↑ Up

Vampire---5.0.1.THM-Ref.s

View TPTP
Problem
Process solution in
SystemOnTSTP
Download .tgz
%------------------------------------------------------------------------------
% File     : Vampire---5.0.1
% Problem  : SET013+4 : TPTP v9.3.1. Released v2.2.0.
% Transfm  : none
% Format   : tptp:raw
% Command  : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM

% Computer : n017.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 12:39:31 PM UTC 2026

% Result   : Theorem 3.43s 11.49s
% Output   : Refutation 3.43s
% Verified : 
% SZS Type : Refutation
%            Derivation depth      :   15
%            Number of leaves      :   10
% Syntax   : Number of formulae    :   70 (  11 unt;   6 def)
%            Number of atoms       :  168 (   0 equ)
%            Maximal formula atoms :    6 (   2 avg)
%            Number of connectives :  156 (  58   ~;  73   |;  13   &)
%                                         (  10 <=>;   2  =>;   0  <=;   0 <~>)
%            Maximal formula depth :    8 (   4 avg)
%            Maximal term depth    :    3 (   1 avg)
%            Number of predicates  :   10 (   9 usr;   7 prp; 0-2 aty)
%            Number of functors    :    4 (   4 usr;   2 con; 0-2 aty)
%            Number of variables   :   55 (   0 sgn  51   !;   4   ?)

% Comments : 
%------------------------------------------------------------------------------
fof(f1,axiom,
    ! [X0,X1] :
      ( subset(X0,X1)
    <=> ! [X2] :
          ( member(X2,X0)
         => member(X2,X1) ) ),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p',subset) ).

fof(f2,axiom,
    ! [X0,X1] :
      ( equal_set(X0,X1)
    <=> ( subset(X0,X1)
        & subset(X1,X0) ) ),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p',equal_set) ).

fof(f4,axiom,
    ! [X0,X1,X2] :
      ( member(X0,intersection(X1,X2))
    <=> ( member(X0,X1)
        & member(X0,X2) ) ),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p',intersection) ).

fof(f12,conjecture,
    ! [X0,X1] : equal_set(intersection(X0,X1),intersection(X1,X0)),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p',thI06) ).

fof(f13,negated_conjecture,
    ~ ! [X0,X1] : equal_set(intersection(X0,X1),intersection(X1,X0)),
    inference(negated_conjecture,[status(cth)],[f12]) ).

fof(f14,plain,
    ! [X0,X1] :
      ( ( subset(X0,X1)
        & subset(X1,X0) )
     => equal_set(X0,X1) ),
    inference(unused_predicate_definition_removal,[],[f2]) ).

fof(f15,plain,
    ? [X0,X1] : ~ equal_set(intersection(X0,X1),intersection(X1,X0)),
    inference(ennf_transformation,[],[f13]) ).

fof(f16,plain,
    ! [X0,X1] :
      ( equal_set(X0,X1)
      | ~ subset(X0,X1)
      | ~ subset(X1,X0) ),
    inference(ennf_transformation,[],[f14]) ).

fof(f17,plain,
    ! [X0,X1] :
      ( equal_set(X0,X1)
      | ~ subset(X0,X1)
      | ~ subset(X1,X0) ),
    inference(flattening,[],[f16]) ).

fof(f18,plain,
    ! [X0,X1] :
      ( subset(X0,X1)
    <=> ! [X2] :
          ( member(X2,X1)
          | ~ member(X2,X0) ) ),
    inference(ennf_transformation,[],[f1]) ).

fof(f19,plain,
    ~ equal_set(intersection(sK0,sK1),intersection(sK1,sK0)),
    inference(skolemize,[status(esa),new_symbols(skolem,[sK0,sK1]),skolemize(X0,sK0),skolemize(X1,sK1)],[f15]) ).

fof(f20,plain,
    ! [X0,X1,X2] :
      ( ( member(X0,intersection(X1,X2))
        | ~ member(X0,X1)
        | ~ member(X0,X2) )
      & ( ( member(X0,X1)
          & member(X0,X2) )
        | ~ member(X0,intersection(X1,X2)) ) ),
    inference(nnf_transformation,[],[f4]) ).

fof(f21,plain,
    ! [X0,X1,X2] :
      ( ( member(X0,intersection(X1,X2))
        | ~ member(X0,X1)
        | ~ member(X0,X2) )
      & ( ( member(X0,X1)
          & member(X0,X2) )
        | ~ member(X0,intersection(X1,X2)) ) ),
    inference(flattening,[],[f20]) ).

