%------------------------------------------------------------------------------
% File : Vampire---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 THM
% Computer : n020.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 12:31:12 PM UTC 2026
% Result : Unsatisfiable 3.64s 1.50s
% Output : Refutation 3.64s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 14
% Syntax : Number of formulae : 46 ( 16 unt; 5 def)
% Number of atoms : 81 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 72 ( 37 ~; 30 |; 0 &)
% ( 5 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 9 ( 8 usr; 6 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 6 con; 0-0 aty)
% Number of variables : 8 ( 0 sgn 8 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
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(boxc,X0)
| contains(boxb,X0)
| contains(boxa,X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',each_thing_is_in_a_box) ).
fof(f6,axiom,
! [X2,X0,X1] :
( equal_fruits(X1,X2)
| ~ contains(X0,X2)
| ~ contains(X0,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',contains_is_well_defined1) ).
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(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(f20,definition,
( spl0_1
<=> contains(boxc,oranges) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f21,plain,
( ~ contains(boxc,oranges)
| spl0_1 ),
inference(avatar_component_clause,[],[f20]) ).
fof(f23,definition,
( spl0_2
<=> contains(boxa,bananas) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f25,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f18,f23,f20]) ).
fof(f27,plain,
~ contains(boxb,oranges),
inference(resolution,[],[f3,f15]) ).
fof(f28,plain,
~ contains(boxc,bananas),
inference(resolution,[],[f3,f16]) ).
fof(f31,definition,
( spl0_3
<=> contains(boxa,oranges) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f32,plain,
( contains(boxa,oranges)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f31]) ).
fof(f34,definition,
( spl0_4
<=> contains(boxb,oranges) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f35,plain,
( contains(boxb,oranges)
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f34]) ).
fof(f38,plain,
! [X0] :
( ~ contains(X0,bananas)
| ~ contains(X0,apples) ),
inference(resolution,[],[f6,f11]) ).
fof(f40,plain,
! [X0] :
( ~ contains(X0,oranges)
| ~ contains(X0,bananas) ),
inference(resolution,[],[f6,f12]) ).
fof(f41,plain,
( contains(boxb,bananas)
| contains(boxa,bananas) ),
inference(resolution,[],[f28,f4]) ).
fof(f44,definition,
( spl0_5
<=> contains(boxb,bananas) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f45,plain,
( contains(boxb,bananas)
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f44]) ).
fof(f46,plain,
( spl0_2
| spl0_5 ),
inference(avatar_split_clause,[],[f41,f44,f23]) ).
fof(f50,plain,
( ~ contains(boxb,apples)
| ~ spl0_5 ),
inference(resolution,[],[f38,f45]) ).
fof(f52,plain,
( $false
| ~ spl0_5 ),
inference(resolution,[],[f50,f17]) ).
fof(f53,plain,
~ spl0_5,
inference(avatar_contradiction_clause,[],[f52]) ).
fof(f58,plain,
( contains(boxb,oranges)
| contains(boxa,oranges)
| spl0_1 ),
inference(resolution,[],[f21,f4]) ).
fof(f65,plain,
( spl0_3
| spl0_4
| spl0_1 ),
inference(avatar_split_clause,[],[f58,f20,f34,f31]) ).
fof(f66,plain,
( $false
| ~ spl0_4 ),
inference(resolution,[],[f35,f27]) ).
fof(f67,plain,
~ spl0_4,
inference(avatar_contradiction_clause,[],[f66]) ).
fof(f73,plain,
( ~ contains(boxa,bananas)
| ~ spl0_3 ),
inference(resolution,[],[f40,f32]) ).
fof(f75,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(avatar_split_clause,[],[f73,f31,f23]) ).
cnf(s1,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f25]) ).
cnf(s3,plain,
( spl0_2
| spl0_5 ),
inference(sat_conversion,[],[f46]) ).
cnf(s4,plain,
~ spl0_5,
inference(sat_conversion,[],[f53]) ).
cnf(s7,plain,
( spl0_1
| spl0_3
| spl0_4 ),
inference(sat_conversion,[],[f65]) ).
cnf(s8,plain,
~ spl0_4,
inference(sat_conversion,[],[f67]) ).
cnf(s9,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(sat_conversion,[],[f75]) ).
cnf(s10,plain,
( spl0_1
| spl0_3 ),
inference(rat,[],[s7,s8]) ).
cnf(s11,plain,
spl0_2,
inference(rat,[],[s3,s4]) ).
cnf(s12,plain,
~ spl0_3,
inference(rat,[],[s9,s11]) ).
cnf(s13,plain,
spl0_1,
inference(rat,[],[s10,s12]) ).
cnf(s14,plain,
$false,
inference(rat,[],[s1,s11,s13]) ).
fof(f76,plain,
$false,
inference(avatar_sat_refutation,[],[s14]) ).
%------------------------------------------------------------------------------
%----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 THM
% 0.12/0.38 % Computer : n020.cluster.edu
% 0.12/0.38 % Model : x86_64 x86_64
% 0.12/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.38 % Memory : 8046.5625MB
% 0.12/0.38 % OS : Linux 6.8.0-71-generic
% 0.12/0.38 % CPULimit : 300
% 0.12/0.38 % WCLimit : 300
% 0.12/0.38 % DateTime : Sun Sep 27 22:30:04 UTC 2026
% 0.12/0.38 % CPUTime :
% 0.12/0.38 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.42 Running first-order theorem proving
% 0.12/0.42 Running: /export/starexec/sandbox2/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 3.64/1.50 % (3829232)Input is clausal, will run a generic CNF schedule.
% 3.64/1.50 % (3829237)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=full:npcc=on:drc=off:sp=weighted_frequency:spb=goal:fd=preordered:foolp=on:random_seed=3849397614:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.64/1.50 % (3829239)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=952118101:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.64/1.50 % (3829240)lrs+10_1_sil=8000:sp=occurrence:random_seed=799149170:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.64/1.50 % (3829242)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1469608626:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.64/1.50 % (3829241)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=8457598:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.64/1.50 % (3829243)dis-21_1_sil=8000:lcm=predicate:random_seed=3535483202:st=5:avsq=on:i=117:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/117Mi)
% 3.64/1.50 % (3829238)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=1274973792:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.64/1.50 % (3829243)First to succeed.
% 3.64/1.50 % (3829242)Also succeeded, but the first one will report.
% 3.64/1.50 % (3829243)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3829232"
% 3.64/1.50 % (3829240)Also succeeded, but the first one will report.
% 3.64/1.50 % (3829241)Also succeeded, but the first one will report.
% 3.64/1.50 % (3829243)Refutation found. Thanks to Tanya!
% 3.64/1.50 % SZS status Unsatisfiable for theBenchmark
% 3.64/1.50 % SZS output start Proof for theBenchmark
% See solution above
% 3.64/1.50 % (3829243)------------------------------
% 3.64/1.50 % (3829243)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.64/1.50 % (3829243)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.64/1.50 % (3829243)CaDiCaL version: 2.1.3
% 3.64/1.50 % (3829243)Termination reason: Refutation
% 3.64/1.50 % (3829243)Time elapsed: 0.003 s
% 3.64/1.50 % (3829243)Peak memory usage: 89 MB
% 3.64/1.50 % (3829243)Instructions burned: 2 (million)
% 3.64/1.50 % (3829243)------------------------------
% 3.64/1.50 % (3829243)------------------------------
% 3.64/1.50 % (3829232)Success in time 0.433 s
% 3.64/1.50 % Vampire exiting
%------------------------------------------------------------------------------