%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN224-1 : TPTP v9.3.1. Released v1.1.0.
% 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 01:49:57 PM UTC 2026
% Result : Unsatisfiable 3.39s 1.31s
% Output : Refutation 3.39s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 13
% Syntax : Number of formulae : 40 ( 13 unt; 5 def)
% Number of atoms : 71 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 61 ( 30 ~; 26 |; 0 &)
% ( 5 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 13 ( 12 usr; 6 prp; 0-3 aty)
% Number of functors : 3 ( 3 usr; 3 con; 0-0 aty)
% Number of variables : 10 ( 0 sgn 10 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f7,axiom,
n0(d,b),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',axiom_7) ).
fof(f14,axiom,
! [X0] : p0(b,X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',axiom_14) ).
fof(f39,axiom,
! [X0,X1] :
( ~ n0(X1,X0)
| k1(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rule_001) ).
fof(f113,axiom,
( p1(a,a,a)
| ~ p0(b,a) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rule_075) ).
fof(f174,axiom,
( m2(b)
| ~ k1(b) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rule_136) ).
fof(f175,axiom,
! [X2,X0,X1] :
( ~ p1(X1,X2,X0)
| n2(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rule_137) ).
fof(f255,axiom,
! [X0] :
( l3(X0,X0)
| ~ n2(X0)
| ~ m2(b) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rule_217) ).
fof(f369,negated_conjecture,
! [X0] : ~ l3(a,X0),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_this) ).
fof(f609,definition,
( spl0_70
<=> p1(a,a,a) ),
introduced(definition,[new_symbols(definition,[spl0_70])],[avatar_definition]) ).
fof(f610,plain,
( p1(a,a,a)
| ~ spl0_70 ),
inference(avatar_component_clause,[],[f609]) ).
fof(f662,definition,
( spl0_84
<=> k1(b) ),
introduced(definition,[new_symbols(definition,[spl0_84])],[avatar_definition]) ).
fof(f663,plain,
( ~ k1(b)
| spl0_84 ),
inference(avatar_component_clause,[],[f662]) ).
fof(f665,definition,
( spl0_85
<=> m2(b) ),
introduced(definition,[new_symbols(definition,[spl0_85])],[avatar_definition]) ).
fof(f667,plain,
( ~ spl0_84
| spl0_85 ),
inference(avatar_split_clause,[],[f174,f665,f662]) ).
fof(f1272,definition,
( spl0_255
<=> ! [X0] :
( l3(X0,X0)
| ~ n2(X0) ) ),
introduced(definition,[new_symbols(definition,[spl0_255])],[avatar_definition]) ).
fof(f1273,plain,
( ! [X0] :
( l3(X0,X0)
| ~ n2(X0) )
| ~ spl0_255 ),
inference(avatar_component_clause,[],[f1272]) ).
fof(f1274,plain,
( ~ spl0_85
| spl0_255 ),
inference(avatar_split_clause,[],[f255,f1272,f665]) ).
fof(f1347,definition,
( spl0_276
<=> p0(b,a) ),
introduced(definition,[new_symbols(definition,[spl0_276])],[avatar_definition]) ).
fof(f1348,plain,
( ~ p0(b,a)
| spl0_276 ),
inference(avatar_component_clause,[],[f1347]) ).
fof(f1349,plain,
( ~ spl0_276
| spl0_70 ),
inference(avatar_split_clause,[],[f113,f609,f1347]) ).
fof(f1439,plain,
( $false
| spl0_276 ),
inference(forward_subsumption_resolution,[],[f1348,f14]) ).
fof(f1440,plain,
spl0_276,
inference(avatar_contradiction_clause,[],[f1439]) ).
fof(f1481,plain,
k1(b),
inference(resolution,[],[f39,f7]) ).
fof(f1498,plain,
( $false
| spl0_84 ),
inference(forward_subsumption_resolution,[],[f1481,f663]) ).
fof(f1499,plain,
spl0_84,
inference(avatar_contradiction_clause,[],[f1498]) ).
fof(f1596,plain,
( ~ n2(a)
| ~ spl0_255 ),
inference(resolution,[],[f1273,f369]) ).
