↑ Up

Vampire---5.0.1.UNS-Ref.s

View TPTP
Problem
Process solution in
SystemOnTSTP
Download .tgz
%------------------------------------------------------------------------------
% File     : Vampire---5.0.1
% Problem  : GRP034-3 : 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 : n006.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 10:12:11 AM UTC 2026

% Result   : Unsatisfiable 2.65s 1.34s
% Output   : Refutation 2.65s
% Verified : 
% SZS Type : Refutation
%            Derivation depth      :    8
%            Number of leaves      :    8
% Syntax   : Number of formulae    :   27 (  11 unt;   3 def)
%            Number of atoms       :   49 (   0 equ)
%            Maximal formula atoms :    4 (   1 avg)
%            Number of connectives :   48 (  26   ~;  19   |;   0   &)
%                                         (   3 <=>;   0  =>;   0  <=;   0 <~>)
%            Maximal formula depth :    8 (   3 avg)
%            Maximal term depth    :    2 (   1 avg)
%            Number of predicates  :    6 (   5 usr;   4 prp; 0-3 aty)
%            Number of functors    :    3 (   3 usr;   2 con; 0-1 aty)
%            Number of variables   :   12 (   0 sgn  12   !;   0   ?)

% Comments : 
%------------------------------------------------------------------------------
fof(f1,axiom,
    ! [X0] : product(identity,X0,X0),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',left_identity) ).

fof(f4,axiom,
    ! [X0] : product(X0,inverse(X0),identity),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',right_inverse) ).

fof(f9,axiom,
    ! [X2,X0,X1] :
      ( ~ product(X0,inverse(X1),X2)
      | ~ subgroup_member(X1)
      | ~ subgroup_member(X0)
      | subgroup_member(X2) ),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',closure_of_product_and_inverse) ).

fof(f10,axiom,
    subgroup_member(a),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',a_is_in_subgroup) ).

fof(f11,negated_conjecture,
    ~ subgroup_member(inverse(a)),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_a_inverse_is_in_subgroup) ).

fof(f12,plain,
    ! [X0] :
      ( ~ subgroup_member(X0)
      | ~ subgroup_member(identity)
      | subgroup_member(inverse(X0)) ),
    inference(resolution,[],[f9,f1]) ).

fof(f14,plain,
    ! [X0] :
      ( ~ subgroup_member(X0)
      | ~ subgroup_member(X0)
      | subgroup_member(identity) ),
    inference(resolution,[],[f9,f4]) ).

fof(f15,plain,
    ! [X0] :
      ( ~ subgroup_member(X0)
      | subgroup_member(identity) ),
    inference(duplicate_literal_removal,[],[f14]) ).

fof(f17,definition,
    ( spl0_1
  <=> subgroup_member(identity) ),
    introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).

fof(f20,definition,
    ( spl0_2
  <=> ! [X0] : ~ subgroup_member(X0) ),
    introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).

fof(f21,plain,
    ( ! [X0] : ~ subgroup_member(X0)
    | ~ spl0_2 ),
    inference(avatar_component_clause,[],[f20]) ).

fof(f22,plain,
    ( spl0_1
    | spl0_2 ),
    inference(avatar_split_clause,[],[f15,f20,f17]) ).

fof(f29,definition,
    ( spl0_4
  <=> ! [X0] :
        ( ~ subgroup_member(X0)
        | subgroup_member(inverse(X0)) ) ),
    introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).

fof(f30,plain,
    ( ! [X0] :
        ( subgroup_member(inverse(X0))
        | ~ subgroup_member(X0) )
    | ~ spl0_4 ),
    inference(avatar_component_clause,[],[f29]) ).

fof(f31,plain,
    ( ~ spl0_1
    | spl0_4 ),
    inference(avatar_split_clause,[],[f12,f29,f17]) ).

fof(f33,plain,
    ( $false
    | ~ spl0_2 ),
    inference(resolution,[],[f21,f10]) ).

fof(f34,plain,
    ~ spl0_2,
    inference(avatar_contradiction_clause,[],[f33]) ).

fof(f36,plain,
    ( ~ subgroup_member(a)
    | ~ spl0_4 ),
    inference(resolution,[],[f30,f11]) ).

