| answer(no) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',liar_denies_truths) ).
cnf(truthteller_identifies_truths,axiom,
( ~ a_truth(X2)
| ~ a_truth(truthteller(X1))
| ~ ask_1_if_2(X1,X2)
| answer(yes) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',truthteller_identifies_truths) ).
cnf(ask_c_if_a_and_b_equal,hypothesis,
ask_1_if_2(c,equal_type(a,b)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ask_c_if_a_and_b_equal) ).
cnf(truthteller_or_liar,axiom,
( a_truth(liar(X1))
| a_truth(truthteller(X1)) ),
file('/export/starexec/sandbox/benchmark/Axioms/PUZ002-0.ax',truthteller_or_liar) ).
cnf(c_0_7,plain,
( ~ a_truth(liar(X1))
| ~ ask_1_if_2(X1,X2)
| answer(yes)
| a_truth(X2) ),
inference(fof_simplification,[status(thm)],[liar_supports_lies]) ).
cnf(c_0_8,negated_conjecture,
~ answer(X1),
inference(fof_simplification,[status(thm)],[prove_there_is_an_answer]) ).
cnf(c_0_9,plain,
( ~ a_truth(truthteller(X1))
| ~ ask_1_if_2(X1,X2)
| answer(no)
| a_truth(X2) ),
inference(fof_simplification,[status(thm)],[truthteller_denies_lies]) ).
cnf(c_0_10,plain,
( ~ a_truth(X2)
| ~ a_truth(liar(X1))
| ~ ask_1_if_2(X1,X2)
| answer(no) ),
inference(fof_simplification,[status(thm)],[liar_denies_truths]) ).
cnf(c_0_11,plain,
( ~ a_truth(liar(X1))
| ~ ask_1_if_2(X1,X2)
| answer(yes)
| a_truth(X2) ),
c_0_7 ).
cnf(c_0_12,negated_conjecture,
~ answer(X1),
c_0_8 ).
cnf(c_0_13,plain,
( ~ a_truth(X2)
| ~ a_truth(truthteller(X1))
| ~ ask_1_if_2(X1,X2)
| answer(yes) ),
inference(fof_simplification,[status(thm)],[truthteller_identifies_truths]) ).
cnf(c_0_14,plain,
( ~ a_truth(truthteller(X1))
| ~ ask_1_if_2(X1,X2)
| answer(no)
| a_truth(X2) ),
c_0_9 ).
cnf(c_0_15,plain,
( ~ a_truth(X2)
| ~ a_truth(liar(X1))
| ~ ask_1_if_2(X1,X2)
| answer(no) ),
c_0_10 ).
cnf(c_0_16,plain,
( ~ a_truth(liar(X2))
| ~ ask_1_if_2(X2,X1)
| a_truth(X1) ),
inference(sr,[status(thm)],[c_0_11,c_0_12]) ).
cnf(c_0_17,plain,
( ~ a_truth(X2)
| ~ a_truth(truthteller(X1))
| ~ ask_1_if_2(X1,X2)
| answer(yes) ),
c_0_13 ).
cnf(c_0_18,plain,
( ~ a_truth(truthteller(X2))
| ~ ask_1_if_2(X2,X1)
| a_truth(X1) ),
inference(sr,[status(thm)],[c_0_14,c_0_12]) ).
cnf(c_0_19,plain,
( ~ a_truth(liar(X1))
| ~ ask_1_if_2(X1,X2) ),
inference(csr,[status(thm)],[inference(sr,[status(thm)],[c_0_15,c_0_12]),c_0_16]) ).
cnf(c_0_20,hypothesis,
ask_1_if_2(c,equal_type(a,b)),
ask_c_if_a_and_b_equal ).
cnf(c_0_21,plain,
( ~ a_truth(truthteller(X1))
| ~ ask_1_if_2(X1,X2) ),
inference(csr,[status(thm)],[inference(sr,[status(thm)],[c_0_17,c_0_12]),c_0_18]) ).
