%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ132+1 : TPTP v9.3.1. Released v4.1.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n008.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 12:31:40 PM UTC 2026
% Result : Theorem 2.55s 1.15s
% Output : Refutation 2.55s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 10
% Syntax : Number of formulae : 38 ( 13 unt; 3 def)
% Number of atoms : 63 ( 2 equ)
% Maximal formula atoms : 2 ( 1 avg)
% Number of connectives : 46 ( 21 ~; 17 |; 2 &)
% ( 3 <=>; 3 =>; 0 <=; 0 <~>)
% Maximal formula depth : 4 ( 2 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 10 ( 8 usr; 4 prp; 0-2 aty)
% Number of functors : 3 ( 3 usr; 2 con; 0-1 aty)
% Number of variables : 10 ( 0 sgn 10 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f3,axiom,
! [X0] :
( capital(X0)
=> city(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',capital_city_type) ).
fof(f5,axiom,
capital(washington),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',washington_type) ).
fof(f6,axiom,
country(usa),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',usa_type) ).
fof(f8,axiom,
! [X0] :
( city(X0)
=> has_crime(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',crime_axiom) ).
fof(f9,axiom,
capital_city(usa) = washington,
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',usa_capital_axiom) ).
fof(f10,axiom,
! [X0] :
( country(X0)
=> beautiful(capital_city(X0)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',beautiful_capital_axiom) ).
fof(f11,conjecture,
( beautiful(washington)
& has_crime(washington) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',washington_conjecture) ).
fof(f12,negated_conjecture,
~ ( beautiful(washington)
& has_crime(washington) ),
inference(negated_conjecture,[status(cth)],[f11]) ).
fof(f13,plain,
! [X0] :
( city(X0)
| ~ capital(X0) ),
inference(ennf_transformation,[],[f3]) ).
fof(f15,plain,
! [X0] :
( has_crime(X0)
| ~ city(X0) ),
inference(ennf_transformation,[],[f8]) ).
fof(f16,plain,
! [X0] :
( beautiful(capital_city(X0))
| ~ country(X0) ),
inference(ennf_transformation,[],[f10]) ).
fof(f17,plain,
( ~ beautiful(washington)
| ~ has_crime(washington) ),
inference(ennf_transformation,[],[f12]) ).
fof(f23,plain,
! [X0] :
( city(X0)
| ~ capital(X0) ),
inference(cnf_transformation,[],[f13]) ).
fof(f25,plain,
capital(washington),
inference(cnf_transformation,[],[f5]) ).
fof(f26,plain,
country(usa),
inference(cnf_transformation,[],[f6]) ).
fof(f28,plain,
! [X0] :
( ~ city(X0)
| has_crime(X0) ),
inference(cnf_transformation,[],[f15]) ).
fof(f29,plain,
washington = capital_city(usa),
inference(cnf_transformation,[],[f9]) ).
fof(f30,plain,
! [X0] :
( beautiful(capital_city(X0))
| ~ country(X0) ),
inference(cnf_transformation,[],[f16]) ).
fof(f31,plain,
( ~ beautiful(washington)
| ~ has_crime(washington) ),
inference(cnf_transformation,[],[f17]) ).
fof(f33,definition,
( spl3_1
<=> has_crime(washington) ),
introduced(definition,[new_symbols(definition,[spl3_1])],[avatar_definition]) ).
fof(f35,plain,
( ~ has_crime(washington)
| spl3_1 ),
inference(avatar_component_clause,[],[f33]) ).
fof(f37,definition,
( spl3_2
<=> beautiful(washington) ),
introduced(definition,[new_symbols(definition,[spl3_2])],[avatar_definition]) ).
fof(f40,plain,
( ~ spl3_1
| ~ spl3_2 ),
inference(avatar_split_clause,[],[f31,f37,f33]) ).
fof(f42,plain,
( beautiful(washington)
| ~ country(usa) ),
inference(superposition,[],[f30,f29]) ).
fof(f44,definition,
( spl3_3
<=> country(usa) ),
introduced(definition,[new_symbols(definition,[spl3_3])],[avatar_definition]) ).
fof(f47,plain,
( ~ spl3_3
| spl3_2 ),
inference(avatar_split_clause,[],[f42,f37,f44]) ).
fof(f48,plain,
spl3_3,
inference(avatar_split_clause,[],[f26,f44]) ).
fof(f49,plain,
! [X0] :
( has_crime(X0)
| ~ capital(X0) ),
inference(resolution,[],[f23,f28]) ).
fof(f51,plain,
( ~ capital(washington)
| spl3_1 ),
inference(resolution,[],[f49,f35]) ).
fof(f52,plain,
( $false
| spl3_1 ),
inference(forward_subsumption_resolution,[],[f51,f25]) ).
fof(f53,plain,
spl3_1,
inference(avatar_contradiction_clause,[],[f52]) ).
cnf(s1,plain,
( ~ spl3_1
| ~ spl3_2 ),
inference(sat_conversion,[],[f40]) ).
