%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : MGT006-1 : TPTP v9.3.1. Released v2.4.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n010.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 12:01:58 PM UTC 2026
% Result : Unsatisfiable 1.46s 1.31s
% Output : Refutation 0.18s
% Verified :
% SZS Type : Refutation
% Derivation depth : 13
% Number of leaves : 21
% Syntax : Number of formulae : 78 ( 22 unt; 8 def)
% Number of atoms : 246 ( 0 equ)
% Maximal formula atoms : 10 ( 3 avg)
% Number of connectives : 335 ( 167 ~; 160 |; 0 &)
% ( 8 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 21 ( 5 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 15 ( 14 usr; 9 prp; 0-3 aty)
% Number of functors : 8 ( 8 usr; 7 con; 0-2 aty)
% Number of variables : 112 ( 0 sgn 112 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0,X1] :
( reproducibility(X0,sk1(X1,X0),X1)
| ~ organization(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',mp3_1) ).
fof(f2,axiom,
! [X2,X3,X0,X1,X8,X6,X9,X7,X4,X5] :
( ~ accountability(X2,X7,X3)
| ~ organization(X2,X3)
| ~ reliability(X0,X4,X1)
| ~ reliability(X2,X5,X3)
| ~ accountability(X0,X6,X1)
| ~ organization(X0,X1)
| ~ reproducibility(X0,X8,X1)
| ~ reproducibility(X2,X9,X3)
| ~ greater(X9,X8)
| greater(X5,X4) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a2_FOL_2) ).
fof(f3,axiom,
! [X2,X3,X0,X1,X8,X6,X9,X7,X4,X5] :
( ~ accountability(X2,X7,X3)
| ~ organization(X2,X3)
| ~ reliability(X0,X4,X1)
| ~ reliability(X2,X5,X3)
| ~ accountability(X0,X6,X1)
| ~ organization(X0,X1)
| ~ reproducibility(X0,X8,X1)
| ~ reproducibility(X2,X9,X3)
| ~ greater(X9,X8)
| greater(X7,X6) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a2_FOL_3) ).
fof(f5,axiom,
! [X2,X3,X0,X1,X4] :
( ~ reorganization_free(X0,X1,X2)
| ~ organization(X0,X2)
| ~ organization(X0,X1)
| ~ reproducibility(X0,X3,X1)
| ~ reproducibility(X0,X4,X2)
| ~ greater(X2,X1)
| greater(X4,X3) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',a4_FOL_5) ).
fof(f6,negated_conjecture,
organization(sk2,sk7),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_6) ).
fof(f7,negated_conjecture,
organization(sk2,sk8),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_7) ).
fof(f8,negated_conjecture,
reorganization_free(sk2,sk7,sk8),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_8) ).
fof(f9,negated_conjecture,
reliability(sk2,sk3,sk7),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_9) ).
fof(f10,negated_conjecture,
reliability(sk2,sk4,sk8),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_10) ).
fof(f11,negated_conjecture,
accountability(sk2,sk5,sk7),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_11) ).
fof(f12,negated_conjecture,
accountability(sk2,sk6,sk8),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_12) ).
fof(f13,negated_conjecture,
greater(sk8,sk7),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_13) ).
fof(f14,negated_conjecture,
( ~ greater(sk4,sk3)
| ~ greater(sk6,sk5) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',t6_FOL_14) ).
fof(f16,definition,
( spl0_1
<=> greater(sk6,sk5) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f18,plain,
( ~ greater(sk6,sk5)
| spl0_1 ),
inference(avatar_component_clause,[],[f16]) ).
fof(f20,definition,
( spl0_2
<=> greater(sk4,sk3) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f22,plain,
( ~ greater(sk4,sk3)
| spl0_2 ),
inference(avatar_component_clause,[],[f20]) ).
fof(f23,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f14,f20,f16]) ).