fof(f22,plain,
    ! [X0,X1] :
      ( ( subset(X0,X1)
        | ? [X2] :
            ( ~ member(X2,X1)
            & member(X2,X0) ) )
      & ( ! [X2] :
            ( member(X2,X1)
            | ~ member(X2,X0) )
        | ~ subset(X0,X1) ) ),
    inference(nnf_transformation,[],[f18]) ).

fof(f23,plain,
    ! [X0,X1] :
      ( ( subset(X0,X1)
        | ? [X2] :
            ( ~ member(X2,X1)
            & member(X2,X0) ) )
      & ( ! [X3] :
            ( member(X3,X1)
            | ~ member(X3,X0) )
        | ~ subset(X0,X1) ) ),
    inference(rectify,[],[f22]) ).

fof(f24,plain,
    ! [X0,X1] :
      ( ( subset(X0,X1)
        | ( ~ member(sK2(X0,X1),X1)
          & member(sK2(X0,X1),X0) ) )
      & ( ! [X3] :
            ( member(X3,X1)
            | ~ member(X3,X0) )
        | ~ subset(X0,X1) ) ),
    inference(skolemize,[status(esa),new_symbols(skolem,[sK2]),skolemize(X2,sK2(X0,X1))],[f23]) ).

fof(f26,plain,
    ~ equal_set(intersection(sK0,sK1),intersection(sK1,sK0)),
    inference(cnf_transformation,[],[f19]) ).

fof(f27,plain,
    ! [X2,X0,X1] :
      ( ~ member(X0,intersection(X1,X2))
      | member(X0,X2) ),
    inference(cnf_transformation,[],[f21]) ).

fof(f28,plain,
    ! [X2,X0,X1] :
      ( ~ member(X0,intersection(X1,X2))
      | member(X0,X1) ),
    inference(cnf_transformation,[],[f21]) ).

fof(f29,plain,
    ! [X2,X0,X1] :
      ( member(X0,intersection(X1,X2))
      | ~ member(X0,X1)
      | ~ member(X0,X2) ),
    inference(cnf_transformation,[],[f21]) ).

fof(f30,plain,
    ! [X0,X1] :
      ( equal_set(X0,X1)
      | ~ subset(X0,X1)
      | ~ subset(X1,X0) ),
    inference(cnf_transformation,[],[f17]) ).

fof(f32,plain,
    ! [X0,X1] :
      ( subset(X0,X1)
      | member(sK2(X0,X1),X0) ),
    inference(cnf_transformation,[],[f24]) ).

fof(f33,plain,
    ! [X0,X1] :
      ( subset(X0,X1)
      | ~ member(sK2(X0,X1),X1) ),
    inference(cnf_transformation,[],[f24]) ).

fof(f39,plain,
    ( ~ subset(intersection(sK0,sK1),intersection(sK1,sK0))
    | ~ subset(intersection(sK1,sK0),intersection(sK0,sK1)) ),
    inference(resolution,[],[f30,f26]) ).

fof(f41,definition,
    ( spl3_1
  <=> subset(intersection(sK1,sK0),intersection(sK0,sK1)) ),
    introduced(definition,[new_symbols(definition,[spl3_1])],[avatar_definition]) ).

fof(f42,plain,
    ( ~ subset(intersection(sK1,sK0),intersection(sK0,sK1))
    | spl3_1 ),
    inference(avatar_component_clause,[],[f41]) ).

fof(f44,definition,
    ( spl3_2
  <=> subset(intersection(sK0,sK1),intersection(sK1,sK0)) ),
    introduced(definition,[new_symbols(definition,[spl3_2])],[avatar_definition]) ).

fof(f45,plain,
    ( ~ subset(intersection(sK0,sK1),intersection(sK1,sK0))
    | spl3_2 ),
    inference(avatar_component_clause,[],[f44]) ).

fof(f46,plain,
    ( ~ spl3_1
    | ~ spl3_2 ),
    inference(avatar_split_clause,[],[f39,f44,f41]) ).

fof(f47,plain,
    ( ~ member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),intersection(sK0,sK1))
    | spl3_1 ),
    inference(resolution,[],[f42,f33]) ).

fof(f48,plain,
    ( member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),intersection(sK1,sK0))
    | spl3_1 ),
    inference(resolution,[],[f42,f32]) ).

