%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ020-1 : 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 : n006.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 12:31:14 PM UTC 2026
% Result : Unsatisfiable 2.55s 1.22s
% Output : Refutation 2.55s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 8
% Syntax : Number of formulae : 25 ( 8 unt; 3 def)
% Number of atoms : 45 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 37 ( 17 ~; 17 |; 0 &)
% ( 3 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 2 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 7 ( 6 usr; 4 prp; 0-1 aty)
% Number of functors : 3 ( 3 usr; 2 con; 0-1 aty)
% Number of variables : 1 ( 0 sgn 1 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f9,axiom,
! [X0] :
( ~ a_truth(statement_by(X0))
| ~ person(X0)
| knight(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knights_make_true_statements) ).
fof(f13,axiom,
person(husband),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',husband) ).
fof(f19,axiom,
( a_truth(statement_by(husband))
| knight(wife) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knight_wife_or_truthful_husband) ).
fof(f20,axiom,
( ~ knight(wife)
| a_truth(statement_by(husband)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',knight_wife_means_truthful_husband) ).
fof(f21,negated_conjecture,
~ knight(husband),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_knight_husband) ).
fof(f25,definition,
( spl0_1
<=> a_truth(statement_by(husband)) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f26,plain,
( a_truth(statement_by(husband))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f25]) ).
fof(f28,definition,
( spl0_2
<=> knight(wife) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f30,plain,
( spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f20,f28,f25]) ).
fof(f32,plain,
( spl0_2
| spl0_1 ),
inference(avatar_split_clause,[],[f19,f25,f28]) ).
fof(f34,definition,
( spl0_3
<=> knight(husband) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f35,plain,
( ~ knight(husband)
| spl0_3 ),
inference(avatar_component_clause,[],[f34]) ).
fof(f39,plain,
~ spl0_3,
inference(avatar_split_clause,[],[f21,f34]) ).
fof(f47,plain,
( ~ person(husband)
| knight(husband)
| ~ spl0_1 ),
inference(resolution,[],[f9,f26]) ).
fof(f49,plain,
( knight(husband)
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f47,f13]) ).
fof(f50,plain,
( $false
| ~ spl0_1
| spl0_3 ),
inference(forward_subsumption_resolution,[],[f49,f35]) ).
fof(f51,plain,
( ~ spl0_1
| spl0_3 ),
inference(avatar_contradiction_clause,[],[f50]) ).
cnf(s1,plain,
( spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f30]) ).
cnf(s2,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f32]) ).
cnf(s5,plain,
~ spl0_3,
inference(sat_conversion,[],[f39]) ).
cnf(s6,plain,
( ~ spl0_1
| spl0_3 ),
inference(sat_conversion,[],[f51]) ).
cnf(s7,plain,
~ spl0_1,
inference(rat,[],[s6,s5]) ).
cnf(s8,plain,
spl0_2,
inference(rat,[],[s2,s7]) ).
cnf(s9,plain,
$false,
inference(rat,[],[s1,s8,s7]) ).
fof(f52,plain,
$false,
inference(avatar_sat_refutation,[],[s9]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ020-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.36 % Computer : n006.cluster.edu
% 0.10/0.36 % Model : x86_64 x86_64
% 0.10/0.36 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.36 % Memory : 8046.5625MB
% 0.10/0.36 % OS : Linux 6.8.0-71-generic
% 0.10/0.36 % CPULimit : 300
% 0.10/0.36 % WCLimit : 300
% 0.10/0.36 % DateTime : Sun Sep 27 22:29:56 UTC 2026
% 0.10/0.36 % CPUTime :
% 0.10/0.36 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.39 Running first-order theorem proving
% 0.10/0.39 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
% 2.55/1.22 % (3389394)Input is clausal, will run a generic CNF schedule.
% 2.55/1.22 % (3389403)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=695326203:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.55/1.22 % (3389403)First to succeed.
% 2.55/1.22 % (3389403)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3389394"
% 2.55/1.22 % (3389402)lrs+10_1_sil=8000:sp=occurrence:random_seed=926221212:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.55/1.22 % (3389399)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=2660672147:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.55/1.22 % (3389400)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2340789815:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.55/1.22 % (3389401)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=116979076:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.55/1.22 % (3389405)dis-21_1_sil=8000:lcm=predicate:random_seed=2074674291: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)
% 2.55/1.22 % (3389404)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=518704026:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.55/1.22 % (3389405)Also succeeded, but the first one will report.
% 2.55/1.22 % (3389402)Also succeeded, but the first one will report.
% 2.55/1.22 % (3389404)Also succeeded, but the first one will report.
% 2.55/1.22 % (3389403)Refutation found. Thanks to Tanya!
% 2.55/1.22 % SZS status Unsatisfiable for theBenchmark
% 2.55/1.22 % SZS output start Proof for theBenchmark
% See solution above
% 2.55/1.22 % (3389403)------------------------------
% 2.55/1.22 % (3389403)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.55/1.22 % (3389403)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.55/1.22 % (3389403)CaDiCaL version: 2.1.3
% 2.55/1.22 % (3389403)Termination reason: Refutation
% 2.55/1.22 % (3389403)Time elapsed: 0.002 s
% 2.55/1.22 % (3389403)Peak memory usage: 89 MB
% 2.55/1.22 % (3389403)Instructions burned: 1 (million)
% 2.55/1.22 % (3389403)------------------------------
% 2.55/1.22 % (3389403)------------------------------
% 2.55/1.22 % (3389394)Success in time 0.289 s
% 2.55/1.22 % Vampire exiting
%------------------------------------------------------------------------------