%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ025-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n006.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 3.62s 1.49s
% Output : Refutation 3.62s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 13
% Syntax : Number of formulae : 46 ( 12 unt; 6 def)
% Number of atoms : 120 ( 0 equ)
% Maximal formula atoms : 5 ( 2 avg)
% Number of connectives : 146 ( 72 ~; 68 |; 0 &)
% ( 6 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 8 ( 4 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 10 ( 9 usr; 7 prp; 0-2 aty)
% Number of functors : 8 ( 8 usr; 5 con; 0-2 aty)
% Number of variables : 34 ( 0 sgn 34 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( a_truth(liar(X0))
| a_truth(truthteller(X0)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',truthteller_or_liar) ).
fof(f14,axiom,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(truthteller(X0))
| ~ a_truth(X1)
| answer(yes) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',truthteller_identifies_truths) ).
fof(f15,axiom,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(truthteller(X0))
| a_truth(X1)
| answer(no) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',truthteller_denies_lies) ).
fof(f16,axiom,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(liar(X0))
| ~ a_truth(X1)
| answer(no) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',liar_denies_truths) ).
fof(f17,axiom,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(liar(X0))
| a_truth(X1)
| answer(yes) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',liar_supports_lies) ).
fof(f23,axiom,
ask_1_if_2(c,equal_type(a,b)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ask_c_if_a_and_b_equal) ).
fof(f24,negated_conjecture,
! [X0] : ~ answer(X0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_there_is_an_answer) ).
fof(f26,definition,
( spl0_1
<=> answer(yes) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f28,plain,
( answer(yes)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f26]) ).
fof(f30,definition,
( spl0_2
<=> ! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| a_truth(X1)
| ~ a_truth(liar(X0)) ) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f31,plain,
( ! [X0,X1] :
( ~ a_truth(liar(X0))
| a_truth(X1)
| ~ ask_1_if_2(X0,X1) )
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f30]) ).
fof(f32,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f17,f30,f26]) ).
fof(f34,definition,
( spl0_3
<=> answer(no) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f36,plain,
( answer(no)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f34]) ).
fof(f38,definition,
( spl0_4
<=> ! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(X1)
| ~ a_truth(liar(X0)) ) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f39,plain,
( ! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(X1)
| ~ a_truth(liar(X0)) )
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f38]) ).
fof(f40,plain,
( spl0_3
| spl0_4 ),
inference(avatar_split_clause,[],[f16,f38,f34]) ).
fof(f42,definition,
( spl0_5
<=> ! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| a_truth(X1)
| ~ a_truth(truthteller(X0)) ) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f43,plain,
( ! [X0,X1] :
( ~ a_truth(truthteller(X0))
| a_truth(X1)
| ~ ask_1_if_2(X0,X1) )
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f42]) ).
fof(f44,plain,
( spl0_3
| spl0_5 ),
inference(avatar_split_clause,[],[f15,f42,f34]) ).
fof(f46,definition,
( spl0_6
<=> ! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(X1)
| ~ a_truth(truthteller(X0)) ) ),
introduced(definition,[new_symbols(definition,[spl0_6])],[avatar_definition]) ).
fof(f47,plain,
( ! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(X1)
| ~ a_truth(truthteller(X0)) )
| ~ spl0_6 ),
inference(avatar_component_clause,[],[f46]) ).
fof(f48,plain,
( spl0_1
| spl0_6 ),
inference(avatar_split_clause,[],[f14,f46,f26]) ).
fof(f49,plain,
( $false
| ~ spl0_3 ),
inference(forward_subsumption_resolution,[],[f36,f24]) ).
fof(f50,plain,
~ spl0_3,
inference(avatar_contradiction_clause,[],[f49]) ).
fof(f51,plain,
( ! [X0,X1] :
( ~ a_truth(liar(X0))
| ~ ask_1_if_2(X0,X1) )
| ~ spl0_2
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f39,f31]) ).
fof(f52,plain,
( ! [X0,X1] :
( ~ a_truth(truthteller(X0))
| ~ ask_1_if_2(X0,X1) )
| ~ spl0_5
| ~ spl0_6 ),
inference(forward_subsumption_resolution,[],[f47,f43]) ).
fof(f53,plain,
( ! [X0,X1] :
( a_truth(truthteller(X0))
| ~ ask_1_if_2(X0,X1) )
| ~ spl0_2
| ~ spl0_4 ),
inference(resolution,[],[f1,f51]) ).
fof(f56,plain,
( ! [X0,X1] : ~ ask_1_if_2(X0,X1)
| ~ spl0_2
| ~ spl0_4
| ~ spl0_5
| ~ spl0_6 ),
inference(forward_subsumption_resolution,[],[f53,f52]) ).
fof(f57,plain,
( $false
| ~ spl0_2
| ~ spl0_4
| ~ spl0_5
| ~ spl0_6 ),
inference(resolution,[],[f56,f23]) ).