fof(f1597,plain,
( n2(a)
| ~ spl0_70 ),
inference(resolution,[],[f175,f610]) ).
fof(f1604,plain,
( $false
| ~ spl0_70
| ~ spl0_255 ),
inference(forward_subsumption_resolution,[],[f1597,f1596]) ).
fof(f1605,plain,
( ~ spl0_70
| ~ spl0_255 ),
inference(avatar_contradiction_clause,[],[f1604]) ).
cnf(s42,plain,
( ~ spl0_84
| spl0_85 ),
inference(sat_conversion,[],[f667]) ).
cnf(s136,plain,
( ~ spl0_85
| spl0_255 ),
inference(sat_conversion,[],[f1274]) ).
cnf(s147,plain,
( spl0_70
| ~ spl0_276 ),
inference(sat_conversion,[],[f1349]) ).
cnf(s178,plain,
spl0_276,
inference(sat_conversion,[],[f1440]) ).
cnf(s203,plain,
spl0_84,
inference(sat_conversion,[],[f1499]) ).
cnf(s238,plain,
( ~ spl0_70
| ~ spl0_255 ),
inference(sat_conversion,[],[f1605]) ).
cnf(s242,plain,
spl0_70,
inference(rat,[],[s147,s178]) ).
cnf(s243,plain,
~ spl0_255,
inference(rat,[],[s238,s242]) ).
cnf(s249,plain,
~ spl0_85,
inference(rat,[],[s136,s243]) ).
cnf(s299,plain,
$false,
inference(rat,[],[s42,s249,s203]) ).
fof(f1606,plain,
$false,
inference(avatar_sat_refutation,[],[s299]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYN224-1 : TPTP v9.3.1. Released v1.1.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.17 % Computer : n016.cluster.edu
% 0.12/0.17 % Model : x86_64 x86_64
% 0.12/0.17 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.17 % Memory : 8046.5625MB
% 0.12/0.17 % OS : Linux 6.8.0-71-generic
% 0.12/0.17 % CPULimit : 300
% 0.12/0.17 % WCLimit : 300
% 0.12/0.17 % DateTime : Mon Sep 28 15:43:33 UTC 2026
% 0.12/0.18 % CPUTime :
% 0.12/0.18 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.12/0.21 Running first-order theorem proving
% 0.12/0.21 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
% 3.39/1.31 % (3719344)Input is clausal, will run a generic CNF schedule.
% 3.39/1.31 % (3719371)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2767756880:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.39/1.31 % (3719371)First to succeed.
% 3.39/1.31 % (3719371)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3719344"
% 3.39/1.31 % (3719372)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=893805903:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.39/1.31 % (3719369)lrs+10_1_sil=8000:sp=occurrence:random_seed=3824709136:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.39/1.31 % (3719367)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2863800969:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.39/1.31 % (3719366)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=3465489101:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.39/1.31 % (3719372)Also succeeded, but the first one will report.
% 3.39/1.31 % (3719368)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=4244044997:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.39/1.31 % (3719369)Also succeeded, but the first one will report.
% 3.39/1.31 % (3719373)dis-21_1_sil=8000:lcm=predicate:random_seed=427973796: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)
% 3.39/1.31 % (3719373)Also succeeded, but the first one will report.
% 3.39/1.31 % (3719371)Refutation found. Thanks to Tanya!
% 3.39/1.31 % SZS status Unsatisfiable for theBenchmark
% 3.39/1.31 % SZS output start Proof for theBenchmark
% See solution above
% 3.39/1.31 % (3719371)------------------------------
% 3.39/1.31 % (3719371)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.39/1.31 % (3719371)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.39/1.31 % (3719371)CaDiCaL version: 2.1.3
% 3.39/1.31 % (3719371)Termination reason: Refutation
% 3.39/1.31 % (3719371)Time elapsed: 0.012 s
% 3.39/1.31 % (3719371)Peak memory usage: 90 MB
% 3.39/1.31 % (3719371)Instructions burned: 19 (million)
% 3.39/1.31 % (3719371)------------------------------
% 3.39/1.31 % (3719371)------------------------------
% 3.39/1.31 % (3719344)Success in time 0.388 s
% 3.39/1.31 % Vampire exiting
%------------------------------------------------------------------------------