%------------------------------------------------------------------------------
% File : Prover9---2026-6A
% Problem : PUZ012-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% Transfm : none
% Format : tptp:raw
% Command : prover9 -casc 300 -f /export/starexec/sandbox2/benchmark/theBenchmark.p
% Computer : n016.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 : Sun Sep 27 08:22:44 AM UTC 2026
% Result : Unsatisfiable 0.08s 20.33s
% Output : CNFRefutation 0.08s
% Verified :
% SZS Type : Refutation
% Derivation depth : 6
% Number of leaves : 10
% Syntax : Number of formulae : 31 ( 14 unt; 0 def)
% Number of atoms : 57 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 55 ( 29 ~; 26 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% 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 10 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(apples_not_bananas,axiom,
~ equal_fruits(apples,bananas),
file('theBenchmark.p',apples_not_bananas) ).
cnf(c_1,plain,
~ equal_fruits(apples,bananas),
inference(clausify,[status(thm)],[apples_not_bananas]) ).
fof(contains_is_well_defined1,axiom,
! [VAR_0,VAR_1,VAR_2] :
( equal_fruits(VAR_1,VAR_2)
| ~ contains(VAR_0,VAR_2)
| ~ contains(VAR_0,VAR_1) ),
file('theBenchmark.p',contains_is_well_defined1) ).
cnf(c_2,plain,
( equal_fruits(B,C)
| ~ contains(A,C)
| ~ contains(A,B) ),
inference(clausify,[status(thm)],[contains_is_well_defined1]) ).
fof(contains_is_well_defined2,axiom,
! [VAR_0,VAR_1,VAR_2] :
( equal_boxes(VAR_0,VAR_2)
| ~ contains(VAR_2,VAR_1)
| ~ contains(VAR_0,VAR_1) ),
file('theBenchmark.p',contains_is_well_defined2) ).
cnf(c_6,plain,
( equal_boxes(A,C)
| ~ contains(C,B)
| ~ contains(A,B) ),
inference(clausify,[status(thm)],[contains_is_well_defined2]) ).
fof(boxb_not_boxc,axiom,
~ equal_boxes(boxb,boxc),
file('theBenchmark.p',boxb_not_boxc) ).
cnf(c_8,plain,
~ equal_boxes(boxb,boxc),
inference(clausify,[status(thm)],[boxb_not_boxc]) ).
fof(label_is_wrong,axiom,
! [VAR_0,VAR_1] :
( ~ contains(VAR_0,VAR_1)
| ~ label(VAR_0,VAR_1) ),
file('theBenchmark.p',label_is_wrong) ).
cnf(c_12,plain,
( ~ contains(A,B)
| ~ label(A,B) ),
inference(clausify,[status(thm)],[label_is_wrong]) ).
fof(boxc_labelled_bananas,axiom,
label(boxc,bananas),
file('theBenchmark.p',boxc_labelled_bananas) ).
cnf(c_14,plain,
label(boxc,bananas),
inference(clausify,[status(thm)],[boxc_labelled_bananas]) ).
cnf(c_15,plain,
~ contains(boxc,bananas),
inference(resolve,[status(thm)],[c_14,c_12]) ).
cnf(c_20,plain,
( ~ contains(A,bananas)
| ~ contains(A,apples) ),
inference(resolve,[status(thm)],[c_1,c_2]) ).
fof(prove_boxa_contains_bananas_and_boxc_oranges,axiom,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
file('theBenchmark.p',prove_boxa_contains_bananas_and_boxc_oranges) ).
cnf(c_21,plain,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
inference(clausify,[status(thm)],[prove_boxa_contains_bananas_and_boxc_oranges]) ).
fof(boxb_contains_apples,axiom,
contains(boxb,apples),
file('theBenchmark.p',boxb_contains_apples) ).
cnf(c_22,plain,
contains(boxb,apples),
inference(clausify,[status(thm)],[boxb_contains_apples]) ).
