%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ001-1 : 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 12:31:02 PM UTC 2026
% Result : Unsatisfiable 3.48s 1.40s
% Output : Refutation 3.48s
% Verified :
% SZS Type : Refutation
% Derivation depth : 11
% Number of leaves : 12
% Syntax : Number of formulae : 33 ( 10 unt; 2 def)
% Number of atoms : 59 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 57 ( 31 ~; 24 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 7 ( 6 usr; 3 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/sandbox/benchmark/theBenchmark.p',butler) ).
fof(f4,axiom,
! [X0,X1] :
( ~ richer(X0,X1)
| ~ killed(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',poorer_killer) ).
fof(f5,axiom,
! [X0] :
( ~ hates(charles,X0)
| ~ hates(agatha,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',different_hates) ).
fof(f6,axiom,
! [X0] :
( ~ hates(X0,charles)
| ~ hates(X0,butler)
| ~ hates(X0,agatha) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',no_one_hates_everyone) ).
fof(f7,axiom,
hates(agatha,agatha),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',agatha_hates_agatha) ).
fof(f8,axiom,
hates(agatha,charles),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',agatha_hates_charles) ).
fof(f9,axiom,
! [X0,X1] :
( ~ killed(X0,X1)
| hates(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',killer_hates_victim) ).
fof(f10,axiom,
! [X0] :
( ~ hates(agatha,X0)
| hates(butler,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',same_hates) ).
fof(f11,axiom,
! [X0] :
( hates(butler,X0)
| richer(X0,agatha)
| ~ lives(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',butler_hates_poor) ).
fof(f12,negated_conjecture,
( killed(butler,agatha)
| killed(charles,agatha) ),
file('/export/starexec/sandbox/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(f26,plain,
( ~ hates(butler,butler)
| ~ hates(butler,agatha) ),
inference(resolution,[],[f6,f24]) ).
fof(f29,plain,
( ~ hates(butler,butler)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f26,f22]) ).
fof(f32,plain,
( richer(butler,agatha)
| ~ lives(butler)
| ~ spl0_2 ),
inference(resolution,[],[f29,f11]) ).
fof(f33,plain,
( richer(butler,agatha)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f32,f2]) ).
fof(f34,plain,
( ~ killed(butler,agatha)
| ~ spl0_2 ),
inference(resolution,[],[f33,f4]) ).
fof(f35,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f34,f20]) ).
fof(f36,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f35]) ).
fof(f40,plain,
( hates(charles,agatha)
| ~ spl0_1 ),
inference(resolution,[],[f16,f9]) ).
fof(f41,plain,
( ~ hates(agatha,agatha)
| ~ spl0_1 ),
inference(resolution,[],[f40,f5]) ).
fof(f42,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f41,f7]) ).
fof(f43,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f42]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f21]) ).
cnf(s2,plain,
~ spl0_2,
inference(sat_conversion,[],[f36]) ).
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
% 0.00/0.02 % Problem : PUZ001-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.04 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.38 % Computer : n007.cluster.edu
% 0.10/0.38 % Model : x86_64 x86_64
% 0.10/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.38 % Memory : 8046.5625MB
% 0.10/0.38 % 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 22:25:25 UTC 2026
% 0.10/0.38 % CPUTime :
% 0.10/0.38 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.41 Running first-order theorem proving
% 0.10/0.41 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
% 3.48/1.40 % (1831918)Input is clausal, will run a generic CNF schedule.
% 3.48/1.40 % (1831923)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=3443241730:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.48/1.40 % (1831925)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=2385072268:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.48/1.40 % (1831924)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=332740070:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.48/1.40 % (1831926)lrs+10_1_sil=8000:sp=occurrence:random_seed=2926935689:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.48/1.40 % (1831927)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2711050692:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.48/1.40 % (1831929)dis-21_1_sil=8000:lcm=predicate:random_seed=1268522029: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)
% 3.48/1.40 % (1831926)First to succeed.
% 3.48/1.40 % (1831929)Also succeeded, but the first one will report.
% 3.48/1.40 % (1831927)Also succeeded, but the first one will report.
% 3.48/1.40 % (1831926)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-1831918"
% 3.48/1.40 % (1831928)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3370281415:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.48/1.40 % (1831928)Also succeeded, but the first one will report.
% 3.48/1.40 % (1831926)Refutation found. Thanks to Tanya!
% 3.48/1.40 % SZS status Unsatisfiable for theBenchmark
% 3.48/1.40 % SZS output start Proof for theBenchmark
% See solution above
% 3.48/1.40 % (1831926)------------------------------
% 3.48/1.40 % (1831926)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.48/1.40 % (1831926)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.48/1.40 % (1831926)CaDiCaL version: 2.1.3
% 3.48/1.40 % (1831926)Termination reason: Refutation
% 3.48/1.40 % (1831926)Time elapsed: 0.003 s
% 3.48/1.40 % (1831926)Peak memory usage: 89 MB
% 3.48/1.40 % (1831926)Instructions burned: 1 (million)
% 3.48/1.40 % (1831926)------------------------------
% 3.48/1.40 % (1831926)------------------------------
% 3.48/1.40 % (1831918)Success in time 0.432 s
% 3.48/1.40 % Vampire exiting
%------------------------------------------------------------------------------