%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ035-2 : TPTP v9.3.1. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n004.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 0.18s 0.46s
% Output : Refutation 0.18s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 10
% Syntax : Number of formulae : 40 ( 11 unt; 5 def)
% Number of atoms : 75 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 72 ( 37 ~; 30 |; 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] :
( ~ person(X0)
| isa(X0,knight)
| isa(X0,knave) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',everyone_a_knight_or_knave) ).
fof(f13,axiom,
( response(yes)
| response(no) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',two_answers) ).
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] :
( ~ response(X0)
| ~ isa(asked,X1)
| ~ isa(other,X2) ),
file('/export/starexec/sandbox/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(f80,plain,
( isa(asked,knight)
| isa(asked,knave) ),
inference(resolution,[],[f1,f14]) ).
fof(f81,plain,
( isa(other,knight)
| isa(other,knave) ),
inference(resolution,[],[f1,f15]) ).
fof(f82,plain,
( isa(asked,knave)
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f80,f22]) ).
fof(f83,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f82,f22]) ).
fof(f84,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f83]) ).
fof(f87,plain,
( $false
| ~ spl0_3
| ~ spl0_5 ),
inference(resolution,[],[f25,f34]) ).
fof(f88,plain,
( ~ spl0_3
| ~ spl0_5 ),
inference(avatar_contradiction_clause,[],[f87]) ).
fof(f91,plain,
( isa(other,knave)
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f81,f19]) ).
fof(f92,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f91,f19]) ).
fof(f93,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f92]) ).
fof(f94,plain,
( $false
| ~ spl0_3
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f30,f25]) ).
fof(f95,plain,
( ~ spl0_3
| ~ spl0_4 ),
inference(avatar_contradiction_clause,[],[f94]) ).
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(s12,plain,
~ spl0_2,
inference(sat_conversion,[],[f84]) ).
cnf(s14,plain,
( ~ spl0_3
| ~ spl0_5 ),
inference(sat_conversion,[],[f88]) ).
cnf(s16,plain,
~ spl0_1,
inference(sat_conversion,[],[f93]) ).
cnf(s17,plain,
( ~ spl0_3
| ~ spl0_4 ),
inference(sat_conversion,[],[f95]) ).
cnf(s18,plain,
spl0_3,
inference(rat,[],[s1,s12,s16]) ).
cnf(s19,plain,
~ spl0_4,
inference(rat,[],[s17,s18]) ).
cnf(s20,plain,
~ spl0_5,
inference(rat,[],[s14,s18]) ).
cnf(s21,plain,
$false,
inference(rat,[],[s2,s20,s19]) ).
fof(f97,plain,
$false,
inference(avatar_sat_refutation,[],[s21]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ035-2 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.12/0.39 % Computer : n004.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 22:34:37 UTC 2026
% 0.12/0.39 % CPUTime :
% 0.12/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.12/0.42 Running first-order model finding
% 0.12/0.42 Running: /export/starexec/sandbox/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 0.18/0.46 % (3946137)Will run a generic schedule for satisfiability detection.
% 0.18/0.46 % (3946146)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=2482602967:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.18/0.46 % (3946146) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-3946137-3946146"...
% 0.18/0.46 % (3946146)...printing done.
% 0.18/0.46 % (3946146)Refutation found. Thanks to Tanya!
% 0.18/0.46 % SZS status Unsatisfiable for theBenchmark
% 0.18/0.46 % SZS output start Proof for theBenchmark
% See solution above
% 0.18/0.46 % (3946146)------------------------------
% 0.18/0.46 % (3946146)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.18/0.46 % (3946146)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.18/0.46 % (3946146)CaDiCaL version: 2.1.3
% 0.18/0.46 % (3946146)Termination reason: Refutation
% 0.18/0.46 % (3946146)Time elapsed: 0.001 s
% 0.18/0.46 % (3946146)Peak memory usage: 12 MB
% 0.18/0.46 % (3946146)Instructions burned: 2 (million)
% 0.18/0.46 % (3946137)Success in time 0.032 s
% 0.18/0.46 % Vampire exiting
%------------------------------------------------------------------------------