fof(f58,plain,
( ~ spl0_2
| ~ spl0_4
| ~ spl0_5
| ~ spl0_6 ),
inference(avatar_contradiction_clause,[],[f57]) ).
fof(f59,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f28,f24]) ).
fof(f60,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f59]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f32]) ).
cnf(s2,plain,
( spl0_3
| spl0_4 ),
inference(sat_conversion,[],[f40]) ).
cnf(s3,plain,
( spl0_3
| spl0_5 ),
inference(sat_conversion,[],[f44]) ).
cnf(s4,plain,
( spl0_1
| spl0_6 ),
inference(sat_conversion,[],[f48]) ).
cnf(s5,plain,
~ spl0_3,
inference(sat_conversion,[],[f50]) ).
cnf(s6,plain,
( ~ spl0_2
| ~ spl0_4
| ~ spl0_5
| ~ spl0_6 ),
inference(sat_conversion,[],[f58]) ).
cnf(s7,plain,
~ spl0_1,
inference(sat_conversion,[],[f60]) ).
cnf(s8,plain,
spl0_6,
inference(rat,[],[s4,s7]) ).
cnf(s9,plain,
spl0_5,
inference(rat,[],[s3,s5]) ).
cnf(s10,plain,
spl0_4,
inference(rat,[],[s2,s5]) ).
cnf(s11,plain,
~ spl0_2,
inference(rat,[],[s6,s8,s9,s10]) ).
cnf(s12,plain,
$false,
inference(rat,[],[s1,s11,s7]) ).
fof(f61,plain,
$false,
inference(avatar_sat_refutation,[],[s12]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ025-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.37 % Computer : n006.cluster.edu
% 0.09/0.37 % Model : x86_64 x86_64
% 0.09/0.37 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.37 % Memory : 8046.5625MB
% 0.09/0.37 % OS : Linux 6.8.0-71-generic
% 0.09/0.37 % CPULimit : 300
% 0.09/0.37 % WCLimit : 300
% 0.09/0.37 % DateTime : Sun Sep 27 22:30:10 UTC 2026
% 0.09/0.37 % CPUTime :
% 0.09/0.37 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.41 Running first-order theorem proving
% 0.09/0.41 Running: /export/starexec/sandbox/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 3.62/1.49 % (3389798)Input is clausal, will run a generic CNF schedule.
% 3.62/1.49 % (3389803)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=3102314514:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.62/1.49 % (3389808)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1838102925:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.62/1.49 % (3389805)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=647483749:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.62/1.49 % (3389804)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=1124503561:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.62/1.49 % (3389806)lrs+10_1_sil=8000:sp=occurrence:random_seed=152328516:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.62/1.49 % (3389807)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=1843901791:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.62/1.49 % (3389806)Also succeeded, but the first one will report.
% 3.62/1.49 % (3389808)First to succeed.
% 3.62/1.49 % (3389807)Refutation not found, incomplete strategy
% 3.62/1.49 % (3389807)------------------------------
% 3.62/1.49 % (3389807)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.62/1.49 % (3389807)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.62/1.49 % (3389807)CaDiCaL version: 2.1.3
% 3.62/1.49 % (3389807)Termination reason: Refutation not found, incomplete strategy
% 3.62/1.49 % (3389807)Time elapsed: 0.003 s
% 3.62/1.49 % (3389807)Peak memory usage: 87 MB
% 3.62/1.49 % (3389807)Instructions burned: 2 (million)
% 3.62/1.49 % (3389808)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3389798"
% 3.62/1.49 % (3389809)dis-21_1_sil=8000:lcm=predicate:random_seed=1834693888: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)
% 3.62/1.49 % (3389809)Also succeeded, but the first one will report.
% 3.62/1.49 % (3389807)------------------------------
% 3.62/1.49 % (3389807)------------------------------
% 3.62/1.49 % (3389808)Refutation found. Thanks to Tanya!
% 3.62/1.49 % SZS status Unsatisfiable for theBenchmark
% 3.62/1.49 % SZS output start Proof for theBenchmark
% See solution above
% 3.62/1.49 % (3389808)------------------------------
% 3.62/1.49 % (3389808)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.62/1.49 % (3389808)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.62/1.49 % (3389808)CaDiCaL version: 2.1.3
% 3.62/1.49 % (3389808)Termination reason: Refutation
% 3.62/1.49 % (3389808)Time elapsed: 0.003 s
% 3.62/1.49 % (3389808)Peak memory usage: 88 MB
% 3.62/1.49 % (3389808)Instructions burned: 2 (million)
% 3.62/1.49 % (3389808)------------------------------
% 3.62/1.49 % (3389808)------------------------------
% 3.62/1.49 % (3389798)Success in time 0.437 s
% 3.62/1.49 % Vampire exiting
%------------------------------------------------------------------------------