%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : PUZ137_8 : TPTP v9.3.1. Released v8.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% Computer : n011.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 12:32:34 PM UTC 2026
% Result : Theorem 0.22s 0.50s
% Output : Refutation 0.22s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 6
% Syntax : Number of formulae : 36 ( 12 unt; 0 typ; 4 def)
% Number of atoms : 101 ( 0 equ)
% Maximal formula atoms : 2 ( 2 avg)
% Number of connectives : 57 ( 30 ~; 21 |; 0 &)
% ( 4 <=>; 2 =>; 0 <=; 0 <~>)
% Maximal formula depth : 3 ( 2 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of FOOLs : 51 ( 41 fml; 10 var)
% Number of types : 2 ( 0 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 10 ( 8 usr; 9 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 7 ( 0 sgn 6 !; 1 ?; 7 :)
% Comments :
%------------------------------------------------------------------------------
tff(pred_def_1,type,
says: ( $i * $o ) > $o ).
tff(f1,axiom,
says(peter,
! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) )),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ax1) ).
tff(f2,conjecture,
! [X0: $o] : says(peter,(X0)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',thm) ).
tff(f3,negated_conjecture,
~ ! [X0: $o] : says(peter,(X0)),
inference(negated_conjecture,[status(cth)],[f2]) ).
tff(f4,plain,
says(peter,
! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) )),
inference(rectify,[],[f1]) ).
tff(f5,plain,
~ ! [X0: $o] : says(peter,(X0)),
inference(rectify,[],[f3]) ).
tff(f6,plain,
says(peter,
! [X0: $o] :
( ~ (X0)
| ~ says(peter,(X0)) )),
inference(ennf_transformation,[],[f4]) ).
tff(f7,plain,
? [X0: $o] : ~ says(peter,(X0)),
inference(ennf_transformation,[],[f5]) ).
tff(f9,plain,
( ~ sK0
| says(peter,$true) ),
inference(cnf_transformation,[],[f6]) ).
tff(f10,plain,
( ~ says(peter,$true)
| says(peter,$false) ),
inference(cnf_transformation,[],[f6]) ).
tff(f11,plain,
( sK0
| says(peter,$true) ),
inference(cnf_transformation,[],[f6]) ).
tff(f12,plain,
( sK1
| ~ says(peter,$false) ),
inference(cnf_transformation,[],[f7]) ).
tff(f13,plain,
( ~ sK1
| ~ says(peter,$true) ),
inference(cnf_transformation,[],[f7]) ).
tff(f16,plain,
( ~ sK0
| ~ says(peter,$true) ),
inference(consistent_polarity_flipping,[],[f11]) ).
tff(f17,plain,
( says(peter,$true)
| ~ says(peter,$false) ),
inference(consistent_polarity_flipping,[],[f10]) ).
tff(f18,plain,
( sK0
| ~ says(peter,$true) ),
inference(consistent_polarity_flipping,[],[f9]) ).
tff(f20,plain,
( ~ sK1
| says(peter,$true) ),
inference(consistent_polarity_flipping,[],[f13]) ).
tff(f21,plain,
( sK1
| says(peter,$false) ),
inference(consistent_polarity_flipping,[],[f12]) ).
tff(f23,definition,
( spl2_1
<=> says(peter,$false) ),
introduced(definition,[new_symbols(definition,[spl2_1])],[avatar_definition]) ).
tff(f27,definition,
( spl2_2
<=> sK1 ),
introduced(definition,[new_symbols(definition,[spl2_2])],[avatar_definition]) ).
tff(f30,plain,
( spl2_1
| spl2_2 ),
inference(avatar_split_clause,[],[f21,f27,f23]) ).
tff(f32,definition,
( spl2_3
<=> says(peter,$true) ),
introduced(definition,[new_symbols(definition,[spl2_3])],[avatar_definition]) ).
tff(f35,plain,
( spl2_3
| ~ spl2_2 ),
inference(avatar_split_clause,[],[f20,f27,f32]) ).
