↑ Up

Vampire---5.0.1.UNS-Ref.s

View TPTP
Problem
Process solution in
SystemOnTSTP
Download .tgz
%------------------------------------------------------------------------------
% File     : Vampire---5.0.1
% Problem  : MSC005-1 : 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 : n003.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 12:04:46 PM UTC 2026

% Result   : Unsatisfiable 2.63s 1.24s
% Output   : Refutation 2.63s
% Verified : 
% SZS Type : Refutation
%            Derivation depth      :   11
%            Number of leaves      :    8
% Syntax   : Number of formulae    :   30 (  11 unt;   2 def)
%            Number of atoms       :   56 (   0 equ)
%            Maximal formula atoms :    3 (   1 avg)
%            Number of connectives :   53 (  27   ~;  24   |;   0   &)
%                                         (   2 <=>;   0  =>;   0  <=;   0 <~>)
%            Maximal formula depth :    6 (   3 avg)
%            Maximal term depth    :    5 (   1 avg)
%            Number of predicates  :    4 (   3 usr;   3 prp; 0-2 aty)
%            Number of functors    :    3 (   3 usr;   2 con; 0-2 aty)
%            Number of variables   :    7 (   0 sgn   7   !;   0   ?)

% Comments : 
%------------------------------------------------------------------------------
fof(f1,axiom,
    value(truth,truth),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',true_is_true) ).

fof(f2,axiom,
    value(falsity,falsity),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',false_is_false) ).

fof(f3,axiom,
    ! [X0,X1] :
      ( value(xor(X0,X1),falsity)
      | ~ value(X1,truth)
      | ~ value(X0,truth) ),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',true_xor_true) ).

fof(f4,axiom,
    ! [X0,X1] :
      ( value(xor(X0,X1),truth)
      | ~ value(X1,falsity)
      | ~ value(X0,truth) ),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',true_xor_false) ).

fof(f6,axiom,
    ! [X0,X1] :
      ( value(xor(X0,X1),falsity)
      | ~ value(X1,falsity)
      | ~ value(X0,falsity) ),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',false_xor_false) ).

fof(f7,negated_conjecture,
    ! [X0] : ~ value(xor(xor(xor(xor(truth,falsity),falsity),truth),falsity),X0),
    file('/export/starexec/sandbox/benchmark/theBenchmark.p',evaluate_expression) ).

fof(f21,definition,
    ( spl0_3
  <=> value(xor(xor(truth,falsity),falsity),truth) ),
    introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).

fof(f22,plain,
    ( value(xor(xor(truth,falsity),falsity),truth)
    | ~ spl0_3 ),
    inference(avatar_component_clause,[],[f21]) ).

fof(f23,plain,
    ( ~ value(xor(xor(truth,falsity),falsity),truth)
    | spl0_3 ),
    inference(avatar_component_clause,[],[f21]) ).

fof(f29,plain,
    ( ~ value(falsity,falsity)
    | ~ value(xor(truth,falsity),truth)
    | spl0_3 ),
    inference(resolution,[],[f23,f4]) ).

fof(f30,plain,
    ( ~ value(xor(truth,falsity),truth)
    | spl0_3 ),
    inference(forward_subsumption_resolution,[],[f29,f2]) ).

fof(f40,definition,
    ( spl0_6
  <=> value(xor(xor(xor(truth,falsity),falsity),truth),falsity) ),
    introduced(definition,[new_symbols(definition,[spl0_6])],[avatar_definition]) ).

fof(f42,plain,
    ( ~ value(xor(xor(xor(truth,falsity),falsity),truth),falsity)
    | spl0_6 ),
    inference(avatar_component_clause,[],[f40]) ).

fof(f45,plain,
    ( ~ value(falsity,falsity)
    | ~ value(xor(xor(xor(truth,falsity),falsity),truth),falsity) ),
    inference(resolution,[],[f6,f7]) ).

fof(f46,plain,
    ~ value(xor(xor(xor(truth,falsity),falsity),truth),falsity),
    inference(forward_subsumption_resolution,[],[f45,f2]) ).

fof(f47,plain,
    ~ spl0_6,
    inference(avatar_split_clause,[],[f46,f40]) ).

fof(f49,plain,
    ( ~ value(falsity,falsity)
    | ~ value(truth,truth)
    | spl0_3 ),
    inference(resolution,[],[f30,f4]) ).

