%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ029-1 : 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 : n002.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 12:31:16 PM UTC 2026
% Result : Unsatisfiable 3.40s 1.36s
% Output : Refutation 3.40s
% Verified :
% SZS Type : Refutation
% Derivation depth : 17
% Number of leaves : 16
% Syntax : Number of formulae : 47 ( 15 unt; 2 def)
% Number of atoms : 95 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 88 ( 40 ~; 46 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 16 ( 15 usr; 3 prp; 0-1 aty)
% Number of functors : 1 ( 1 usr; 1 con; 0-0 aty)
% Number of variables : 10 ( 0 sgn 10 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0] :
( old(X0)
| eats_pennybuns(X0)
| dances_on_tightropes(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',boring_old_people) ).
fof(f2,axiom,
! [X0] :
( ~ liable_to_giddiness(X0)
| ~ pig(X0)
| treated_with_respect(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',giddy_pigs_reated_with_respect) ).
fof(f3,axiom,
! [X0] :
( ~ balloonist(X0)
| ~ wise(X0)
| has_umbrella(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',wise_ballonists_have_umbrellas) ).
fof(f4,axiom,
! [X0] :
( ~ eats_lunch_in_public(X0)
| ~ eats_pennybuns(X0)
| ~ looks_ridiculous(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',dont_look_ridiculous_eating_buns_in_public) ).
fof(f5,axiom,
! [X0] :
( ~ young(X0)
| ~ balloonist(X0)
| liable_to_giddiness(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',young_balloonists_get_giddy) ).
fof(f6,axiom,
! [X0] :
( ~ fat(X0)
| ~ looks_ridiculous(X0)
| dances_on_tightropes(X0)
| eats_lunch_in_public(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',fat_ridiculous_off_tightrope_eat_in_public) ).
fof(f7,axiom,
! [X0] :
( ~ wise(X0)
| ~ liable_to_giddiness(X0)
| ~ dances_on_tightropes(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',wise_giddy_dont_dance_on_tightrope) ).
fof(f8,axiom,
! [X0] :
( ~ has_umbrella(X0)
| ~ pig(X0)
| looks_ridiculous(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pigs_look_ridiculous_with_umbrellas) ).
fof(f9,axiom,
! [X0] :
( ~ treated_with_respect(X0)
| dances_on_tightropes(X0)
| fat(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',non_dancers_who_are_respected_are_fat) ).
fof(f11,axiom,
! [X0] :
( ~ young(X0)
| ~ old(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',not_young_and_old) ).
fof(f12,axiom,
wise(piggy),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',piggy_is_wise) ).
fof(f13,axiom,
young(piggy),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',piggy_is_young) ).
fof(f14,axiom,
pig(piggy),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',piggy_is_a_pig) ).
fof(f15,negated_conjecture,
balloonist(piggy),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_piggy_is_no_balloonist) ).
fof(f16,plain,
~ old(piggy),
inference(resolution,[],[f11,f13]) ).
fof(f18,plain,
( eats_pennybuns(piggy)
| dances_on_tightropes(piggy) ),
inference(resolution,[],[f1,f16]) ).
fof(f20,definition,
( spl0_1
<=> dances_on_tightropes(piggy) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f21,plain,
( ~ dances_on_tightropes(piggy)
| spl0_1 ),
inference(avatar_component_clause,[],[f20]) ).
fof(f24,definition,
( spl0_2
<=> eats_pennybuns(piggy) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f26,plain,
( eats_pennybuns(piggy)
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f24]) ).
fof(f27,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f18,f24,f20]) ).
fof(f28,plain,
( ~ wise(piggy)
| has_umbrella(piggy) ),
inference(resolution,[],[f3,f15]) ).
fof(f29,plain,
has_umbrella(piggy),
inference(forward_subsumption_resolution,[],[f28,f12]) ).
fof(f30,plain,
( ~ balloonist(piggy)
| liable_to_giddiness(piggy) ),
inference(resolution,[],[f5,f13]) ).
fof(f32,plain,
liable_to_giddiness(piggy),
inference(forward_subsumption_resolution,[],[f30,f15]) ).
fof(f33,plain,
( ~ pig(piggy)
| treated_with_respect(piggy) ),
inference(resolution,[],[f32,f2]) ).
fof(f34,plain,
treated_with_respect(piggy),
inference(forward_subsumption_resolution,[],[f33,f14]) ).
fof(f35,plain,
( ~ liable_to_giddiness(piggy)
| ~ dances_on_tightropes(piggy) ),
inference(resolution,[],[f7,f12]) ).
fof(f36,plain,
~ dances_on_tightropes(piggy),
inference(forward_subsumption_resolution,[],[f35,f32]) ).
