%------------------------------------------------------------------------------
% File : Vampire---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 THM
% Computer : n002.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 : Theorem 3.44s 1.46s
% Output : Refutation 3.44s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 10
% Syntax : Number of formulae : 38 ( 13 unt; 0 typ; 0 def)
% Number of atoms : 76 ( 0 equ)
% Maximal formula atoms : 3 ( 2 avg)
% Number of connectives : 75 ( 37 ~; 31 |; 5 &)
% ( 0 <=>; 2 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 4 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 : 5 ( 4 usr; 1 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 6 con; 0-0 aty)
% Number of variables : 36 ( 36 !; 0 ?; 36 :)
% 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(f5,axiom,
! [X0: box] :
( contains(X0,apples)
| contains(X0,bananas)
| contains(X0,oranges) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',each_box_contains_something) ).
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(f7,axiom,
! [X0: box,X1: fruit,X2: box] :
( ( contains(X0,X1)
& contains(X2,X1) )
=> equal_boxes(X0,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',contains_is_well_defined2) ).
tff(f9,axiom,
~ equal_boxes(boxb,boxc),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',boxb_not_boxc) ).
tff(f11,axiom,
~ equal_fruits(apples,bananas),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',apples_not_bananas) ).
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,
( ~ contains(boxa,bananas)
| ~ contains(boxc,oranges) ),
inference(ennf_transformation,[],[f19]) ).
tff(f21,plain,
! [X0: box,X1: fruit] :
( ~ label(X0,X1)
| ~ contains(X0,X1) ),
inference(ennf_transformation,[],[f3]) ).
tff(f22,plain,
! [X0: box,X1: fruit,X2: box] :
( equal_boxes(X0,X2)
| ~ contains(X0,X1)
| ~ contains(X2,X1) ),
inference(ennf_transformation,[],[f7]) ).
tff(f23,plain,
! [X0: box,X1: fruit,X2: box] :
( equal_boxes(X0,X2)
| ~ contains(X0,X1)
| ~ contains(X2,X1) ),
inference(flattening,[],[f22]) ).
tff(f24,plain,
! [X0: box,X1: fruit,X2: fruit] :
( equal_fruits(X1,X2)
| ~ contains(X0,X1)
| ~ contains(X0,X2) ),
inference(ennf_transformation,[],[f6]) ).
tff(f25,plain,
! [X0: box,X1: fruit,X2: fruit] :
( equal_fruits(X1,X2)
| ~ contains(X0,X1)
| ~ contains(X0,X2) ),
inference(flattening,[],[f24]) ).
tff(f28,plain,
label(boxc,bananas),
inference(cnf_transformation,[],[f16]) ).
tff(f29,plain,
contains(boxb,apples),
inference(cnf_transformation,[],[f17]) ).
tff(f30,plain,
( ~ contains(boxc,oranges)
| ~ contains(boxa,bananas) ),
inference(cnf_transformation,[],[f20]) ).
tff(f33,plain,
! [X0: fruit] :
( contains(boxc,X0)
| contains(boxb,X0)
| contains(boxa,X0) ),
inference(cnf_transformation,[],[f4]) ).
tff(f35,plain,
~ equal_fruits(apples,bananas),
inference(cnf_transformation,[],[f11]) ).
tff(f36,plain,
! [X0: box] :
( contains(X0,oranges)
| contains(X0,bananas)
| contains(X0,apples) ),
inference(cnf_transformation,[],[f5]) ).
tff(f37,plain,
! [X0: box,X1: fruit] :
( ~ label(X0,X1)
| ~ contains(X0,X1) ),
inference(cnf_transformation,[],[f21]) ).
tff(f38,plain,
~ equal_boxes(boxb,boxc),
inference(cnf_transformation,[],[f9]) ).
tff(f40,plain,
! [X2: box,X0: box,X1: fruit] :
( equal_boxes(X0,X2)
| ~ contains(X0,X1)
| ~ contains(X2,X1) ),
inference(cnf_transformation,[],[f23]) ).
tff(f42,plain,
! [X2: fruit,X0: box,X1: fruit] :
( equal_fruits(X1,X2)
| ~ contains(X0,X1)
| ~ contains(X0,X2) ),
inference(cnf_transformation,[],[f25]) ).
tff(f46,plain,
~ contains(boxc,bananas),
inference(resolution,[],[f37,f28]) ).
tff(f49,plain,
( contains(boxc,bananas)
| contains(boxc,apples)
| ~ contains(boxa,bananas) ),
inference(resolution,[],[f36,f30]) ).
