%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ032-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n001.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 12:31:59 PM UTC 2026
% Result : Unsatisfiable 0.13s 0.42s
% Output : Refutation 0.13s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 10
% Syntax : Number of formulae : 38 ( 11 unt; 3 def)
% Number of atoms : 72 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 67 ( 33 ~; 31 |; 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 : 7 ( 0 sgn 7 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( a_truth(truthteller(X0))
| a_truth(liar(X0)) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ002-0.ax',truthteller_or_liar) ).
fof(f3,axiom,
! [X0,X1] :
( ~ a_truth(says(X0,X1))
| ~ a_truth(truthteller(X0))
| a_truth(X1) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ002-0.ax',truthtellers_tell_truth) ).
fof(f4,axiom,
! [X0,X1] :
( ~ a_truth(says(X0,X1))
| ~ a_truth(liar(X0))
| ~ a_truth(X1) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ002-0.ax',liars_lie) ).
fof(f6,axiom,
! [X0,X1] :
( ~ a_truth(says(X1,X0))
| a_truth(X0)
| a_truth(liar(X1)) ),
file('/export/starexec/sandbox2/benchmark/Axioms/PUZ002-0.ax',liars_are_told_by_liars) ).
fof(f8,axiom,
a_truth(says(b,says(a,liar(a)))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b_says_a_says_hes_a_liar) ).
fof(f9,axiom,
a_truth(says(c,liar(b))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',c_says_b_is_a_liar) ).
fof(f10,negated_conjecture,
~ a_truth(truthteller(c)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_c_is_a_truthteller) ).
fof(f11,plain,
a_truth(liar(c)),
inference(resolution,[],[f1,f10]) ).
fof(f15,plain,
( ~ a_truth(truthteller(b))
| a_truth(says(a,liar(a))) ),
inference(resolution,[],[f3,f8]) ).
fof(f17,definition,
( spl0_1
<=> a_truth(says(a,liar(a))) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f19,plain,
( a_truth(says(a,liar(a)))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f17]) ).
fof(f21,definition,
( spl0_2
<=> a_truth(truthteller(b)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f23,plain,
( ~ a_truth(truthteller(b))
| spl0_2 ),
inference(avatar_component_clause,[],[f21]) ).
fof(f24,plain,
( spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f15,f21,f17]) ).
fof(f34,plain,
( a_truth(liar(b))
| spl0_2 ),
inference(resolution,[],[f23,f1]) ).
fof(f36,plain,
( ~ a_truth(liar(c))
| ~ a_truth(liar(b)) ),
inference(resolution,[],[f4,f9]) ).
fof(f39,plain,
~ a_truth(liar(b)),
inference(forward_subsumption_resolution,[],[f36,f11]) ).
fof(f41,definition,
( spl0_5
<=> a_truth(liar(a)) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f42,plain,
( a_truth(liar(a))
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f41]) ).
fof(f43,plain,
( ~ a_truth(liar(a))
| spl0_5 ),
inference(avatar_component_clause,[],[f41]) ).
fof(f46,plain,
( $false
| spl0_2 ),
inference(forward_subsumption_resolution,[],[f39,f34]) ).
fof(f47,plain,
spl0_2,
inference(avatar_contradiction_clause,[],[f46]) ).
fof(f62,plain,
( a_truth(liar(a))
| a_truth(liar(a))
| ~ spl0_1 ),
inference(resolution,[],[f19,f6]) ).
fof(f64,plain,
( ~ a_truth(liar(a))
| ~ a_truth(liar(a))
| ~ spl0_1 ),
inference(resolution,[],[f19,f4]) ).
fof(f66,plain,
( ~ a_truth(liar(a))
| ~ spl0_1 ),
inference(duplicate_literal_removal,[],[f64]) ).
fof(f67,plain,
( a_truth(liar(a))
| ~ spl0_1 ),
inference(duplicate_literal_removal,[],[f62]) ).
fof(f69,plain,
( $false
| ~ spl0_1
| ~ spl0_5 ),
inference(forward_subsumption_resolution,[],[f66,f42]) ).
fof(f70,plain,
( ~ spl0_1
| ~ spl0_5 ),
inference(avatar_contradiction_clause,[],[f69]) ).
fof(f74,plain,
( $false
| ~ spl0_1
| spl0_5 ),
inference(forward_subsumption_resolution,[],[f67,f43]) ).
fof(f75,plain,
( ~ spl0_1
| spl0_5 ),
inference(avatar_contradiction_clause,[],[f74]) ).
cnf(s1,plain,
( spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f24]) ).
cnf(s5,plain,
spl0_2,
inference(sat_conversion,[],[f47]) ).
cnf(s8,plain,
( ~ spl0_1
| ~ spl0_5 ),
inference(sat_conversion,[],[f70]) ).
cnf(s10,plain,
( ~ spl0_1
| spl0_5 ),
inference(sat_conversion,[],[f75]) ).
cnf(s12,plain,
spl0_1,
inference(rat,[],[s1,s5]) ).
cnf(s14,plain,
spl0_5,
inference(rat,[],[s10,s12]) ).
cnf(s15,plain,
$false,
inference(rat,[],[s8,s14,s12]) ).
fof(f78,plain,
$false,
inference(avatar_sat_refutation,[],[s15]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ032-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.09/0.36 % Computer : n001.cluster.edu
% 0.09/0.36 % Model : x86_64 x86_64
% 0.09/0.36 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.36 % Memory : 8046.5625MB
% 0.09/0.36 % OS : Linux 6.8.0-71-generic
% 0.09/0.36 % CPULimit : 300
% 0.09/0.36 % WCLimit : 300
% 0.09/0.36 % DateTime : Sun Sep 27 22:38:48 UTC 2026
% 0.09/0.36 % CPUTime :
% 0.09/0.36 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.13/0.39 Running first-order model finding
% 0.13/0.39 Running: /export/starexec/sandbox2/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.13/0.42 % (4033573)Will run a generic schedule for satisfiability detection.
% 0.13/0.42 % (4033582)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=3058716929:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.13/0.42 % (4033582) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-4033573-4033582"...
% 0.13/0.42 % (4033582)...printing done.
% 0.13/0.42 % (4033582)Refutation found. Thanks to Tanya!
% 0.13/0.42 % SZS status Unsatisfiable for theBenchmark
% 0.13/0.42 % SZS output start Proof for theBenchmark
% See solution above
% 0.13/0.42 % (4033582)------------------------------
% 0.13/0.42 % (4033582)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.13/0.42 % (4033582)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.13/0.42 % (4033582)CaDiCaL version: 2.1.3
% 0.13/0.42 % (4033582)Termination reason: Refutation
% 0.13/0.42 % (4033582)Time elapsed: 0.001 s
% 0.13/0.42 % (4033582)Peak memory usage: 12 MB
% 0.13/0.42 % (4033582)Instructions burned: 1 (million)
% 0.13/0.42 % (4033573)Success in time 0.025 s
% 0.13/0.42 % Vampire exiting
%------------------------------------------------------------------------------