%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PLA003-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n007.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 12:27:40 PM UTC 2026
% Result : Unsatisfiable 2.77s 1.36s
% Output : Refutation 2.77s
% Verified :
% SZS Type : Refutation
% Derivation depth : 7
% Number of leaves : 8
% Syntax : Number of formulae : 15 ( 9 unt; 0 def)
% Number of atoms : 21 ( 0 equ)
% Maximal formula atoms : 2 ( 1 avg)
% Number of connectives : 13 ( 7 ~; 6 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 4 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 2 ( 1 usr; 1 prp; 0-3 aty)
% Number of functors : 11 ( 11 usr; 8 con; 0-3 aty)
% Number of variables : 27 ( 27 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0,X1] :
( ~ can(monkey(X0,floor,nothing),ladder(X0,floor),X1)
| can(monkey(X0,ceiling,nothing),ladder(X0,floor),X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',climb_up) ).
fof(f3,axiom,
! [X2,X0,X1] :
( ~ can(monkey(X2,floor,the_ladder),ladder(X2,floor),X1)
| can(monkey(X0,floor,the_ladder),ladder(X0,floor),X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',go_holding_ladder) ).
fof(f5,axiom,
! [X2,X3,X0,X1] :
( ~ can(monkey(X3,floor,nothing),X1,X2)
| can(monkey(X0,floor,nothing),X1,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',go_holding_nothing) ).
fof(f6,axiom,
! [X2,X3,X0,X1] :
( ~ can(monkey(X0,X1,the_ladder),ladder(X0,X3),X2)
| can(monkey(X0,X1,nothing),ladder(X0,floor),X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',drop_ladder) ).
fof(f8,axiom,
! [X2,X0,X1] :
( ~ can(monkey(X0,X1,nothing),X2,bananas(X0,X1))
| can(monkey(X0,X1,the_bananas),X2,bananas(X0,X1)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',grab_bananas) ).
fof(f9,axiom,
! [X2,X0,X1] :
( ~ can(monkey(X0,X1,nothing),ladder(X0,X1),X2)
| can(monkey(X0,X1,the_ladder),ladder(X0,X1),X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',grab_ladder) ).
fof(f10,axiom,
can(monkey(l0,floor,nothing),ladder(l1,floor),bananas(l2,ceiling)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',initial_situation) ).
fof(f11,negated_conjecture,
! [X2,X3,X0,X1] : ~ can(monkey(X0,X1,the_bananas),X2,X3),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_the_monkey_can_get_the_bananas) ).
fof(f12,plain,
! [X0] : can(monkey(X0,floor,nothing),ladder(l1,floor),bananas(l2,ceiling)),
inference(resolution,[],[f5,f10]) ).
fof(f16,plain,
can(monkey(l1,floor,the_ladder),ladder(l1,floor),bananas(l2,ceiling)),
inference(resolution,[],[f9,f12]) ).
fof(f17,plain,
! [X0] : can(monkey(X0,floor,the_ladder),ladder(X0,floor),bananas(l2,ceiling)),
inference(resolution,[],[f16,f3]) ).
fof(f20,plain,
! [X0] : can(monkey(X0,floor,nothing),ladder(X0,floor),bananas(l2,ceiling)),
inference(resolution,[],[f17,f6]) ).
fof(f21,plain,
! [X0] : can(monkey(X0,ceiling,nothing),ladder(X0,floor),bananas(l2,ceiling)),
inference(resolution,[],[f20,f1]) ).
fof(f25,plain,
can(monkey(l2,ceiling,the_bananas),ladder(l2,floor),bananas(l2,ceiling)),
inference(resolution,[],[f21,f8]) ).
fof(f26,plain,
$false,
inference(forward_subsumption_resolution,[],[f25,f11]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PLA003-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.11/0.37 % Computer : n007.cluster.edu
% 0.11/0.37 % Model : x86_64 x86_64
% 0.11/0.37 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.37 % Memory : 8046.5625MB
% 0.11/0.37 % 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 22:07:10 UTC 2026
% 0.11/0.38 % CPUTime :
% 0.11/0.38 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.11/0.41 Running first-order theorem proving
% 0.11/0.41 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
% 2.77/1.36 % (1825774)Input is clausal, will run a generic CNF schedule.
% 2.77/1.36 % (1825782)lrs+10_1_sil=8000:sp=occurrence:random_seed=493294299:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.77/1.36 % (1825782)First to succeed.
% 2.77/1.36 % (1825782)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-1825774"
% 2.77/1.36 % (1825785)dis-21_1_sil=8000:lcm=predicate:random_seed=3805985186: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)
% 2.77/1.36 % (1825779)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=209247064:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.77/1.36 % (1825781)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=3910986493:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.77/1.36 % (1825783)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=1338470737:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.77/1.36 % (1825780)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=3080168447:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.77/1.36 % (1825784)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3375863488:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.77/1.36 % (1825783)Refutation not found, incomplete strategy
% 2.77/1.36 % (1825783)------------------------------
% 2.77/1.36 % (1825783)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.77/1.36 % (1825783)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.77/1.36 % (1825783)CaDiCaL version: 2.1.3
% 2.77/1.36 % (1825783)Termination reason: Refutation not found, incomplete strategy
% 2.77/1.36 % (1825783)Time elapsed: 0.001 s
% 2.77/1.36 % (1825783)Peak memory usage: 87 MB
% 2.77/1.36 % (1825785)Also succeeded, but the first one will report.
% 2.77/1.36 % (1825784)Also succeeded, but the first one will report.
% 2.77/1.36 % (1825782)Refutation found. Thanks to Tanya!
% 2.77/1.36 % SZS status Unsatisfiable for theBenchmark
% 2.77/1.36 % SZS output start Proof for theBenchmark
% See solution above
% 2.77/1.36 % (1825782)------------------------------
% 2.77/1.36 % (1825782)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.77/1.36 % (1825782)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.77/1.36 % (1825782)CaDiCaL version: 2.1.3
% 2.77/1.36 % (1825782)Termination reason: Refutation
% 2.77/1.36 % (1825782)Time elapsed: 0.001 s
% 2.77/1.36 % (1825782)Peak memory usage: 88 MB
% 2.77/1.36 % (1825782)Instructions burned: 1 (million)
% 2.77/1.36 % (1825782)------------------------------
% 2.77/1.36 % (1825782)------------------------------
% 2.77/1.36 % (1825774)Success in time 0.311 s
% 2.77/1.36 % Vampire exiting
%------------------------------------------------------------------------------