↑ Up

Vampire---5.0.1.THM-Ref.s

View TPTP
Problem
Process solution in
SystemOnTSTP
Download .tgz
%------------------------------------------------------------------------------
% File     : Vampire---5.0.1
% Problem  : NUM849+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 : n016.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 3.48s 1.24s
% Output   : Refutation 3.48s
% Verified : 
% SZS Type : Refutation
%            Derivation depth      :   14
%            Number of leaves      :    7
% Syntax   : Number of formulae    :   35 (  21 unt;   0 def)
%            Number of atoms       :   49 (  48 equ)
%            Maximal formula atoms :    2 (   1 avg)
%            Number of connectives :   30 (  16   ~;   7   |;   4   &)
%                                         (   0 <=>;   3  =>;   0  <=;   0 <~>)
%            Maximal formula depth :    4 (   3 avg)
%            Maximal term depth    :    4 (   2 avg)
%            Number of predicates  :    2 (   0 usr;   1 prp; 0-2 aty)
%            Number of functors    :    7 (   7 usr;   4 con; 0-2 aty)
%            Number of variables   :   35 (  34   !;   1   ?)

% Comments : 
%------------------------------------------------------------------------------
fof(f1,conjecture,
    ! [X0] :
      ( vmul(vmul(vd448,vd449),X0) = vmul(vd448,vmul(vd449,X0))
     => vmul(vmul(vd448,vd449),vsucc(X0)) = vmul(vd448,vmul(vd449,vsucc(X0))) ),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','qu(ind(296), imp(296))') ).

fof(f2,negated_conjecture,
    ~ ! [X0] :
        ( vmul(vmul(vd448,vd449),X0) = vmul(vd448,vmul(vd449,X0))
       => vmul(vmul(vd448,vd449),vsucc(X0)) = vmul(vd448,vmul(vd449,vsucc(X0))) ),
    inference(negated_conjecture,[status(cth)],[f1]) ).

fof(f5,axiom,
    ! [X0] :
      ( vmul(vmul(vd448,vd449),X0) = vmul(vd448,vmul(vd449,X0))
     => vplus(vmul(vmul(vd448,vd449),X0),vmul(vd448,vd449)) = vplus(vmul(vd448,vmul(vd449,X0)),vmul(vd448,vd449)) ),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','ass(cond(conseq(292), 1), 2)') ).

fof(f9,axiom,
    ! [X0,X1,X2] : vmul(X0,vplus(X1,X2)) = vplus(vmul(X0,X1),vmul(X0,X2)),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','ass(cond(281, 0), 0)') ).

fof(f10,axiom,
    ! [X0,X1] : vmul(X0,X1) = vmul(X1,X0),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','ass(cond(270, 0), 0)') ).

fof(f13,axiom,
    ! [X0,X1] :
      ( vmul(X0,vsucc(X1)) = vplus(vmul(X0,X1),X0)
      & vmul(X0,v1) = X0 ),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','qu(cond(conseq(axiom(3)), 32), and(holds(definiens(249), 399, 0), holds(definiens(249), 398, 0)))') ).

fof(f48,axiom,
    ! [X0,X1] : vplus(X1,X0) = vplus(X0,X1),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','ass(cond(61, 0), 0)') ).

fof(f52,axiom,
    ! [X0,X1] :
      ( vplus(X0,vsucc(X1)) = vsucc(vplus(X0,X1))
      & vplus(X0,v1) = vsucc(X0) ),
    file('/export/starexec/sandbox2/benchmark/theBenchmark.p','qu(cond(conseq(axiom(3)), 3), and(holds(definiens(29), 45, 0), holds(definiens(29), 44, 0)))') ).

fof(f58,plain,
    ? [X0] :
      ( vmul(vmul(vd448,vd449),vsucc(X0)) != vmul(vd448,vmul(vd449,vsucc(X0)))
      & vmul(vmul(vd448,vd449),X0) = vmul(vd448,vmul(vd449,X0)) ),
    inference(ennf_transformation,[],[f2]) ).

fof(f60,plain,
    ! [X0] :
      ( vplus(vmul(vmul(vd448,vd449),X0),vmul(vd448,vd449)) = vplus(vmul(vd448,vmul(vd449,X0)),vmul(vd448,vd449))
      | vmul(vmul(vd448,vd449),X0) != vmul(vd448,vmul(vd449,X0)) ),
    inference(ennf_transformation,[],[f5]) ).

fof(f71,plain,
    ( vmul(vmul(vd448,vd449),vsucc(sK0)) != vmul(vd448,vmul(vd449,vsucc(sK0)))
    & vmul(vmul(vd448,vd449),sK0) = vmul(vd448,vmul(vd449,sK0)) ),
    inference(skolemize,[status(esa),new_symbols(skolem,[sK0]),skolemize(X0,sK0)],[f58]) ).

fof(f73,plain,
    vmul(vmul(vd448,vd449),sK0) = vmul(vd448,vmul(vd449,sK0)),
    inference(cnf_transformation,[],[f71]) ).

