%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ032-1 : 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 : n017.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 12:31:18 PM UTC 2026
% Result : Unsatisfiable 0.19s 1.70s
% Output : Refutation 0.19s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 11
% Syntax : Number of formulae : 31 ( 10 unt; 3 def)
% Number of atoms : 57 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 52 ( 26 ~; 23 |; 0 &)
% ( 3 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 4 ( 2 avg)
% Number of predicates : 5 ( 4 usr; 4 prp; 0-1 aty)
% Number of functors : 6 ( 6 usr; 3 con; 0-2 aty)
% Number of variables : 8 ( 0 sgn 8 !; 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(f2,axiom,
! [X0] :
( ~ a_truth(liar(X0))
| ~ a_truth(truthteller(X0)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',not_both) ).
fof(f3,axiom,
! [X0,X1] :
( ~ a_truth(says(X0,X1))
| ~ a_truth(truthteller(X0))
| a_truth(X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',truthtellers_tell_truth) ).
fof(f5,axiom,
! [X0,X1] :
( ~ a_truth(says(X1,X0))
| ~ a_truth(X0)
| a_truth(truthteller(X1)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',truths_are_told_by_truthtellers) ).
fof(f6,axiom,
! [X0,X1] :
( ~ a_truth(says(X1,X0))
| a_truth(X0)
| a_truth(liar(X1)) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',liars_are_told_by_liars) ).
fof(f8,axiom,
a_truth(says(b,says(a,liar(a)))),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',b_says_a_says_hes_a_liar) ).
fof(f9,axiom,
a_truth(says(c,liar(b))),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',c_says_b_is_a_liar) ).
fof(f10,negated_conjecture,
~ a_truth(truthteller(c)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_c_is_a_truthteller) ).
fof(f16,definition,
( spl0_1
<=> a_truth(says(a,liar(a))) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f17,plain,
( a_truth(says(a,liar(a)))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f16]) ).
fof(f26,definition,
( spl0_4
<=> a_truth(truthteller(a)) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f34,definition,
( spl0_5
<=> a_truth(liar(b)) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f47,plain,
( ~ a_truth(liar(b))
| a_truth(truthteller(c)) ),
inference(resolution,[],[f5,f9]) ).
fof(f50,plain,
~ a_truth(liar(b)),
inference(forward_subsumption_resolution,[],[f47,f10]) ).
fof(f54,plain,
~ spl0_5,
inference(avatar_split_clause,[],[f50,f34]) ).
fof(f57,plain,
( a_truth(says(a,liar(a)))
| a_truth(liar(b)) ),
inference(resolution,[],[f6,f8]) ).
fof(f59,plain,
( spl0_5
| spl0_1 ),
inference(avatar_split_clause,[],[f57,f16,f34]) ).
fof(f73,plain,
( ~ a_truth(liar(a))
| a_truth(truthteller(a))
| ~ spl0_1 ),
inference(resolution,[],[f17,f5]) ).
fof(f75,plain,
( ~ a_truth(truthteller(a))
| a_truth(liar(a))
| ~ spl0_1 ),
inference(resolution,[],[f17,f3]) ).
fof(f78,plain,
( ~ a_truth(truthteller(a))
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f75,f2]) ).
fof(f81,plain,
( a_truth(truthteller(a))
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f73,f1]) ).
fof(f85,plain,
( ~ spl0_4
| ~ spl0_1 ),
inference(avatar_split_clause,[],[f78,f16,f26]) ).
fof(f86,plain,
( spl0_4
| ~ spl0_1 ),
inference(avatar_split_clause,[],[f81,f16,f26]) ).
cnf(s8,plain,
~ spl0_5,
inference(sat_conversion,[],[f54]) ).
cnf(s9,plain,
( spl0_1
| spl0_5 ),
inference(sat_conversion,[],[f59]) ).
cnf(s17,plain,
( ~ spl0_1
| ~ spl0_4 ),
inference(sat_conversion,[],[f85]) ).
cnf(s18,plain,
( ~ spl0_1
| spl0_4 ),
inference(sat_conversion,[],[f86]) ).
cnf(s24,plain,
spl0_1,
inference(rat,[],[s9,s8]) ).
cnf(s26,plain,
spl0_4,
inference(rat,[],[s18,s24]) ).
cnf(s28,plain,
$false,
inference(rat,[],[s17,s26,s24]) ).
fof(f91,plain,
$false,
inference(avatar_sat_refutation,[],[s28]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ032-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.12/0.60 % Computer : n017.cluster.edu
% 0.12/0.60 % Model : x86_64 x86_64
% 0.12/0.60 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.60 % Memory : 8046.5625MB
% 0.12/0.60 % OS : Linux 6.8.0-71-generic
% 0.12/0.60 % CPULimit : 300
% 0.12/0.60 % WCLimit : 300
% 0.12/0.60 % DateTime : Sun Sep 27 22:28:23 UTC 2026
% 0.12/0.60 % CPUTime :
% 0.12/0.60 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.16/0.64 Running first-order theorem proving
% 0.16/0.64 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
% 0.19/1.70 % (2998762)Input is clausal, will run a generic CNF schedule.
% 0.19/1.70 % (2998768)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=4245907965:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 0.19/1.70 % (2998767)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=1919155066:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 0.19/1.70 % (2998771)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=4226131313:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 0.19/1.70 % (2998770)lrs+10_1_sil=8000:sp=occurrence:random_seed=1635590868:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 0.19/1.70 % (2998772)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=901281125:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 0.19/1.70 % (2998773)dis-21_1_sil=8000:lcm=predicate:random_seed=3475962246: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)
% 0.19/1.70 % (2998769)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=2834152128:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 0.19/1.70 % (2998773)Also succeeded, but the first one will report.
% 0.19/1.70 % (2998770)Also succeeded, but the first one will report.
% 0.19/1.70 % (2998771)First to succeed.
% 0.19/1.70 % (2998772)Also succeeded, but the first one will report.
% 0.19/1.70 % (2998771)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-2998762"
% 0.19/1.70 % (2998771)Refutation found. Thanks to Tanya!
% 0.19/1.70 % SZS status Unsatisfiable for theBenchmark
% 0.19/1.70 % SZS output start Proof for theBenchmark
% See solution above
% 0.19/1.70 % (2998771)------------------------------
% 0.19/1.70 % (2998771)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.19/1.70 % (2998771)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.19/1.70 % (2998771)CaDiCaL version: 2.1.3
% 0.19/1.70 % (2998771)Termination reason: Refutation
% 0.19/1.70 % (2998771)Time elapsed: 0.003 s
% 0.19/1.70 % (2998771)Peak memory usage: 88 MB
% 0.19/1.70 % (2998771)Instructions burned: 1 (million)
% 0.19/1.70 % (2998771)------------------------------
% 0.19/1.70 % (2998771)------------------------------
% 0.19/1.70 % (2998762)Success in time 0.431 s
% 0.19/1.70 % Vampire exiting
%------------------------------------------------------------------------------