%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PLA002-1 : 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 : n009.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 2.63s 1.38s
% Output : Refutation 2.63s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 10
% Syntax : Number of formulae : 30 ( 9 unt; 2 def)
% Number of atoms : 54 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 55 ( 31 ~; 22 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 6 ( 5 usr; 3 prp; 0-2 aty)
% Number of functors : 10 ( 10 usr; 6 con; 0-2 aty)
% Number of variables : 20 ( 0 sgn 20 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0,X1] :
( warm(X0)
| cold(X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',warm_or_cold) ).
fof(f4,axiom,
! [X0] :
( ~ at(b,X0)
| at(a,walk(a,X0)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',walk_b_to_a) ).
fof(f7,axiom,
! [X0] :
( ~ cold(X0)
| ~ at(c,X0)
| at(b,skate(b,X0)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',cross_river_c_to_b) ).
fof(f9,axiom,
! [X0] :
( ~ warm(X0)
| ~ at(d,X0)
| at(b,climb(b,X0)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',climb_mountain_d_to_b) ).
fof(f11,axiom,
! [X0] :
( at(c,go(c,X0))
| ~ at(d,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',go_d_to_c) ).
fof(f15,axiom,
! [X0] :
( at(d,go(d,X0))
| ~ at(f,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',go_f_to_d) ).
fof(f16,axiom,
at(f,s0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',initial) ).
fof(f17,negated_conjecture,
! [X0] : ~ at(a,X0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_you_can_get_to_a) ).
fof(f19,definition,
( spl0_1
<=> ! [X1] : cold(X1) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f20,plain,
( ! [X1] : cold(X1)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f19]) ).
fof(f22,definition,
( spl0_2
<=> ! [X0] : warm(X0) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f23,plain,
( ! [X0] : warm(X0)
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f22]) ).
fof(f24,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f1,f22,f19]) ).
fof(f25,plain,
! [X0] : ~ at(b,X0),
inference(forward_subsumption_resolution,[],[f4,f17]) ).
fof(f26,plain,
! [X0] :
( ~ cold(X0)
| ~ at(c,X0) ),
inference(forward_subsumption_resolution,[],[f7,f25]) ).
fof(f27,plain,
( ! [X0] :
( ~ at(d,X0)
| at(b,climb(b,X0)) )
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f9,f23]) ).
fof(f28,plain,
( ! [X0] : ~ at(d,X0)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f27,f25]) ).
fof(f29,plain,
( ! [X0] : ~ at(f,X0)
| ~ spl0_2 ),
inference(resolution,[],[f28,f15]) ).
fof(f31,plain,
( $false
| ~ spl0_2 ),
inference(resolution,[],[f29,f16]) ).
fof(f33,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f31]) ).
fof(f35,plain,
( ! [X0] : ~ at(c,X0)
| ~ spl0_1 ),
inference(resolution,[],[f20,f26]) ).
fof(f37,plain,
( ! [X0] : ~ at(d,X0)
| ~ spl0_1 ),
inference(resolution,[],[f35,f11]) ).
fof(f39,plain,
( ! [X0] : ~ at(f,X0)
| ~ spl0_1 ),
inference(resolution,[],[f37,f15]) ).
fof(f41,plain,
( $false
| ~ spl0_1 ),
inference(resolution,[],[f39,f16]) ).
fof(f43,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f41]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f24]) ).
cnf(s2,plain,
~ spl0_2,
inference(sat_conversion,[],[f33]) ).
cnf(s3,plain,
~ spl0_1,
inference(sat_conversion,[],[f43]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s2,s3]) ).
fof(f44,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PLA002-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.37 % Computer : n009.cluster.edu
% 0.10/0.37 % Model : x86_64 x86_64
% 0.10/0.37 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.37 % Memory : 8046.5625MB
% 0.10/0.37 % OS : Linux 6.8.0-71-generic
% 0.10/0.38 % CPULimit : 300
% 0.10/0.38 % WCLimit : 300
% 0.10/0.38 % DateTime : Sun Sep 27 22:09:15 UTC 2026
% 0.10/0.38 % CPUTime :
% 0.10/0.38 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.15/0.41 Running first-order theorem proving
% 0.15/0.41 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
% 2.63/1.38 % (2454044)Input is clausal, will run a generic CNF schedule.
% 2.63/1.38 % (2454134)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=890806419:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.63/1.38 % (2454134)First to succeed.
% 2.63/1.38 % (2454134)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-2454044"
% 2.63/1.38 % (2454127)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=2628444723:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.63/1.38 % (2454131)lrs+10_1_sil=8000:sp=occurrence:random_seed=332727544:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.63/1.38 % (2454128)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=924218594:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.63/1.38 % (2454131)Also succeeded, but the first one will report.
% 2.63/1.38 % (2454135)dis-21_1_sil=8000:lcm=predicate:random_seed=4048404822: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)
% 2.63/1.38 % (2454135)Also succeeded, but the first one will report.
% 2.63/1.38 % (2454130)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1636846897:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.63/1.38 % (2454133)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=294858059:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.63/1.38 % (2454133)Also succeeded, but the first one will report.
% 2.63/1.38 % (2454134)Refutation found. Thanks to Tanya!
% 2.63/1.38 % SZS status Unsatisfiable for theBenchmark
% 2.63/1.38 % SZS output start Proof for theBenchmark
% See solution above
% 2.63/1.38 % (2454134)------------------------------
% 2.63/1.38 % (2454134)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.63/1.38 % (2454134)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.63/1.38 % (2454134)CaDiCaL version: 2.1.3
% 2.63/1.38 % (2454134)Termination reason: Refutation
% 2.63/1.38 % (2454134)Time elapsed: 0.002 s
% 2.63/1.38 % (2454134)Peak memory usage: 89 MB
% 2.63/1.38 % (2454134)Instructions burned: 1 (million)
% 2.63/1.38 % (2454134)------------------------------
% 2.63/1.38 % (2454134)------------------------------
% 2.63/1.38 % (2454044)Success in time 0.3 s
% 2.63/1.38 % Vampire exiting
%------------------------------------------------------------------------------