%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ027-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n010.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 12:31:15 PM UTC 2026
% Result : Unsatisfiable 1.10s 1.13s
% Output : Refutation 2.52s
% Verified :
% SZS Type : Refutation
% Derivation depth : 11
% Number of leaves : 26
% Syntax : Number of formulae : 105 ( 25 unt; 15 def)
% Number of atoms : 219 ( 0 equ)
% Maximal formula atoms : 3 ( 2 avg)
% Number of connectives : 229 ( 115 ~; 99 |; 0 &)
% ( 15 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 4 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 18 ( 17 usr; 16 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/sandbox2/benchmark/theBenchmark.p',person_is_one_type) ).
fof(f23,axiom,
( ~ a_truth(truthteller(a))
| ~ a_truth(truthteller(b))
| answer(a_and_b_truthteller) ),
file('/export/starexec/sandbox2/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/sandbox2/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/sandbox2/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/sandbox2/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/sandbox2/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/sandbox2/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/sandbox2/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/sandbox2/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/sandbox2/benchmark/theBenchmark.p',a_and_b_liar) ).
fof(f32,negated_conjecture,
! [X0] : ~ answer(X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_there_is_an_answer) ).
fof(f34,definition,
( spl0_1
<=> answer(a_and_b_liar) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f35,plain,
( answer(a_and_b_liar)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f34]) ).
fof(f37,definition,
( spl0_2
<=> a_truth(liar(b)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f40,definition,
( spl0_3
<=> a_truth(liar(a)) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f42,plain,
( spl0_1
| ~ spl0_2
| ~ spl0_3 ),
inference(avatar_split_clause,[],[f31,f40,f37,f34]) ).
fof(f44,definition,
( spl0_4
<=> answer(a_liar_b_normal) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f45,plain,
( answer(a_liar_b_normal)
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f44]) ).
fof(f47,definition,
( spl0_5
<=> a_truth(normal(b)) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f48,plain,
( ~ a_truth(normal(b))
| spl0_5 ),
inference(avatar_component_clause,[],[f47]) ).
fof(f49,plain,
( spl0_4
| ~ spl0_5
| ~ spl0_3 ),
inference(avatar_split_clause,[],[f30,f40,f47,f44]) ).
fof(f51,definition,
( spl0_6
<=> answer(a_liar_b_truthteller) ),
introduced(definition,[new_symbols(definition,[spl0_6])],[avatar_definition]) ).
fof(f52,plain,
( answer(a_liar_b_truthteller)
| ~ spl0_6 ),
inference(avatar_component_clause,[],[f51]) ).
fof(f54,definition,
( spl0_7
<=> a_truth(truthteller(b)) ),
introduced(definition,[new_symbols(definition,[spl0_7])],[avatar_definition]) ).
fof(f56,plain,
( spl0_6
| ~ spl0_7
| ~ spl0_3 ),
inference(avatar_split_clause,[],[f29,f40,f54,f51]) ).
fof(f58,definition,
( spl0_8
<=> answer(a_normal_b_liar) ),
introduced(definition,[new_symbols(definition,[spl0_8])],[avatar_definition]) ).
fof(f59,plain,
( answer(a_normal_b_liar)
| ~ spl0_8 ),
inference(avatar_component_clause,[],[f58]) ).
fof(f61,definition,
( spl0_9
<=> a_truth(normal(a)) ),
introduced(definition,[new_symbols(definition,[spl0_9])],[avatar_definition]) ).
fof(f62,plain,
( ~ a_truth(normal(a))
| spl0_9 ),
inference(avatar_component_clause,[],[f61]) ).
fof(f63,plain,
( spl0_8
| ~ spl0_2
| ~ spl0_9 ),
inference(avatar_split_clause,[],[f28,f61,f37,f58]) ).
fof(f65,definition,
( spl0_10
<=> answer(a_and_b_normal) ),
introduced(definition,[new_symbols(definition,[spl0_10])],[avatar_definition]) ).
fof(f66,plain,
( answer(a_and_b_normal)
| ~ spl0_10 ),
inference(avatar_component_clause,[],[f65]) ).
