%------------------------------------------------------------------------------
% File : iProver---3.9.4
% Problem : PUZ012-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% Transfm : none
% Format : tptp:raw
% Command : run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% Computer : n026.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 02:32:41 PM UTC 2026
% Result : Unsatisfiable 0.85s 1.10s
% Output : CNFRefutation 0.85s
% Verified :
% SZS Type : Refutation
% Derivation depth : 4
% Number of leaves : 10
% Syntax : Number of formulae : 28 ( 10 unt; 0 def)
% Number of atoms : 56 ( 0 equ)
% Maximal formula atoms : 3 ( 2 avg)
% Number of connectives : 57 ( 29 ~; 28 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of types : 1 ( 0 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 5 ( 4 usr; 1 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 6 con; 0-0 aty)
% Number of variables : 22 ( 0 sgn 22 !; 0 ?; 12 :)
% Comments :
%------------------------------------------------------------------------------
fof(f3,axiom,
! [X0,X1] :
( ~ contains(X0,X1)
| ~ label(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',label_is_wrong) ).
fof(f4,axiom,
! [X0] :
( contains(boxc,X0)
| contains(boxb,X0)
| contains(boxa,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',each_thing_is_in_a_box) ).
fof(f5,axiom,
! [X0] :
( contains(X0,oranges)
| contains(X0,bananas)
| contains(X0,apples) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',each_box_contains_something) ).
fof(f6,axiom,
! [X2,X0,X1] :
( equal_fruits(X1,X2)
| ~ contains(X0,X2)
| ~ contains(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',contains_is_well_defined1) ).
fof(f7,axiom,
! [X2,X0,X1] :
( equal_boxes(X0,X2)
| ~ contains(X2,X1)
| ~ contains(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',contains_is_well_defined2) ).
fof(f9,axiom,
~ equal_boxes(boxb,boxc),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',boxb_not_boxc) ).
fof(f11,axiom,
~ equal_fruits(apples,bananas),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',apples_not_bananas) ).
fof(f16,axiom,
label(boxc,bananas),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',boxc_labelled_bananas) ).
fof(f17,axiom,
contains(boxb,apples),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',boxb_contains_apples) ).
fof(f18,negated_conjecture,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_boxa_contains_bananas_and_boxc_oranges) ).
tcf(c_69,plain,
! [X0: $i,X1: $i] :
( ~ contains(X0,X1)
| ~ label(X0,X1) ),
inference(cnf_transformation,[],[f3]) ).
tcf(c_70,plain,
! [X0: $i] :
( contains(boxc,X0)
| contains(boxb,X0)
| contains(boxa,X0) ),
inference(cnf_transformation,[],[f4]) ).
tcf(c_71,plain,
! [X0: $i] :
( contains(X0,oranges)
| contains(X0,bananas)
| contains(X0,apples) ),
inference(cnf_transformation,[],[f5]) ).
tcf(c_72,plain,
! [X0: $i,X1: $i,X2: $i] :
( equal_fruits(X1,X2)
| ~ contains(X0,X2)
| ~ contains(X0,X1) ),
inference(cnf_transformation,[],[f6]) ).
tcf(c_73,plain,
! [X0: $i,X1: $i,X2: $i] :
( equal_boxes(X0,X2)
| ~ contains(X2,X1)
| ~ contains(X0,X1) ),
inference(cnf_transformation,[],[f7]) ).
tcf(c_75,plain,
~ equal_boxes(boxb,boxc),
inference(cnf_transformation,[],[f9]) ).
tcf(c_77,plain,
~ equal_fruits(apples,bananas),
inference(cnf_transformation,[],[f11]) ).
tcf(c_82,plain,
label(boxc,bananas),
inference(cnf_transformation,[],[f16]) ).
tcf(c_83,plain,
contains(boxb,apples),
inference(cnf_transformation,[],[f17]) ).
tcf(c_84,negated_conjecture,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
inference(cnf_transformation,[],[f18]) ).
tcf(c_153,plain,
~ contains(boxc,bananas),
inference(resolution,[status(thm)],[c_69,c_82]) ).
tcf(c_160,plain,
! [X0: $i] :
( ~ contains(X0,bananas)
| ~ contains(X0,apples) ),
inference(resolution,[status(thm)],[c_72,c_77]) ).
tcf(c_197,plain,
! [X0: $i] :
( ~ contains(boxc,X0)
| ~ contains(boxb,X0) ),
inference(resolution,[status(thm)],[c_73,c_75]) ).
tcf(c_198,plain,
( ~ contains(boxc,apples)
| ~ contains(boxb,apples) ),
inference(instantiation,[status(thm)],[c_197]) ).
tcf(c_266,plain,
( contains(boxc,bananas)
| contains(boxb,bananas)
| contains(boxa,bananas) ),
inference(instantiation,[status(thm)],[c_70]) ).
