%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ035-3 : 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 : n017.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 2.58s 1.26s
% Output : Refutation 2.58s
% 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 : 4 ( 1 avg)
% Number of predicates : 9 ( 8 usr; 6 prp; 0-2 aty)
% Number of functors : 7 ( 7 usr; 4 con; 0-2 aty)
% Number of variables : 10 ( 0 sgn 10 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( truth(isa(X0,knave))
| truth(isa(X0,knight))
| ~ person(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',everyone_a_knight_or_knave) ).
fof(f7,axiom,
( says(asked,or(isa(asked,knight),isa(other,knight)))
| says(asked,not(or(isa(asked,knight),isa(other,knight)))) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',one_is_knight_answer) ).
fof(f14,axiom,
person(asked),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',asked_person) ).
fof(f15,axiom,
person(other),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',other_person) ).
fof(f16,negated_conjecture,
! [X2,X0,X1] :
( ~ truth(isa(asked,X0))
| ~ truth(isa(other,X1))
| ~ says(asked,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_answer) ).
fof(f18,definition,
( spl0_1
<=> says(asked,not(or(isa(asked,knight),isa(other,knight)))) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f19,plain,
( says(asked,not(or(isa(asked,knight),isa(other,knight))))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f18]) ).
fof(f21,definition,
( spl0_2
<=> says(asked,or(isa(asked,knight),isa(other,knight))) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f22,plain,
( says(asked,or(isa(asked,knight),isa(other,knight)))
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f21]) ).
fof(f23,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f7,f21,f18]) ).
fof(f25,definition,
( spl0_3
<=> ! [X2] : ~ says(asked,X2) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f26,plain,
( ! [X2] : ~ says(asked,X2)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f25]) ).
fof(f28,definition,
( spl0_4
<=> ! [X1] : ~ truth(isa(other,X1)) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f29,plain,
( ! [X1] : ~ truth(isa(other,X1))
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f28]) ).
fof(f31,definition,
( spl0_5
<=> ! [X0] : ~ truth(isa(asked,X0)) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f32,plain,
( ! [X0] : ~ truth(isa(asked,X0))
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f31]) ).
fof(f33,plain,
( spl0_3
| spl0_4
| spl0_5 ),
inference(avatar_split_clause,[],[f16,f31,f28,f25]) ).
fof(f35,plain,
( $false
| ~ spl0_2
| ~ spl0_3 ),
inference(forward_subsumption_resolution,[],[f22,f26]) ).
fof(f36,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(avatar_contradiction_clause,[],[f35]) ).
fof(f37,plain,
( $false
| ~ spl0_1
| ~ spl0_3 ),
inference(forward_subsumption_resolution,[],[f19,f26]) ).
fof(f38,plain,
( ~ spl0_1
| ~ spl0_3 ),
inference(avatar_contradiction_clause,[],[f37]) ).
fof(f50,plain,
( truth(isa(asked,knight))
| ~ person(asked)
| ~ spl0_5 ),
inference(resolution,[],[f1,f32]) ).
fof(f51,plain,
( ~ person(asked)
| ~ spl0_5 ),
inference(forward_subsumption_resolution,[],[f50,f32]) ).
fof(f52,plain,
( $false
| ~ spl0_5 ),
inference(forward_subsumption_resolution,[],[f51,f14]) ).
fof(f53,plain,
~ spl0_5,
inference(avatar_contradiction_clause,[],[f52]) ).
fof(f55,plain,
( truth(isa(other,knight))
| ~ person(other)
| ~ spl0_4 ),
inference(resolution,[],[f29,f1]) ).
fof(f56,plain,
( ~ person(other)
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f55,f29]) ).
fof(f57,plain,
( $false
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f56,f15]) ).
fof(f58,plain,
~ spl0_4,
inference(avatar_contradiction_clause,[],[f57]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f23]) ).
cnf(s2,plain,
( spl0_3
| spl0_4
| spl0_5 ),
inference(sat_conversion,[],[f33]) ).
cnf(s3,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(sat_conversion,[],[f36]) ).
cnf(s4,plain,
( ~ spl0_1
| ~ spl0_3 ),
inference(sat_conversion,[],[f38]) ).
cnf(s6,plain,
~ spl0_5,
inference(sat_conversion,[],[f53]) ).
cnf(s7,plain,
~ spl0_4,
inference(sat_conversion,[],[f58]) ).
cnf(s8,plain,
spl0_3,
inference(rat,[],[s2,s6,s7]) ).
cnf(s9,plain,
~ spl0_1,
inference(rat,[],[s4,s8]) ).
cnf(s10,plain,
~ spl0_2,
inference(rat,[],[s3,s8]) ).
cnf(s11,plain,
$false,
inference(rat,[],[s1,s10,s9]) ).
fof(f59,plain,
$false,
inference(avatar_sat_refutation,[],[s11]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ035-3 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.12/0.39 % Computer : n017.cluster.edu
% 0.12/0.39 % Model : x86_64 x86_64
% 0.12/0.39 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.39 % Memory : 8046.5625MB
% 0.12/0.39 % OS : Linux 6.8.0-71-generic
% 0.12/0.39 % CPULimit : 300
% 0.12/0.39 % WCLimit : 300
% 0.12/0.39 % DateTime : Sun Sep 27 22:29:50 UTC 2026
% 0.12/0.39 % CPUTime :
% 0.12/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.12/0.43 Running first-order theorem proving
% 0.12/0.43 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
% 2.58/1.26 % (3001470)Input is clausal, will run a generic CNF schedule.
% 2.58/1.26 % (3001533)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2657479398:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.58/1.26 % (3001533)First to succeed.
% 2.58/1.26 % (3001533)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3001470"
% 2.58/1.26 % (3001535)dis-21_1_sil=8000:lcm=predicate:random_seed=4048255013: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)
% 2.58/1.26 % (3001532)lrs+10_1_sil=8000:sp=occurrence:random_seed=2795859541:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.58/1.26 % (3001534)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1998227559:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.58/1.26 % (3001530)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2275350273:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.58/1.26 % (3001529)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=2882221059:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.58/1.26 % (3001531)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1348531274:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.58/1.26 % (3001532)Also succeeded, but the first one will report.
% 2.58/1.26 % (3001534)Also succeeded, but the first one will report.
% 2.58/1.26 % (3001535)Also succeeded, but the first one will report.
% 2.58/1.26 % (3001533)Refutation found. Thanks to Tanya!
% 2.58/1.26 % SZS status Unsatisfiable for theBenchmark
% 2.58/1.26 % SZS output start Proof for theBenchmark
% See solution above
% 2.58/1.26 % (3001533)------------------------------
% 2.58/1.26 % (3001533)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.58/1.26 % (3001533)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.58/1.26 % (3001533)CaDiCaL version: 2.1.3
% 2.58/1.26 % (3001533)Termination reason: Refutation
% 2.58/1.26 % (3001533)Time elapsed: 0.002 s
% 2.58/1.26 % (3001533)Peak memory usage: 89 MB
% 2.58/1.26 % (3001533)Instructions burned: 1 (million)
% 2.58/1.26 % (3001533)------------------------------
% 2.58/1.26 % (3001533)------------------------------
% 2.58/1.26 % (3001470)Success in time 0.284 s
% 2.58/1.26 % Vampire exiting
%------------------------------------------------------------------------------