%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : NUM843+2 : TPTP v9.3.1. Released v4.1.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n014.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 12:17:14 PM UTC 2026
% Result : Theorem 3.46s 1.37s
% Output : Refutation 3.46s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 8
% Syntax : Number of formulae : 34 ( 14 unt; 0 def)
% Number of atoms : 74 ( 15 equ)
% Maximal formula atoms : 6 ( 2 avg)
% Number of connectives : 70 ( 30 ~; 27 |; 8 &)
% ( 2 <=>; 3 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 4 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 6 ( 4 usr; 1 prp; 0-2 aty)
% Number of functors : 2 ( 2 usr; 2 con; 0-0 aty)
% Number of variables : 39 ( 39 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,conjecture,
greater(vd390,vd391),
file('/export/starexec/sandbox/benchmark/theBenchmark.p','holds(244, 394, 0)') ).
fof(f2,negated_conjecture,
~ greater(vd390,vd391),
inference(negated_conjecture,[status(cth)],[f1]) ).
fof(f3,axiom,
~ leq(vd390,vd391),
file('/export/starexec/sandbox/benchmark/theBenchmark.p','holds(conjunct2(243), 393, 0)') ).
fof(f21,axiom,
! [X0,X1] :
( geq(X0,X1)
=> leq(X1,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p','ass(cond(158, 0), 0)') ).
fof(f22,axiom,
! [X0,X1] :
( leq(X1,X0)
<=> ( less(X1,X0)
| X1 = X0 ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p','def(cond(conseq(axiom(3)), 17), 1)') ).
fof(f23,axiom,
! [X0,X1] :
( geq(X1,X0)
<=> ( greater(X1,X0)
| X1 = X0 ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p','def(cond(conseq(axiom(3)), 16), 1)') ).
fof(f24,axiom,
! [X0,X1] :
( less(X0,X1)
=> greater(X1,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p','ass(cond(147, 0), 0)') ).
fof(f25,axiom,
! [X0,X1] :
( greater(X0,X1)
=> less(X1,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p','ass(cond(140, 0), 0)') ).
fof(f26,axiom,
! [X0,X1] :
( X0 = X1
| greater(X0,X1)
| less(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p','ass(cond(goal(130), 0), 0)') ).
fof(f48,plain,
~ greater(vd390,vd391),
inference(flattening,[],[f2]) ).
fof(f54,plain,
! [X0,X1] :
( less(X1,X0)
| ~ greater(X0,X1) ),
inference(ennf_transformation,[],[f25]) ).
fof(f55,plain,
! [X0,X1] :
( greater(X1,X0)
| ~ less(X0,X1) ),
inference(ennf_transformation,[],[f24]) ).
fof(f66,plain,
! [X0,X1] :
( leq(X1,X0)
| ~ geq(X0,X1) ),
inference(ennf_transformation,[],[f21]) ).
fof(f83,plain,
! [X0,X1] :
( ( leq(X1,X0)
| ( ~ less(X1,X0)
& X0 != X1 ) )
& ( less(X1,X0)
| X1 = X0
| ~ leq(X1,X0) ) ),
inference(nnf_transformation,[],[f22]) ).
fof(f84,plain,
! [X0,X1] :
( ( leq(X1,X0)
| ( ~ less(X1,X0)
& X0 != X1 ) )
& ( less(X1,X0)
| X1 = X0
| ~ leq(X1,X0) ) ),
inference(flattening,[],[f83]) ).
fof(f85,plain,
! [X0,X1] :
( ( geq(X1,X0)
| ( ~ greater(X1,X0)
& X0 != X1 ) )
& ( greater(X1,X0)
| X1 = X0
| ~ geq(X1,X0) ) ),
inference(nnf_transformation,[],[f23]) ).
fof(f86,plain,
! [X0,X1] :
( ( geq(X1,X0)
| ( ~ greater(X1,X0)
& X0 != X1 ) )
& ( greater(X1,X0)
| X1 = X0
| ~ geq(X1,X0) ) ),
inference(flattening,[],[f85]) ).
fof(f87,plain,
~ greater(vd390,vd391),
inference(cnf_transformation,[],[f48]) ).
fof(f89,plain,
~ leq(vd390,vd391),
inference(cnf_transformation,[],[f3]) ).
fof(f107,plain,
! [X0,X1] :
( less(X0,X1)
| greater(X0,X1)
| X0 = X1 ),
inference(cnf_transformation,[],[f26]) ).
fof(f108,plain,
! [X0,X1] :
( less(X1,X0)
| ~ greater(X0,X1) ),
inference(cnf_transformation,[],[f54]) ).
fof(f109,plain,
! [X0,X1] :
( greater(X1,X0)
| ~ less(X0,X1) ),
inference(cnf_transformation,[],[f55]) ).
fof(f125,plain,
! [X0,X1] :
( leq(X1,X0)
| ~ less(X1,X0) ),
inference(cnf_transformation,[],[f84]) ).
