%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ035-1 : 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 : n002.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 12:31:18 PM UTC 2026
% Result : Unsatisfiable 3.62s 1.47s
% Output : Refutation 3.62s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 10
% Syntax : Number of formulae : 40 ( 11 unt; 5 def)
% Number of atoms : 77 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 80 ( 43 ~; 32 |; 0 &)
% ( 5 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 9 ( 8 usr; 6 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 6 con; 0-0 aty)
% Number of variables : 10 ( 0 sgn 10 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( isa(X0,knave)
| isa(X0,knight)
| ~ person(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',everyone_a_knight_or_knave) ).
fof(f12,axiom,
( response(yes)
| response(no) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',two_answers) ).
fof(f13,axiom,
person(asked),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',asked_person) ).
fof(f14,axiom,
person(other),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',other_person) ).
fof(f15,negated_conjecture,
! [X2,X0,X1] :
( ~ response(X0)
| ~ isa(asked,X1)
| ~ isa(other,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_answer) ).
fof(f23,definition,
( spl0_3
<=> response(yes) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f27,definition,
( spl0_4
<=> response(no) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f28,plain,
( response(no)
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f27]) ).
fof(f29,plain,
( response(yes)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f23]) ).
fof(f30,plain,
( spl0_4
| spl0_3 ),
inference(avatar_split_clause,[],[f12,f23,f27]) ).
fof(f47,definition,
( spl0_8
<=> ! [X2] : ~ isa(other,X2) ),
introduced(definition,[new_symbols(definition,[spl0_8])],[avatar_definition]) ).
fof(f48,plain,
( ! [X2] : ~ isa(other,X2)
| ~ spl0_8 ),
inference(avatar_component_clause,[],[f47]) ).
fof(f50,definition,
( spl0_9
<=> ! [X1] : ~ isa(asked,X1) ),
introduced(definition,[new_symbols(definition,[spl0_9])],[avatar_definition]) ).
fof(f51,plain,
( ! [X1] : ~ isa(asked,X1)
| ~ spl0_9 ),
inference(avatar_component_clause,[],[f50]) ).
fof(f53,definition,
( spl0_10
<=> ! [X0] : ~ response(X0) ),
introduced(definition,[new_symbols(definition,[spl0_10])],[avatar_definition]) ).
fof(f54,plain,
( ! [X0] : ~ response(X0)
| ~ spl0_10 ),
inference(avatar_component_clause,[],[f53]) ).
fof(f55,plain,
( spl0_8
| spl0_9
| spl0_10 ),
inference(avatar_split_clause,[],[f15,f53,f50,f47]) ).
fof(f56,plain,
( isa(other,knight)
| ~ person(other)
| ~ spl0_8 ),
inference(resolution,[],[f1,f48]) ).
fof(f59,plain,
( ~ person(other)
| ~ spl0_8 ),
inference(forward_subsumption_resolution,[],[f56,f48]) ).
fof(f60,plain,
( $false
| ~ spl0_8 ),
inference(forward_subsumption_resolution,[],[f59,f14]) ).
fof(f61,plain,
~ spl0_8,
inference(avatar_contradiction_clause,[],[f60]) ).
fof(f62,plain,
( isa(asked,knight)
| ~ person(asked)
| ~ spl0_9 ),
inference(resolution,[],[f51,f1]) ).
fof(f63,plain,
( ~ person(asked)
| ~ spl0_9 ),
inference(forward_subsumption_resolution,[],[f62,f51]) ).
fof(f64,plain,
( $false
| ~ spl0_9 ),
inference(forward_subsumption_resolution,[],[f63,f13]) ).
fof(f65,plain,
~ spl0_9,
inference(avatar_contradiction_clause,[],[f64]) ).
fof(f66,plain,
( $false
| ~ spl0_3
| ~ spl0_10 ),
inference(resolution,[],[f54,f29]) ).
fof(f67,plain,
( ~ spl0_3
| ~ spl0_10 ),
inference(avatar_contradiction_clause,[],[f66]) ).
fof(f68,plain,
( $false
| ~ spl0_4
| ~ spl0_10 ),
inference(forward_subsumption_resolution,[],[f28,f54]) ).
fof(f69,plain,
( ~ spl0_4
| ~ spl0_10 ),
inference(avatar_contradiction_clause,[],[f68]) ).
cnf(s2,plain,
( spl0_3
| spl0_4 ),
inference(sat_conversion,[],[f30]) ).
cnf(s8,plain,
( spl0_8
| spl0_9
| spl0_10 ),
inference(sat_conversion,[],[f55]) ).
cnf(s9,plain,
~ spl0_8,
inference(sat_conversion,[],[f61]) ).
cnf(s10,plain,
~ spl0_9,
inference(sat_conversion,[],[f65]) ).
cnf(s11,plain,
( ~ spl0_3
| ~ spl0_10 ),
inference(sat_conversion,[],[f67]) ).
cnf(s12,plain,
( ~ spl0_4
| ~ spl0_10 ),
inference(sat_conversion,[],[f69]) ).
cnf(s13,plain,
spl0_10,
inference(rat,[],[s8,s10,s9]) ).
cnf(s14,plain,
~ spl0_4,
inference(rat,[],[s12,s13]) ).
cnf(s15,plain,
~ spl0_3,
inference(rat,[],[s11,s13]) ).
cnf(s18,plain,
$false,
inference(rat,[],[s2,s14,s15]) ).
fof(f70,plain,
$false,
inference(avatar_sat_refutation,[],[s18]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ035-1 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.36 % Computer : n002.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 22:34:06 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
% 3.62/1.47 % (3955121)Input is clausal, will run a generic CNF schedule.
% 3.62/1.47 % (3955126)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=3373753544:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.62/1.47 % (3955129)lrs+10_1_sil=8000:sp=occurrence:random_seed=2023749508:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.62/1.47 % (3955130)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=4105542189:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.62/1.47 % (3955132)dis-21_1_sil=8000:lcm=predicate:random_seed=4177532772: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)
% 3.62/1.47 % (3955127)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=1308606652:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.62/1.47 % (3955131)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=188097395:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.62/1.47 % (3955128)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1152727731:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.62/1.47 % (3955129)Also succeeded, but the first one will report.
% 3.62/1.47 % (3955131)Also succeeded, but the first one will report.
% 3.62/1.47 % (3955130)First to succeed.
% 3.62/1.47 % (3955132)Also succeeded, but the first one will report.
% 3.62/1.47 % (3955130)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3955121"
% 3.62/1.47 % (3955130)Refutation found. Thanks to Tanya!
% 3.62/1.47 % SZS status Unsatisfiable for theBenchmark
% 3.62/1.47 % SZS output start Proof for theBenchmark
% See solution above
% 3.62/1.47 % (3955130)------------------------------
% 3.62/1.47 % (3955130)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.62/1.47 % (3955130)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.62/1.47 % (3955130)CaDiCaL version: 2.1.3
% 3.62/1.47 % (3955130)Termination reason: Refutation
% 3.62/1.47 % (3955130)Time elapsed: 0.002 s
% 3.62/1.47 % (3955130)Peak memory usage: 89 MB
% 3.62/1.47 % (3955130)Instructions burned: 1 (million)
% 3.62/1.47 % (3955130)------------------------------
% 3.62/1.47 % (3955130)------------------------------
% 3.62/1.47 % (3955121)Success in time 0.431 s
% 3.62/1.47 % Vampire exiting
%------------------------------------------------------------------------------