cnf(c_0_22,hypothesis,
~ a_truth(liar(c)),
inference(spm,[status(thm)],[c_0_19,c_0_20]) ).
cnf(c_0_23,axiom,
( a_truth(liar(X1))
| a_truth(truthteller(X1)) ),
truthteller_or_liar ).
cnf(c_0_24,hypothesis,
~ a_truth(truthteller(c)),
inference(spm,[status(thm)],[c_0_21,c_0_20]) ).
cnf(c_0_25,hypothesis,
$false,
inference(sr,[status(thm)],[inference(spm,[status(thm)],[c_0_22,c_0_23]),c_0_24]),
[proof] ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ025-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_E /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.12/0.54 % Computer : n005.cluster.edu
% 0.12/0.54 % Model : x86_64 x86_64
% 0.12/0.54 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.54 % Memory : 8046.5625MB
% 0.12/0.54 % OS : Linux 6.8.0-71-generic
% 0.12/0.54 % CPULimit : 300
% 0.12/0.54 % WCLimit : 300
% 0.12/0.54 % DateTime : Mon Sep 21 03:45:48 UTC 2026
% 0.12/0.55 % CPUTime :
% 0.12/0.55 Running run_E /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.16/0.58 Running first-order theorem proving
% 0.16/0.58 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
% 0.16/0.60 % Version: 3.5.1
% 0.16/0.60 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.16/0.60 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.16/0.60 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.16/0.60 % Starting new_bool_3 with 300s (1) cores
% 0.16/0.60 % Starting new_bool_1 with 300s (1) cores
% 0.16/0.60 % Starting sh5l with 300s (1) cores
% 0.16/0.60 % G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with pid 2478573 completed with status 0
% 0.16/0.60 % Result found by G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN
% 0.16/0.60 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.16/0.60 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.16/0.60 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.16/0.60 % (lift_lambdas = 1, lambda_to_forall = 1,unroll_only_formulas = 1, sine = Auto)
% 0.16/0.60 % No SInE strategy applied
% 0.16/0.60 % Search class: FGHNF-FFSM21-SFFFFFNN
% 0.16/0.60 % Scheduled 7 strats onto 5 cores with 1500 seconds (1500 total)
% 0.16/0.60 % Starting SubtermCWHack with 136s (1) cores
% 0.16/0.60 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 151s (1) cores
% 0.16/0.60 % Starting G-E--_208_C18_F1_SE_CS_SP_PS_S5PRR_S0Y with 136s (1) cores
% 0.16/0.60 % Starting new_bool_3 with 136s (1) cores
% 0.16/0.60 % Starting new_bool_1 with 136s (1) cores
% 0.16/0.60 % SubtermCWHack with pid 2478577 completed with status 0
% 0.16/0.60 % Result found by SubtermCWHack
% 0.16/0.60 % Preprocessing class: FSMSSMSSSSSNFFN.
% 0.16/0.60 % Scheduled 4 strats onto 8 cores with 300 seconds (2400 total)
% 0.16/0.60 % Starting G-E--_208_C18_F1_SE_CS_SOS_SP_PS_S5PRR_RG_S04AN with 1500s (5) cores
% 0.16/0.60 % (lift_lambdas = 1, lambda_to_forall = 1,unroll_only_formulas = 1, sine = Auto)
% 0.16/0.60 % No SInE strategy applied
% 0.16/0.60 % Search class: FGHNF-FFSM21-SFFFFFNN
% 0.16/0.60 % Scheduled 7 strats onto 5 cores with 1500 seconds (1500 total)
% 0.16/0.60 % Starting SubtermCWHack with 136s (1) cores
% 0.16/0.60 % Preprocessing time : 0.001 s
% 0.16/0.60
% 0.16/0.60 % Proof found!