fof(f67,plain,
( spl0_10
| ~ spl0_5
| ~ spl0_9 ),
inference(avatar_split_clause,[],[f27,f61,f47,f65]) ).
fof(f69,definition,
( spl0_11
<=> answer(a_normal_b_truthteller) ),
introduced(definition,[new_symbols(definition,[spl0_11])],[avatar_definition]) ).
fof(f70,plain,
( answer(a_normal_b_truthteller)
| ~ spl0_11 ),
inference(avatar_component_clause,[],[f69]) ).
fof(f71,plain,
( spl0_11
| ~ spl0_7
| ~ spl0_9 ),
inference(avatar_split_clause,[],[f26,f61,f54,f69]) ).
fof(f73,definition,
( spl0_12
<=> answer(a_truthteller_b_liar) ),
introduced(definition,[new_symbols(definition,[spl0_12])],[avatar_definition]) ).
fof(f74,plain,
( answer(a_truthteller_b_liar)
| ~ spl0_12 ),
inference(avatar_component_clause,[],[f73]) ).
fof(f76,definition,
( spl0_13
<=> a_truth(truthteller(a)) ),
introduced(definition,[new_symbols(definition,[spl0_13])],[avatar_definition]) ).
fof(f78,plain,
( spl0_12
| ~ spl0_2
| ~ spl0_13 ),
inference(avatar_split_clause,[],[f25,f76,f37,f73]) ).
fof(f80,definition,
( spl0_14
<=> answer(a_truthteller_b_normal) ),
introduced(definition,[new_symbols(definition,[spl0_14])],[avatar_definition]) ).
fof(f81,plain,
( answer(a_truthteller_b_normal)
| ~ spl0_14 ),
inference(avatar_component_clause,[],[f80]) ).
fof(f82,plain,
( spl0_14
| ~ spl0_5
| ~ spl0_13 ),
inference(avatar_split_clause,[],[f24,f76,f47,f80]) ).
fof(f84,definition,
( spl0_15
<=> answer(a_and_b_truthteller) ),
introduced(definition,[new_symbols(definition,[spl0_15])],[avatar_definition]) ).
fof(f85,plain,
( answer(a_and_b_truthteller)
| ~ spl0_15 ),
inference(avatar_component_clause,[],[f84]) ).
fof(f86,plain,
( spl0_15
| ~ spl0_7
| ~ spl0_13 ),
inference(avatar_split_clause,[],[f23,f76,f54,f84]) ).
fof(f89,plain,
( a_truth(liar(b))
| a_truth(truthteller(b))
| spl0_5 ),
inference(resolution,[],[f1,f48]) ).
fof(f94,plain,
( spl0_7
| spl0_2
| spl0_5 ),
inference(avatar_split_clause,[],[f89,f47,f37,f54]) ).
fof(f101,plain,
( a_truth(liar(a))
| a_truth(truthteller(a))
| spl0_9 ),
inference(resolution,[],[f62,f1]) ).
fof(f104,plain,
( spl0_13
| spl0_3
| spl0_9 ),
inference(avatar_split_clause,[],[f101,f61,f40,f76]) ).
fof(f105,plain,
( $false
| ~ spl0_10 ),
inference(resolution,[],[f66,f32]) ).
fof(f106,plain,
~ spl0_10,
inference(avatar_contradiction_clause,[],[f105]) ).
fof(f107,plain,
( $false
| ~ spl0_8 ),
inference(resolution,[],[f59,f32]) ).
fof(f108,plain,
~ spl0_8,
inference(avatar_contradiction_clause,[],[f107]) ).
fof(f113,plain,
( $false
| ~ spl0_6 ),
inference(resolution,[],[f52,f32]) ).
fof(f114,plain,
~ spl0_6,
inference(avatar_contradiction_clause,[],[f113]) ).
fof(f115,plain,
( $false
| ~ spl0_15 ),
inference(resolution,[],[f85,f32]) ).
fof(f116,plain,
~ spl0_15,
inference(avatar_contradiction_clause,[],[f115]) ).