fof(f24,plain,
! [X0,X1] :
( ~ organization(sk2,sk8)
| ~ organization(sk2,sk7)
| ~ reproducibility(sk2,X0,sk7)
| ~ reproducibility(sk2,X1,sk8)
| ~ greater(sk8,sk7)
| greater(X1,X0) ),
inference(resolution,[],[f5,f8]) ).
fof(f25,plain,
! [X0,X1] :
( ~ organization(sk2,sk7)
| ~ reproducibility(sk2,X0,sk7)
| ~ reproducibility(sk2,X1,sk8)
| ~ greater(sk8,sk7)
| greater(X1,X0) ),
inference(forward_subsumption_resolution,[],[f24,f7]) ).
fof(f26,plain,
! [X0,X1] :
( ~ reproducibility(sk2,X0,sk7)
| ~ reproducibility(sk2,X1,sk8)
| ~ greater(sk8,sk7)
| greater(X1,X0) ),
inference(forward_subsumption_resolution,[],[f25,f6]) ).
fof(f27,plain,
! [X0,X1] :
( ~ reproducibility(sk2,X1,sk8)
| ~ reproducibility(sk2,X0,sk7)
| greater(X1,X0) ),
inference(forward_subsumption_resolution,[],[f26,f13]) ).
fof(f29,plain,
! [X2,X3,X0,X1,X6,X4,X5] :
( ~ organization(sk2,sk8)
| ~ reliability(X0,X1,X2)
| ~ reliability(sk2,X3,sk8)
| ~ accountability(X0,X4,X2)
| ~ organization(X0,X2)
| ~ reproducibility(X0,X5,X2)
| ~ reproducibility(sk2,X6,sk8)
| ~ greater(X6,X5)
| greater(X3,X1) ),
inference(resolution,[],[f2,f12]) ).
fof(f30,plain,
! [X2,X3,X0,X1,X6,X4,X5] :
( ~ accountability(X0,X4,X2)
| ~ reliability(sk2,X3,sk8)
| ~ reliability(X0,X1,X2)
| ~ organization(X0,X2)
| ~ reproducibility(X0,X5,X2)
| ~ reproducibility(sk2,X6,sk8)
| ~ greater(X6,X5)
| greater(X3,X1) ),
inference(forward_subsumption_resolution,[],[f29,f7]) ).
fof(f35,plain,
! [X2,X3,X0,X1,X6,X4,X5] :
( ~ organization(sk2,sk8)
| ~ reliability(X0,X1,X2)
| ~ reliability(sk2,X3,sk8)
| ~ accountability(X0,X4,X2)
| ~ organization(X0,X2)
| ~ reproducibility(X0,X5,X2)
| ~ reproducibility(sk2,X6,sk8)
| ~ greater(X6,X5)
| greater(sk6,X4) ),
inference(resolution,[],[f3,f12]) ).
fof(f36,plain,
! [X2,X3,X0,X1,X6,X4,X5] :
( ~ reliability(X0,X1,X2)
| ~ reliability(sk2,X3,sk8)
| ~ accountability(X0,X4,X2)
| ~ organization(X0,X2)
| ~ reproducibility(X0,X5,X2)
| ~ reproducibility(sk2,X6,sk8)
| ~ greater(X6,X5)
| greater(sk6,X4) ),
inference(forward_subsumption_resolution,[],[f35,f7]) ).
fof(f39,definition,
( spl0_3
<=> ! [X3] : ~ reliability(sk2,X3,sk8) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f40,plain,
( ! [X3] : ~ reliability(sk2,X3,sk8)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f39]) ).
fof(f42,definition,
( spl0_4
<=> ! [X5,X4,X0,X6,X2,X1] :
( ~ reliability(X0,X1,X2)
| greater(sk6,X4)
| ~ reproducibility(sk2,X6,sk8)
| ~ greater(X6,X5)
| ~ reproducibility(X0,X5,X2)
| ~ organization(X0,X2)
| ~ accountability(X0,X4,X2) ) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f43,plain,
( ! [X2,X0,X1,X6,X4,X5] :
( ~ accountability(X0,X4,X2)
| greater(sk6,X4)
| ~ reproducibility(sk2,X6,sk8)
| ~ greater(X6,X5)
| ~ reproducibility(X0,X5,X2)
| ~ organization(X0,X2)
| ~ reliability(X0,X1,X2) )
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f42]) ).
