%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ027-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n013.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 12:31:57 PM UTC 2026
% Result : Unsatisfiable 0.13s 0.45s
% Output : Refutation 0.13s
% Verified :
% SZS Type : Refutation
% Derivation depth : 12
% Number of leaves : 17
% Syntax : Number of formulae : 68 ( 7 unt; 6 def)
% Number of atoms : 151 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 166 ( 83 ~; 77 |; 0 &)
% ( 6 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 4 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 9 ( 8 usr; 7 prp; 0-1 aty)
% Number of functors : 14 ( 14 usr; 11 con; 0-1 aty)
% Number of variables : 2 ( 0 sgn 2 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( a_truth(normal(X0))
| a_truth(liar(X0))
| a_truth(truthteller(X0)) ),
file('/export/starexec/sandbox/benchmark/Axioms/PUZ003-0.ax',person_is_one_type) ).
fof(f23,axiom,
( ~ a_truth(truthteller(a))
| ~ a_truth(truthteller(b))
| answer(a_and_b_truthteller) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_and_b_truthteller) ).
fof(f24,axiom,
( ~ a_truth(truthteller(a))
| ~ a_truth(normal(b))
| answer(a_truthteller_b_normal) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_truthteller_b_normal) ).
fof(f25,axiom,
( ~ a_truth(truthteller(a))
| ~ a_truth(liar(b))
| answer(a_truthteller_b_liar) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_truthteller_b_liar) ).
fof(f26,axiom,
( ~ a_truth(normal(a))
| ~ a_truth(truthteller(b))
| answer(a_normal_b_truthteller) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_normal_b_truthteller) ).
fof(f27,axiom,
( ~ a_truth(normal(a))
| ~ a_truth(normal(b))
| answer(a_and_b_normal) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_and_b_normal) ).
fof(f28,axiom,
( ~ a_truth(normal(a))
| ~ a_truth(liar(b))
| answer(a_normal_b_liar) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_normal_b_liar) ).
fof(f29,axiom,
( ~ a_truth(liar(a))
| ~ a_truth(truthteller(b))
| answer(a_liar_b_truthteller) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_liar_b_truthteller) ).
fof(f30,axiom,
( ~ a_truth(liar(a))
| ~ a_truth(normal(b))
| answer(a_liar_b_normal) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_liar_b_normal) ).
fof(f31,axiom,
( ~ a_truth(liar(a))
| ~ a_truth(liar(b))
| answer(a_and_b_liar) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_and_b_liar) ).
fof(f32,negated_conjecture,
! [X0] : ~ answer(X0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_there_is_an_answer) ).
fof(f33,plain,
( ~ a_truth(liar(a))
| ~ a_truth(liar(b)) ),
inference(forward_subsumption_resolution,[],[f31,f32]) ).
fof(f34,plain,
( ~ a_truth(liar(a))
| ~ a_truth(normal(b)) ),
inference(forward_subsumption_resolution,[],[f30,f32]) ).
fof(f35,plain,
( ~ a_truth(liar(a))
| ~ a_truth(truthteller(b)) ),
inference(forward_subsumption_resolution,[],[f29,f32]) ).
fof(f36,plain,
( ~ a_truth(normal(a))
| ~ a_truth(liar(b)) ),
inference(forward_subsumption_resolution,[],[f28,f32]) ).
fof(f37,plain,
( ~ a_truth(normal(a))
| ~ a_truth(normal(b)) ),
inference(forward_subsumption_resolution,[],[f27,f32]) ).
fof(f38,plain,
( ~ a_truth(normal(a))
| ~ a_truth(truthteller(b)) ),
inference(forward_subsumption_resolution,[],[f26,f32]) ).
fof(f39,plain,
( ~ a_truth(truthteller(a))
| ~ a_truth(liar(b)) ),
inference(forward_subsumption_resolution,[],[f25,f32]) ).
fof(f40,plain,
( ~ a_truth(truthteller(a))
| ~ a_truth(normal(b)) ),
inference(forward_subsumption_resolution,[],[f24,f32]) ).