fof(f117,plain,
( $false
| ~ spl0_11 ),
inference(resolution,[],[f70,f32]) ).
fof(f118,plain,
~ spl0_11,
inference(avatar_contradiction_clause,[],[f117]) ).
fof(f119,plain,
( $false
| ~ spl0_14 ),
inference(resolution,[],[f81,f32]) ).
fof(f120,plain,
~ spl0_14,
inference(avatar_contradiction_clause,[],[f119]) ).
fof(f121,plain,
( $false
| ~ spl0_12 ),
inference(resolution,[],[f74,f32]) ).
fof(f122,plain,
~ spl0_12,
inference(avatar_contradiction_clause,[],[f121]) ).
fof(f123,plain,
( $false
| ~ spl0_4 ),
inference(resolution,[],[f45,f32]) ).
fof(f124,plain,
~ spl0_4,
inference(avatar_contradiction_clause,[],[f123]) ).
fof(f125,plain,
( $false
| ~ spl0_1 ),
inference(resolution,[],[f35,f32]) ).
fof(f126,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f125]) ).
cnf(s1,plain,
( spl0_1
| ~ spl0_2
| ~ spl0_3 ),
inference(sat_conversion,[],[f42]) ).
cnf(s2,plain,
( ~ spl0_3
| spl0_4
| ~ spl0_5 ),
inference(sat_conversion,[],[f49]) ).
cnf(s3,plain,
( ~ spl0_3
| spl0_6
| ~ spl0_7 ),
inference(sat_conversion,[],[f56]) ).
cnf(s4,plain,
( ~ spl0_2
| spl0_8
| ~ spl0_9 ),
inference(sat_conversion,[],[f63]) ).
cnf(s5,plain,
( ~ spl0_5
| ~ spl0_9
| spl0_10 ),
inference(sat_conversion,[],[f67]) ).
cnf(s6,plain,
( ~ spl0_7
| ~ spl0_9
| spl0_11 ),
inference(sat_conversion,[],[f71]) ).
cnf(s7,plain,
( ~ spl0_2
| spl0_12
| ~ spl0_13 ),
inference(sat_conversion,[],[f78]) ).
cnf(s8,plain,
( ~ spl0_5
| ~ spl0_13
| spl0_14 ),
inference(sat_conversion,[],[f82]) ).
cnf(s9,plain,
( ~ spl0_7
| ~ spl0_13
| spl0_15 ),
inference(sat_conversion,[],[f86]) ).
cnf(s10,plain,
( spl0_2
| spl0_5
| spl0_7 ),
inference(sat_conversion,[],[f94]) ).
cnf(s12,plain,
( spl0_3
| spl0_9
| spl0_13 ),
inference(sat_conversion,[],[f104]) ).
cnf(s13,plain,
~ spl0_10,
inference(sat_conversion,[],[f106]) ).
cnf(s14,plain,
~ spl0_8,
inference(sat_conversion,[],[f108]) ).
cnf(s16,plain,
~ spl0_6,
inference(sat_conversion,[],[f114]) ).
cnf(s17,plain,
~ spl0_15,
inference(sat_conversion,[],[f116]) ).
cnf(s18,plain,
~ spl0_11,
inference(sat_conversion,[],[f118]) ).
cnf(s19,plain,
~ spl0_14,
inference(sat_conversion,[],[f120]) ).
cnf(s20,plain,
~ spl0_12,
inference(sat_conversion,[],[f122]) ).
cnf(s21,plain,
~ spl0_4,
inference(sat_conversion,[],[f124]) ).
cnf(s22,plain,
~ spl0_1,
inference(sat_conversion,[],[f126]) ).
cnf(s23,plain,
( ~ spl0_7
| ~ spl0_13 ),
inference(rat,[],[s9,s17]) ).
cnf(s24,plain,
( ~ spl0_5
| ~ spl0_13 ),
inference(rat,[],[s8,s19]) ).
cnf(s25,plain,
( ~ spl0_2
| ~ spl0_13 ),
inference(rat,[],[s7,s20]) ).