fof(f74,plain,
    vmul(vmul(vd448,vd449),vsucc(sK0)) != vmul(vd448,vmul(vd449,vsucc(sK0))),
    inference(cnf_transformation,[],[f71]) ).

fof(f78,plain,
    ! [X0] :
      ( vplus(vmul(vd448,vmul(vd449,X0)),vmul(vd448,vd449)) = vplus(vmul(vmul(vd448,vd449),X0),vmul(vd448,vd449))
      | vmul(vmul(vd448,vd449),X0) != vmul(vd448,vmul(vd449,X0)) ),
    inference(cnf_transformation,[],[f60]) ).

fof(f82,plain,
    ! [X0,X1] : vmul(X0,X1) = vmul(X1,X0),
    inference(cnf_transformation,[],[f10]) ).

fof(f83,plain,
    ! [X2,X0,X1] : vmul(X0,vplus(X1,X2)) = vplus(vmul(X0,X1),vmul(X0,X2)),
    inference(cnf_transformation,[],[f9]) ).

fof(f89,plain,
    ! [X0] : vsucc(X0) = vplus(X0,v1),
    inference(cnf_transformation,[],[f52]) ).

fof(f93,plain,
    ! [X0,X1] : vmul(X0,vsucc(X1)) = vplus(vmul(X0,X1),X0),
    inference(cnf_transformation,[],[f13]) ).

fof(f96,plain,
    ! [X0,X1] : vplus(X0,X1) = vplus(X1,X0),
    inference(cnf_transformation,[],[f48]) ).

fof(f105,plain,
    vmul(vmul(vd448,vd449),vplus(sK0,v1)) != vmul(vd448,vmul(vd449,vplus(sK0,v1))),
    inference(definition_unfolding,[],[f74,f89,f89]) ).

fof(f116,plain,
    ! [X0,X1] : vplus(vmul(X0,X1),X0) = vmul(X0,vplus(X1,v1)),
    inference(definition_unfolding,[],[f93,f89]) ).

fof(f129,plain,
    vmul(vd448,vmul(vd449,vplus(sK0,v1))) != vmul(vplus(sK0,v1),vmul(vd448,vd449)),
    inference(superposition,[],[f105,f82]) ).

fof(f237,plain,
    ! [X0,X1] : vmul(X0,vplus(X1,v1)) = vplus(X0,vmul(X0,X1)),
    inference(forward_demodulation,[],[f116,f96]) ).

fof(f534,plain,
    ! [X0] :
      ( vplus(vmul(vd448,vmul(vd449,X0)),vmul(vd448,vd449)) = vplus(vmul(vd448,vd449),vmul(vmul(vd448,vd449),X0))
      | vmul(vmul(vd448,vd449),X0) != vmul(vd448,vmul(vd449,X0)) ),
    inference(forward_demodulation,[],[f78,f96]) ).

fof(f535,plain,
    ! [X0] :
      ( vplus(vmul(vd448,vmul(vd449,X0)),vmul(vd448,vd449)) = vmul(vmul(vd448,vd449),vplus(X0,v1))
      | vmul(vmul(vd448,vd449),X0) != vmul(vd448,vmul(vd449,X0)) ),
    inference(forward_demodulation,[],[f534,f237]) ).

fof(f536,plain,
    ! [X0] :
      ( vmul(vmul(vd448,vd449),vplus(X0,v1)) = vplus(vmul(vd448,vd449),vmul(vd448,vmul(vd449,X0)))
      | vmul(vmul(vd448,vd449),X0) != vmul(vd448,vmul(vd449,X0)) ),
    inference(forward_demodulation,[],[f535,f96]) ).

fof(f537,plain,
    ! [X0] :
      ( vmul(vmul(vd448,vd449),X0) != vmul(vd448,vmul(vd449,X0))
      | vmul(vmul(vd448,vd449),vplus(X0,v1)) = vmul(vd448,vplus(vd449,vmul(vd449,X0))) ),
    inference(forward_demodulation,[],[f536,f83]) ).

fof(f538,plain,
    ( vmul(vd448,vmul(vd449,sK0)) != vmul(vd448,vmul(vd449,sK0))
    | vmul(vmul(vd448,vd449),vplus(sK0,v1)) = vmul(vd448,vplus(vd449,vmul(vd449,sK0))) ),
    inference(superposition,[],[f537,f73]) ).

fof(f542,plain,
    vmul(vmul(vd448,vd449),vplus(sK0,v1)) = vmul(vd448,vplus(vd449,vmul(vd449,sK0))),
    inference(trivial_inequality_removal,[],[f538]) ).

fof(f545,plain,
    vmul(vmul(vd448,vd449),vplus(sK0,v1)) = vmul(vd448,vplus(vd449,vmul(sK0,vd449))),
    inference(forward_demodulation,[],[f542,f82]) ).

fof(f547,plain,
    vmul(vplus(sK0,v1),vmul(vd448,vd449)) = vmul(vd448,vplus(vd449,vmul(sK0,vd449))),
    inference(forward_demodulation,[],[f545,f82]) ).