fof(f37,plain,
~ spl0_1,
inference(avatar_split_clause,[],[f36,f20]) ).
fof(f38,plain,
( ~ pig(piggy)
| looks_ridiculous(piggy) ),
inference(resolution,[],[f8,f29]) ).
fof(f39,plain,
looks_ridiculous(piggy),
inference(forward_subsumption_resolution,[],[f38,f14]) ).
fof(f40,plain,
( dances_on_tightropes(piggy)
| fat(piggy) ),
inference(resolution,[],[f9,f34]) ).
fof(f41,plain,
( fat(piggy)
| spl0_1 ),
inference(forward_subsumption_resolution,[],[f40,f21]) ).
fof(f42,plain,
( ~ looks_ridiculous(piggy)
| dances_on_tightropes(piggy)
| eats_lunch_in_public(piggy)
| spl0_1 ),
inference(resolution,[],[f6,f41]) ).
fof(f43,plain,
( dances_on_tightropes(piggy)
| eats_lunch_in_public(piggy)
| spl0_1 ),
inference(forward_subsumption_resolution,[],[f42,f39]) ).
fof(f44,plain,
( eats_lunch_in_public(piggy)
| spl0_1 ),
inference(forward_subsumption_resolution,[],[f43,f21]) ).
fof(f45,plain,
( ~ eats_pennybuns(piggy)
| ~ looks_ridiculous(piggy)
| spl0_1 ),
inference(resolution,[],[f44,f4]) ).
fof(f46,plain,
( ~ looks_ridiculous(piggy)
| spl0_1
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f45,f26]) ).
fof(f47,plain,
( $false
| spl0_1
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f46,f39]) ).
fof(f48,plain,
( spl0_1
| ~ spl0_2 ),
inference(avatar_contradiction_clause,[],[f47]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f27]) ).
cnf(s2,plain,
~ spl0_1,
inference(sat_conversion,[],[f37]) ).
cnf(s3,plain,
( spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f48]) ).
cnf(s4,plain,
~ spl0_2,
inference(rat,[],[s3,s2]) ).
cnf(s5,plain,
$false,
inference(rat,[],[s1,s4,s2]) ).
fof(f49,plain,
$false,
inference(avatar_sat_refutation,[],[s5]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ029-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.11/0.38 % Computer : n002.cluster.edu
% 0.11/0.38 % Model : x86_64 x86_64
% 0.11/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.38 % Memory : 8046.5625MB
% 0.11/0.38 % OS : Linux 6.8.0-71-generic
% 0.11/0.38 % CPULimit : 300
% 0.11/0.38 % WCLimit : 300
% 0.11/0.38 % DateTime : Sun Sep 27 22:33:52 UTC 2026
% 0.11/0.38 % CPUTime :
% 0.11/0.38 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.11/0.41 Running first-order theorem proving
% 0.11/0.41 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
% 3.40/1.35 % (3954723)Input is clausal, will run a generic CNF schedule.
% 3.40/1.35 % (3954729)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=3930824826:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.40/1.35 % (3954730)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=3398378596:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.40/1.35 % (3954728)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=918821722:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.40/1.35 % (3954733)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3336656178:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.40/1.35 % (3954734)dis-21_1_sil=8000:lcm=predicate:random_seed=2138653997: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)
% 3.40/1.35 % (3954732)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2438226307:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.40/1.36 % (3954731)lrs+10_1_sil=8000:sp=occurrence:random_seed=2506688282:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.40/1.36 % (3954731)First to succeed.
% 3.40/1.36 % (3954732)Also succeeded, but the first one will report.
% 3.40/1.36 % (3954734)Also succeeded, but the first one will report.
% 3.40/1.36 % (3954733)Also succeeded, but the first one will report.
% 3.40/1.36 % (3954731)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3954723"
% 3.40/1.36 % (3954731)Refutation found. Thanks to Tanya!
% 3.40/1.36 % SZS status Unsatisfiable for theBenchmark
% 3.40/1.36 % SZS output start Proof for theBenchmark
% See solution above
% 3.40/1.36 % (3954731)------------------------------
% 3.40/1.36 % (3954731)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.40/1.36 % (3954731)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.40/1.36 % (3954731)CaDiCaL version: 2.1.3
% 3.40/1.36 % (3954731)Termination reason: Refutation
% 3.40/1.36 % (3954731)Time elapsed: 0.002 s
% 3.40/1.36 % (3954731)Peak memory usage: 89 MB
% 3.40/1.36 % (3954731)Instructions burned: 1 (million)
% 3.40/1.36 % (3954731)------------------------------
% 3.40/1.36 % (3954731)------------------------------
% 3.40/1.36 % (3954723)Success in time 0.409 s
% 3.40/1.36 % Vampire exiting
%------------------------------------------------------------------------------