cnf(s26,plain,
( ~ spl0_7
| ~ spl0_9 ),
inference(rat,[],[s6,s18]) ).
cnf(s27,plain,
( ~ spl0_5
| ~ spl0_9 ),
inference(rat,[],[s5,s13]) ).
cnf(s28,plain,
( ~ spl0_2
| ~ spl0_9 ),
inference(rat,[],[s4,s14]) ).
cnf(s29,plain,
( ~ spl0_3
| ~ spl0_7 ),
inference(rat,[],[s3,s16]) ).
cnf(s30,plain,
( ~ spl0_3
| ~ spl0_5 ),
inference(rat,[],[s2,s21]) ).
cnf(s31,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(rat,[],[s1,s22]) ).
cnf(s32,plain,
( ~ spl0_7
| spl0_3 ),
inference(rat,[],[s12,s26,s23]) ).
cnf(s33,plain,
( spl0_3
| spl0_2 ),
inference(rat,[],[s12,s27,s24,s10,s32]) ).
cnf(s34,plain,
spl0_2,
inference(rat,[],[s10,s30,s29,s33]) ).
cnf(s35,plain,
~ spl0_13,
inference(rat,[],[s25,s34]) ).
cnf(s36,plain,
~ spl0_9,
inference(rat,[],[s28,s34]) ).
cnf(s37,plain,
~ spl0_3,
inference(rat,[],[s31,s34]) ).
cnf(s38,plain,
$false,
inference(rat,[],[s12,s37,s35,s36]) ).
fof(f127,plain,
$false,
inference(avatar_sat_refutation,[],[s38]) ).
%------------------------------------------------------------------------------
%----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/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.38 % Computer : n010.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 22:30:47 UTC 2026
% 0.12/0.38 % CPUTime :
% 0.12/0.38 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.42 Running first-order theorem proving
% 0.12/0.42 Running: /export/starexec/sandbox2/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 1.10/1.13 % (1370320)Input is clausal, will run a generic CNF schedule.
% 1.10/1.13 % (1370331)dis-21_1_sil=8000:lcm=predicate:random_seed=287398704:st=5:avsq=on:i=117:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/117Mi)
% 1.10/1.13 % (1370331)First to succeed.
% 1.10/1.13 % (1370331)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-1370320"
% 1.10/1.13 % (1370329)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=1690241440:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 1.10/1.13 % (1370328)lrs+10_1_sil=8000:sp=occurrence:random_seed=3506835173:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 1.10/1.13 % (1370327)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=662355837:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 1.10/1.13 % (1370326)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2333286062:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 1.10/1.13 % (1370330)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=923566851:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 1.10/1.13 % (1370325)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=full:npcc=on:drc=off:sp=weighted_frequency:spb=goal:fd=preordered:foolp=on:random_seed=534159194:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 1.10/1.13 % (1370328)Also succeeded, but the first one will report.
% 1.10/1.13 % (1370329)Also succeeded, but the first one will report.
% 1.10/1.13 % (1370330)Also succeeded, but the first one will report.
% 1.10/1.13 % (1370331)Refutation found. Thanks to Tanya!
% 1.10/1.13 % SZS status Unsatisfiable for theBenchmark
% 1.10/1.13 % SZS output start Proof for theBenchmark
% See solution above
% 2.52/1.33 % (1370331)------------------------------
% 2.52/1.33 % (1370331)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.52/1.33 % (1370331)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.52/1.33 % (1370331)CaDiCaL version: 2.1.3
% 2.52/1.33 % (1370331)Termination reason: Refutation
% 2.52/1.33 % (1370331)Time elapsed: 0.002 s
% 2.52/1.33 % (1370331)Peak memory usage: 89 MB
% 2.52/1.33 % (1370331)Instructions burned: 3 (million)
% 2.52/1.33 % (1370331)------------------------------
% 2.52/1.33 % (1370331)------------------------------
% 2.52/1.33 % (1370320)Success in time 0.272 s
% 2.52/1.33 % Vampire exiting
%------------------------------------------------------------------------------