%------------------------------------------------------------------------------
% File : Vampire-SAT---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 SAT
% Computer : n020.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 0.10s 0.44s
% Output : Refutation 0.10s
% Verified :
% SZS Type : Refutation
% Derivation depth : 5
% Number of leaves : 7
% Syntax : Number of formulae : 17 ( 6 unt; 0 def)
% Number of atoms : 40 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 50 ( 27 ~; 23 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 4 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 4 ( 3 usr; 1 prp; 0-2 aty)
% Number of functors : 8 ( 8 usr; 5 con; 0-2 aty)
% Number of variables : 22 ( 22 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( a_truth(liar(X0))
| a_truth(truthteller(X0)) ),
file('/export/starexec/sandbox/benchmark/Axioms/PUZ002-0.ax',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(f25,plain,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(liar(X0))
| a_truth(X1) ),
inference(forward_subsumption_resolution,[],[f17,f24]) ).
fof(f26,plain,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(liar(X0))
| ~ a_truth(X1) ),
inference(forward_subsumption_resolution,[],[f16,f24]) ).
fof(f27,plain,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(truthteller(X0))
| a_truth(X1) ),
inference(forward_subsumption_resolution,[],[f15,f24]) ).
fof(f28,plain,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(truthteller(X0))
| ~ a_truth(X1) ),
inference(forward_subsumption_resolution,[],[f14,f24]) ).
fof(f29,plain,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(liar(X0)) ),
inference(forward_subsumption_resolution,[],[f26,f25]) ).
fof(f30,plain,
! [X0,X1] :
( ~ ask_1_if_2(X0,X1)
| ~ a_truth(truthteller(X0)) ),
inference(forward_subsumption_resolution,[],[f28,f27]) ).
fof(f33,plain,
~ a_truth(truthteller(c)),
inference(resolution,[],[f23,f30]) ).
fof(f34,plain,
~ a_truth(liar(c)),
inference(resolution,[],[f23,f29]) ).
fof(f35,plain,
a_truth(truthteller(c)),
inference(resolution,[],[f1,f34]) ).
fof(f36,plain,
$false,
inference(forward_subsumption_resolution,[],[f35,f33]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ025-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.10/0.36 % Computer : n020.cluster.edu
% 0.10/0.36 % Model : x86_64 x86_64
% 0.10/0.36 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.36 % Memory : 8046.5625MB
% 0.10/0.36 % OS : Linux 6.8.0-71-generic
% 0.10/0.36 % CPULimit : 300
% 0.10/0.36 % WCLimit : 300
% 0.10/0.36 % DateTime : Sun Sep 27 22:31:20 UTC 2026
% 0.10/0.36 % CPUTime :
% 0.10/0.36 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.10/0.39 Running first-order model finding
% 0.10/0.39 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
% 0.10/0.44 % (3831709)Will run a generic schedule for satisfiability detection.
% 0.10/0.44 % (3831718)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=1197386862:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.10/0.44 % (3831718) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-3831709-3831718"...
% 0.10/0.44 % (3831718)...printing done.
% 0.10/0.44 % (3831718)Refutation found. Thanks to Tanya!
% 0.10/0.44 % SZS status Unsatisfiable for theBenchmark
% 0.10/0.44 % SZS output start Proof for theBenchmark
% See solution above
% 0.10/0.44 % (3831718)------------------------------
% 0.10/0.44 % (3831718)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.10/0.44 % (3831718)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.10/0.44 % (3831718)CaDiCaL version: 2.1.3
% 0.10/0.44 % (3831718)Termination reason: Refutation
% 0.10/0.44 % (3831718)Time elapsed: 0.001 s
% 0.10/0.44 % (3831718)Peak memory usage: 11 MB
% 0.10/0.44 % (3831718)Instructions burned: 1 (million)
% 0.10/0.44 % (3831709)Success in time 0.033 s
% 0.10/0.44 % Vampire exiting
%------------------------------------------------------------------------------