tcf(c_267,plain,
( ~ contains(boxb,bananas)
| ~ contains(boxb,apples) ),
inference(instantiation,[status(thm)],[c_160]) ).
tcf(c_274,plain,
( contains(boxc,oranges)
| contains(boxc,bananas)
| contains(boxc,apples) ),
inference(instantiation,[status(thm)],[c_71]) ).
tcf(c_277,plain,
$false,
inference(prop_impl_just,[status(thm)],[c_274,c_267,c_266,c_198,c_153,c_84,c_83]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ012-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% 0.00/0.04 % Command : run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% 0.08/0.35 % Computer : n026.cluster.edu
% 0.08/0.35 % Model : x86_64 x86_64
% 0.08/0.35 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.08/0.35 % Memory : 8046.5625MB
% 0.08/0.35 % OS : Linux 6.8.0-71-generic
% 0.08/0.35 % CPULimit : 300
% 0.08/0.35 % WCLimit : 300
% 0.08/0.35 % DateTime : Thu Sep 24 06:40:11 UTC 2026
% 0.08/0.36 % CPUTime :
% 0.08/0.36 Running run_iprover 300 /export/starexec/sandbox/benchmark/theBenchmark.p THM
% 0.12/0.39 Running EPR theorem proving
% 0.12/0.39 Running: /export/starexec/sandbox/solver/bin/iproveropt-multi-core.sh -d -n -l tptp -s epr_schedule -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 0.12/0.41
% 0.12/0.41 % ======== iProver multi-core TPTP/SMT =========
% 0.12/0.41
% 0.12/0.41 % Detected problem language: tptp
% 0.12/0.42 % Proving...
% 0.85/1.10 % SZS status Started for theBenchmark.p
% 0.85/1.10 % SZS status Unsatisfiable for theBenchmark.p
% 0.85/1.10
% 0.85/1.10 %---------------- iProver v3.9.4 (pre CASC 2026/SMT-COMP 2026) ----------------%
% 0.85/1.10
% 0.85/1.10 % ------ iProver source info
% 0.85/1.10
% 0.85/1.10 % git: date: 2026-07-19 20:42:38 +0200
% 0.85/1.10 % git: sha1: 804e7d636a263075307957e923b7a22a4035de61
% 0.85/1.10 % git: non_committed_changes: false
% 0.85/1.10
% 0.85/1.10 % ------ Parsing...% successful
% 0.85/1.10
% 0.85/1.10
% 0.85/1.10 % ------ Clausification by vclausify_rel & Parsing by iProver...% ------ preprocesses with Option_epr_non_horn_non_eq
% 0.85/1.10 %
% 0.85/1.10
% 0.85/1.10 % ------ Preprocessing... sf_s rm: 0 0s sf_e pe_s pe:1:0s pe:2:0s pe_e sf_s rm: 0 0s sf_e pe_s pe_e %
% 0.85/1.10
% 0.85/1.10 % ------ Preprocessing...% ------ preprocesses with Option_epr_non_horn_non_eq
% 0.85/1.10 gs_s sp: 0 0s gs_e snvd_s sp: 0 0s snvd_e
% 0.85/1.10 % ------ Proving...
% 0.85/1.10 % ------ Problem Properties
% 0.85/1.10
% 0.85/1.10 %
% 0.85/1.10 % clauses 13
% 0.85/1.10 % conjectures 1
% 0.85/1.10 % EPR 13
% 0.85/1.10 % Horn 11
% 0.85/1.10 % unary 4
% 0.85/1.10 % binary 7
% 0.85/1.10 % lits 24
% 0.85/1.10 % lits eq 0
% 0.85/1.10 % fd_pure 0
% 0.85/1.10 % fd_pseudo 0
% 0.85/1.10 % fd_cond 0
% 0.85/1.10 % fd_pseudo_cond 0
% 0.85/1.10 % AC symbols 0
% 0.85/1.10
% 0.85/1.10 % ------ Schedule EPR non Horn non eq is on
% 0.85/1.10
% 0.85/1.10 % ------ no equalities: superposition off
% 0.85/1.10
% 0.85/1.10 % ------ Input Options "--resolution_flag false" Time Limit: 70.
% 0.85/1.10
% 0.85/1.10
% 0.85/1.10 % ------
% 0.85/1.10 % Current options:
% 0.85/1.10 % ------
% 0.85/1.10
% 0.85/1.10
% 0.85/1.10 %
% 0.85/1.10
% 0.85/1.10 % ------ Proving...
% 0.85/1.10 %
% 0.85/1.10
% 0.85/1.10 % SZS status Unsatisfiable for theBenchmark.p
% 0.85/1.10
% 0.85/1.10 % SZS output start CNFRefutation for theBenchmark.p
% See solution above
% 0.85/1.10
% 0.85/1.10
%------------------------------------------------------------------------------