%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ035-2 : TPTP v9.3.1. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n013.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 2.45s 1.10s
% Output : Refutation 2.45s
% 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 : 78 ( 41 ~; 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,knight)
| ~ person(X0)
| isa(X0,knave) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',everyone_a_knight_or_knave) ).
fof(f13,axiom,
( response(yes)
| response(no) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',two_answers) ).
fof(f14,axiom,
person(asked),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',asked_person) ).
fof(f15,axiom,
person(other),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',other_person) ).
fof(f16,negated_conjecture,
! [X2,X0,X1] :
( ~ response(X0)
| ~ isa(asked,X1)
| ~ isa(other,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_answer) ).
fof(f18,definition,
( spl0_1
<=> ! [X2] : ~ isa(other,X2) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f19,plain,
( ! [X2] : ~ isa(other,X2)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f18]) ).
fof(f21,definition,
( spl0_2
<=> ! [X1] : ~ isa(asked,X1) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f22,plain,
( ! [X1] : ~ isa(asked,X1)
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f21]) ).
fof(f24,definition,
( spl0_3
<=> ! [X0] : ~ response(X0) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f25,plain,
( ! [X0] : ~ response(X0)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f24]) ).
fof(f26,plain,
( spl0_1
| spl0_2
| spl0_3 ),
inference(avatar_split_clause,[],[f16,f24,f21,f18]) ).
fof(f28,definition,
( spl0_4
<=> response(no) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f30,plain,
( response(no)
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f28]) ).
fof(f32,definition,
( spl0_5
<=> response(yes) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f34,plain,
( response(yes)
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f32]) ).
fof(f35,plain,
( spl0_4
| spl0_5 ),
inference(avatar_split_clause,[],[f13,f32,f28]) ).
fof(f66,plain,
( ~ person(asked)
| isa(asked,knave)
| ~ spl0_2 ),
inference(resolution,[],[f1,f22]) ).
fof(f68,plain,
( isa(asked,knave)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f66,f14]) ).
fof(f69,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f68,f22]) ).
fof(f70,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f69]) ).
fof(f72,plain,
( ~ person(other)
| isa(other,knave)
| ~ spl0_1 ),
inference(resolution,[],[f19,f1]) ).
fof(f74,plain,
( isa(other,knave)
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f72,f15]) ).
fof(f75,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f74,f19]) ).
fof(f76,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f75]) ).
fof(f77,plain,
( $false
| ~ spl0_3
| ~ spl0_5 ),
inference(resolution,[],[f25,f34]) ).
fof(f78,plain,
( ~ spl0_3
| ~ spl0_5 ),
inference(avatar_contradiction_clause,[],[f77]) ).
fof(f79,plain,
( $false
| ~ spl0_3
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f30,f25]) ).
fof(f80,plain,
( ~ spl0_3
| ~ spl0_4 ),
inference(avatar_contradiction_clause,[],[f79]) ).
cnf(s1,plain,
( spl0_1
| spl0_2
| spl0_3 ),
inference(sat_conversion,[],[f26]) ).
cnf(s2,plain,
( spl0_4
| spl0_5 ),
inference(sat_conversion,[],[f35]) ).
cnf(s10,plain,
~ spl0_2,
inference(sat_conversion,[],[f70]) ).
cnf(s12,plain,
~ spl0_1,
inference(sat_conversion,[],[f76]) ).
cnf(s13,plain,
( ~ spl0_3
| ~ spl0_5 ),
inference(sat_conversion,[],[f78]) ).
cnf(s14,plain,
( ~ spl0_3
| ~ spl0_4 ),
inference(sat_conversion,[],[f80]) ).
cnf(s15,plain,
spl0_3,
inference(rat,[],[s1,s10,s12]) ).
cnf(s16,plain,
~ spl0_4,
inference(rat,[],[s14,s15]) ).
cnf(s17,plain,
~ spl0_5,
inference(rat,[],[s13,s15]) ).
cnf(s18,plain,
$false,
inference(rat,[],[s2,s17,s16]) ).
fof(f81,plain,
$false,
inference(avatar_sat_refutation,[],[s18]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ035-2 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.04 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.08/0.36 % Computer : n013.cluster.edu
% 0.08/0.36 % Model : x86_64 x86_64
% 0.08/0.36 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.08/0.36 % Memory : 8046.5625MB
% 0.08/0.36 % OS : Linux 6.8.0-71-generic
% 0.08/0.36 % CPULimit : 300
% 0.08/0.36 % WCLimit : 300
% 0.08/0.36 % DateTime : Sun Sep 27 22:34:06 UTC 2026
% 0.08/0.36 % CPUTime :
% 0.08/0.37 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.08/0.40 Running first-order theorem proving
% 0.08/0.40 Running: /export/starexec/sandbox2/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 2.45/1.10 % (614042)Input is clausal, will run a generic CNF schedule.
% 2.45/1.10 % (614052)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=4049548352:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.45/1.10 % (614052)First to succeed.
% 2.45/1.10 % (614052)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-614042"
% 2.45/1.10 % (614049)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1429273287:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.45/1.10 % (614053)dis-21_1_sil=8000:lcm=predicate:random_seed=1570772388: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)
% 2.45/1.10 % (614048)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=4203326204:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.45/1.10 % (614050)lrs+10_1_sil=8000:sp=occurrence:random_seed=3012196497:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.45/1.10 % (614051)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2355239089:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.45/1.10 % (614047)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=1901641387:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.45/1.10 % (614051)Also succeeded, but the first one will report.
% 2.45/1.10 % (614053)Also succeeded, but the first one will report.
% 2.45/1.10 % (614050)Also succeeded, but the first one will report.
% 2.45/1.10 % (614052)Refutation found. Thanks to Tanya!
% 2.45/1.10 % SZS status Unsatisfiable for theBenchmark
% 2.45/1.10 % SZS output start Proof for theBenchmark
% See solution above
% 2.45/1.10 % (614052)------------------------------
% 2.45/1.10 % (614052)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.45/1.10 % (614052)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.45/1.10 % (614052)CaDiCaL version: 2.1.3
% 2.45/1.10 % (614052)Termination reason: Refutation
% 2.45/1.10 % (614052)Time elapsed: 0.002 s
% 2.45/1.10 % (614052)Peak memory usage: 89 MB
% 2.45/1.10 % (614052)Instructions burned: 1 (million)
% 2.45/1.10 % (614052)------------------------------
% 2.45/1.10 % (614052)------------------------------
% 2.45/1.10 % (614042)Success in time 0.302 s
% 2.45/1.10 % Vampire exiting
%------------------------------------------------------------------------------