%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ001-1 : 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 : n001.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 12:31:47 PM UTC 2026
% Result : Unsatisfiable 0.22s 0.51s
% Output : Refutation 0.22s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 13
% Syntax : Number of formulae : 39 ( 10 unt; 3 def)
% Number of atoms : 72 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 67 ( 34 ~; 30 |; 0 &)
% ( 3 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 8 ( 7 usr; 4 prp; 0-2 aty)
% Number of functors : 3 ( 3 usr; 3 con; 0-0 aty)
% Number of variables : 8 ( 0 sgn 8 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f2,axiom,
lives(butler),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',butler) ).
fof(f4,axiom,
! [X0,X1] :
( ~ richer(X0,X1)
| ~ killed(X0,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',poorer_killer) ).
fof(f5,axiom,
! [X0] :
( ~ hates(charles,X0)
| ~ hates(agatha,X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',different_hates) ).
fof(f6,axiom,
! [X0] :
( ~ hates(X0,charles)
| ~ hates(X0,butler)
| ~ hates(X0,agatha) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',no_one_hates_everyone) ).
fof(f7,axiom,
hates(agatha,agatha),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',agatha_hates_agatha) ).
fof(f8,axiom,
hates(agatha,charles),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',agatha_hates_charles) ).
fof(f9,axiom,
! [X0,X1] :
( ~ killed(X0,X1)
| hates(X0,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',killer_hates_victim) ).
fof(f10,axiom,
! [X0] :
( ~ hates(agatha,X0)
| hates(butler,X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',same_hates) ).
fof(f11,axiom,
! [X0] :
( hates(butler,X0)
| richer(X0,agatha)
| ~ lives(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',butler_hates_poor) ).
fof(f12,negated_conjecture,
( killed(butler,agatha)
| killed(charles,agatha) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_neither_charles_nor_butler_did_it) ).
fof(f14,definition,
( spl0_1
<=> killed(charles,agatha) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f16,plain,
( killed(charles,agatha)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f14]) ).
fof(f18,definition,
( spl0_2
<=> killed(butler,agatha) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f20,plain,
( killed(butler,agatha)
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f18]) ).
fof(f21,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f12,f18,f14]) ).
fof(f22,plain,
( hates(butler,agatha)
| ~ spl0_2 ),
inference(resolution,[],[f9,f20]) ).
fof(f24,plain,
hates(butler,charles),
inference(resolution,[],[f10,f8]) ).
fof(f35,definition,
( spl0_4
<=> hates(butler,butler) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f37,plain,
( ~ hates(butler,butler)
| spl0_4 ),
inference(avatar_component_clause,[],[f35]) ).
fof(f39,plain,
( richer(butler,agatha)
| ~ lives(butler)
| spl0_4 ),
inference(resolution,[],[f37,f11]) ).
fof(f40,plain,
( richer(butler,agatha)
| spl0_4 ),
inference(forward_subsumption_resolution,[],[f39,f2]) ).
fof(f41,plain,
( ~ hates(butler,butler)
| ~ hates(butler,agatha) ),
inference(resolution,[],[f24,f6]) ).
fof(f42,plain,
( ~ killed(butler,agatha)
| spl0_4 ),
inference(resolution,[],[f40,f4]) ).
fof(f43,plain,
( $false
| ~ spl0_2
| spl0_4 ),
inference(forward_subsumption_resolution,[],[f42,f20]) ).
fof(f44,plain,
( ~ spl0_2
| spl0_4 ),
inference(avatar_contradiction_clause,[],[f43]) ).
fof(f45,plain,
( ~ hates(butler,butler)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f41,f22]) ).
fof(f46,plain,
( ~ spl0_4
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f45,f18,f35]) ).
fof(f54,plain,
( hates(charles,agatha)
| ~ spl0_1 ),
inference(resolution,[],[f16,f9]) ).
fof(f58,plain,
( ~ hates(agatha,agatha)
| ~ spl0_1 ),
inference(resolution,[],[f54,f5]) ).
fof(f59,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f58,f7]) ).
fof(f60,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f59]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f21]) ).
cnf(s3,plain,
( ~ spl0_2
| spl0_4 ),
inference(sat_conversion,[],[f44]) ).
cnf(s4,plain,
( ~ spl0_2
| ~ spl0_4 ),
inference(sat_conversion,[],[f46]) ).
cnf(s8,plain,
~ spl0_1,
inference(sat_conversion,[],[f60]) ).
cnf(s9,plain,
spl0_2,
inference(rat,[],[s1,s8]) ).
cnf(s10,plain,
~ spl0_4,
inference(rat,[],[s4,s9]) ).
cnf(s11,plain,
$false,
inference(rat,[],[s3,s10,s9]) ).
fof(f61,plain,
$false,
inference(avatar_sat_refutation,[],[s11]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.04 % Problem : PUZ001-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.08 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.15/0.42 % Computer : n001.cluster.edu
% 0.15/0.42 % Model : x86_64 x86_64
% 0.15/0.42 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.15/0.42 % Memory : 8046.5625MB
% 0.15/0.42 % OS : Linux 6.8.0-71-generic
% 0.15/0.42 % CPULimit : 300
% 0.15/0.42 % WCLimit : 300
% 0.15/0.42 % DateTime : Sun Sep 27 22:33:01 UTC 2026
% 0.15/0.43 % CPUTime :
% 0.15/0.43 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.22/0.47 Running first-order model finding
% 0.22/0.47 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
% 0.22/0.51 % (4030705)Will run a generic schedule for satisfiability detection.
% 0.22/0.51 % (4030713)dis+10_1_sil=32000:sp=arity:random_seed=431313797:i=103:fgj=on_3000 on theBenchmark for (3000ds/103Mi)
% 0.22/0.51 % (4030713) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-4030705-4030713"...
% 0.22/0.51 % (4030713)...printing done.
% 0.22/0.51 % (4030713)Refutation found. Thanks to Tanya!
% 0.22/0.51 % SZS status Unsatisfiable for theBenchmark
% 0.22/0.51 % SZS output start Proof for theBenchmark
% See solution above
% 0.22/0.51 % (4030713)------------------------------
% 0.22/0.51 % (4030713)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.22/0.51 % (4030713)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.22/0.51 % (4030713)CaDiCaL version: 2.1.3
% 0.22/0.51 % (4030713)Termination reason: Refutation
% 0.22/0.51 % (4030713)Time elapsed: 0.002 s
% 0.22/0.51 % (4030713)Peak memory usage: 11 MB
% 0.22/0.51 % (4030713)Instructions burned: 1 (million)
% 0.22/0.51 % (4030705)Success in time 0.024 s
% 0.22/0.51 % Vampire exiting
%------------------------------------------------------------------------------