tff(f37,definition,
( spl2_4
<=> sK0 ),
introduced(definition,[new_symbols(definition,[spl2_4])],[avatar_definition]) ).
tff(f41,plain,
( ~ spl2_3
| spl2_4 ),
inference(avatar_split_clause,[],[f18,f37,f32]) ).
tff(f42,plain,
( ~ spl2_1
| spl2_3 ),
inference(avatar_split_clause,[],[f17,f32,f23]) ).
tff(f43,plain,
( ~ spl2_3
| ~ spl2_4 ),
inference(avatar_split_clause,[],[f16,f37,f32]) ).
cnf(s1,plain,
( spl2_1
| spl2_2 ),
inference(sat_conversion,[],[f30]) ).
cnf(s2,plain,
( ~ spl2_2
| spl2_3 ),
inference(sat_conversion,[],[f35]) ).
cnf(s4,plain,
( ~ spl2_3
| spl2_4 ),
inference(sat_conversion,[],[f41]) ).
cnf(s5,plain,
( ~ spl2_1
| spl2_3 ),
inference(sat_conversion,[],[f42]) ).
cnf(s6,plain,
( ~ spl2_3
| ~ spl2_4 ),
inference(sat_conversion,[],[f43]) ).
cnf(s7,plain,
~ spl2_3,
inference(rat,[],[s4,s6]) ).
cnf(s8,plain,
~ spl2_1,
inference(rat,[],[s5,s7]) ).
cnf(s9,plain,
~ spl2_2,
inference(rat,[],[s2,s7]) ).
cnf(s10,plain,
$false,
inference(rat,[],[s1,s9,s8]) ).
tff(f44,plain,
$false,
inference(avatar_sat_refutation,[],[s10]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ137_8 : TPTP v9.3.1. Released v8.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.13/0.41 % Computer : n011.cluster.edu
% 0.13/0.41 % Model : x86_64 x86_64
% 0.13/0.41 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.13/0.41 % Memory : 8046.5625MB
% 0.13/0.41 % OS : Linux 6.8.0-71-generic
% 0.13/0.41 % CPULimit : 300
% 0.13/0.41 % WCLimit : 300
% 0.13/0.41 % DateTime : Sun Sep 27 22:45:30 UTC 2026
% 0.13/0.41 % CPUTime :
% 0.13/0.42 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 SAT
% 0.13/0.46 Running first-order model finding
% 0.13/0.47 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
% 0.22/0.50 % (2835486)Will run a generic schedule for satisfiability detection.
% 0.22/0.50 % (2835492)% WARNING: option uhcvi not known.
% 0.22/0.50 % (2835492)dis+11_61:31_drc=ordering:lsd=5:bsr=unit_only:rp=on:newcnf=on:random_seed=1936861566:i=135531:add=off:rawr=on_3000 on theBenchmark for (3000ds/135531Mi)
% 0.22/0.50 % (2835492) found proof, printing to "/export/starexec/sandbox/tmp/vampire-proof-2835486-2835492"...
% 0.22/0.50 % (2835491)fmb+10_1_sas=cadical:bce=on:rp=on:random_seed=519840942_3000 on theBenchmark for (3000ds/0Mi)
% 0.22/0.50 % (2835492)...printing done.
% 0.22/0.50 % (2835492)Refutation found. Thanks to Tanya!
% 0.22/0.50 % SZS status Theorem for theBenchmark
% 0.22/0.50 % SZS output start Proof for theBenchmark
% See solution above
% 0.22/0.50 % (2835492)------------------------------
% 0.22/0.50 % (2835492)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.22/0.50 % (2835492)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.22/0.50 % (2835492)CaDiCaL version: 2.1.3
% 0.22/0.50 % (2835492)Termination reason: Refutation
% 0.22/0.50 % (2835492)Time elapsed: 0.001 s
% 0.22/0.50 % (2835492)Peak memory usage: 12 MB
% 0.22/0.50 % (2835492)Instructions burned: 1 (million)
% 0.22/0.50 % (2835486)Success in time 0.024 s
% 0.22/0.50 % Vampire exiting
%------------------------------------------------------------------------------