%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ012_1 : TPTP v9.3.1. Released v5.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n010.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 : Theorem 0.11s 0.45s
% Output : Refutation 0.11s
% Verified :
% SZS Type : Refutation
% Derivation depth : 12
% Number of leaves : 11
% Syntax : Number of formulae : 49 ( 17 unt; 0 typ; 2 def)
% Number of atoms : 89 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 78 ( 38 ~; 33 |; 4 &)
% ( 2 <=>; 1 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of types : 3 ( 2 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 7 ( 6 usr; 3 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 6 con; 0-0 aty)
% Number of variables : 22 ( 0 sgn 22 !; 0 ?; 22 :)
% Comments :
%------------------------------------------------------------------------------
tff(type_def_5,type,
box: $tType ).
tff(type_def_6,type,
fruit: $tType ).
tff(func_def_0,type,
boxa: box ).
tff(func_def_1,type,
boxb: box ).
tff(func_def_2,type,
boxc: box ).
tff(func_def_3,type,
apples: fruit ).
tff(func_def_4,type,
bananas: fruit ).
tff(func_def_5,type,
oranges: fruit ).
tff(pred_def_1,type,
equal_fruits: ( fruit * fruit ) > $o ).
tff(pred_def_2,type,
equal_boxes: ( box * box ) > $o ).
tff(pred_def_3,type,
contains: ( box * fruit ) > $o ).
tff(pred_def_4,type,
label: ( box * fruit ) > $o ).
tff(f3,axiom,
! [X0: box,X1: fruit] :
~ ( label(X0,X1)
& contains(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',label_is_wrong) ).
tff(f4,axiom,
! [X0: fruit] :
( contains(boxa,X0)
| contains(boxb,X0)
| contains(boxc,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',each_thing_is_in_a_box) ).
tff(f6,axiom,
! [X0: box,X1: fruit,X2: fruit] :
( ( contains(X0,X1)
& contains(X0,X2) )
=> equal_fruits(X1,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',contains_is_well_defined1) ).
tff(f11,axiom,
~ equal_fruits(apples,bananas),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',apples_not_bananas) ).
tff(f12,axiom,
~ equal_fruits(bananas,oranges),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',bananas_not_oranges) ).
tff(f15,axiom,
label(boxb,oranges),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',boxb_labelled_oranges) ).
tff(f16,axiom,
label(boxc,bananas),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',boxc_labelled_bananas) ).
tff(f17,axiom,
contains(boxb,apples),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',boxb_contains_apples) ).
tff(f18,conjecture,
( contains(boxa,bananas)
& contains(boxc,oranges) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_boxa_contains_bananas_and_boxc_oranges) ).
tff(f19,negated_conjecture,
~ ( contains(boxa,bananas)
& contains(boxc,oranges) ),
inference(negated_conjecture,[status(cth)],[f18]) ).
tff(f20,plain,
! [X0: box,X1: fruit] :
( ~ label(X0,X1)
| ~ contains(X0,X1) ),
inference(ennf_transformation,[],[f3]) ).
tff(f21,plain,
! [X0: box,X1: fruit,X2: fruit] :
( equal_fruits(X1,X2)
| ~ contains(X0,X1)
| ~ contains(X0,X2) ),
inference(ennf_transformation,[],[f6]) ).
tff(f22,plain,
! [X0: box,X1: fruit,X2: fruit] :
( equal_fruits(X1,X2)
| ~ contains(X0,X1)
| ~ contains(X0,X2) ),
inference(flattening,[],[f21]) ).
tff(f25,plain,
( ~ contains(boxa,bananas)
| ~ contains(boxc,oranges) ),
inference(ennf_transformation,[],[f19]) ).
tff(f28,plain,
! [X0: box,X1: fruit] :
( ~ label(X0,X1)
| ~ contains(X0,X1) ),
inference(cnf_transformation,[],[f20]) ).
tff(f29,plain,
! [X0: fruit] :
( contains(boxc,X0)
| contains(boxb,X0)
| contains(boxa,X0) ),
inference(cnf_transformation,[],[f4]) ).
tff(f31,plain,
! [X2: fruit,X0: box,X1: fruit] :
( equal_fruits(X1,X2)
| ~ contains(X0,X1)
| ~ contains(X0,X2) ),
inference(cnf_transformation,[],[f22]) ).
tff(f36,plain,
~ equal_fruits(apples,bananas),
inference(cnf_transformation,[],[f11]) ).
tff(f37,plain,
~ equal_fruits(bananas,oranges),
inference(cnf_transformation,[],[f12]) ).
tff(f40,plain,
label(boxb,oranges),
inference(cnf_transformation,[],[f15]) ).
tff(f41,plain,
label(boxc,bananas),
inference(cnf_transformation,[],[f16]) ).
tff(f42,plain,
contains(boxb,apples),
inference(cnf_transformation,[],[f17]) ).
tff(f43,plain,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
inference(cnf_transformation,[],[f25]) ).
