%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : LCL023-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n017.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 11:50:57 AM UTC 2026
% Result : Unsatisfiable 3.73s 6.56s
% Output : Refutation 3.73s
% Verified :
% SZS Type : Refutation
% Derivation depth : 17
% Number of leaves : 5
% Syntax : Number of formulae : 43 ( 17 unt; 2 def)
% Number of atoms : 73 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 71 ( 41 ~; 28 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 9 ( 4 avg)
% Maximal term depth : 6 ( 2 avg)
% Number of predicates : 4 ( 3 usr; 3 prp; 0-1 aty)
% Number of functors : 4 ( 4 usr; 3 con; 0-2 aty)
% Number of variables : 79 ( 0 sgn 79 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X0,X1] :
( ~ is_a_theorem(equivalent(X0,X1))
| ~ is_a_theorem(X0)
| is_a_theorem(X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',condensed_detachment) ).
fof(f2,axiom,
! [X2,X0,X1] : is_a_theorem(equivalent(equivalent(X0,X1),equivalent(equivalent(X2,X1),equivalent(X0,X2)))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',yql) ).
fof(f3,negated_conjecture,
~ is_a_theorem(equivalent(equivalent(a,equivalent(b,c)),equivalent(equivalent(a,b),c))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_ec_2) ).
fof(f4,plain,
! [X2,X0,X1] :
( ~ is_a_theorem(equivalent(X0,X1))
| is_a_theorem(equivalent(equivalent(X2,X1),equivalent(X0,X2))) ),
inference(resolution,[],[f2,f1]) ).
fof(f5,plain,
! [X2,X3,X0,X1] : is_a_theorem(equivalent(equivalent(X0,equivalent(equivalent(X1,X2),equivalent(X3,X1))),equivalent(equivalent(X3,X2),X0))),
inference(resolution,[],[f4,f2]) ).
fof(f6,plain,
! [X2,X3,X0,X1,X4] : is_a_theorem(equivalent(equivalent(X0,equivalent(equivalent(X1,X2),X3)),equivalent(equivalent(X3,equivalent(equivalent(X4,X2),equivalent(X1,X4))),X0))),
inference(resolution,[],[f5,f4]) ).
fof(f7,plain,
! [X2,X3,X0,X1] :
( ~ is_a_theorem(equivalent(X0,equivalent(equivalent(X1,X2),equivalent(X3,X1))))
| is_a_theorem(equivalent(equivalent(X3,X2),X0)) ),
inference(resolution,[],[f5,f1]) ).
fof(f8,plain,
! [X0,X1] : is_a_theorem(equivalent(equivalent(X0,X1),equivalent(X0,X1))),
inference(resolution,[],[f7,f2]) ).
fof(f9,plain,
! [X2,X3,X0,X1] : is_a_theorem(equivalent(equivalent(X0,X1),equivalent(equivalent(X0,X2),equivalent(equivalent(X3,X1),equivalent(X2,X3))))),
inference(resolution,[],[f7,f5]) ).
fof(f11,plain,
! [X2,X0,X1] : is_a_theorem(equivalent(equivalent(X0,equivalent(X1,X2)),equivalent(equivalent(X1,X2),X0))),
inference(resolution,[],[f8,f4]) ).
fof(f15,plain,
! [X2,X3,X0,X1,X4] :
( is_a_theorem(equivalent(equivalent(X3,equivalent(equivalent(X4,X2),equivalent(X1,X4))),X0))
| ~ is_a_theorem(equivalent(X0,equivalent(equivalent(X1,X2),X3))) ),
inference(resolution,[],[f6,f1]) ).
fof(f16,plain,
! [X2,X0,X1] : is_a_theorem(equivalent(equivalent(X0,X1),equivalent(equivalent(X0,X2),equivalent(X2,X1)))),
inference(resolution,[],[f11,f7]) ).
fof(f19,plain,
! [X2,X0,X1] : is_a_theorem(equivalent(equivalent(equivalent(X0,X1),X2),equivalent(equivalent(X2,X0),X1))),
inference(resolution,[],[f9,f7]) ).
fof(f21,plain,
! [X2,X3,X0,X1] :
( is_a_theorem(equivalent(equivalent(X0,X2),equivalent(equivalent(X3,X1),equivalent(X2,X3))))
| ~ is_a_theorem(equivalent(X0,X1)) ),
inference(resolution,[],[f9,f1]) ).
fof(f24,plain,
! [X2,X0,X1] :
( is_a_theorem(equivalent(equivalent(X2,X0),X1))
| ~ is_a_theorem(equivalent(equivalent(X0,X1),X2)) ),
inference(resolution,[],[f19,f1]) ).
