%------------------------------------------------------------------------------
% File : iProver---3.9.4
% Problem : PUZ023-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% Computer : n009.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 : Fri Sep 25 02:32:43 PM UTC 2026
% Result : Unsatisfiable 1.66s 1.28s
% Output : CNFRefutation 1.66s
% Verified :
% SZS Type : Refutation
% Derivation depth : 3
% Number of leaves : 7
% Syntax : Number of formulae : 21 ( 5 unt; 0 def)
% Number of atoms : 46 ( 0 equ)
% Maximal formula atoms : 3 ( 2 avg)
% Number of connectives : 48 ( 23 ~; 25 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of types : 1 ( 0 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 3 ( 2 usr; 1 prp; 0-1 aty)
% Number of functors : 8 ( 8 usr; 5 con; 0-2 aty)
% Number of variables : 8 ( 0 sgn 8 !; 0 ?; 4 :)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( a_truth(liar(X0))
| a_truth(truthteller(X0)) ),
file('/export/starexec/sandbox/benchmark/Axioms/PUZ002-0.ax',truthteller_or_liar) ).
fof(f6,axiom,
! [X0,X1] :
( a_truth(liar(X1))
| ~ a_truth(says(X1,X0))
| a_truth(X0) ),
file('/export/starexec/sandbox/benchmark/Axioms/PUZ002-0.ax',liars_are_told_by_liars) ).
fof(f17,axiom,
a_truth(says(c,liar(b))),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c_says_b_lies) ).
fof(f18,axiom,
( an_answer(b_and_c_liars)
| ~ a_truth(liar(c))
| ~ a_truth(liar(b)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',b_and_c_liars) ).
fof(f19,axiom,
( an_answer(b_liar_and_c_truthteller)
| ~ a_truth(truthteller(c))
| ~ a_truth(liar(b)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',b_liar_and_c_truthteller) ).
fof(f20,axiom,
( an_answer(b_truthteller_and_c_liar)
| ~ a_truth(liar(c))
| ~ a_truth(truthteller(b)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',b_truthteller_and_c_liar) ).
fof(f22,negated_conjecture,
! [X0] : ~ an_answer(X0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_there_is_an_answer) ).
tcf(c_71,plain,
! [X0: $i] :
( a_truth(liar(X0))
| a_truth(truthteller(X0)) ),
inference(cnf_transformation,[],[f1]) ).
tcf(c_76,plain,
! [X0: $i,X1: $i] :
( a_truth(X1)
| a_truth(liar(X0))
| ~ a_truth(says(X0,X1)) ),
inference(cnf_transformation,[],[f6]) ).
tcf(c_87,plain,
a_truth(says(c,liar(b))),
inference(cnf_transformation,[],[f17]) ).
tcf(c_88,plain,
( an_answer(b_and_c_liars)
| ~ a_truth(liar(c))
| ~ a_truth(liar(b)) ),
inference(cnf_transformation,[],[f18]) ).
tcf(c_89,plain,
( an_answer(b_liar_and_c_truthteller)
| ~ a_truth(liar(b))
| ~ a_truth(truthteller(c)) ),
inference(cnf_transformation,[],[f19]) ).
tcf(c_90,plain,
( an_answer(b_truthteller_and_c_liar)
| ~ a_truth(liar(c))
| ~ a_truth(truthteller(b)) ),
inference(cnf_transformation,[],[f20]) ).
tcf(c_92,negated_conjecture,
! [X0: $i] : ~ an_answer(X0),
inference(cnf_transformation,[],[f22]) ).
tcf(c_147,plain,
( ~ a_truth(liar(b))
| ~ a_truth(truthteller(c)) ),
inference(backward_subsumption_resolution,[status(thm)],[c_89,c_92]) ).
tcf(c_149,plain,
( ~ a_truth(liar(c))
| ~ a_truth(truthteller(b)) ),
inference(backward_subsumption_resolution,[status(thm)],[c_90,c_92]) ).
tcf(c_150,plain,
( ~ a_truth(liar(c))
| ~ a_truth(liar(b)) ),
inference(backward_subsumption_resolution,[status(thm)],[c_88,c_92]) ).
tcf(c_474,plain,
( a_truth(liar(c))
| a_truth(truthteller(c)) ),
inference(instantiation,[status(thm)],[c_71]) ).
tcf(c_485,plain,
( a_truth(liar(c))
| a_truth(liar(b))
| ~ a_truth(says(c,liar(b))) ),
inference(instantiation,[status(thm)],[c_76]) ).