fof(f552,plain,
    vmul(vd448,vmul(vd449,vplus(sK0,v1))) != vmul(vd448,vplus(vd449,vmul(sK0,vd449))),
    inference(superposition,[],[f129,f547]) ).

fof(f559,plain,
    vmul(vd448,vplus(vd449,vmul(vd449,sK0))) != vmul(vd448,vplus(vd449,vmul(sK0,vd449))),
    inference(forward_demodulation,[],[f552,f237]) ).

fof(f562,plain,
    vmul(vd448,vplus(vd449,vmul(sK0,vd449))) != vmul(vd448,vplus(vd449,vmul(sK0,vd449))),
    inference(forward_demodulation,[],[f559,f82]) ).

fof(f563,plain,
    $false,
    inference(trivial_inequality_removal,[],[f562]) ).

%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02  % Problem  : NUM849+1 : TPTP v9.3.1. Released v4.1.0.
% 0.00/0.05  % Command  : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.37  % Computer : n016.cluster.edu
% 0.12/0.37  % Model    : x86_64 x86_64
% 0.12/0.37  % CPU      : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.37  % Memory   : 8046.5625MB
% 0.12/0.37  % OS       : Linux 6.8.0-71-generic
% 0.12/0.37  % CPULimit : 300
% 0.12/0.37  % WCLimit  : 300
% 0.12/0.37  % DateTime : Sun Sep 27 21:35:32 UTC 2026
% 0.12/0.37  % CPUTime  : 
% 0.12/0.37  Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.40  Running first-order theorem proving
% 0.12/0.41  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
% 3.48/1.24  % (3010645)Detected formulas, will run a generic FOF schedule.
% 3.48/1.24  % (3010656)dis-21_1_sil=8000:lcm=predicate:random_seed=3916883812: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)
% 3.48/1.24  % (3010654)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=2088567427:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.48/1.24  % (3010653)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=2314555880:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.48/1.24  % (3010651)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=894060786:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.48/1.24  % (3010652)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=3452330506:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.48/1.24  % (3010650)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=1392244989:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.48/1.24  % (3010655)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=108002789:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.48/1.24  % (3010656)Instruction limit reached! 
% 3.48/1.24  % (3010656)------------------------------
% 3.48/1.24  % (3010656)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.48/1.24  % (3010656)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.48/1.24  % (3010656)CaDiCaL version: 2.1.3
% 3.48/1.24  % (3010656)Termination reason: Instruction limit
% 3.48/1.24  % (3010656)Termination phase: Saturation
% 3.48/1.24  % (3010656)Time elapsed: 0.042 s
% 3.48/1.24  % (3010656)Peak memory usage: 89 MB
% 3.48/1.24  % (3010656)Instructions burned: 131 (million)
% 3.48/1.24  % (3010653)Refutation not found, incomplete strategy
% 3.48/1.24  % (3010653)------------------------------
% 3.48/1.24  % (3010653)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.48/1.24  % (3010653)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.48/1.24  % (3010653)CaDiCaL version: 2.1.3
% 3.48/1.24  % (3010653)Termination reason: Refutation not found, incomplete strategy
% 3.48/1.24  % (3010653)Time elapsed: 0.002 s
% 3.48/1.24  % (3010653)Peak memory usage: 88 MB
% 3.48/1.24  % (3010653)Instructions burned: 1 (million)
% 3.48/1.24  % (3010654)First to succeed.
% 3.48/1.24  % (3010654)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3010645"
% 3.48/1.24  % (3010655)Also succeeded, but the first one will report.
% 3.48/1.24  % (3010664)lrs+10_1_sil=8000:sp=occurrence:random_seed=1132520231:i=285:sd=3:ss=axioms:sgt=8_2998 on theBenchmark for (2998ds/285Mi)
% 3.48/1.24  % (3010664)Also succeeded, but the first one will report.
% 3.48/1.24  % (3010653)------------------------------
% 3.48/1.24  % (3010653)------------------------------
% 3.48/1.24  % (3010654)Refutation found. Thanks to Tanya!
% 3.48/1.24  % SZS status Theorem for theBenchmark
% 3.48/1.24  % SZS output start Proof for theBenchmark
% See solution above
% 3.48/1.24  % (3010654)------------------------------
% 3.48/1.24  % (3010654)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.48/1.24  % (3010654)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.48/1.24  % (3010654)CaDiCaL version: 2.1.3
% 3.48/1.24  % (3010654)Termination reason: Refutation
% 3.48/1.24  % (3010654)Time elapsed: 0.014 s
% 3.48/1.24  % (3010654)Peak memory usage: 88 MB
% 3.48/1.24  % (3010654)Instructions burned: 23 (million)
% 3.48/1.24  % (3010654)------------------------------
% 3.48/1.24  % (3010654)------------------------------
% 3.48/1.24  % (3010645)Success in time 0.439 s
% 3.48/1.24  % Vampire exiting
%------------------------------------------------------------------------------