fof(f126,plain,
! [X0,X1] :
( leq(X1,X0)
| ~ geq(X0,X1) ),
inference(cnf_transformation,[],[f66]) ).
fof(f136,plain,
! [X0,X1] :
( geq(X1,X0)
| X0 != X1 ),
inference(cnf_transformation,[],[f86]) ).
fof(f157,plain,
! [X1] : geq(X1,X1),
inference(equality_resolution,[],[f136]) ).
fof(f162,plain,
~ less(vd391,vd390),
inference(resolution,[],[f109,f87]) ).
fof(f166,plain,
~ less(vd390,vd391),
inference(resolution,[],[f125,f89]) ).
fof(f168,plain,
~ geq(vd391,vd390),
inference(resolution,[],[f126,f89]) ).
fof(f169,plain,
~ greater(vd391,vd390),
inference(resolution,[],[f166,f108]) ).
fof(f206,plain,
( greater(vd391,vd390)
| vd390 = vd391 ),
inference(resolution,[],[f107,f162]) ).
fof(f209,plain,
vd390 = vd391,
inference(forward_subsumption_resolution,[],[f206,f169]) ).
fof(f218,plain,
~ geq(vd390,vd390),
inference(superposition,[],[f168,f209]) ).
fof(f220,plain,
$false,
inference(forward_subsumption_resolution,[],[f218,f157]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : NUM843+2 : TPTP v9.3.1. Released v4.1.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.37 % Computer : n014.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 21:29:46 UTC 2026
% 0.10/0.37 % CPUTime :
% 0.10/0.37 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.41 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
% 3.46/1.37 % (1185531)Detected formulas, will run a generic FOF schedule.
% 3.46/1.37 % (1185537)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=3574903350:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.46/1.37 % (1185540)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=2781318829:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.46/1.37 % (1185536)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=1952598145:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.46/1.37 % (1185539)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=587704560:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.46/1.37 % (1185542)dis-21_1_sil=8000:lcm=predicate:random_seed=3589732753: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)
% 3.46/1.37 % (1185538)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=2592287808:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.46/1.37 % (1185539)Refutation not found, incomplete strategy
% 3.46/1.37 % (1185539)------------------------------
% 3.46/1.37 % (1185539)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.46/1.37 % (1185539)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.46/1.37 % (1185539)CaDiCaL version: 2.1.3
% 3.46/1.37 % (1185539)Termination reason: Refutation not found, incomplete strategy
% 3.46/1.37 % (1185539)Time elapsed: 0.002 s
% 3.46/1.37 % (1185539)Peak memory usage: 88 MB
% 3.46/1.37 % (1185540)First to succeed.
% 3.46/1.37 % (1185540)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-1185531"
% 3.46/1.37 % (1185541)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=4252489751:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.46/1.37 % (1185541)Also succeeded, but the first one will report.
% 3.46/1.37 % (1185542)Instruction limit reached!
% 3.46/1.37 % (1185542)------------------------------
% 3.46/1.37 % (1185542)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.46/1.37 % (1185542)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.46/1.37 % (1185542)CaDiCaL version: 2.1.3
% 3.46/1.37 % (1185542)Termination reason: Instruction limit
% 3.46/1.37 % (1185542)Termination phase: Saturation
% 3.46/1.37 % (1185542)Time elapsed: 0.082 s
% 3.46/1.37 % (1185542)Peak memory usage: 88 MB
% 3.46/1.37 % (1185542)Instructions burned: 130 (million)
% 3.46/1.37 % (1185539)------------------------------
% 3.46/1.37 % (1185539)------------------------------
% 3.46/1.37 % (1185550)lrs+10_1_sil=8000:sp=occurrence:random_seed=3156142746:i=285:sd=3:ss=axioms:sgt=8_2997 on theBenchmark for (2997ds/285Mi)
% 3.46/1.37 % (1185540)Refutation found. Thanks to Tanya!
% 3.46/1.37 % SZS status Theorem for theBenchmark
% 3.46/1.37 % SZS output start Proof for theBenchmark
% See solution above
% 3.46/1.37 % (1185540)------------------------------
% 3.46/1.37 % (1185540)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.46/1.37 % (1185540)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.46/1.37 % (1185540)CaDiCaL version: 2.1.3
% 3.46/1.37 % (1185540)Termination reason: Refutation
% 3.46/1.37 % (1185540)Time elapsed: 0.004 s
% 3.46/1.37 % (1185540)Peak memory usage: 88 MB
% 3.46/1.37 % (1185540)Instructions burned: 4 (million)
% 3.46/1.37 % (1185540)------------------------------
% 3.46/1.37 % (1185540)------------------------------
% 3.46/1.37 % (1185531)Success in time 0.421 s
% 3.46/1.37 % Vampire exiting
%------------------------------------------------------------------------------