%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ035-6 : TPTP v9.3.1. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 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 12:31:19 PM UTC 2026
% Result : Unsatisfiable 1.86s 1.39s
% Output : Refutation 1.86s
% Verified :
% SZS Type : Refutation
% Derivation depth : 7
% Number of leaves : 4
% Syntax : Number of formulae : 18 ( 6 unt; 2 def)
% Number of atoms : 30 ( 0 equ)
% Maximal formula atoms : 2 ( 1 avg)
% Number of connectives : 28 ( 16 ~; 10 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 4 ( 3 usr; 3 prp; 0-1 aty)
% Number of functors : 5 ( 5 usr; 4 con; 0-2 aty)
% Number of variables : 7 ( 0 sgn 7 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( truth(isa(X0,knave))
| truth(isa(X0,knight)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',everyone_a_knight_or_knave) ).
fof(f11,negated_conjecture,
! [X0,X1] :
( ~ truth(isa(asked,X0))
| ~ truth(isa(other,X1)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',query) ).
fof(f13,definition,
( spl0_1
<=> ! [X1] : ~ truth(isa(other,X1)) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f14,plain,
( ! [X1] : ~ truth(isa(other,X1))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f13]) ).
fof(f16,definition,
( spl0_2
<=> ! [X0] : ~ truth(isa(asked,X0)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f17,plain,
( ! [X0] : ~ truth(isa(asked,X0))
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f16]) ).
fof(f18,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f11,f16,f13]) ).
fof(f20,plain,
( truth(isa(asked,knight))
| ~ spl0_2 ),
inference(resolution,[],[f1,f17]) ).
fof(f21,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f20,f17]) ).
fof(f22,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f21]) ).
fof(f23,plain,
( truth(isa(other,knight))
| ~ spl0_1 ),
inference(resolution,[],[f14,f1]) ).
fof(f24,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f23,f14]) ).
fof(f25,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f24]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f18]) ).
cnf(s2,plain,
~ spl0_2,
inference(sat_conversion,[],[f22]) ).
cnf(s3,plain,
~ spl0_1,
inference(sat_conversion,[],[f25]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s2,s3]) ).
fof(f26,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ035-6 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.37 % Computer : n001.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
% 0.10/0.37 % CPULimit : 300
% 0.10/0.37 % WCLimit : 300
% 0.10/0.37 % DateTime : Sun Sep 27 22:40:46 UTC 2026
% 0.10/0.37 % CPUTime :
% 0.10/0.37 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.40 Running first-order theorem proving
% 0.10/0.40 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
% 1.86/1.39 % (4036027)Input is clausal, will run a generic CNF schedule.
% 1.86/1.39 % (4036033)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=3598274544:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 1.86/1.39 % (4036032)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=353585435:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 1.86/1.39 % (4036035)lrs+10_1_sil=8000:sp=occurrence:random_seed=2351277674:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 1.86/1.39 % (4036034)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=4134374540:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 1.86/1.39 % (4036036)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=1804523701:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 1.86/1.39 % (4036038)dis-21_1_sil=8000:lcm=predicate:random_seed=3291151869: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)
% 1.86/1.39 % (4036037)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=174887930:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 1.86/1.39 % (4036036)Refutation not found, incomplete strategy
% 1.86/1.39 % (4036036)------------------------------
% 1.86/1.39 % (4036036)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 1.86/1.39 % (4036036)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 1.86/1.39 % (4036036)CaDiCaL version: 2.1.3
% 1.86/1.39 % (4036036)Termination reason: Refutation not found, incomplete strategy
% 1.86/1.39 % (4036036)Time elapsed: 0.001 s
% 1.86/1.39 % (4036036)Peak memory usage: 87 MB
% 1.86/1.39 % (4036035)Also succeeded, but the first one will report.
% 1.86/1.39 % (4036038)Also succeeded, but the first one will report.
% 1.86/1.39 % (4036037)First to succeed.
% 1.86/1.39 % (4036037)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-4036027"
% 1.86/1.39 % (4036036)------------------------------
% 1.86/1.39 % (4036036)------------------------------
% 1.86/1.39 % (4036037)Refutation found. Thanks to Tanya!
% 1.86/1.39 % SZS status Unsatisfiable for theBenchmark
% 1.86/1.39 % SZS output start Proof for theBenchmark
% See solution above
% 1.86/1.39 % (4036037)------------------------------
% 1.86/1.39 % (4036037)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 1.86/1.39 % (4036037)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 1.86/1.39 % (4036037)CaDiCaL version: 2.1.3
% 1.86/1.39 % (4036037)Termination reason: Refutation
% 1.86/1.39 % (4036037)Time elapsed: 0.002 s
% 1.86/1.39 % (4036037)Peak memory usage: 89 MB
% 1.86/1.39 % (4036037)Instructions burned: 1 (million)
% 1.86/1.39 % (4036037)------------------------------
% 1.86/1.39 % (4036037)------------------------------
% 1.86/1.39 % (4036027)Success in time 0.437 s
% 1.86/1.39 % Vampire exiting
%------------------------------------------------------------------------------