tff(f51,plain,
( contains(boxc,apples)
| ~ contains(boxa,bananas) ),
inference(resolution,[],[f46,f49]) ).
tff(f52,plain,
( contains(boxb,bananas)
| contains(boxa,bananas) ),
inference(resolution,[],[f46,f33]) ).
tff(f55,plain,
! [X0: fruit] :
( ~ contains(boxc,X0)
| ~ contains(boxb,X0) ),
inference(resolution,[],[f40,f38]) ).
tff(f57,plain,
! [X0: box] :
( ~ contains(X0,bananas)
| ~ contains(X0,apples) ),
inference(resolution,[],[f42,f35]) ).
tff(f69,plain,
( ~ contains(boxb,apples)
| ~ contains(boxa,bananas) ),
inference(resolution,[],[f55,f51]) ).
tff(f71,plain,
~ contains(boxa,bananas),
inference(forward_subsumption_resolution,[],[f69,f29]) ).
tff(f85,plain,
contains(boxb,bananas),
inference(forward_subsumption_resolution,[],[f52,f71]) ).
tff(f87,plain,
~ contains(boxb,apples),
inference(resolution,[],[f85,f57]) ).
tff(f88,plain,
$false,
inference(forward_subsumption_resolution,[],[f87,f29]) ).
%------------------------------------------------------------------------------
%----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 THM
% 0.11/0.38 % Computer : n002.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 22:32:07 UTC 2026
% 0.11/0.39 % CPUTime :
% 0.11/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.11/0.42 Running first-order theorem proving
% 0.11/0.42 Running: /export/starexec/sandbox/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 3.44/1.46 % (3952295)Detected formulas, will run a generic FOF schedule.
% 3.44/1.46 % (3952302)lrs+1010_1_anc=all:sfv=off:to=kbo:ncem=casc2026/models/loop7.pt:sil=128000:npcc=on:prc=on:sos=all:bsr=unit_only:sac=on:random_seed=2201305014:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.44/1.46 % (3952303)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=22340447:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.44/1.46 % (3952306)dis-21_1_sil=8000:lcm=predicate:random_seed=1421705058:st=5:avsq=on:i=129:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/129Mi)
% 3.44/1.46 % (3952304)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=3113649509:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.44/1.46 % (3952301)lrs+11_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:lma=off:spb=units:urr=ec_only:bce=on:s2agt=64:updr=off:random_seed=1943122163:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.44/1.46 % (3952300)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=2830540778:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.44/1.46 % (3952305)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=2293593290:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.44/1.46 % (3952303)Refutation not found, incomplete strategy
% 3.44/1.46 % (3952303)------------------------------
% 3.44/1.46 % (3952303)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.44/1.46 % (3952303)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.44/1.46 % (3952303)CaDiCaL version: 2.1.3
% 3.44/1.46 % (3952303)Termination reason: Refutation not found, incomplete strategy
% 3.44/1.46 % (3952303)Time elapsed: 0.001 s
% 3.44/1.46 % (3952303)Peak memory usage: 88 MB
% 3.44/1.46 % (3952304)First to succeed.
% 3.44/1.46 % (3952306)Also succeeded, but the first one will report.
% 3.44/1.46 % (3952304)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3952295"
% 3.44/1.46 % (3952305)Also succeeded, but the first one will report.
% 3.44/1.46 % (3952303)------------------------------
% 3.44/1.46 % (3952303)------------------------------
% 3.44/1.46 % (3952304)Refutation found. Thanks to Tanya!
% 3.44/1.46 % SZS status Theorem for theBenchmark
% 3.44/1.46 % SZS output start Proof for theBenchmark
% See solution above
% 3.44/1.46 % (3952304)------------------------------
% 3.44/1.46 % (3952304)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.44/1.46 % (3952304)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.44/1.46 % (3952304)CaDiCaL version: 2.1.3
% 3.44/1.46 % (3952304)Termination reason: Refutation
% 3.44/1.46 % (3952304)Time elapsed: 0.002 s
% 3.44/1.46 % (3952304)Peak memory usage: 88 MB
% 3.44/1.46 % (3952304)Instructions burned: 2 (million)
% 3.44/1.46 % (3952304)------------------------------
% 3.44/1.46 % (3952304)------------------------------
% 3.44/1.46 % (3952295)Success in time 0.406 s
% 3.44/1.46 % Vampire exiting
%------------------------------------------------------------------------------