%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : GEO051-3 : TPTP v9.3.1. Bugfixed v1.2.1.
% 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 09:51:21 AM UTC 2026
% Result : Unsatisfiable 3.38s 1.14s
% Output : Refutation 3.38s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 9
% Syntax : Number of formulae : 28 ( 11 unt; 2 def)
% Number of atoms : 54 ( 3 equ)
% Maximal formula atoms : 5 ( 1 avg)
% Number of connectives : 49 ( 23 ~; 24 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 10 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 5 ( 3 usr; 3 prp; 0-3 aty)
% Number of functors : 4 ( 4 usr; 4 con; 0-0 aty)
% Number of variables : 12 ( 0 sgn 12 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f61,axiom,
! [X2,X3,X0,X1] :
( ~ between(X0,X2,X3)
| ~ between(X0,X1,X2)
| between(X1,X2,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b5) ).
fof(f86,axiom,
! [X2,X3,X0,X1] :
( ~ between(X0,X1,X3)
| ~ between(X0,X1,X2)
| X0 = X1
| between(X0,X2,X3)
| between(X0,X3,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b12) ).
fof(f87,axiom,
between(u,v,w),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',v_between_u_and_w) ).
fof(f88,axiom,
between(u,v,x),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',v_between_u_and_x) ).
fof(f89,axiom,
u != v,
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',u_not_v) ).
fof(f90,axiom,
~ between(v,w,x),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',w_not_between_v_and_x) ).
fof(f91,negated_conjecture,
~ between(v,x,w),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_x_between_v_and_w) ).
fof(f207,plain,
! [X0] :
( ~ between(u,v,X0)
| u = v
| between(u,X0,x)
| between(u,x,X0) ),
inference(resolution,[],[f86,f88]) ).
fof(f211,plain,
! [X0] :
( ~ between(u,v,X0)
| between(u,X0,x)
| between(u,x,X0) ),
inference(forward_subsumption_resolution,[],[f207,f89]) ).
fof(f246,plain,
( between(u,w,x)
| between(u,x,w) ),
inference(resolution,[],[f211,f87]) ).
fof(f251,definition,
( spl0_10
<=> between(u,x,w) ),
introduced(definition,[new_symbols(definition,[spl0_10])],[avatar_definition]) ).
fof(f253,plain,
( between(u,x,w)
| ~ spl0_10 ),
inference(avatar_component_clause,[],[f251]) ).
fof(f255,definition,
( spl0_11
<=> between(u,w,x) ),
introduced(definition,[new_symbols(definition,[spl0_11])],[avatar_definition]) ).
fof(f257,plain,
( between(u,w,x)
| ~ spl0_11 ),
inference(avatar_component_clause,[],[f255]) ).
fof(f258,plain,
( spl0_10
| spl0_11 ),
inference(avatar_split_clause,[],[f246,f255,f251]) ).
fof(f383,plain,
( ! [X0] :
( ~ between(u,X0,w)
| between(X0,w,x) )
| ~ spl0_11 ),
inference(resolution,[],[f257,f61]) ).
fof(f417,plain,
( between(v,w,x)
| ~ spl0_11 ),
inference(resolution,[],[f383,f87]) ).
fof(f420,plain,
( $false
| ~ spl0_11 ),
inference(forward_subsumption_resolution,[],[f417,f90]) ).
fof(f421,plain,
~ spl0_11,
inference(avatar_contradiction_clause,[],[f420]) ).
fof(f427,plain,
( ! [X0] :
( ~ between(u,X0,x)
| between(X0,x,w) )
| ~ spl0_10 ),
inference(resolution,[],[f253,f61]) ).
fof(f528,plain,
( between(v,x,w)
| ~ spl0_10 ),
inference(resolution,[],[f427,f88]) ).
fof(f531,plain,
( $false
| ~ spl0_10 ),
inference(forward_subsumption_resolution,[],[f528,f91]) ).
fof(f532,plain,
~ spl0_10,
inference(avatar_contradiction_clause,[],[f531]) ).
cnf(s12,plain,
( spl0_10
| spl0_11 ),
inference(sat_conversion,[],[f258]) ).
cnf(s32,plain,
~ spl0_11,
inference(sat_conversion,[],[f421]) ).
cnf(s48,plain,
~ spl0_10,
inference(sat_conversion,[],[f532]) ).
cnf(s54,plain,
$false,
inference(rat,[],[s12,s32,s48]) ).