fof(f44,plain,
( spl0_3
| spl0_4 ),
inference(avatar_split_clause,[],[f36,f42,f39]) ).
fof(f46,definition,
( spl0_5
<=> ! [X3] : ~ reliability(sk2,X3,sk7) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f47,plain,
( ! [X3] : ~ reliability(sk2,X3,sk7)
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f46]) ).
fof(f52,plain,
( $false
| ~ spl0_3 ),
inference(resolution,[],[f40,f10]) ).
fof(f53,plain,
~ spl0_3,
inference(avatar_contradiction_clause,[],[f52]) ).
fof(f57,plain,
( $false
| ~ spl0_5 ),
inference(resolution,[],[f47,f9]) ).
fof(f58,plain,
~ spl0_5,
inference(avatar_contradiction_clause,[],[f57]) ).
fof(f60,plain,
( ! [X2,X0,X1] :
( greater(sk6,sk5)
| ~ reproducibility(sk2,X0,sk8)
| ~ greater(X0,X1)
| ~ reproducibility(sk2,X1,sk7)
| ~ organization(sk2,sk7)
| ~ reliability(sk2,X2,sk7) )
| ~ spl0_4 ),
inference(resolution,[],[f43,f11]) ).
fof(f63,plain,
( ! [X2,X0,X1] :
( greater(sk6,sk5)
| ~ reproducibility(sk2,X0,sk8)
| ~ reproducibility(sk2,X1,sk7)
| ~ organization(sk2,sk7)
| ~ reliability(sk2,X2,sk7) )
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f60,f27]) ).
fof(f72,plain,
( ! [X2,X0,X1] :
( ~ reproducibility(sk2,X0,sk8)
| ~ reproducibility(sk2,X1,sk7)
| ~ organization(sk2,sk7)
| ~ reliability(sk2,X2,sk7) )
| spl0_1
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f63,f18]) ).
fof(f73,plain,
( ! [X2,X0,X1] :
( ~ reproducibility(sk2,X0,sk8)
| ~ reproducibility(sk2,X1,sk7)
| ~ reliability(sk2,X2,sk7) )
| spl0_1
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f72,f6]) ).
fof(f75,definition,
( spl0_9
<=> ! [X1] : ~ reproducibility(sk2,X1,sk7) ),
introduced(definition,[new_symbols(definition,[spl0_9])],[avatar_definition]) ).
fof(f76,plain,
( ! [X1] : ~ reproducibility(sk2,X1,sk7)
| ~ spl0_9 ),
inference(avatar_component_clause,[],[f75]) ).
fof(f78,definition,
( spl0_10
<=> ! [X0] : ~ reproducibility(sk2,X0,sk8) ),
introduced(definition,[new_symbols(definition,[spl0_10])],[avatar_definition]) ).
fof(f79,plain,
( ! [X0] : ~ reproducibility(sk2,X0,sk8)
| ~ spl0_10 ),
inference(avatar_component_clause,[],[f78]) ).
fof(f80,plain,
( spl0_5
| spl0_9
| spl0_10
| spl0_1
| ~ spl0_4 ),
inference(avatar_split_clause,[],[f73,f42,f16,f78,f75,f46]) ).
fof(f103,plain,
! [X2,X3,X0,X1] :
( ~ reliability(sk2,X0,sk8)
| ~ reliability(sk2,X1,sk7)
| ~ organization(sk2,sk7)
| ~ reproducibility(sk2,X2,sk7)
| ~ reproducibility(sk2,X3,sk8)
| ~ greater(X3,X2)
| greater(X0,X1) ),
inference(resolution,[],[f30,f11]) ).