fof(f28,plain,
! [X0,X1] : is_a_theorem(equivalent(equivalent(X0,X0),equivalent(X1,X1))),
inference(resolution,[],[f16,f7]) ).
fof(f32,plain,
! [X2,X3,X0,X1,X4] :
( is_a_theorem(X0)
| ~ is_a_theorem(equivalent(X3,equivalent(equivalent(X4,X2),equivalent(X1,X4))))
| ~ is_a_theorem(equivalent(X0,equivalent(equivalent(X1,X2),X3))) ),
inference(resolution,[],[f15,f1]) ).
fof(f36,plain,
! [X0,X1] :
( ~ is_a_theorem(equivalent(X0,X0))
| is_a_theorem(equivalent(X1,X1)) ),
inference(resolution,[],[f28,f1]) ).
fof(f38,definition,
( spl0_1
<=> ! [X1] : is_a_theorem(equivalent(X1,X1)) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f39,plain,
( ! [X1] : is_a_theorem(equivalent(X1,X1))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f38]) ).
fof(f41,definition,
( spl0_2
<=> ! [X0] : ~ is_a_theorem(equivalent(X0,X0)) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f42,plain,
( ! [X0] : ~ is_a_theorem(equivalent(X0,X0))
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f41]) ).
fof(f43,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f36,f41,f38]) ).
fof(f51,plain,
( ! [X2,X3,X0,X1] : ~ is_a_theorem(equivalent(equivalent(X0,equivalent(equivalent(X1,X2),equivalent(X3,X1))),equivalent(equivalent(X3,X2),X0)))
| ~ spl0_2 ),
inference(resolution,[],[f42,f15]) ).
fof(f56,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f51,f5]) ).
fof(f57,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f56]) ).
fof(f60,plain,
! [X2,X3,X0,X1] :
( is_a_theorem(equivalent(equivalent(X3,X1),equivalent(X2,X3)))
| ~ is_a_theorem(equivalent(X0,X2))
| ~ is_a_theorem(equivalent(X0,X1)) ),
inference(resolution,[],[f21,f1]) ).
fof(f61,plain,
( ! [X0,X1] : is_a_theorem(equivalent(equivalent(X0,X1),equivalent(X1,X0)))
| ~ spl0_1 ),
inference(resolution,[],[f39,f4]) ).
fof(f69,plain,
( ! [X0,X1] :
( is_a_theorem(equivalent(X1,X0))
| ~ is_a_theorem(equivalent(X0,X1)) )
| ~ spl0_1 ),
inference(resolution,[],[f61,f1]) ).
fof(f81,plain,
! [X2,X3,X0,X1] :
( ~ is_a_theorem(equivalent(equivalent(equivalent(a,equivalent(b,c)),equivalent(equivalent(a,b),c)),equivalent(equivalent(X3,X2),X0)))
| ~ is_a_theorem(equivalent(X0,equivalent(equivalent(X1,X2),equivalent(X3,X1)))) ),
inference(resolution,[],[f32,f3]) ).
fof(f95,plain,
! [X0] : ~ is_a_theorem(equivalent(equivalent(equivalent(a,b),c),equivalent(equivalent(X0,equivalent(b,c)),equivalent(a,X0)))),
inference(resolution,[],[f81,f8]) ).
fof(f173,plain,
! [X0] :
( ~ is_a_theorem(equivalent(X0,c))
| ~ is_a_theorem(equivalent(X0,equivalent(b,equivalent(b,c)))) ),
inference(resolution,[],[f60,f95]) ).
fof(f182,plain,
( ~ is_a_theorem(equivalent(c,equivalent(b,equivalent(b,c))))
| ~ spl0_1 ),
inference(resolution,[],[f173,f39]) ).
fof(f189,plain,
( ~ is_a_theorem(equivalent(equivalent(b,equivalent(b,c)),c))
| ~ spl0_1 ),
inference(resolution,[],[f182,f69]) ).
fof(f198,plain,
( ~ is_a_theorem(equivalent(equivalent(equivalent(b,c),c),b))
| ~ spl0_1 ),
inference(resolution,[],[f189,f24]) ).
fof(f204,plain,
( ~ is_a_theorem(equivalent(equivalent(c,b),equivalent(b,c)))
| ~ spl0_1 ),
inference(resolution,[],[f198,f24]) ).
fof(f207,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f204,f61]) ).
fof(f208,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f207]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f43]) ).
cnf(s6,plain,
~ spl0_2,
inference(sat_conversion,[],[f57]) ).
cnf(s7,plain,
~ spl0_1,
inference(sat_conversion,[],[f208]) ).
