%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PLA002-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n003.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 12:28:33 PM UTC 2026
% Result : Unsatisfiable 0.12s 0.42s
% Output : Refutation 0.12s
% 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/sandbox2/benchmark/theBenchmark.p',warm_or_cold) ).
fof(f4,axiom,
! [X0] :
( ~ at(b,X0)
| at(a,walk(a,X0)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',walk_b_to_a) ).
fof(f7,axiom,
! [X0] :
( ~ cold(X0)
| ~ at(c,X0)
| at(b,skate(b,X0)) ),
file('/export/starexec/sandbox2/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/sandbox2/benchmark/theBenchmark.p',climb_mountain_d_to_b) ).
fof(f11,axiom,
! [X0] :
( at(c,go(c,X0))
| ~ at(d,X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',go_d_to_c) ).
fof(f15,axiom,
! [X0] :
( at(d,go(d,X0))
| ~ at(f,X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',go_f_to_d) ).
fof(f16,axiom,
at(f,s0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',initial) ).
fof(f17,negated_conjecture,
! [X0] : ~ at(a,X0),
file('/export/starexec/sandbox2/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] :
( ~ at(c,X0)
| ~ cold(X0) ),
inference(forward_subsumption_resolution,[],[f7,f25]) ).
fof(f28,plain,
! [X0] :
( ~ cold(go(c,X0))
| ~ at(d,X0) ),
inference(resolution,[],[f26,f11]) ).
fof(f29,plain,
( ! [X0] :
( ~ at(d,X0)
| at(b,climb(b,X0)) )
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f9,f23]) ).
fof(f30,plain,
( ! [X0] : ~ at(d,X0)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f29,f25]) ).
fof(f31,plain,
( ! [X0] : ~ at(f,X0)
| ~ spl0_2 ),
inference(resolution,[],[f30,f15]) ).
fof(f33,plain,
( $false
| ~ spl0_2 ),
inference(resolution,[],[f31,f16]) ).
fof(f35,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f33]) ).
fof(f41,plain,
( ! [X0] : ~ at(d,X0)
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f28,f20]) ).
fof(f42,plain,
( ! [X0] : ~ at(f,X0)
| ~ spl0_1 ),
inference(resolution,[],[f41,f15]) ).
fof(f44,plain,
( $false
| ~ spl0_1 ),
inference(resolution,[],[f42,f16]) ).
fof(f46,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f44]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f24]) ).
cnf(s2,plain,
~ spl0_2,
inference(sat_conversion,[],[f35]) ).
cnf(s3,plain,
~ spl0_1,
inference(sat_conversion,[],[f46]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s2,s3]) ).
fof(f47,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/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.08/0.36 % Computer : n003.cluster.edu
% 0.08/0.36 % Model : x86_64 x86_64
% 0.08/0.36 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.08/0.36 % Memory : 8046.5625MB
% 0.08/0.36 % OS : Linux 6.8.0-71-generic
% 0.08/0.36 % CPULimit : 300
% 0.08/0.36 % WCLimit : 300
% 0.08/0.36 % DateTime : Sun Sep 27 22:10:57 UTC 2026
% 0.08/0.36 % CPUTime :
% 0.08/0.36 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.12/0.39 Running first-order model finding
% 0.12/0.39 Running: /export/starexec/sandbox2/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.12/0.42 % (965846)Will run a generic schedule for satisfiability detection.
% 0.12/0.42 % (965854)dis+10_1_sil=32000:sp=arity:random_seed=356520098:i=103:fgj=on_3000 on theBenchmark for (3000ds/103Mi)
% 0.12/0.42 % (965854) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-965846-965854"...
% 0.12/0.42 % (965854)...printing done.
% 0.12/0.42 % (965854)Refutation found. Thanks to Tanya!
% 0.12/0.42 % SZS status Unsatisfiable for theBenchmark
% 0.12/0.42 % SZS output start Proof for theBenchmark
% See solution above
% 0.12/0.42 % (965854)------------------------------
% 0.12/0.42 % (965854)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.12/0.42 % (965854)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.12/0.42 % (965854)CaDiCaL version: 2.1.3
% 0.12/0.42 % (965854)Termination reason: Refutation
% 0.12/0.42 % (965854)Time elapsed: 0.001 s
% 0.12/0.42 % (965854)Peak memory usage: 11 MB
% 0.12/0.42 % (965854)Instructions burned: 1 (million)
% 0.12/0.42 % (965846)Success in time 0.015 s
% 0.12/0.42 % Vampire exiting
%------------------------------------------------------------------------------