%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ035-7 : 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 : n014.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 12:32:01 PM UTC 2026
% Result : Unsatisfiable 0.16s 0.47s
% Output : Refutation 0.16s
% Verified :
% SZS Type : Refutation
% Derivation depth : 7
% Number of leaves : 6
% Syntax : Number of formulae : 25 ( 8 unt; 3 def)
% Number of atoms : 45 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 44 ( 24 ~; 17 |; 0 &)
% ( 3 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of predicates : 6 ( 5 usr; 4 prp; 0-3 aty)
% Number of functors : 8 ( 8 usr; 6 con; 0-2 aty)
% Number of variables : 12 ( 0 sgn 12 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( truth(isa(X0,knave))
| truth(isa(X0,knight)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',everyone_a_knight_or_knave) ).
fof(f7,axiom,
! [X0,X1] :
( reply(X0,X1,no)
| reply(X0,X1,yes) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',yes_or_no) ).
fof(f14,negated_conjecture,
! [X2,X0,X1] :
( ~ reply(asked,or(isa(asked,knight),isa(other,knight)),X0)
| ~ truth(isa(asked,X1))
| ~ truth(isa(other,X2)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_answer) ).
fof(f16,definition,
( spl0_1
<=> ! [X2] : ~ truth(isa(other,X2)) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f17,plain,
( ! [X2] : ~ truth(isa(other,X2))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f16]) ).
fof(f19,definition,
( spl0_2
<=> ! [X1] : ~ truth(isa(asked,X1)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f20,plain,
( ! [X1] : ~ truth(isa(asked,X1))
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f19]) ).
fof(f22,definition,
( spl0_3
<=> ! [X0] : ~ reply(asked,or(isa(asked,knight),isa(other,knight)),X0) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f23,plain,
( ! [X0] : ~ reply(asked,or(isa(asked,knight),isa(other,knight)),X0)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f22]) ).
fof(f24,plain,
( spl0_1
| spl0_2
| spl0_3 ),
inference(avatar_split_clause,[],[f14,f22,f19,f16]) ).
fof(f26,plain,
( truth(isa(asked,knight))
| ~ spl0_2 ),
inference(resolution,[],[f1,f20]) ).
fof(f27,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f26,f20]) ).
fof(f28,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f27]) ).
fof(f30,plain,
( reply(asked,or(isa(asked,knight),isa(other,knight)),yes)
| ~ spl0_3 ),
inference(resolution,[],[f7,f23]) ).
fof(f31,plain,
( $false
| ~ spl0_3 ),
inference(forward_subsumption_resolution,[],[f30,f23]) ).
fof(f32,plain,
~ spl0_3,
inference(avatar_contradiction_clause,[],[f31]) ).
fof(f33,plain,
( truth(isa(other,knight))
| ~ spl0_1 ),
inference(resolution,[],[f17,f1]) ).
fof(f34,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f33,f17]) ).
fof(f35,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f34]) ).
cnf(s1,plain,
( spl0_1
| spl0_2
| spl0_3 ),
inference(sat_conversion,[],[f24]) ).
cnf(s2,plain,
~ spl0_2,
inference(sat_conversion,[],[f28]) ).
cnf(s3,plain,
~ spl0_3,
inference(sat_conversion,[],[f32]) ).
cnf(s4,plain,
~ spl0_1,
inference(sat_conversion,[],[f35]) ).
cnf(s5,plain,
$false,
inference(rat,[],[s1,s3,s2,s4]) ).
fof(f36,plain,
$false,
inference(avatar_sat_refutation,[],[s5]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ035-7 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.12/0.38 % Computer : n014.cluster.edu
% 0.12/0.38 % Model : x86_64 x86_64
% 0.12/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.38 % Memory : 8046.5625MB
% 0.12/0.38 % OS : Linux 6.8.0-71-generic
% 0.12/0.38 % CPULimit : 300
% 0.12/0.38 % WCLimit : 300
% 0.12/0.38 % DateTime : Sun Sep 27 22:34:46 UTC 2026
% 0.12/0.38 % CPUTime :
% 0.12/0.38 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.12/0.41 Running first-order model finding
% 0.12/0.41 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
% 0.16/0.46 % (1233908)Will run a generic schedule for satisfiability detection.