fof(each_box_contains_something,axiom,
! [VAR_0] :
( contains(VAR_0,oranges)
| contains(VAR_0,bananas)
| contains(VAR_0,apples) ),
file('theBenchmark.p',each_box_contains_something) ).
cnf(c_23,plain,
( contains(A,oranges)
| contains(A,bananas)
| contains(A,apples) ),
inference(clausify,[status(thm)],[each_box_contains_something]) ).
fof(each_thing_is_in_a_box,axiom,
! [VAR_0] :
( contains(boxc,VAR_0)
| contains(boxb,VAR_0)
| contains(boxa,VAR_0) ),
file('theBenchmark.p',each_thing_is_in_a_box) ).
cnf(c_24,plain,
( contains(boxc,A)
| contains(boxb,A)
| contains(boxa,A) ),
inference(clausify,[status(thm)],[each_thing_is_in_a_box]) ).
cnf(c_26,plain,
( ~ contains(boxc,A)
| ~ contains(boxb,A) ),
inference(resolve,[status(thm)],[c_6,c_8]) ).
cnf(c_28,plain,
~ contains(boxb,bananas),
inference(resolve,[status(thm)],[c_20,c_22]) ).
cnf(c_38,plain,
( ~ contains(boxa,bananas)
| contains(boxc,bananas)
| contains(boxc,apples) ),
inference(resolve,[status(thm)],[c_23,c_21]) ).
cnf(c_29,plain,
( ~ contains(boxa,bananas)
| contains(boxc,apples) ),
inference(resolve,[status(thm)],[c_15,c_38]) ).
cnf(c_39,plain,
( contains(boxb,bananas)
| contains(boxa,bananas) ),
inference(resolve,[status(thm)],[c_24,c_15]) ).
cnf(c_33,plain,
contains(boxa,bananas),
inference(resolve,[status(thm)],[c_28,c_39]) ).
cnf(c_35,plain,
contains(boxc,apples),
inference(resolve,[status(thm)],[c_33,c_29]) ).
cnf(c_40,plain,
~ contains(boxc,apples),
inference(resolve,[status(thm)],[c_26,c_22]) ).
cnf(c_37,plain,
$false,
inference(resolve,[status(thm)],[c_35,c_40]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ012-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% 0.00/0.04 % Command : prover9 -casc 300 -f /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.09/5.38 % Computer : n016.cluster.edu
% 0.09/5.38 % Model : x86_64 x86_64
% 0.09/5.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/5.38 % Memory : 8046.5625MB
% 0.09/5.38 % OS : Linux 6.8.0-71-generic
% 0.08/20.31 % CPULimit : 300
% 0.08/20.31 % WCLimit : 300
% 0.08/20.31 % DateTime : Sat Sep 26 05:03:48 UTC 2026
% 0.08/20.31 % CPUTime :
% 0.08/20.31 % Prover9 (64) version 2026-6A, July 2026, CASC-J13.
% 0.08/20.31 % Process 416243 was started by sandbox2 on n006,
% 0.08/20.31 % Sat Sep 26 05:03:48 2026
% 0.08/20.31 % The command was "/export/starexec/sandbox2/solver/bin/prover9 -casc 300 -f /export/starexec/sandbox2/benchmark/theBenchmark.p".
% 0.08/20.32
% 0.08/20.32 % From the command line: assign(max_seconds, 300).
% 0.08/20.33
% 0.08/20.33 % SZS status Unsatisfiable for theBenchmark
% 0.08/20.33
% 0.08/20.33 % Proof 1 at 0.00 (+ 0.00) seconds.
% 0.08/20.33 % Length of proof is 18.
% 0.08/20.33 % Level of proof is 5.
% 0.08/20.33 % Maximum clause weight is 9.000.
% 0.08/20.33 % Given clauses 12.
% 0.08/20.33
% 0.08/20.33 % SZS output start CNFRefutation for theBenchmark
% See solution above
%------------------------------------------------------------------------------