fof(f50,plain,
    ( member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),sK1)
    | spl3_1 ),
    inference(resolution,[],[f48,f28]) ).

fof(f51,plain,
    ( member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),sK0)
    | spl3_1 ),
    inference(resolution,[],[f48,f27]) ).

fof(f57,plain,
    ( ~ member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),sK0)
    | ~ member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),sK1)
    | spl3_1 ),
    inference(resolution,[],[f29,f47]) ).

fof(f59,definition,
    ( spl3_3
  <=> member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),sK1) ),
    introduced(definition,[new_symbols(definition,[spl3_3])],[avatar_definition]) ).

fof(f60,plain,
    ( ~ member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),sK1)
    | spl3_3 ),
    inference(avatar_component_clause,[],[f59]) ).

fof(f62,definition,
    ( spl3_4
  <=> member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),sK0) ),
    introduced(definition,[new_symbols(definition,[spl3_4])],[avatar_definition]) ).

fof(f63,plain,
    ( ~ member(sK2(intersection(sK1,sK0),intersection(sK0,sK1)),sK0)
    | spl3_4 ),
    inference(avatar_component_clause,[],[f62]) ).

fof(f64,plain,
    ( ~ spl3_3
    | ~ spl3_4
    | spl3_1 ),
    inference(avatar_split_clause,[],[f57,f41,f62,f59]) ).

fof(f65,plain,
    ( $false
    | spl3_1
    | spl3_3 ),
    inference(resolution,[],[f60,f50]) ).

fof(f66,plain,
    ( spl3_1
    | spl3_3 ),
    inference(avatar_contradiction_clause,[],[f65]) ).

fof(f69,plain,
    ( $false
    | spl3_1
    | spl3_4 ),
    inference(resolution,[],[f63,f51]) ).

fof(f70,plain,
    ( spl3_1
    | spl3_4 ),
    inference(avatar_contradiction_clause,[],[f69]) ).

fof(f71,plain,
    ( ~ member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),intersection(sK1,sK0))
    | spl3_2 ),
    inference(resolution,[],[f45,f33]) ).

fof(f72,plain,
    ( member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),intersection(sK0,sK1))
    | spl3_2 ),
    inference(resolution,[],[f45,f32]) ).

fof(f74,plain,
    ( ~ member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),sK1)
    | ~ member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),sK0)
    | spl3_2 ),
    inference(resolution,[],[f71,f29]) ).

fof(f76,definition,
    ( spl3_5
  <=> member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),sK0) ),
    introduced(definition,[new_symbols(definition,[spl3_5])],[avatar_definition]) ).

fof(f77,plain,
    ( ~ member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),sK0)
    | spl3_5 ),
    inference(avatar_component_clause,[],[f76]) ).

fof(f79,definition,
    ( spl3_6
  <=> member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),sK1) ),
    introduced(definition,[new_symbols(definition,[spl3_6])],[avatar_definition]) ).

fof(f80,plain,
    ( ~ member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),sK1)
    | spl3_6 ),
    inference(avatar_component_clause,[],[f79]) ).

fof(f81,plain,
    ( ~ spl3_5
    | ~ spl3_6
    | spl3_2 ),
    inference(avatar_split_clause,[],[f74,f44,f79,f76]) ).

fof(f82,plain,
    ( member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),sK0)
    | spl3_2 ),
    inference(resolution,[],[f72,f28]) ).

fof(f83,plain,
    ( member(sK2(intersection(sK0,sK1),intersection(sK1,sK0)),sK1)
    | spl3_2 ),
    inference(resolution,[],[f72,f27]) ).

fof(f84,plain,
    ( $false
    | spl3_2
    | spl3_5 ),
    inference(resolution,[],[f82,f77]) ).

fof(f85,plain,
    ( spl3_2
    | spl3_5 ),
    inference(avatar_contradiction_clause,[],[f84]) ).

fof(f86,plain,
    ( $false
    | spl3_2
    | spl3_6 ),
    inference(resolution,[],[f83,f80]) ).

fof(f87,plain,
    ( spl3_2
    | spl3_6 ),
    inference(avatar_contradiction_clause,[],[f86]) ).

cnf(s1,plain,
    ( ~ spl3_1
    | ~ spl3_2 ),
    inference(sat_conversion,[],[f46]) ).

cnf(s2,plain,
    ( spl3_1
    | ~ spl3_3
    | ~ spl3_4 ),
    inference(sat_conversion,[],[f64]) ).