fof(f41,plain,
( ~ a_truth(truthteller(a))
| ~ a_truth(truthteller(b)) ),
inference(forward_subsumption_resolution,[],[f23,f32]) ).
fof(f43,definition,
( spl0_1
<=> a_truth(liar(b)) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f45,plain,
( ~ a_truth(liar(b))
| spl0_1 ),
inference(avatar_component_clause,[],[f43]) ).
fof(f47,definition,
( spl0_2
<=> a_truth(liar(a)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f49,plain,
( ~ a_truth(liar(a))
| spl0_2 ),
inference(avatar_component_clause,[],[f47]) ).
fof(f50,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f33,f47,f43]) ).
fof(f52,definition,
( spl0_3
<=> a_truth(normal(b)) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f54,plain,
( ~ a_truth(normal(b))
| spl0_3 ),
inference(avatar_component_clause,[],[f52]) ).
fof(f55,plain,
( ~ spl0_3
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f34,f47,f52]) ).
fof(f57,definition,
( spl0_4
<=> a_truth(truthteller(b)) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f59,plain,
( ~ a_truth(truthteller(b))
| spl0_4 ),
inference(avatar_component_clause,[],[f57]) ).
fof(f60,plain,
( ~ spl0_4
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f35,f47,f57]) ).
fof(f62,definition,
( spl0_5
<=> a_truth(normal(a)) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f64,plain,
( ~ a_truth(normal(a))
| spl0_5 ),
inference(avatar_component_clause,[],[f62]) ).
fof(f65,plain,
( ~ spl0_1
| ~ spl0_5 ),
inference(avatar_split_clause,[],[f36,f62,f43]) ).
fof(f66,plain,
( ~ spl0_3
| ~ spl0_5 ),
inference(avatar_split_clause,[],[f37,f62,f52]) ).
fof(f67,plain,
( ~ spl0_4
| ~ spl0_5 ),
inference(avatar_split_clause,[],[f38,f62,f57]) ).
fof(f69,definition,
( spl0_6
<=> a_truth(truthteller(a)) ),
introduced(definition,[new_symbols(definition,[spl0_6])],[avatar_definition]) ).
fof(f71,plain,
( ~ a_truth(truthteller(a))
| spl0_6 ),
inference(avatar_component_clause,[],[f69]) ).
fof(f72,plain,
( ~ spl0_1
| ~ spl0_6 ),
inference(avatar_split_clause,[],[f39,f69,f43]) ).
fof(f73,plain,
( ~ spl0_3
| ~ spl0_6 ),
inference(avatar_split_clause,[],[f40,f69,f52]) ).
fof(f74,plain,
( ~ spl0_4
| ~ spl0_6 ),
inference(avatar_split_clause,[],[f41,f69,f57]) ).
fof(f77,plain,
( a_truth(liar(b))
| a_truth(truthteller(b))
| spl0_3 ),
inference(resolution,[],[f1,f54]) ).
fof(f80,plain,
( a_truth(truthteller(b))
| spl0_1
| spl0_3 ),
inference(forward_subsumption_resolution,[],[f77,f45]) ).
fof(f81,plain,
( $false
| spl0_1
| spl0_3
| spl0_4 ),
inference(forward_subsumption_resolution,[],[f80,f59]) ).
fof(f82,plain,
( spl0_1
| spl0_3
| spl0_4 ),
inference(avatar_contradiction_clause,[],[f81]) ).
fof(f85,plain,
( a_truth(liar(a))
| a_truth(truthteller(a))
| spl0_5 ),
inference(resolution,[],[f64,f1]) ).
fof(f86,plain,
( a_truth(truthteller(a))
| spl0_2
| spl0_5 ),
inference(forward_subsumption_resolution,[],[f85,f49]) ).
fof(f87,plain,
( $false
| spl0_2
| spl0_5
| spl0_6 ),
inference(forward_subsumption_resolution,[],[f86,f71]) ).
fof(f88,plain,
( spl0_2
| spl0_5
| spl0_6 ),
inference(avatar_contradiction_clause,[],[f87]) ).