fof(f105,plain,
! [X2,X3,X0,X1] :
( ~ reliability(sk2,X0,sk8)
| ~ reliability(sk2,X1,sk7)
| ~ organization(sk2,sk7)
| ~ reproducibility(sk2,X2,sk7)
| ~ reproducibility(sk2,X3,sk8)
| greater(X0,X1) ),
inference(forward_subsumption_resolution,[],[f103,f27]) ).
fof(f106,plain,
! [X2,X3,X0,X1] :
( ~ reliability(sk2,X0,sk8)
| ~ reliability(sk2,X1,sk7)
| ~ reproducibility(sk2,X2,sk7)
| ~ reproducibility(sk2,X3,sk8)
| greater(X0,X1) ),
inference(forward_subsumption_resolution,[],[f105,f6]) ).
fof(f108,definition,
( spl0_15
<=> ! [X0,X1] :
( ~ reliability(sk2,X0,sk8)
| greater(X0,X1)
| ~ reliability(sk2,X1,sk7) ) ),
introduced(definition,[new_symbols(definition,[spl0_15])],[avatar_definition]) ).
fof(f109,plain,
( ! [X0,X1] :
( ~ reliability(sk2,X1,sk7)
| greater(X0,X1)
| ~ reliability(sk2,X0,sk8) )
| ~ spl0_15 ),
inference(avatar_component_clause,[],[f108]) ).
fof(f110,plain,
( spl0_10
| spl0_9
| spl0_15 ),
inference(avatar_split_clause,[],[f106,f108,f75,f78]) ).
fof(f111,plain,
( ~ organization(sk2,sk7)
| ~ spl0_9 ),
inference(resolution,[],[f76,f1]) ).
fof(f112,plain,
( $false
| ~ spl0_9 ),
inference(forward_subsumption_resolution,[],[f111,f6]) ).
fof(f113,plain,
~ spl0_9,
inference(avatar_contradiction_clause,[],[f112]) ).
fof(f116,plain,
( ~ organization(sk2,sk8)
| ~ spl0_10 ),
inference(resolution,[],[f79,f1]) ).
fof(f117,plain,
( $false
| ~ spl0_10 ),
inference(forward_subsumption_resolution,[],[f116,f7]) ).
fof(f118,plain,
~ spl0_10,
inference(avatar_contradiction_clause,[],[f117]) ).
fof(f158,plain,
( ! [X0] :
( ~ reliability(sk2,X0,sk8)
| greater(X0,sk3) )
| ~ spl0_15 ),
inference(resolution,[],[f109,f9]) ).
fof(f159,plain,
( greater(sk4,sk3)
| ~ spl0_15 ),
inference(resolution,[],[f158,f10]) ).
fof(f160,plain,
( $false
| spl0_2
| ~ spl0_15 ),
inference(forward_subsumption_resolution,[],[f159,f22]) ).
fof(f161,plain,
( spl0_2
| ~ spl0_15 ),
inference(avatar_contradiction_clause,[],[f160]) ).
cnf(s1,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f23]) ).
cnf(s2,plain,
( spl0_3
| spl0_4 ),
inference(sat_conversion,[],[f44]) ).
cnf(s4,plain,
~ spl0_3,
inference(sat_conversion,[],[f53]) ).
cnf(s5,plain,
~ spl0_5,
inference(sat_conversion,[],[f58]) ).
cnf(s7,plain,
( spl0_1
| ~ spl0_4
| spl0_5
| spl0_9
| spl0_10 ),
inference(sat_conversion,[],[f80]) ).
cnf(s10,plain,
( spl0_9
| spl0_10
| spl0_15 ),
inference(sat_conversion,[],[f110]) ).
cnf(s11,plain,
~ spl0_9,
inference(sat_conversion,[],[f113]) ).
cnf(s12,plain,
~ spl0_10,
inference(sat_conversion,[],[f118]) ).
cnf(s19,plain,
( spl0_2
| ~ spl0_15 ),
inference(sat_conversion,[],[f161]) ).
