%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ012-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n011.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 : Tue Sep 29 12:31:52 PM UTC 2026
% Result : Unsatisfiable 0.17s 0.48s
% Output : Refutation 0.17s
% Verified :
% SZS Type : Refutation
% Derivation depth : 2
% Number of leaves : 18
% Syntax : Number of formulae : 26 ( 14 unt; 0 def)
% Number of atoms : 46 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 42 ( 22 ~; 20 |; 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 ( 22 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] : equal_fruits(X0,X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',reflexivity_for_fruits) ).
fof(f2,axiom,
! [X0] : equal_boxes(X0,X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',reflexivity_for_boxes) ).
fof(f3,axiom,
! [X0,X1] :
( ~ label(X0,X1)
| ~ contains(X0,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',label_is_wrong) ).
fof(f4,axiom,
! [X0] :
( contains(boxa,X0)
| contains(boxb,X0)
| contains(boxc,X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',each_thing_is_in_a_box) ).
fof(f5,axiom,
! [X0] :
( contains(X0,apples)
| contains(X0,bananas)
| contains(X0,oranges) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',each_box_contains_something) ).
fof(f6,axiom,
! [X2,X0,X1] :
( ~ contains(X0,X1)
| ~ contains(X0,X2)
| equal_fruits(X1,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',contains_is_well_defined1) ).
fof(f7,axiom,
! [X2,X0,X1] :
( ~ contains(X0,X1)
| ~ contains(X2,X1)
| equal_boxes(X0,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',contains_is_well_defined2) ).
fof(f8,axiom,
~ equal_boxes(boxa,boxb),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxa_not_boxb) ).
fof(f9,axiom,
~ equal_boxes(boxb,boxc),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxb_not_boxc) ).
fof(f10,axiom,
~ equal_boxes(boxa,boxc),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxa_not_boxc) ).
fof(f11,axiom,
~ equal_fruits(apples,bananas),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',apples_not_bananas) ).
fof(f12,axiom,
~ equal_fruits(bananas,oranges),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',bananas_not_oranges) ).
fof(f13,axiom,
~ equal_fruits(apples,oranges),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',apples_not_oranges) ).
fof(f14,axiom,
label(boxa,apples),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxa_labelled_apples) ).
fof(f15,axiom,
label(boxb,oranges),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxb_labelled_oranges) ).
fof(f16,axiom,
label(boxc,bananas),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxc_labelled_bananas) ).
fof(f17,axiom,
contains(boxb,apples),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',boxb_contains_apples) ).
fof(f18,negated_conjecture,
( ~ contains(boxa,bananas)
| ~ contains(boxc,oranges) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_boxa_contains_bananas_and_boxc_oranges) ).
fof(f19,plain,
! [X0,X1] :
( ~ label(X0,X1)
| contains(X0,X1) ),
inference(consistent_polarity_flipping,[],[f3]) ).
fof(f20,plain,
! [X0] :
( ~ contains(boxa,X0)
| ~ contains(boxb,X0)
| ~ contains(boxc,X0) ),
inference(consistent_polarity_flipping,[],[f4]) ).
fof(f21,plain,
! [X0] :
( ~ contains(X0,apples)
| ~ contains(X0,bananas)
| ~ contains(X0,oranges) ),
inference(consistent_polarity_flipping,[],[f5]) ).
fof(f22,plain,
! [X2,X0,X1] :
( contains(X0,X1)
| contains(X0,X2)
| equal_fruits(X1,X2) ),
inference(consistent_polarity_flipping,[],[f6]) ).
fof(f23,plain,
! [X2,X0,X1] :
( contains(X0,X1)
| contains(X2,X1)
| equal_boxes(X0,X2) ),
inference(consistent_polarity_flipping,[],[f7]) ).
fof(f24,plain,
~ contains(boxb,apples),
inference(consistent_polarity_flipping,[],[f17]) ).
fof(f25,plain,
( contains(boxa,bananas)
| contains(boxc,oranges) ),
inference(consistent_polarity_flipping,[],[f18]) ).
fof(f51,plain,
$false,
inference(finite_model_not_found_(exhaustively_excluded_all_possible_domain_size_assignments),[],[f1,f2,f19,f20,f21,f22,f23,f8,f9,f10,f11,f12,f13,f14,f15,f16,f24,f25]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ012-1 : TPTP v9.3.1. Bugfixed v1.2.1.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.11/0.39 % Computer : n011.cluster.edu
% 0.11/0.39 % Model : x86_64 x86_64
% 0.11/0.39 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.39 % Memory : 8046.5625MB
% 0.11/0.39 % OS : Linux 6.8.0-71-generic
% 0.11/0.39 % CPULimit : 300
% 0.11/0.39 % WCLimit : 300
% 0.11/0.39 % DateTime : Sun Sep 27 22:29:31 UTC 2026
% 0.11/0.39 % CPUTime :
% 0.11/0.39 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.11/0.42 Running first-order model finding
% 0.11/0.42 Running: /export/starexec/sandbox2/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.17/0.48 % (2820680)Will run a generic schedule for satisfiability detection.
% 0.17/0.48 % (2820685)fmb+10_1_sas=cadical:bce=on:rp=on:random_seed=3540575999_2999 on theBenchmark for (2999ds/0Mi)
% 0.17/0.48 % Detected minimum model sizes of [1]
% 0.17/0.48 % Detected maximum model sizes of [6]
% 0.17/0.48 % TRYING [1]
% 0.17/0.48 % TRYING [2]
% 0.17/0.48 % TRYING [3]
% 0.17/0.48 % (2820685) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-2820680-2820685"...
% 0.17/0.48 % (2820685)...printing done.
% 0.17/0.48 % (2820685)Refutation found. Thanks to Tanya!
% 0.17/0.48 % SZS status Unsatisfiable for theBenchmark
% 0.17/0.48 % SZS output start Proof for theBenchmark
% See solution above
% 0.17/0.48 % (2820685)------------------------------
% 0.17/0.48 % (2820685)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.17/0.48 % (2820685)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.17/0.48 % (2820685)CaDiCaL version: 2.1.3
% 0.17/0.48 % (2820685)Termination reason: Refutation
% 0.17/0.48 % (2820685)Time elapsed: 0.001 s
% 0.17/0.48 % (2820685)Peak memory usage: 11 MB
% 0.17/0.48 % (2820685)Instructions burned: 2 (million)
% 0.17/0.48 % (2820680)Success in time 0.046 s
% 0.17/0.48 % Vampire exiting
%------------------------------------------------------------------------------