tcf(c_489,plain,
( a_truth(liar(b))
| a_truth(truthteller(b)) ),
inference(instantiation,[status(thm)],[c_71]) ).
tcf(c_490,plain,
$false,
inference(prop_impl_just,[status(thm)],[c_489,c_485,c_474,c_147,c_149,c_150,c_87]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ023-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.04 % Command : run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% 0.11/0.37 % Computer : n009.cluster.edu
% 0.11/0.37 % Model : x86_64 x86_64
% 0.11/0.37 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.37 % Memory : 8046.5625MB
% 0.11/0.37 % OS : Linux 6.8.0-71-generic
% 0.11/0.37 % CPULimit : 300
% 0.11/0.37 % WCLimit : 300
% 0.11/0.37 % DateTime : Thu Sep 24 06:41:13 UTC 2026
% 0.11/0.38 % CPUTime :
% 0.11/0.38 Running run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% 0.11/0.41 Running first-order theorem proving
% 0.11/0.41 Running: /export/starexec/sandbox/solver/bin/iproveropt-multi-core.sh -d -n -l tptp -s fof_schedule -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 0.11/0.42
% 0.11/0.42 % ======== iProver multi-core TPTP/SMT =========
% 0.11/0.42
% 0.11/0.42 % Detected problem language: tptp
% 0.11/0.43 % Proving...
% 1.66/1.28 % SZS status Started for theBenchmark.p
% 1.66/1.28 % SZS status Unsatisfiable for theBenchmark.p
% 1.66/1.28
% 1.66/1.28 %---------------- iProver v3.9.4 (pre CASC 2026/SMT-COMP 2026) ----------------%
% 1.66/1.28
% 1.66/1.28 % ------ iProver source info
% 1.66/1.28
% 1.66/1.28 % git: date: 2026-07-19 20:42:38 +0200
% 1.66/1.28 % git: sha1: 804e7d636a263075307957e923b7a22a4035de61
% 1.66/1.28 % git: non_committed_changes: false
% 1.66/1.28
% 1.66/1.28 % ------ Parsing...% successful
% 1.66/1.28
% 1.66/1.28
% 1.66/1.28 % ------ Clausification by vclausify_rel & Parsing by iProver...%
% 1.66/1.28
% 1.66/1.28 % ------ Preprocessing... sf_s rm: 1 0s sf_e pe_s pe:1:0s pe_e sf_s rm: 0 0s sf_e pe_s pe_e %
% 1.66/1.28
% 1.66/1.28 % ------ Preprocessing... gs_s sp: 0 0s gs_e snvd_s sp: 0 0s snvd_e
% 1.66/1.28 % ------ Proving...
% 1.66/1.28 % ------ Problem Properties
% 1.66/1.28
% 1.66/1.28 %
% 1.66/1.28 % clauses 17
% 1.66/1.28 % conjectures 0
% 1.66/1.28 % EPR 0
% 1.66/1.28 % Horn 13
% 1.66/1.28 % unary 3
% 1.66/1.28 % binary 6
% 1.66/1.28 % lits 41
% 1.66/1.28 % lits eq 0
% 1.66/1.28 % fd_pure 0
% 1.66/1.28 % fd_pseudo 0
% 1.66/1.28 % fd_cond 0
% 1.66/1.28 % fd_pseudo_cond 0
% 1.66/1.28 % AC symbols 0
% 1.66/1.28
% 1.66/1.28 % ------ Schedule dynamic 5 is on
% 1.66/1.28
% 1.66/1.28 % ------ no conjectures: strip conj schedule
% 1.66/1.28
% 1.66/1.28 % ------ no equalities: superposition off
% 1.66/1.28
% 1.66/1.28 % ------ Input Options "--resolution_flag false --inst_lit_sel_side none" stripped conjectures Time Limit: 10.
% 1.66/1.28
% 1.66/1.28
% 1.66/1.28 % ------
% 1.66/1.28 % Current options:
% 1.66/1.28 % ------
% 1.66/1.28
% 1.66/1.28
% 1.66/1.28 %
% 1.66/1.28
% 1.66/1.28 % ------ Proving...
% 1.66/1.28 %
% 1.66/1.28
% 1.66/1.28 % SZS status Unsatisfiable for theBenchmark.p
% 1.66/1.28
% 1.66/1.28 % SZS output start CNFRefutation for theBenchmark.p
% See solution above
% 1.66/1.28
% 1.66/1.28
%------------------------------------------------------------------------------