cnf(s2,plain,
( spl3_2
| ~ spl3_3 ),
inference(sat_conversion,[],[f47]) ).
cnf(s3,plain,
spl3_3,
inference(sat_conversion,[],[f48]) ).
cnf(s4,plain,
spl3_1,
inference(sat_conversion,[],[f53]) ).
cnf(s5,plain,
spl3_2,
inference(rat,[],[s2,s3]) ).
cnf(s6,plain,
$false,
inference(rat,[],[s1,s5,s4]) ).
fof(f54,plain,
$false,
inference(avatar_sat_refutation,[],[s6]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ132+1 : TPTP v9.3.1. Released v4.1.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.41 % Computer : n008.cluster.edu
% 0.12/0.41 % Model : x86_64 x86_64
% 0.12/0.41 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.41 % Memory : 8046.5625MB
% 0.12/0.41 % OS : Linux 6.8.0-71-generic
% 0.12/0.41 % CPULimit : 300
% 0.12/0.41 % WCLimit : 300
% 0.12/0.41 % DateTime : Sun Sep 27 22:45:39 UTC 2026
% 0.12/0.41 % CPUTime :
% 0.12/0.41 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.44 Running first-order theorem proving
% 0.12/0.44 Running: /export/starexec/sandbox2/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 2.55/1.15 % (1681125)Detected formulas, will run a generic FOF schedule.
% 2.55/1.15 % (1681205)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3050116298:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 2.55/1.15 % (1681205)First to succeed.
% 2.55/1.15 % (1681205)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-1681125"
% 2.55/1.15 % (1681204)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=1225843262:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 2.55/1.15 % (1681201)lrs+11_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:lma=off:spb=units:urr=ec_only:bce=on:s2agt=64:updr=off:random_seed=4265791086:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 2.55/1.15 % (1681203)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=2564423911:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 2.55/1.15 % (1681206)dis-21_1_sil=8000:lcm=predicate:random_seed=504946826:st=5:avsq=on:i=129:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/129Mi)
% 2.55/1.15 % (1681200)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=3647375753:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 2.55/1.15 % (1681202)lrs+1010_1_anc=all:sfv=off:to=kbo:ncem=casc2026/models/loop7.pt:sil=128000:npcc=on:prc=on:sos=all:bsr=unit_only:sac=on:random_seed=960449213:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 2.55/1.15 % (1681203)Refutation not found, incomplete strategy
% 2.55/1.15 % (1681203)------------------------------
% 2.55/1.15 % (1681203)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.55/1.15 % (1681203)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.55/1.15 % (1681203)CaDiCaL version: 2.1.3
% 2.55/1.15 % (1681203)Termination reason: Refutation not found, incomplete strategy
% 2.55/1.15 % (1681203)Time elapsed: 0.0000 s
% 2.55/1.15 % (1681203)Peak memory usage: 86 MB
% 2.55/1.15 % (1681204)Refutation not found, incomplete strategy
% 2.55/1.15 % (1681204)------------------------------
% 2.55/1.15 % (1681204)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.55/1.15 % (1681204)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.55/1.15 % (1681204)CaDiCaL version: 2.1.3
% 2.55/1.15 % (1681204)Termination reason: Refutation not found, incomplete strategy
% 2.55/1.15 % (1681204)Time elapsed: 0.001 s
% 2.55/1.15 % (1681204)Peak memory usage: 87 MB
% 2.55/1.15 % (1681206)Refutation not found, incomplete strategy
% 2.55/1.15 % (1681206)------------------------------
% 2.55/1.15 % (1681206)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.55/1.15 % (1681206)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.55/1.15 % (1681206)CaDiCaL version: 2.1.3
% 2.55/1.15 % (1681206)Termination reason: Refutation not found, incomplete strategy
% 2.55/1.15 % (1681206)Time elapsed: 0.001 s
% 2.55/1.15 % (1681206)Peak memory usage: 88 MB
% 2.55/1.15 % (1681205)Refutation found. Thanks to Tanya!
% 2.55/1.15 % SZS status Theorem for theBenchmark
% 2.55/1.15 % SZS output start Proof for theBenchmark
% See solution above
% 2.55/1.15 % (1681205)------------------------------
% 2.55/1.15 % (1681205)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.55/1.15 % (1681205)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.55/1.15 % (1681205)CaDiCaL version: 2.1.3
% 2.55/1.15 % (1681205)Termination reason: Refutation
% 2.55/1.15 % (1681205)Time elapsed: 0.002 s
% 2.55/1.15 % (1681205)Peak memory usage: 89 MB
% 2.55/1.15 % (1681205)Instructions burned: 1 (million)
% 2.55/1.15 % (1681205)------------------------------
% 2.55/1.15 % (1681205)------------------------------
% 2.55/1.15 % (1681125)Success in time 0.306 s
% 2.55/1.15 % Vampire exiting
%------------------------------------------------------------------------------