%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SWW350+1 : TPTP v9.3.1. Released v5.2.0.
% 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 01:30:10 PM UTC 2026
% Result : Theorem 6.64s 2.49s
% Output : Refutation 6.64s
% Verified :
% SZS Type : Refutation
% Derivation depth : 13
% Number of leaves : 5
% Syntax : Number of formulae : 30 ( 10 unt; 0 def)
% Number of atoms : 63 ( 37 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 57 ( 24 ~; 26 |; 2 &)
% ( 0 <=>; 5 =>; 0 <=; 0 <~>)
% Maximal formula depth : 8 ( 4 avg)
% Maximal term depth : 4 ( 2 avg)
% Number of predicates : 4 ( 2 usr; 2 prp; 0-2 aty)
% Number of functors : 7 ( 7 usr; 3 con; 0-2 aty)
% Number of variables : 43 ( 41 !; 2 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f2,axiom,
! [X0,X1,X2,X3] :
( hBOOL(hAPP(hAPP(c_Natural_Oevalc(X3),X2),X1))
=> ( hBOOL(hAPP(hAPP(c_Natural_Oevalc(X3),X2),X0))
=> X0 = X1 ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',fact_com__det) ).
fof(f4,axiom,
( c_Hoare__Mirabelle_Ostate__not__singleton
=> ! [X0] :
~ ! [X1] : X1 = X0 ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',fact_single__stateE) ).
fof(f5226,axiom,
c_Hoare__Mirabelle_Ostate__not__singleton,
file('/export/starexec/sandbox/benchmark/theBenchmark.p',conj_0) ).
fof(f5227,axiom,
! [X0] :
( ! [X1] :
( hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),X1))
=> X0 = X1 )
=> X0 = v_s_H ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',conj_1) ).
fof(f5229,conjecture,
hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),v_s_H)),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',conj_3) ).
fof(f5230,negated_conjecture,
~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),v_s_H)),
inference(negated_conjecture,[status(cth)],[f5229]) ).
fof(f5231,plain,
~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),v_s_H)),
inference(flattening,[],[f5230]) ).
fof(f5232,plain,
! [X0] :
( X0 = v_s_H
| ? [X1] :
( X0 != X1
& hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),X1)) ) ),
inference(ennf_transformation,[],[f5227]) ).
fof(f5233,plain,
( ! [X0] :
? [X1] : X0 != X1
| ~ c_Hoare__Mirabelle_Ostate__not__singleton ),
inference(ennf_transformation,[],[f4]) ).
fof(f5235,plain,
! [X0,X1,X2,X3] :
( X0 = X1
| ~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(X3),X2),X0))
| ~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(X3),X2),X1)) ),
inference(ennf_transformation,[],[f2]) ).
fof(f5236,plain,
! [X0,X1,X2,X3] :
( X0 = X1
| ~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(X3),X2),X0))
| ~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(X3),X2),X1)) ),
inference(flattening,[],[f5235]) ).
fof(f5237,plain,
! [X0] :
( X0 = v_s_H
| ( sK0(X0) != X0
& hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),sK0(X0))) ) ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK0]),skolemize(X1,sK0(X0))],[f5232]) ).
fof(f5239,plain,
( ! [X0] : sK2(X0) != X0
| ~ c_Hoare__Mirabelle_Ostate__not__singleton ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK2]),skolemize(X1,sK2(X0))],[f5233]) ).
fof(f5244,plain,
c_Hoare__Mirabelle_Ostate__not__singleton,
inference(cnf_transformation,[],[f5226]) ).
fof(f5245,plain,
! [X0] :
( hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),sK0(X0)))
| v_s_H = X0 ),
inference(cnf_transformation,[],[f5237]) ).
fof(f5246,plain,
! [X0] :
( sK0(X0) != X0
| v_s_H = X0 ),
inference(cnf_transformation,[],[f5237]) ).
fof(f5248,plain,
~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),v_s_H)),
inference(cnf_transformation,[],[f5231]) ).
fof(f5249,plain,
! [X0] :
( sK2(X0) != X0
| ~ c_Hoare__Mirabelle_Ostate__not__singleton ),
inference(cnf_transformation,[],[f5239]) ).
fof(f5253,plain,
! [X2,X3,X0,X1] :
( ~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(X3),X2),X1))
| ~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(X3),X2),X0))
| X0 = X1 ),
inference(cnf_transformation,[],[f5236]) ).
fof(f5255,plain,
! [X0] : sK2(X0) != X0,
inference(forward_subsumption_resolution,[],[f5249,f5244]) ).
fof(f5258,plain,
! [X0,X1] :
( ~ hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),X0))
| sK0(X1) = X0
| v_s_H = X1 ),
inference(resolution,[],[f5253,f5245]) ).
fof(f5261,plain,
! [X0,X1] :
( sK0(X0) = sK0(X1)
| v_s_H = X0
| v_s_H = X1 ),
inference(resolution,[],[f5258,f5245]) ).
fof(f5269,plain,
! [X0,X1] :
( sK0(X0) != X1
| v_s_H = X1
| v_s_H = X0
| v_s_H = X1 ),
inference(superposition,[],[f5246,f5261]) ).
fof(f5270,plain,
! [X0,X1] :
( sK0(X0) != X1
| v_s_H = X1
| v_s_H = X0 ),
inference(duplicate_literal_removal,[],[f5269]) ).
fof(f5280,plain,
! [X0] :
( v_s_H = sK0(X0)
| v_s_H = X0 ),
inference(equality_resolution,[],[f5270]) ).
fof(f5288,plain,
! [X0] :
( hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),v_s_H))
| v_s_H = X0
| v_s_H = X0 ),
inference(superposition,[],[f5245,f5280]) ).
fof(f5291,plain,
! [X0] :
( hBOOL(hAPP(hAPP(c_Natural_Oevalc(v_c),v_Z),v_s_H))
| v_s_H = X0 ),
inference(duplicate_literal_removal,[],[f5288]) ).
fof(f5297,plain,
! [X0] : v_s_H = X0,
inference(forward_subsumption_resolution,[],[f5291,f5248]) ).
fof(f5329,plain,
! [X0] : v_s_H != X0,
inference(superposition,[],[f5255,f5297]) ).
fof(f5332,plain,
$false,
inference(forward_subsumption_resolution,[],[f5329,f5297]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.04 % Problem : SWW350+1 : TPTP v9.3.1. Released v5.2.0.
