%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ035-3 : TPTP v9.3.1. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 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 12:32:00 PM UTC 2026
% Result : Unsatisfiable 0.10s 0.45s
% Output : Refutation 0.10s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 12
% Syntax : Number of formulae : 50 ( 10 unt; 7 def)
% Number of atoms : 98 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 96 ( 48 ~; 41 |; 0 &)
% ( 7 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 4 ( 1 avg)
% Number of predicates : 11 ( 10 usr; 8 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] :
( ~ person(X0)
| truth(isa(X0,knight))
| truth(isa(X0,knave)) ),
file('/export/starexec/sandbox2/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/sandbox2/benchmark/theBenchmark.p',one_is_knight_answer) ).
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] :
( ~ truth(isa(asked,X0))
| ~ truth(isa(other,X1))
| ~ says(asked,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_answer) ).
fof(f18,definition,
( spl0_1
<=> ! [X2] : ~ says(asked,X2) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f19,plain,
( ! [X2] : ~ says(asked,X2)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f18]) ).
fof(f21,definition,
( spl0_2
<=> ! [X1] : ~ truth(isa(other,X1)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f22,plain,
( ! [X1] : ~ truth(isa(other,X1))
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f21]) ).
fof(f24,definition,
( spl0_3
<=> ! [X0] : ~ truth(isa(asked,X0)) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f25,plain,
( ! [X0] : ~ truth(isa(asked,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
<=> says(asked,not(or(isa(asked,knight),isa(other,knight)))) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f30,plain,
( says(asked,not(or(isa(asked,knight),isa(other,knight))))
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f28]) ).
fof(f32,definition,
( spl0_5
<=> says(asked,or(isa(asked,knight),isa(other,knight))) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f34,plain,
( says(asked,or(isa(asked,knight),isa(other,knight)))
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f32]) ).
fof(f35,plain,
( spl0_4
| spl0_5 ),
inference(avatar_split_clause,[],[f7,f32,f28]) ).
fof(f36,plain,
( truth(isa(asked,knight))
| truth(isa(asked,knave)) ),
inference(resolution,[],[f1,f14]) ).
fof(f37,plain,
( truth(isa(other,knight))
| truth(isa(other,knave)) ),
inference(resolution,[],[f1,f15]) ).
fof(f38,plain,
( truth(isa(other,knight))
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f37,f22]) ).
fof(f40,definition,
( spl0_6
<=> truth(isa(asked,knave)) ),
introduced(definition,[new_symbols(definition,[spl0_6])],[avatar_definition]) ).
fof(f42,plain,
( truth(isa(asked,knave))
| ~ spl0_6 ),
inference(avatar_component_clause,[],[f40]) ).
fof(f44,definition,
( spl0_7
<=> truth(isa(asked,knight)) ),
introduced(definition,[new_symbols(definition,[spl0_7])],[avatar_definition]) ).
fof(f46,plain,
( truth(isa(asked,knight))
| ~ spl0_7 ),
inference(avatar_component_clause,[],[f44]) ).
fof(f47,plain,
( spl0_6
| spl0_7 ),
inference(avatar_split_clause,[],[f36,f44,f40]) ).
fof(f48,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f38,f22]) ).
fof(f49,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f48]) ).
fof(f50,plain,
( $false
| ~ spl0_3
| ~ spl0_6 ),
inference(forward_subsumption_resolution,[],[f42,f25]) ).
fof(f51,plain,
( ~ spl0_3
| ~ spl0_6 ),
inference(avatar_contradiction_clause,[],[f50]) ).
fof(f61,plain,
( $false
| ~ spl0_3
| ~ spl0_7 ),
inference(forward_subsumption_resolution,[],[f46,f25]) ).
fof(f62,plain,
( ~ spl0_3
| ~ spl0_7 ),
inference(avatar_contradiction_clause,[],[f61]) ).
fof(f71,plain,
( $false
| ~ spl0_1
| ~ spl0_4 ),
inference(resolution,[],[f30,f19]) ).
fof(f74,plain,
( ~ spl0_1
| ~ spl0_4 ),
inference(avatar_contradiction_clause,[],[f71]) ).
fof(f89,plain,
( $false
| ~ spl0_1
| ~ spl0_5 ),
inference(forward_subsumption_resolution,[],[f34,f19]) ).
fof(f90,plain,
( ~ spl0_1
| ~ spl0_5 ),
inference(avatar_contradiction_clause,[],[f89]) ).
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(s3,plain,
( spl0_6
| spl0_7 ),
inference(sat_conversion,[],[f47]) ).
cnf(s4,plain,
~ spl0_2,
inference(sat_conversion,[],[f49]) ).
cnf(s5,plain,
( ~ spl0_3
| ~ spl0_6 ),
inference(sat_conversion,[],[f51]) ).
cnf(s7,plain,
( ~ spl0_3
| ~ spl0_7 ),
inference(sat_conversion,[],[f62]) ).
cnf(s10,plain,
( ~ spl0_1
| ~ spl0_4 ),
inference(sat_conversion,[],[f74]) ).
cnf(s13,plain,
( ~ spl0_1
| ~ spl0_5 ),
inference(sat_conversion,[],[f90]) ).
cnf(s14,plain,
( spl0_1
| spl0_3 ),
inference(rat,[],[s1,s4]) ).
cnf(s15,plain,
~ spl0_3,
inference(rat,[],[s3,s5,s7]) ).
cnf(s16,plain,
spl0_1,
inference(rat,[],[s14,s15]) ).
cnf(s17,plain,
~ spl0_5,
inference(rat,[],[s13,s16]) ).
cnf(s18,plain,
~ spl0_4,
inference(rat,[],[s10,s16]) ).
cnf(s19,plain,
$false,
inference(rat,[],[s2,s17,s18]) ).
fof(f91,plain,
$false,
inference(avatar_sat_refutation,[],[s19]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ035-3 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.10/0.37 % Computer : n017.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
% 0.10/0.38 % CPULimit : 300
% 0.10/0.38 % WCLimit : 300
% 0.10/0.38 % DateTime : Sun Sep 27 22:29:51 UTC 2026
% 0.10/0.38 % CPUTime :
% 0.10/0.38 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.10/0.41 Running first-order model finding
% 0.10/0.41 Running: /export/starexec/sandbox2/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.10/0.45 % (3001514)Will run a generic schedule for satisfiability detection.
% 0.10/0.45 % (3001524)ott+1_1_to=lpo:sil=16000:sp=reverse_arity:erd=off:random_seed=2534821839:i=131_2999 on theBenchmark for (2999ds/131Mi)
% 0.10/0.45 % (3001524) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-3001514-3001524"...
% 0.10/0.45 % (3001524)...printing done.
% 0.10/0.45 % (3001524)Refutation found. Thanks to Tanya!
% 0.10/0.45 % SZS status Unsatisfiable for theBenchmark
% 0.10/0.45 % SZS output start Proof for theBenchmark
% See solution above
% 0.10/0.45 % (3001524)------------------------------
% 0.10/0.45 % (3001524)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.10/0.45 % (3001524)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.10/0.45 % (3001524)CaDiCaL version: 2.1.3
% 0.10/0.45 % (3001524)Termination reason: Refutation
% 0.10/0.45 % (3001524)Time elapsed: 0.001 s
% 0.10/0.45 % (3001524)Peak memory usage: 12 MB
% 0.10/0.45 % (3001524)Instructions burned: 1 (million)
% 0.10/0.45 % (3001514)Success in time 0.028 s
% 0.10/0.45 % Vampire exiting
%------------------------------------------------------------------------------