cnf(s1,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f50]) ).
cnf(s2,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(sat_conversion,[],[f55]) ).
cnf(s3,plain,
( ~ spl0_2
| ~ spl0_4 ),
inference(sat_conversion,[],[f60]) ).
cnf(s4,plain,
( ~ spl0_1
| ~ spl0_5 ),
inference(sat_conversion,[],[f65]) ).
cnf(s5,plain,
( ~ spl0_3
| ~ spl0_5 ),
inference(sat_conversion,[],[f66]) ).
cnf(s6,plain,
( ~ spl0_4
| ~ spl0_5 ),
inference(sat_conversion,[],[f67]) ).
cnf(s7,plain,
( ~ spl0_1
| ~ spl0_6 ),
inference(sat_conversion,[],[f72]) ).
cnf(s8,plain,
( ~ spl0_3
| ~ spl0_6 ),
inference(sat_conversion,[],[f73]) ).
cnf(s9,plain,
( ~ spl0_4
| ~ spl0_6 ),
inference(sat_conversion,[],[f74]) ).
cnf(s10,plain,
( spl0_1
| spl0_3
| spl0_4 ),
inference(sat_conversion,[],[f82]) ).
cnf(s11,plain,
( spl0_2
| spl0_5
| spl0_6 ),
inference(sat_conversion,[],[f88]) ).
cnf(s12,plain,
( ~ spl0_4
| spl0_2 ),
inference(rat,[],[s11,s6,s9]) ).
cnf(s13,plain,
( spl0_2
| spl0_1 ),
inference(rat,[],[s11,s5,s8,s10,s12]) ).
cnf(s14,plain,
spl0_1,
inference(rat,[],[s10,s2,s3,s13]) ).
cnf(s15,plain,
~ spl0_6,
inference(rat,[],[s7,s14]) ).
cnf(s16,plain,
~ spl0_5,
inference(rat,[],[s4,s14]) ).
cnf(s17,plain,
~ spl0_2,
inference(rat,[],[s1,s14]) ).
cnf(s18,plain,
$false,
inference(rat,[],[s11,s17,s15,s16]) ).
fof(f89,plain,
$false,
inference(avatar_sat_refutation,[],[s18]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ027-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.13/0.39 % Computer : n013.cluster.edu
% 0.13/0.39 % Model : x86_64 x86_64
% 0.13/0.39 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.13/0.39 % Memory : 8046.5625MB
% 0.13/0.39 % OS : Linux 6.8.0-71-generic
% 0.13/0.39 % CPULimit : 300
% 0.13/0.39 % WCLimit : 300
% 0.13/0.39 % DateTime : Sun Sep 27 22:29:52 UTC 2026
% 0.13/0.39 % CPUTime :
% 0.13/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.13/0.41 Running first-order model finding
% 0.13/0.41 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
% 0.13/0.45 % (613234)Will run a generic schedule for satisfiability detection.
% 0.13/0.45 % (613243)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=645039183:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.13/0.45 % (613243) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-613234-613243"...
% 0.13/0.45 % (613243)...printing done.
% 0.13/0.45 % (613240)% WARNING: option uhcvi not known.
% 0.13/0.45 % (613243)Refutation found. Thanks to Tanya!
% 0.13/0.45 % SZS status Unsatisfiable for theBenchmark
% 0.13/0.45 % SZS output start Proof for theBenchmark
% See solution above
% 0.13/0.45 % (613243)------------------------------
% 0.13/0.45 % (613243)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.13/0.45 % (613243)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.13/0.45 % (613243)CaDiCaL version: 2.1.3
% 0.13/0.45 % (613243)Termination reason: Refutation
% 0.13/0.45 % (613243)Time elapsed: 0.002 s
% 0.13/0.45 % (613243)Peak memory usage: 12 MB
% 0.13/0.45 % (613243)Instructions burned: 3 (million)
% 0.13/0.45 % (613234)Success in time 0.027 s
% 0.13/0.45 % Vampire exiting
%------------------------------------------------------------------------------