%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ023-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n008.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 12:31:56 PM UTC 2026
% Result : Unsatisfiable 0.11s 0.45s
% Output : Refutation 0.11s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 10
% Syntax : Number of formulae : 40 ( 7 unt; 4 def)
% Number of atoms : 79 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 79 ( 40 ~; 35 |; 0 &)
% ( 4 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 4 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 7 ( 6 usr; 5 prp; 0-1 aty)
% Number of functors : 8 ( 8 usr; 6 con; 0-1 aty)
% Number of variables : 2 ( 0 sgn 2 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( a_truth(liar(X0))
| a_truth(truthteller(X0)) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ002-0.ax',truthteller_or_liar) ).
fof(f18,axiom,
( ~ a_truth(liar(b))
| ~ a_truth(liar(c))
| an_answer(b_and_c_liars) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b_and_c_liars) ).
fof(f19,axiom,
( ~ a_truth(liar(b))
| ~ a_truth(truthteller(c))
| an_answer(b_liar_and_c_truthteller) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b_liar_and_c_truthteller) ).
fof(f20,axiom,
( ~ a_truth(truthteller(b))
| ~ a_truth(liar(c))
| an_answer(b_truthteller_and_c_liar) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b_truthteller_and_c_liar) ).
fof(f21,axiom,
( ~ a_truth(truthteller(b))
| ~ a_truth(truthteller(c))
| an_answer(b_and_c_truthtellers) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b_and_c_truthtellers) ).
fof(f22,negated_conjecture,
! [X0] : ~ an_answer(X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_there_is_an_answer) ).
fof(f23,plain,
( ~ a_truth(truthteller(b))
| ~ a_truth(truthteller(c)) ),
inference(forward_subsumption_resolution,[],[f21,f22]) ).
fof(f24,plain,
( ~ a_truth(truthteller(b))
| ~ a_truth(liar(c)) ),
inference(forward_subsumption_resolution,[],[f20,f22]) ).
fof(f25,plain,
( ~ a_truth(liar(b))
| ~ a_truth(truthteller(c)) ),
inference(forward_subsumption_resolution,[],[f19,f22]) ).
fof(f26,plain,
( ~ a_truth(liar(b))
| ~ a_truth(liar(c)) ),
inference(forward_subsumption_resolution,[],[f18,f22]) ).
fof(f60,definition,
( spl0_9
<=> a_truth(truthteller(c)) ),
introduced(definition,[new_symbols(definition,[spl0_9])],[avatar_definition]) ).
fof(f62,plain,
( ~ a_truth(truthteller(c))
| spl0_9 ),
inference(avatar_component_clause,[],[f60]) ).
fof(f64,definition,
( spl0_10
<=> a_truth(truthteller(b)) ),
introduced(definition,[new_symbols(definition,[spl0_10])],[avatar_definition]) ).
fof(f66,plain,
( ~ a_truth(truthteller(b))
| spl0_10 ),
inference(avatar_component_clause,[],[f64]) ).
fof(f67,plain,
( ~ spl0_9
| ~ spl0_10 ),
inference(avatar_split_clause,[],[f23,f64,f60]) ).
fof(f69,definition,
( spl0_11
<=> a_truth(liar(c)) ),
introduced(definition,[new_symbols(definition,[spl0_11])],[avatar_definition]) ).
fof(f71,plain,
( ~ a_truth(liar(c))
| spl0_11 ),
inference(avatar_component_clause,[],[f69]) ).
fof(f72,plain,
( ~ spl0_11
| ~ spl0_10 ),
inference(avatar_split_clause,[],[f24,f64,f69]) ).
fof(f74,definition,
( spl0_12
<=> a_truth(liar(b)) ),
introduced(definition,[new_symbols(definition,[spl0_12])],[avatar_definition]) ).
fof(f76,plain,
( ~ a_truth(liar(b))
| spl0_12 ),
inference(avatar_component_clause,[],[f74]) ).
fof(f77,plain,
( ~ spl0_9
| ~ spl0_12 ),
inference(avatar_split_clause,[],[f25,f74,f60]) ).
fof(f78,plain,
( ~ spl0_11
| ~ spl0_12 ),
inference(avatar_split_clause,[],[f26,f74,f69]) ).