cnf(s20,plain,
spl0_15,
inference(rat,[],[s10,s12,s11]) ).
cnf(s21,plain,
spl0_2,
inference(rat,[],[s19,s20]) ).
cnf(s22,plain,
( spl0_1
| ~ spl0_4
| spl0_5 ),
inference(rat,[],[s7,s12,s11]) ).
cnf(s24,plain,
spl0_4,
inference(rat,[],[s2,s4]) ).
cnf(s25,plain,
spl0_1,
inference(rat,[],[s22,s5,s24]) ).
cnf(s26,plain,
$false,
inference(rat,[],[s1,s21,s25]) ).
fof(f162,plain,
$false,
inference(avatar_sat_refutation,[],[s26]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : MGT006-1 : TPTP v9.3.1. Released v2.4.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.14/0.39 % Computer : n010.cluster.edu
% 0.14/0.39 % Model : x86_64 x86_64
% 0.14/0.39 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.14/0.39 % Memory : 8046.5625MB
% 0.14/0.39 % OS : Linux 6.8.0-71-generic
% 0.14/0.39 % CPULimit : 300
% 0.14/0.39 % WCLimit : 300
% 0.14/0.39 % DateTime : Sun Sep 27 17:16:16 UTC 2026
% 0.14/0.39 % CPUTime :
% 0.14/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.14/0.42 Running first-order theorem proving
% 0.14/0.42 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
% 1.46/1.30 % (1181716)Input is clausal, will run a generic CNF schedule.
% 1.46/1.30 % (1181721)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=3453848786:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 1.46/1.30 % (1181725)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2200023928:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 1.46/1.30 % (1181724)lrs+10_1_sil=8000:sp=occurrence:random_seed=2532202776:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 1.46/1.30 % (1181727)dis-21_1_sil=8000:lcm=predicate:random_seed=3515622115: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)
% 1.46/1.30 % (1181722)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=1378984337:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 1.46/1.30 % (1181723)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=998295095:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 1.46/1.31 % (1181726)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=53969607:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 1.46/1.31 % (1181725)Refutation not found, incomplete strategy
% 1.46/1.31 % (1181725)------------------------------
% 1.46/1.31 % (1181725)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 1.46/1.31 % (1181725)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 1.46/1.31 % (1181725)CaDiCaL version: 2.1.3
% 1.46/1.31 % (1181725)Termination reason: Refutation not found, incomplete strategy
% 1.46/1.31 % (1181725)Time elapsed: 0.001 s
% 1.46/1.31 % (1181725)Peak memory usage: 87 MB
% 1.46/1.31 % (1181724)First to succeed.
% 1.46/1.31 % (1181727)Also succeeded, but the first one will report.
% 1.46/1.31 % (1181724)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-1181716"
% 1.46/1.31 % (1181726)Also succeeded, but the first one will report.
% 1.46/1.31 % (1181725)------------------------------
% 1.46/1.31 % (1181725)------------------------------
% 1.46/1.31 % (1181724)Refutation found. Thanks to Tanya!
% 1.46/1.31 % SZS status Unsatisfiable for theBenchmark
% 1.46/1.31 % SZS output start Proof for theBenchmark
% See solution above
% 0.18/1.50 % (1181724)------------------------------
% 0.18/1.50 % (1181724)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.18/1.50 % (1181724)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.18/1.50 % (1181724)CaDiCaL version: 2.1.3
% 0.18/1.50 % (1181724)Termination reason: Refutation
% 0.18/1.50 % (1181724)Time elapsed: 0.005 s
% 0.18/1.50 % (1181724)Peak memory usage: 89 MB
% 0.18/1.50 % (1181724)Instructions burned: 5 (million)
% 0.18/1.50 % (1181724)------------------------------
% 0.18/1.50 % (1181724)------------------------------
% 0.18/1.50 % (1181716)Success in time 0.438 s
% 0.18/1.50 % Vampire exiting
%------------------------------------------------------------------------------