tff(f45,definition,
( spl0_1
<=> contains(boxa,bananas) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
tff(f46,plain,
( contains(boxa,bananas)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f45]) ).
tff(f47,plain,
( ~ contains(boxa,bananas)
| spl0_1 ),
inference(avatar_component_clause,[],[f45]) ).
tff(f49,definition,
( spl0_2
<=> contains(boxc,oranges) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
tff(f51,plain,
( ~ contains(boxc,oranges)
| spl0_2 ),
inference(avatar_component_clause,[],[f49]) ).
tff(f52,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f43,f49,f45]) ).
tff(f54,plain,
~ contains(boxb,oranges),
inference(resolution,[],[f28,f40]) ).
tff(f55,plain,
~ contains(boxc,bananas),
inference(resolution,[],[f28,f41]) ).
tff(f57,plain,
( contains(boxb,bananas)
| contains(boxa,bananas) ),
inference(resolution,[],[f55,f29]) ).
tff(f58,plain,
( contains(boxb,bananas)
| spl0_1 ),
inference(forward_subsumption_resolution,[],[f57,f47]) ).
tff(f59,plain,
! [X0: box] :
( ~ contains(X0,bananas)
| ~ contains(X0,apples) ),
inference(resolution,[],[f31,f36]) ).
tff(f61,plain,
! [X0: box] :
( ~ contains(X0,oranges)
| ~ contains(X0,bananas) ),
inference(resolution,[],[f31,f37]) ).
tff(f65,plain,
( ~ contains(boxb,apples)
| spl0_1 ),
inference(resolution,[],[f59,f58]) ).
tff(f67,plain,
( $false
| spl0_1 ),
inference(forward_subsumption_resolution,[],[f65,f42]) ).
tff(f68,plain,
spl0_1,
inference(avatar_contradiction_clause,[],[f67]) ).
tff(f70,plain,
( contains(boxb,oranges)
| contains(boxa,oranges)
| spl0_2 ),
inference(resolution,[],[f51,f29]) ).
tff(f73,plain,
( contains(boxa,oranges)
| spl0_2 ),
inference(forward_subsumption_resolution,[],[f70,f54]) ).
tff(f78,plain,
( ~ contains(boxa,bananas)
| spl0_2 ),
inference(resolution,[],[f61,f73]) ).
tff(f80,plain,
( $false
| ~ spl0_1
| spl0_2 ),
inference(forward_subsumption_resolution,[],[f78,f46]) ).
tff(f81,plain,
( ~ spl0_1
| spl0_2 ),
inference(avatar_contradiction_clause,[],[f80]) ).
cnf(s1,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f52]) ).
cnf(s2,plain,
spl0_1,
inference(sat_conversion,[],[f68]) ).
cnf(s3,plain,
( ~ spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f81]) ).
cnf(s4,plain,
spl0_2,
inference(rat,[],[s3,s2]) ).
cnf(s5,plain,
$false,
inference(rat,[],[s1,s4,s2]) ).
tff(f82,plain,
$false,
inference(avatar_sat_refutation,[],[s5]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ012_1 : TPTP v9.3.1. Released v5.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.11/0.38 % Computer : n010.cluster.edu
% 0.11/0.38 % Model : x86_64 x86_64
% 0.11/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.38 % Memory : 8046.5625MB
% 0.11/0.38 % OS : Linux 6.8.0-71-generic
% 0.11/0.38 % CPULimit : 300
% 0.11/0.38 % WCLimit : 300
% 0.11/0.38 % DateTime : Sun Sep 27 22:29:47 UTC 2026
% 0.11/0.39 % CPUTime :
% 0.11/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.11/0.41 Running first-order model finding
% 0.11/0.42 Running: /export/starexec/sandbox/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 0.11/0.45 % (1368779)Will run a generic schedule for satisfiability detection.
% 0.11/0.45 % (1368788)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=1256682760:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.11/0.45 % (1368788) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-1368779-1368788"...
% 0.11/0.45 % (1368788)...printing done.
% 0.11/0.45 % (1368788)Refutation found. Thanks to Tanya!
% 0.11/0.45 % SZS status Theorem for theBenchmark
% 0.11/0.45 % SZS output start Proof for theBenchmark
% See solution above
% 0.11/0.45 % (1368788)------------------------------
% 0.11/0.45 % (1368788)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.11/0.45 % (1368788)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.11/0.45 % (1368788)CaDiCaL version: 2.1.3
% 0.11/0.45 % (1368788)Termination reason: Refutation
% 0.11/0.45 % (1368788)Time elapsed: 0.001 s
% 0.11/0.45 % (1368788)Peak memory usage: 12 MB
% 0.11/0.45 % (1368788)Instructions burned: 2 (million)
% 0.11/0.45 % (1368779)Success in time 0.025 s
% 0.11/0.45 % Vampire exiting
%------------------------------------------------------------------------------