fof(f79,plain,
( a_truth(truthteller(b))
| spl0_12 ),
inference(resolution,[],[f1,f76]) ).
fof(f80,plain,
( $false
| spl0_10
| spl0_12 ),
inference(forward_subsumption_resolution,[],[f79,f66]) ).
fof(f81,plain,
( spl0_10
| spl0_12 ),
inference(avatar_contradiction_clause,[],[f80]) ).
fof(f82,plain,
( a_truth(truthteller(c))
| spl0_11 ),
inference(resolution,[],[f71,f1]) ).
fof(f83,plain,
( $false
| spl0_9
| spl0_11 ),
inference(forward_subsumption_resolution,[],[f82,f62]) ).
fof(f84,plain,
( spl0_9
| spl0_11 ),
inference(avatar_contradiction_clause,[],[f83]) ).
cnf(s8,plain,
( ~ spl0_9
| ~ spl0_10 ),
inference(sat_conversion,[],[f67]) ).
cnf(s9,plain,
( ~ spl0_10
| ~ spl0_11 ),
inference(sat_conversion,[],[f72]) ).
cnf(s10,plain,
( ~ spl0_9
| ~ spl0_12 ),
inference(sat_conversion,[],[f77]) ).
cnf(s11,plain,
( ~ spl0_11
| ~ spl0_12 ),
inference(sat_conversion,[],[f78]) ).
cnf(s12,plain,
( spl0_10
| spl0_12 ),
inference(sat_conversion,[],[f81]) ).
cnf(s13,plain,
( spl0_9
| spl0_11 ),
inference(sat_conversion,[],[f84]) ).
cnf(s14,plain,
~ spl0_11,
inference(rat,[],[s12,s9,s11]) ).
cnf(s15,plain,
spl0_9,
inference(rat,[],[s13,s14]) ).
cnf(s16,plain,
~ spl0_12,
inference(rat,[],[s10,s15]) ).
cnf(s17,plain,
~ spl0_10,
inference(rat,[],[s8,s15]) ).
cnf(s18,plain,
$false,
inference(rat,[],[s12,s16,s17]) ).
fof(f85,plain,
$false,
inference(avatar_sat_refutation,[],[s18]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ023-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.11/0.38 % Computer : n008.cluster.edu
% 0.11/0.38 % Model : x86_64 x86_64
% 0.11/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.38 % Memory : 8046.5625MB
% 0.11/0.38 % OS : Linux 6.8.0-71-generic
% 0.11/0.38 % CPULimit : 300
% 0.11/0.38 % WCLimit : 300
% 0.11/0.38 % DateTime : Sun Sep 27 22:31:25 UTC 2026
% 0.11/0.38 % CPUTime :
% 0.11/0.38 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.11/0.41 Running first-order model finding
% 0.11/0.41 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
% 0.11/0.45 % (1664668)Will run a generic schedule for satisfiability detection.
% 0.11/0.45 % (1664678)ott+1_1_to=lpo:sil=16000:sp=reverse_arity:erd=off:random_seed=3553299715:i=131_2999 on theBenchmark for (2999ds/131Mi)
% 0.11/0.45 % (1664678) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-1664668-1664678"...
% 0.11/0.45 % (1664678)...printing done.
% 0.11/0.45 % (1664678)Refutation found. Thanks to Tanya!
% 0.11/0.45 % SZS status Unsatisfiable for theBenchmark
% 0.11/0.45 % SZS output start Proof for theBenchmark
% See solution above
% 0.11/0.45 % (1664678)------------------------------
% 0.11/0.45 % (1664678)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.11/0.45 % (1664678)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.11/0.45 % (1664678)CaDiCaL version: 2.1.3
% 0.11/0.45 % (1664678)Termination reason: Refutation
% 0.11/0.45 % (1664678)Time elapsed: 0.001 s
% 0.11/0.45 % (1664678)Peak memory usage: 12 MB
% 0.11/0.45 % (1664678)Instructions burned: 1 (million)
% 0.11/0.45 % (1664668)Success in time 0.027 s
% 0.11/0.45 % Vampire exiting
%------------------------------------------------------------------------------