%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN166-1 : 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 : n018.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 01:49:49 PM UTC 2026
% Result : Unsatisfiable 3.81s 1.32s
% Output : Refutation 3.81s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 12
% Syntax : Number of formulae : 31 ( 16 unt; 4 def)
% Number of atoms : 50 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 42 ( 23 ~; 15 |; 0 &)
% ( 4 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 8 ( 2 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 9 ( 8 usr; 5 prp; 0-3 aty)
% Number of functors : 2 ( 2 usr; 2 con; 0-0 aty)
% Number of variables : 7 ( 0 sgn 7 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f9,axiom,
r0(b),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',axiom_9) ).
fof(f12,axiom,
! [X0] : m0(a,X0,a),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',axiom_12) ).
fof(f20,axiom,
l0(a),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',axiom_20) ).
fof(f38,axiom,
m0(b,a,a),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',axiom_38) ).
fof(f120,axiom,
! [X2,X3,X0,X1] :
( p1(X0,X1,X2)
| ~ m0(X2,X0,X3)
| ~ p1(X2,X0,X3) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rule_082) ).
fof(f125,axiom,
( p1(a,b,a)
| ~ r0(b)
| ~ p1(a,a,a) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rule_087) ).
fof(f126,axiom,
( p1(a,a,a)
| ~ l0(a) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rule_088) ).
fof(f369,negated_conjecture,
~ p1(a,b,b),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_this) ).
fof(f717,definition,
( spl0_89
<=> r0(b) ),
introduced(definition,[new_symbols(definition,[spl0_89])],[avatar_definition]) ).
fof(f1276,definition,
( spl0_227
<=> l0(a) ),
introduced(definition,[new_symbols(definition,[spl0_227])],[avatar_definition]) ).
fof(f1280,definition,
( spl0_228
<=> p1(a,a,a) ),
introduced(definition,[new_symbols(definition,[spl0_228])],[avatar_definition]) ).
fof(f1283,plain,
( ~ spl0_227
| spl0_228 ),
inference(avatar_split_clause,[],[f126,f1280,f1276]) ).
fof(f1285,definition,
( spl0_229
<=> p1(a,b,a) ),
introduced(definition,[new_symbols(definition,[spl0_229])],[avatar_definition]) ).
fof(f1287,plain,
( p1(a,b,a)
| ~ spl0_229 ),
inference(avatar_component_clause,[],[f1285]) ).
fof(f1288,plain,
( ~ spl0_228
| ~ spl0_89
| spl0_229 ),
inference(avatar_split_clause,[],[f125,f1285,f717,f1280]) ).
fof(f1560,plain,
spl0_227,
inference(avatar_split_clause,[],[f20,f1276]) ).
fof(f1565,plain,
spl0_89,
inference(avatar_split_clause,[],[f9,f717]) ).
fof(f1612,plain,
! [X0] :
( ~ m0(b,a,X0)
| ~ p1(b,a,X0) ),
inference(resolution,[],[f120,f369]) ).
fof(f1614,plain,
~ p1(b,a,a),
inference(resolution,[],[f1612,f38]) ).
fof(f1615,plain,
! [X0] :
( ~ m0(a,b,X0)
| ~ p1(a,b,X0) ),
inference(resolution,[],[f1614,f120]) ).
fof(f1616,plain,
~ p1(a,b,a),
inference(resolution,[],[f1615,f12]) ).
fof(f1617,plain,
( $false
| ~ spl0_229 ),
inference(forward_subsumption_resolution,[],[f1616,f1287]) ).
fof(f1618,plain,
~ spl0_229,
inference(avatar_contradiction_clause,[],[f1617]) ).
cnf(s111,plain,
( ~ spl0_227
| spl0_228 ),
inference(sat_conversion,[],[f1283]) ).
cnf(s112,plain,
( ~ spl0_89
| ~ spl0_228
| spl0_229 ),
inference(sat_conversion,[],[f1288]) ).
cnf(s160,plain,
spl0_227,
inference(sat_conversion,[],[f1560]) ).
cnf(s165,plain,
spl0_89,
inference(sat_conversion,[],[f1565]) ).
cnf(s187,plain,
~ spl0_229,
inference(sat_conversion,[],[f1618]) ).
cnf(s215,plain,
~ spl0_228,
inference(rat,[],[s112,s187,s165]) ).
cnf(s217,plain,
$false,
inference(rat,[],[s111,s215,s160]) ).
fof(f1619,plain,
$false,
inference(avatar_sat_refutation,[],[s217]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYN166-1 : TPTP v9.3.1. Released v1.1.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.19 % Computer : n018.cluster.edu
% 0.09/0.19 % Model : x86_64 x86_64
% 0.09/0.19 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.19 % Memory : 8046.5625MB
% 0.09/0.19 % OS : Linux 6.8.0-71-generic
% 0.09/0.19 % CPULimit : 300
% 0.09/0.19 % WCLimit : 300
% 0.09/0.19 % DateTime : Mon Sep 28 15:39:40 UTC 2026
% 0.09/0.20 % CPUTime :
% 0.09/0.20 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.23 Running first-order theorem proving
% 0.09/0.23 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
% 3.81/1.32 % (3490777)Input is clausal, will run a generic CNF schedule.
