↑ Up

Vampire---5.0.1.THM-Ref.s

View TPTP
Problem
Process solution in
SystemOnTSTP
Download .tgz
%------------------------------------------------------------------------------
% File     : Vampire---5.0.1
% Problem  : NUM847+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 : 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 12:17:15 PM UTC 2026

% Result   : Theorem 2.68s 1.34s
% Output   : Refutation 2.68s
% Verified : 
% SZS Type : Refutation
%            Derivation depth      :    5
%            Number of leaves      :    3
% Syntax   : Number of formulae    :   10 (   9 unt;   1 def)
%            Number of atoms       :   11 (   7 equ)
%            Maximal formula atoms :    2 (   1 avg)
%            Number of connectives :    5 (   4   ~;   0   |;   0   &)
%                                         (   1 <=>;   0  =>;   0  <=;   0 <~>)
%            Maximal formula depth :    4 (   3 avg)
%            Maximal term depth    :    4 (   2 avg)
%            Number of predicates  :    3 (   1 usr;   1 prp; 0-2 aty)
%            Number of functors    :    5 (   5 usr;   3 con; 0-2 aty)
%            Number of variables   :   11 (  11   !;   0   ?)

% Comments : 
%------------------------------------------------------------------------------
fof(f1,conjecture,
    vplus(vplus(vmul(vd436,vd437),vmul(vd436,vd439)),vd436) = vplus(vmul(vd436,vd437),vplus(vmul(vd436,vd439),vd436)),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','holds(286, 441, 3)') ).

fof(f2,negated_conjecture,
    vplus(vplus(vmul(vd436,vd437),vmul(vd436,vd439)),vd436) != vplus(vmul(vd436,vd437),vplus(vmul(vd436,vd439),vd436)),
    inference(negated_conjecture,[status(cth)],[f1]) ).

fof(f51,axiom,
    ! [X0,X1,X2] : vplus(vplus(X0,X1),X2) = vplus(X0,vplus(X1,X2)),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','ass(cond(33, 0), 0)') ).

fof(f58,plain,
    vplus(vplus(vmul(vd436,vd437),vmul(vd436,vd439)),vd436) != vplus(vmul(vd436,vd437),vplus(vmul(vd436,vd439),vd436)),
    inference(flattening,[],[f2]) ).

fof(f99,plain,
    vplus(vplus(vmul(vd436,vd437),vmul(vd436,vd439)),vd436) != vplus(vmul(vd436,vd437),vplus(vmul(vd436,vd439),vd436)),
    inference(cnf_transformation,[],[f58]) ).

fof(f157,plain,
    ! [X2,X0,X1] : vplus(vplus(X0,X1),X2) = vplus(X0,vplus(X1,X2)),
    inference(cnf_transformation,[],[f51]) ).

fof(f189,definition,
    ! [X0,X1] :
      ( sQ4_eqProxy(X0,X1)
    <=> X0 = X1 ),
    introduced(definition,[new_symbols(definition,[sQ4_eqProxy])],[equality_proxy_definition]) ).

fof(f190,plain,
    ~ sQ4_eqProxy(vplus(vplus(vmul(vd436,vd437),vmul(vd436,vd439)),vd436),vplus(vmul(vd436,vd437),vplus(vmul(vd436,vd439),vd436))),
    inference(equality_proxy_replacement,[],[f99,f189]) ).

fof(f218,plain,
    ! [X2,X0,X1] : sQ4_eqProxy(vplus(vplus(X0,X1),X2),vplus(X0,vplus(X1,X2))),
    inference(equality_proxy_replacement,[],[f157,f189]) ).

fof(f2381,plain,
    $false,
    inference(resolution,[],[f218,f190]) ).

%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03  % Problem  : NUM847+1 : TPTP v9.3.1. Released v4.1.0.
% 0.00/0.06  % Command  : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.11/0.37  % Computer : n002.cluster.edu
% 0.11/0.37  % Model    : x86_64 x86_64
% 0.11/0.37  % CPU      : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.37  % Memory   : 8046.5625MB
% 0.11/0.37  % OS       : Linux 6.8.0-71-generic
% 0.11/0.37  % CPULimit : 300
% 0.11/0.37  % WCLimit  : 300
% 0.11/0.37  % DateTime : Sun Sep 27 21:32:52 UTC 2026
% 0.11/0.37  % CPUTime  : 
% 0.11/0.37  Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.11/0.41  Running first-order theorem proving
% 0.11/0.41  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
% 2.68/1.34  % (3907236)Detected formulas, will run a generic FOF schedule.
% 2.68/1.34  % (3907247)dis-21_1_sil=8000:lcm=predicate:random_seed=2772190658: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)
% 2.68/1.34  % (3907247)First to succeed.
% 2.68/1.34  % (3907247)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3907236"
% 2.68/1.34  % (3907245)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=179031723:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 2.68/1.34  % (3907245)Also succeeded, but the first one will report.
% 2.68/1.34  % (3907241)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=4181735334:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 2.68/1.34  % (3907242)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=715539283:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 2.68/1.34  % (3907244)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=3166405384:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 2.68/1.34  % (3907243)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=2088289622:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 2.68/1.34  % (3907244)Also succeeded, but the first one will report.
% 2.68/1.34  % (3907246)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1440528298:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 2.68/1.34  % (3907246)Also succeeded, but the first one will report.
% 2.68/1.34  % (3907247)Refutation found. Thanks to Tanya!
% 2.68/1.34  % SZS status Theorem for theBenchmark
% 2.68/1.34  % SZS output start Proof for theBenchmark
% See solution above
% 2.68/1.34  % (3907247)------------------------------
% 2.68/1.34  % (3907247)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.68/1.34  % (3907247)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.68/1.34  % (3907247)CaDiCaL version: 2.1.3
% 2.68/1.34  % (3907247)Termination reason: Refutation
% 2.68/1.34  % (3907247)Time elapsed: 0.024 s
% 2.68/1.34  % (3907247)Peak memory usage: 89 MB
% 2.68/1.34  % (3907247)Instructions burned: 70 (million)
% 2.68/1.34  % (3907247)------------------------------
% 2.68/1.34  % (3907247)------------------------------
% 2.68/1.34  % (3907236)Success in time 0.297 s
% 2.68/1.34  % Vampire exiting
%------------------------------------------------------------------------------