fof(f37,plain,
    ( $false
    | ~ spl0_4 ),
    inference(forward_subsumption_resolution,[],[f36,f10]) ).

fof(f38,plain,
    ~ spl0_4,
    inference(avatar_contradiction_clause,[],[f37]) ).

cnf(s1,plain,
    ( spl0_1
    | spl0_2 ),
    inference(sat_conversion,[],[f22]) ).

cnf(s3,plain,
    ( ~ spl0_1
    | spl0_4 ),
    inference(sat_conversion,[],[f31]) ).

cnf(s4,plain,
    ~ spl0_2,
    inference(sat_conversion,[],[f34]) ).

cnf(s5,plain,
    ~ spl0_4,
    inference(sat_conversion,[],[f38]) ).

cnf(s6,plain,
    ~ spl0_1,
    inference(rat,[],[s3,s5]) ).

cnf(s8,plain,
    $false,
    inference(rat,[],[s1,s4,s6]) ).

fof(f39,plain,
    $false,
    inference(avatar_sat_refutation,[],[s8]) ).

%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03  % Problem  : GRP034-3 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05  % Command  : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.37  % Computer : n006.cluster.edu
% 0.10/0.37  % Model    : x86_64 x86_64
% 0.10/0.37  % CPU      : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.37  % Memory   : 8046.5625MB
% 0.10/0.37  % OS       : Linux 6.8.0-71-generic
% 0.10/0.37  % CPULimit : 300
% 0.10/0.37  % WCLimit  : 300
% 0.10/0.37  % DateTime : Sun Sep 27 09:15:25 UTC 2026
% 0.10/0.37  % CPUTime  : 
% 0.10/0.37  Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.40  Running first-order theorem proving
% 0.10/0.41  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
% 2.65/1.34  % (2723933)Input is clausal, will run a generic CNF schedule.
% 2.65/1.34  % (2723942)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=159669988:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.65/1.34  % (2723942)First to succeed.
% 2.65/1.34  % (2723942)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-2723933"
% 2.65/1.34  % (2723940)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=3299248562:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.65/1.34  % (2723944)dis-21_1_sil=8000:lcm=predicate:random_seed=1298604238: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)
% 2.65/1.34  % (2723941)lrs+10_1_sil=8000:sp=occurrence:random_seed=3257368822:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.65/1.34  % (2723939)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=1266464832:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.65/1.34  % (2723943)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1813434395:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.65/1.34  % (2723938)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=1083891586:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.65/1.34  % (2723943)Also succeeded, but the first one will report.
% 2.65/1.34  % (2723941)Also succeeded, but the first one will report.
% 2.65/1.34  % (2723944)Instruction limit reached! 
% 2.65/1.34  % (2723944)------------------------------
% 2.65/1.34  % (2723944)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.65/1.34  % (2723944)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.65/1.34  % (2723944)CaDiCaL version: 2.1.3
% 2.65/1.34  % (2723944)Termination reason: Instruction limit
% 2.65/1.34  % (2723944)Termination phase: Saturation
% 2.65/1.34  % (2723944)Time elapsed: 0.067 s
% 2.65/1.34  % (2723944)Peak memory usage: 88 MB
% 2.65/1.34  % (2723944)Instructions burned: 117 (million)
% 2.65/1.34  % (2723942)Refutation found. Thanks to Tanya!
% 2.65/1.34  % SZS status Unsatisfiable for theBenchmark
% 2.65/1.34  % SZS output start Proof for theBenchmark
% See solution above
% 2.65/1.34  % (2723942)------------------------------
% 2.65/1.34  % (2723942)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.65/1.34  % (2723942)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.65/1.34  % (2723942)CaDiCaL version: 2.1.3
% 2.65/1.34  % (2723942)Termination reason: Refutation
% 2.65/1.34  % (2723942)Time elapsed: 0.001 s
% 2.65/1.34  % (2723942)Peak memory usage: 89 MB
% 2.65/1.34  % (2723942)Instructions burned: 1 (million)
% 2.65/1.34  % (2723942)------------------------------
% 2.65/1.34  % (2723942)------------------------------
% 2.65/1.34  % (2723933)Success in time 0.291 s
% 2.65/1.34  % Vampire exiting
%------------------------------------------------------------------------------