% 3.81/1.32 % (3490788)dis-21_1_sil=8000:lcm=predicate:random_seed=3022494530: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)
% 3.81/1.32 % (3490788)Instruction limit reached!
% 3.81/1.32 % (3490788)------------------------------
% 3.81/1.32 % (3490788)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.81/1.32 % (3490788)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.81/1.32 % (3490788)CaDiCaL version: 2.1.3
% 3.81/1.32 % (3490788)Termination reason: Instruction limit
% 3.81/1.32 % (3490788)Termination phase: Saturation
% 3.81/1.32 % (3490788)Time elapsed: 0.030 s
% 3.81/1.32 % (3490788)Peak memory usage: 89 MB
% 3.81/1.32 % (3490788)Instructions burned: 118 (million)
% 3.81/1.32 % (3490785)lrs+10_1_sil=8000:sp=occurrence:random_seed=3934421146:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.81/1.32 % (3490783)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=968163461:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.81/1.32 % (3490782)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=1862072395:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.81/1.32 % (3490786)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=3440600318:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.81/1.32 % (3490787)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=332227083:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.81/1.32 % (3490784)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1623509866:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.81/1.32 % (3490785)Refutation not found, incomplete strategy
% 3.81/1.32 % (3490785)------------------------------
% 3.81/1.32 % (3490785)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.81/1.32 % (3490785)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.81/1.32 % (3490785)CaDiCaL version: 2.1.3
% 3.81/1.32 % (3490785)Termination reason: Refutation not found, incomplete strategy
% 3.81/1.32 % (3490785)Time elapsed: 0.004 s
% 3.81/1.32 % (3490785)Peak memory usage: 88 MB
% 3.81/1.32 % (3490785)Instructions burned: 4 (million)
% 3.81/1.32 % (3490787)First to succeed.
% 3.81/1.32 % (3490787)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3490777"
% 3.81/1.32 % (3490786)Also succeeded, but the first one will report.
% 3.81/1.32 % (3490790)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=385437902:i=143:sd=2:aac=none:ss=axioms:sgt=16_2998 on theBenchmark for (2998ds/143Mi)
% 3.81/1.32 % (3490790)Refutation not found, incomplete strategy
% 3.81/1.32 % (3490790)------------------------------
% 3.81/1.32 % (3490790)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.81/1.32 % (3490790)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.81/1.32 % (3490790)CaDiCaL version: 2.1.3
% 3.81/1.32 % (3490790)Termination reason: Refutation not found, incomplete strategy
% 3.81/1.32 % (3490790)Time elapsed: 0.001 s
% 3.81/1.32 % (3490790)Peak memory usage: 87 MB
% 3.81/1.32 % (3490790)Instructions burned: 1 (million)
% 3.81/1.32 % (3490785)------------------------------
% 3.81/1.32 % (3490785)------------------------------
% 3.81/1.32 % (3490790)------------------------------
% 3.81/1.32 % (3490790)------------------------------
% 3.81/1.32 % (3490787)Refutation found. Thanks to Tanya!
% 3.81/1.32 % SZS status Unsatisfiable for theBenchmark
% 3.81/1.32 % SZS output start Proof for theBenchmark
% See solution above
% 3.81/1.32 % (3490787)------------------------------
% 3.81/1.32 % (3490787)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.81/1.32 % (3490787)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.81/1.32 % (3490787)CaDiCaL version: 2.1.3
% 3.81/1.32 % (3490787)Termination reason: Refutation
% 3.81/1.32 % (3490787)Time elapsed: 0.012 s
% 3.81/1.32 % (3490787)Peak memory usage: 90 MB
% 3.81/1.32 % (3490787)Instructions burned: 16 (million)
% 3.81/1.32 % (3490787)------------------------------
% 3.81/1.32 % (3490787)------------------------------
% 3.81/1.32 % (3490777)Success in time 0.453 s
% 3.81/1.32 % Vampire exiting
%------------------------------------------------------------------------------