% 0.00/0.08 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.26 % Computer : n006.cluster.edu
% 0.10/0.26 % Model : x86_64 x86_64
% 0.10/0.26 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.26 % Memory : 8046.5625MB
% 0.10/0.26 % OS : Linux 6.8.0-71-generic
% 0.10/0.26 % CPULimit : 300
% 0.10/0.26 % WCLimit : 300
% 0.10/0.26 % DateTime : Mon Sep 28 13:39:55 UTC 2026
% 0.10/0.26 % CPUTime :
% 0.10/0.26 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.24/0.31 Running first-order theorem proving
% 0.24/0.31 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
% 6.64/2.49 % (3970263)Detected formulas, will run a generic FOF schedule.
% 6.64/2.49 % (3970270)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=1489229635:i=141193_2993 on theBenchmark for (2993ds/141193Mi)
% 6.64/2.49 % (3970276)dis-21_1_sil=8000:lcm=predicate:random_seed=1412279672:st=5:avsq=on:i=129:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2993 on theBenchmark for (2993ds/129Mi)
% 6.64/2.49 % (3970271)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=3001491990:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2993 on theBenchmark for (2993ds/134677Mi)
% 6.64/2.49 % (3970272)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=496014460:i=141695:sd=1:nm=32:gsp=on:ss=included_2993 on theBenchmark for (2993ds/141695Mi)
% 6.64/2.49 % (3970274)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=1895773959:i=119:av=off:ss=axioms_2993 on theBenchmark for (2993ds/119Mi)
% 6.64/2.49 % (3970273)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=3657858634:i=109:sd=1:ins=1:gsp=on:ss=axioms_2993 on theBenchmark for (2993ds/109Mi)
% 6.64/2.49 % (3970275)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=4075772349:s2a=on:i=139:gtg=position_2993 on theBenchmark for (2993ds/139Mi)
% 6.64/2.49 % (3970276)Instruction limit reached!
% 6.64/2.49 % (3970276)------------------------------
% 6.64/2.49 % (3970276)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 6.64/2.49 % (3970276)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 6.64/2.49 % (3970276)CaDiCaL version: 2.1.3
% 6.64/2.49 % (3970276)Termination reason: Instruction limit
% 6.64/2.49 % (3970276)Termination phase: Preprocessing 3
% 6.64/2.49 % (3970276)Time elapsed: 0.114 s
% 6.64/2.49 % (3970276)Peak memory usage: 93 MB
% 6.64/2.49 % (3970276)Instructions burned: 129 (million)
% 6.64/2.49 % (3970274)First to succeed.
% 6.64/2.49 % (3970274)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3970263"
% 6.64/2.49 % (3970273)Also succeeded, but the first one will report.
% 6.64/2.49 % (3970275)Instruction limit reached!
% 6.64/2.49 % (3970275)------------------------------
% 6.64/2.49 % (3970275)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 6.64/2.49 % (3970275)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 6.64/2.49 % (3970275)CaDiCaL version: 2.1.3
% 6.64/2.49 % (3970275)Termination reason: Instruction limit
% 6.64/2.49 % (3970275)Termination phase: SInE selection
% 6.64/2.49 % (3970275)Time elapsed: 0.111 s
% 6.64/2.49 % (3970275)Peak memory usage: 90 MB
% 6.64/2.49 % (3970275)Instructions burned: 139 (million)
% 6.64/2.49 % (3970284)lrs+10_1_sil=8000:sp=occurrence:random_seed=1095754447:i=285:sd=3:ss=axioms:sgt=8_2990 on theBenchmark for (2990ds/285Mi)
% 6.64/2.49 % (3970284)Also succeeded, but the first one will report.
% 6.64/2.49 % (3970285)lrs+10_1_sil=32000:urr=on:br=off:random_seed=3443147110:i=157:sd=1:gtg=position:ss=axioms:sgt=8_2989 on theBenchmark for (2989ds/157Mi)
% 6.64/2.49 % (3970274)Refutation found. Thanks to Tanya!
% 6.64/2.49 % SZS status Theorem for theBenchmark
% 6.64/2.49 % SZS output start Proof for theBenchmark
% See solution above
% 6.64/2.49 % (3970274)------------------------------
% 6.64/2.49 % (3970274)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 6.64/2.49 % (3970274)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 6.64/2.49 % (3970274)CaDiCaL version: 2.1.3
% 6.64/2.49 % (3970274)Termination reason: Refutation
% 6.64/2.49 % (3970274)Time elapsed: 0.039 s
% 6.64/2.49 % (3970274)Peak memory usage: 94 MB
% 6.64/2.49 % (3970274)Instructions burned: 35 (million)
% 6.64/2.49 % (3970274)------------------------------
% 6.64/2.49 % (3970274)------------------------------
% 6.64/2.49 % (3970263)Success in time 1.355 s
% 6.64/2.49 % Vampire exiting
%------------------------------------------------------------------------------