cnf(s3,plain,
    ( spl3_1
    | spl3_3 ),
    inference(sat_conversion,[],[f66]) ).

cnf(s4,plain,
    ( spl3_1
    | spl3_4 ),
    inference(sat_conversion,[],[f70]) ).

cnf(s5,plain,
    ( spl3_2
    | ~ spl3_5
    | ~ spl3_6 ),
    inference(sat_conversion,[],[f81]) ).

cnf(s6,plain,
    ( spl3_2
    | spl3_5 ),
    inference(sat_conversion,[],[f85]) ).

cnf(s7,plain,
    ( spl3_2
    | spl3_6 ),
    inference(sat_conversion,[],[f87]) ).

cnf(s8,plain,
    spl3_1,
    inference(rat,[],[s2,s3,s4]) ).

cnf(s9,plain,
    ~ spl3_2,
    inference(rat,[],[s1,s8]) ).

cnf(s10,plain,
    spl3_6,
    inference(rat,[],[s7,s9]) ).

cnf(s11,plain,
    spl3_5,
    inference(rat,[],[s6,s9]) ).

cnf(s12,plain,
    $false,
    inference(rat,[],[s5,s10,s11,s9]) ).

fof(f88,plain,
    $false,
    inference(avatar_sat_refutation,[],[s12]) ).

%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03  % Problem  : SET013+4 : TPTP v9.3.1. Released v2.2.0.
% 0.00/0.05  % Command  : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.10/10.40  % Computer : n017.cluster.edu
% 0.10/10.40  % Model    : x86_64 x86_64
% 0.10/10.40  % CPU      : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/10.40  % Memory   : 8046.5625MB
% 0.10/10.40  % OS       : Linux 6.8.0-71-generic
% 0.10/10.40  % CPULimit : 300
% 0.10/10.40  % WCLimit  : 300
% 0.10/10.40  % DateTime : Sun Sep 27 23:59:02 UTC 2026
% 0.10/10.41  % CPUTime  : 
% 0.10/10.41  Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.10/10.44  Running first-order theorem proving
% 0.10/10.44  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
% 3.43/11.49  % (3093428)Detected formulas, will run a generic FOF schedule.
% 3.43/11.49  % (3093435)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=2940227465:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.43/11.49  % (3093434)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=3053213796:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.43/11.49  % (3093439)dis-21_1_sil=8000:lcm=predicate:random_seed=2932579732: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)
% 3.43/11.49  % (3093439)First to succeed.
% 3.43/11.49  % (3093439)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3093428"
% 3.43/11.49  % (3093433)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=2350540236:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.43/11.49  % (3093438)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3794021869:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.43/11.49  % (3093436)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=4094552550:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.43/11.49  % (3093437)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=581853348:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.43/11.49  % (3093436)Refutation not found, incomplete strategy
% 3.43/11.49  % (3093436)------------------------------
% 3.43/11.49  % (3093436)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.43/11.49  % (3093436)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.43/11.49  % (3093436)CaDiCaL version: 2.1.3
% 3.43/11.49  % (3093436)Termination reason: Refutation not found, incomplete strategy
% 3.43/11.49  % (3093436)Time elapsed: 0.001 s
% 3.43/11.49  % (3093436)Peak memory usage: 87 MB
% 3.43/11.49  % (3093437)Also succeeded, but the first one will report.
% 3.43/11.49  % (3093438)Also succeeded, but the first one will report.
% 3.43/11.49  % (3093436)------------------------------
% 3.43/11.49  % (3093436)------------------------------
% 3.43/11.49  % (3093439)Refutation found. Thanks to Tanya!
% 3.43/11.49  % SZS status Theorem for theBenchmark
% 3.43/11.49  % SZS output start Proof for theBenchmark
% See solution above
% 3.43/11.49  % (3093439)------------------------------
% 3.43/11.49  % (3093439)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.43/11.49  % (3093439)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.43/11.49  % (3093439)CaDiCaL version: 2.1.3
% 3.43/11.49  % (3093439)Termination reason: Refutation
% 3.43/11.49  % (3093439)Time elapsed: 0.003 s
% 3.43/11.49  % (3093439)Peak memory usage: 89 MB
% 3.43/11.49  % (3093439)Instructions burned: 2 (million)
% 3.43/11.49  % (3093439)------------------------------
% 3.43/11.49  % (3093439)------------------------------
% 3.43/11.49  % (3093428)Success in time 0.42 s
% 3.43/11.49  % Vampire exiting
%------------------------------------------------------------------------------