% 0.16/0.46 % (1233913)fmb+10_1_sas=cadical:bce=on:rp=on:random_seed=100893872_2999 on theBenchmark for (2999ds/0Mi)
% 0.16/0.46 % TRYING [1]
% 0.16/0.46 % TRYING [2]
% 0.16/0.46 % TRYING [3]
% 0.16/0.46 % TRYING [4]
% 0.16/0.46 % (1233914)% WARNING: option uhcvi not known.
% 0.16/0.46 % TRYING [5]
% 0.16/0.46 % TRYING [6]
% 0.16/0.46 % (1233917)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=284652055:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.16/0.46 % (1233914)dis+11_61:31_drc=ordering:lsd=5:bsr=unit_only:rp=on:newcnf=on:random_seed=69005715:i=135531:add=off:rawr=on_2999 on theBenchmark for (2999ds/135531Mi)
% 0.16/0.46 % (1233915)dis+10_161_sil=256000:plsq=on:plsqr=61199697,1048576:gs=on:alpa=true:sac=on:slsq=on:cn=on:random_seed=57500777:i=88024:add=on:rawr=on_2999 on theBenchmark for (2999ds/88024Mi)
% 0.16/0.46 % TRYING [7]
% 0.16/0.46 % (1233916)dis+10_1_sil=32000:sp=arity:random_seed=3345155049:i=103:fgj=on_2999 on theBenchmark for (2999ds/103Mi)
% 0.16/0.46 % (1233918)ott+1_1_to=lpo:sil=16000:sp=reverse_arity:erd=off:random_seed=2637839131:i=131_2999 on theBenchmark for (2999ds/131Mi)
% 0.16/0.47 % (1233919)ott-3_16_to=lpo:sil=16000:sp=arity:fd=off:rp=on:random_seed=200327485:i=159:bs=unit_only:nicw=on:fsr=off:amm=off_2999 on theBenchmark for (2999ds/159Mi)
% 0.16/0.47 % (1233914) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-1233908-1233914"...
% 0.16/0.47 % (1233917) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-1233908-1233917"...
% 0.16/0.47 % (1233916) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-1233908-1233916"...
% 0.16/0.47 % (1233918) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-1233908-1233918"...
% 0.16/0.47 % (1233919) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-1233908-1233919"...
% 0.16/0.47 % (1233915) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-1233908-1233915"...
% 0.16/0.47 % (1233917)...printing done.
% 0.16/0.47 % (1233916)...printing done.
% 0.16/0.47 % TRYING [8]
% 0.16/0.47 % (1233914)...printing done.
% 0.16/0.47 % (1233918)...printing done.
% 0.16/0.47 % (1233919)...printing done.
% 0.16/0.47 % (1233915)...printing done.
% 0.16/0.47 % (1233916)Refutation found. Thanks to Tanya!
% 0.16/0.47 % SZS status Unsatisfiable for theBenchmark
% 0.16/0.47 % SZS output start Proof for theBenchmark
% See solution above
% 0.16/0.47 % (1233916)------------------------------
% 0.16/0.47 % (1233916)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.16/0.47 % (1233916)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.16/0.47 % (1233916)CaDiCaL version: 2.1.3
% 0.16/0.47 % (1233916)Termination reason: Refutation
% 0.16/0.47 % (1233916)Time elapsed: 0.001 s
% 0.16/0.47 % (1233916)Peak memory usage: 12 MB
% 0.16/0.47 % (1233916)Instructions burned: 1 (million)
% 0.16/0.47 % (1233908)Success in time 0.041 s
% 0.16/0.47 % Vampire exiting
%------------------------------------------------------------------------------