fof(f50,plain,
    ( ~ value(truth,truth)
    | spl0_3 ),
    inference(forward_subsumption_resolution,[],[f49,f2]) ).

fof(f51,plain,
    ( $false
    | spl0_3 ),
    inference(forward_subsumption_resolution,[],[f50,f1]) ).

fof(f52,plain,
    spl0_3,
    inference(avatar_contradiction_clause,[],[f51]) ).

fof(f54,plain,
    ( ~ value(truth,truth)
    | ~ value(xor(xor(truth,falsity),falsity),truth)
    | spl0_6 ),
    inference(resolution,[],[f42,f3]) ).

fof(f55,plain,
    ( ~ value(xor(xor(truth,falsity),falsity),truth)
    | spl0_6 ),
    inference(forward_subsumption_resolution,[],[f54,f1]) ).

fof(f56,plain,
    ( $false
    | ~ spl0_3
    | spl0_6 ),
    inference(forward_subsumption_resolution,[],[f55,f22]) ).

fof(f57,plain,
    ( ~ spl0_3
    | spl0_6 ),
    inference(avatar_contradiction_clause,[],[f56]) ).

cnf(s5,plain,
    ~ spl0_6,
    inference(sat_conversion,[],[f47]) ).

cnf(s6,plain,
    spl0_3,
    inference(sat_conversion,[],[f52]) ).

cnf(s7,plain,
    ( ~ spl0_3
    | spl0_6 ),
    inference(sat_conversion,[],[f57]) ).

cnf(s8,plain,
    spl0_6,
    inference(rat,[],[s7,s6]) ).

cnf(s9,plain,
    $false,
    inference(rat,[],[s5,s8]) ).

fof(f58,plain,
    $false,
    inference(avatar_sat_refutation,[],[s9]) ).

%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03  % Problem  : MSC005-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.05  % Command  : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.37  % Computer : n003.cluster.edu
% 0.09/0.37  % Model    : x86_64 x86_64
% 0.09/0.37  % CPU      : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.37  % Memory   : 8046.5625MB
% 0.09/0.37  % OS       : Linux 6.8.0-71-generic
% 0.09/0.37  % CPULimit : 300
% 0.09/0.37  % WCLimit  : 300
% 0.09/0.37  % DateTime : Sun Sep 27 17:42:11 UTC 2026
% 0.09/0.37  % CPUTime  : 
% 0.09/0.37  Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.15/0.40  Running first-order theorem proving
% 0.15/0.40  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
% 2.63/1.24  % (817412)Input is clausal, will run a generic CNF schedule.
% 2.63/1.24  % (817420)lrs+10_1_sil=8000:sp=occurrence:random_seed=3388610939:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.63/1.24  % (817420)First to succeed.
% 2.63/1.24  % (817420)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-817412"
% 2.63/1.24  % (817423)dis-21_1_sil=8000:lcm=predicate:random_seed=3977260728: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)
% 2.63/1.24  % (817417)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=3282869735:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.63/1.24  % (817419)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=2419456604:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.63/1.24  % (817421)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=224889517:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.63/1.24  % (817418)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=1625815323:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.63/1.24  % (817421)Also succeeded, but the first one will report.
% 2.63/1.24  % (817423)Also succeeded, but the first one will report.
% 2.63/1.24  % (817422)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3149191056:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.63/1.24  % (817422)Also succeeded, but the first one will report.
% 2.63/1.24  % (817420)Refutation found. Thanks to Tanya!
% 2.63/1.24  % SZS status Unsatisfiable for theBenchmark
% 2.63/1.24  % SZS output start Proof for theBenchmark
% See solution above
% 2.63/1.24  % (817420)------------------------------
% 2.63/1.24  % (817420)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.63/1.24  % (817420)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.63/1.24  % (817420)CaDiCaL version: 2.1.3
% 2.63/1.24  % (817420)Termination reason: Refutation
% 2.63/1.24  % (817420)Time elapsed: 0.002 s
% 2.63/1.24  % (817420)Peak memory usage: 89 MB
% 2.63/1.24  % (817420)Instructions burned: 1 (million)
% 2.63/1.24  % (817420)------------------------------
% 2.63/1.24  % (817420)------------------------------
% 2.63/1.24  % (817412)Success in time 0.302 s
% 2.63/1.24  % Vampire exiting
%------------------------------------------------------------------------------