fof(f533,plain,
$false,
inference(avatar_sat_refutation,[],[s54]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : GEO051-3 : TPTP v9.3.1. Bugfixed v1.2.1.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.38 % Computer : n016.cluster.edu
% 0.12/0.38 % Model : x86_64 x86_64
% 0.12/0.38 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.38 % Memory : 8046.5625MB
% 0.12/0.38 % OS : Linux 6.8.0-71-generic
% 0.12/0.38 % CPULimit : 300
% 0.12/0.38 % WCLimit : 300
% 0.12/0.38 % DateTime : Sun Sep 27 06:49:01 UTC 2026
% 0.12/0.39 % CPUTime :
% 0.12/0.39 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.42 Running first-order theorem proving
% 0.12/0.42 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
% 3.38/1.14 % (2275850)Input is clausal, will run a generic CNF schedule.
% 3.38/1.14 % (2275861)dis-21_1_sil=8000:lcm=predicate:random_seed=1815245509: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)
% 3.38/1.14 % (2275857)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=126595130:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.38/1.14 % (2275860)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1698258625:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.38/1.14 % (2275855)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=3434594651:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.38/1.14 % (2275859)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2862581782:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.38/1.14 % (2275856)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2533552435:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.38/1.14 % (2275858)lrs+10_1_sil=8000:sp=occurrence:random_seed=3087286626:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.38/1.14 % (2275858)First to succeed.
% 3.38/1.14 % (2275858)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-2275850"
% 3.38/1.14 % (2275860)Also succeeded, but the first one will report.
% 3.38/1.14 % (2275859)Instruction limit reached!
% 3.38/1.14 % (2275859)------------------------------
% 3.38/1.14 % (2275859)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.38/1.14 % (2275859)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.38/1.14 % (2275859)CaDiCaL version: 2.1.3
% 3.38/1.14 % (2275859)Termination reason: Instruction limit
% 3.38/1.14 % (2275859)Termination phase: Saturation
% 3.38/1.14 % (2275859)Time elapsed: 0.064 s
% 3.38/1.14 % (2275859)Peak memory usage: 88 MB
% 3.38/1.14 % (2275859)Instructions burned: 114 (million)
% 3.38/1.14 % (2275861)Instruction limit reached!
% 3.38/1.14 % (2275861)------------------------------
% 3.38/1.14 % (2275861)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.38/1.14 % (2275861)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.38/1.14 % (2275861)CaDiCaL version: 2.1.3
% 3.38/1.14 % (2275861)Termination reason: Instruction limit
% 3.38/1.14 % (2275861)Termination phase: Saturation
% 3.38/1.14 % (2275861)Time elapsed: 0.069 s
% 3.38/1.14 % (2275861)Peak memory usage: 89 MB
% 3.38/1.14 % (2275861)Instructions burned: 117 (million)
% 3.38/1.14 % (2275870)ott-1010_1_to=lpo:sil=16000:sos=on:spb=units:urr=on:bce=on:br=off:random_seed=4152276602:st=3:avsq=on:s2a=on:i=189:s2at=1.2:avsqr=1,16:sd=2:bd=all:nm=64:ss=axioms:sgt=30_2997 on theBenchmark for (2997ds/189Mi)
% 3.38/1.14 % (2275869)dis+1010_3_sil=8000:plsq=on:drc=off:fde=none:plsqc=1:bsd=on:plsqr=7,2:sos=on:spb=goal_then_units:random_seed=1428653531:i=143:sd=2:aac=none:ss=axioms:sgt=16_2997 on theBenchmark for (2997ds/143Mi)
% 3.38/1.14 % (2275869)Also succeeded, but the first one will report.
% 3.38/1.14 % (2275858)Refutation found. Thanks to Tanya!
% 3.38/1.14 % SZS status Unsatisfiable for theBenchmark
% 3.38/1.14 % SZS output start Proof for theBenchmark
% See solution above
% 3.38/1.14 % (2275858)------------------------------
% 3.38/1.14 % (2275858)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.38/1.14 % (2275858)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.38/1.14 % (2275858)CaDiCaL version: 2.1.3
% 3.38/1.14 % (2275858)Termination reason: Refutation
% 3.38/1.14 % (2275858)Time elapsed: 0.008 s
% 3.38/1.14 % (2275858)Peak memory usage: 89 MB
% 3.38/1.14 % (2275858)Instructions burned: 10 (million)
% 3.38/1.14 % (2275858)------------------------------
% 3.38/1.14 % (2275858)------------------------------
% 3.38/1.14 % (2275850)Success in time 0.431 s
% 3.38/1.14 % Vampire exiting
%------------------------------------------------------------------------------