% 0.16/0.60 % SZS status Unsatisfiable
% 0.16/0.60 % SZS output start CNFRefutation
% See solution above
% 0.16/0.60 % Parsed axioms : 24
% 0.16/0.60 % Removed by relevancy pruning/SinE : 0
% 0.16/0.60 % Initial clauses : 24
% 0.16/0.60 % Removed in clause preprocessing : 0
% 0.16/0.60 % Initial clauses in saturation : 24
% 0.16/0.60 % Processed clauses : 36
% 0.16/0.60 % ...of these trivial : 0
% 0.16/0.60 % ...subsumed : 6
% 0.16/0.60 % ...remaining for further processing : 30
% 0.16/0.60 % Other redundant clauses eliminated : 0
% 0.16/0.60 % Clauses deleted for lack of memory : 0
% 0.16/0.60 % Backward-subsumed : 6
% 0.16/0.60 % Backward-rewritten : 0
% 0.16/0.60 % Generated clauses : 22
% 0.16/0.60 % ...of the previous two non-redundant : 18
% 0.16/0.60 % ...aggressively subsumed : 0
% 0.16/0.60 % Contextual simplify-reflections : 2
% 0.16/0.60 % Paramodulations : 22
% 0.16/0.60 % Factorizations : 0
% 0.16/0.60 % NegExts : 0
% 0.16/0.60 % Equation resolutions : 0
% 0.16/0.60 % Disequality decompositions : 0
% 0.16/0.60 % Total rewrite steps : 0
% 0.16/0.60 % ...of those cached : 0
% 0.16/0.60 % Propositional unsat checks : 0
% 0.16/0.60 % Propositional check models : 0
% 0.16/0.60 % Propositional check unsatisfiable : 0
% 0.16/0.60 % Propositional clauses : 0
% 0.16/0.60 % Propositional clauses after purity: 0
% 0.16/0.60 % Propositional unsat core size : 0
% 0.16/0.60 % Propositional preprocessing time : 0.000
% 0.16/0.60 % Propositional encoding time : 0.000
% 0.16/0.60 % Propositional solver time : 0.000
% 0.16/0.60 % Success case prop preproc time : 0.000
% 0.16/0.60 % Success case prop encoding time : 0.000
% 0.16/0.60 % Success case prop solver time : 0.000
% 0.16/0.60 % Current number of processed clauses : 24
% 0.16/0.60 % Positive orientable unit clauses : 6
% 0.16/0.60 % Positive unorientable unit clauses: 0
% 0.16/0.60 % Negative unit clauses : 3
% 0.16/0.60 % Non-unit-clauses : 15
% 0.16/0.60 % Current number of unprocessed clauses: 6
% 0.16/0.60 % ...number of literals in the above : 20
% 0.16/0.60 % Current number of archived formulas : 0
% 0.16/0.60 % Current number of archived clauses : 6
% 0.16/0.60 % Clause-clause subsumption calls (NU) : 38
% 0.16/0.60 % Rec. Clause-clause subsumption calls : 35
% 0.16/0.60 % Non-unit clause-clause subsumptions : 10
% 0.16/0.60 % Unit Clause-clause subsumption calls : 13
% 0.16/0.60 % Rewrite failures with RHS unbound : 0
% 0.16/0.60 % BW rewrite match attempts : 0
% 0.16/0.60 % BW rewrite match successes : 0
% 0.16/0.60 % Condensation attempts : 0
% 0.16/0.60 % Condensation successes : 0
% 0.16/0.60 % Termbank termtop insertions : 996
% 0.16/0.60 % Search garbage collected termcells : 47
% 0.16/0.60
% 0.16/0.60 % -------------------------------------------------
% 0.16/0.60 % User time : 0.006 s
% 0.16/0.60 % System time : 0.001 s
% 0.16/0.60 % Total time : 0.007 s
% 0.16/0.60 % Maximum resident set size: 3648 pages
% 0.16/0.60
% 0.16/0.60 % -------------------------------------------------
% 0.16/0.60 % User time : 0.016 s
% 0.16/0.60 % System time : 0.011 s
% 0.16/0.60 % Total time : 0.027 s
% 0.16/0.60 % Maximum resident set size: 4608 pages
% 0.16/0.60 % E exiting
%------------------------------------------------------------------------------