cnf(s8,plain,
$false,
inference(rat,[],[s1,s6,s7]) ).
fof(f209,plain,
$false,
inference(avatar_sat_refutation,[],[s8]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.04 % Problem : LCL023-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.08 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.18/5.44 % Computer : n017.cluster.edu
% 0.18/5.44 % Model : x86_64 x86_64
% 0.18/5.44 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.18/5.44 % Memory : 8046.5625MB
% 0.18/5.44 % OS : Linux 6.8.0-71-generic
% 0.18/5.44 % CPULimit : 300
% 0.18/5.44 % WCLimit : 300
% 0.18/5.44 % DateTime : Sun Sep 27 15:12:55 UTC 2026
% 0.18/5.45 % CPUTime :
% 0.18/5.45 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.18/5.48 Running first-order theorem proving
% 0.18/5.48 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
% 3.73/6.56 % (2711274)Input is clausal, will run a generic CNF schedule.
% 3.73/6.56 % (2711280)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2574951149:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.73/6.56 % (2711279)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=2376039403:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.73/6.56 % (2711281)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=3855491616:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.73/6.56 % (2711284)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1300234643:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.73/6.56 % (2711283)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=750857205:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.73/6.56 % (2711285)dis-21_1_sil=8000:lcm=predicate:random_seed=482767804: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)
% 3.73/6.56 % (2711282)lrs+10_1_sil=8000:sp=occurrence:random_seed=2950641575:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.73/6.56 % (2711284)First to succeed.
% 3.73/6.56 % (2711284)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-2711274"
% 3.73/6.56 % (2711282)Also succeeded, but the first one will report.
% 3.73/6.56 % (2711283)Instruction limit reached!
% 3.73/6.56 % (2711283)------------------------------
% 3.73/6.56 % (2711283)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.73/6.56 % (2711283)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.73/6.56 % (2711283)CaDiCaL version: 2.1.3
% 3.73/6.56 % (2711283)Termination reason: Instruction limit
% 3.73/6.56 % (2711283)Termination phase: Saturation
% 3.73/6.56 % (2711283)Time elapsed: 0.070 s
% 3.73/6.56 % (2711283)Peak memory usage: 88 MB
% 3.73/6.56 % (2711283)Instructions burned: 115 (million)
% 3.73/6.56 % (2711285)Instruction limit reached!
% 3.73/6.56 % (2711285)------------------------------
% 3.73/6.56 % (2711285)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.73/6.56 % (2711285)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.73/6.56 % (2711285)CaDiCaL version: 2.1.3
% 3.73/6.56 % (2711285)Termination reason: Instruction limit
% 3.73/6.56 % (2711285)Termination phase: Saturation
% 3.73/6.56 % (2711285)Time elapsed: 0.072 s
% 3.73/6.56 % (2711285)Peak memory usage: 88 MB
% 3.73/6.56 % (2711285)Instructions burned: 118 (million)
% 3.73/6.56 % (2711294)ott-1010_1_to=lpo:sil=16000:sos=on:spb=units:urr=on:bce=on:br=off:random_seed=1259691385: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)
% 3.73/6.56 % (2711293)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=2928194836:i=143:sd=2:aac=none:ss=axioms:sgt=16_2997 on theBenchmark for (2997ds/143Mi)
% 3.73/6.56 % (2711293)Refutation not found, incomplete strategy
% 3.73/6.56 % (2711293)------------------------------
% 3.73/6.56 % (2711293)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.73/6.56 % (2711293)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.73/6.56 % (2711293)CaDiCaL version: 2.1.3
% 3.73/6.56 % (2711293)Termination reason: Refutation not found, incomplete strategy
% 3.73/6.56 % (2711293)Time elapsed: 0.001 s
% 3.73/6.56 % (2711293)Peak memory usage: 87 MB
% 3.73/6.56 % (2711284)Refutation found. Thanks to Tanya!
% 3.73/6.56 % SZS status Unsatisfiable for theBenchmark
% 3.73/6.56 % SZS output start Proof for theBenchmark
% See solution above
% 3.73/6.56 % (2711284)------------------------------
% 3.73/6.56 % (2711284)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.73/6.56 % (2711284)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.73/6.56 % (2711284)CaDiCaL version: 2.1.3
% 3.73/6.56 % (2711284)Termination reason: Refutation
% 3.73/6.56 % (2711284)Time elapsed: 0.009 s
% 3.73/6.56 % (2711284)Peak memory usage: 89 MB
% 3.73/6.56 % (2711284)Instructions burned: 10 (million)
% 3.73/6.56 % (2711284)------------------------------
% 3.73/6.56 % (2711284)------------------------------
% 3.73/6.56 % (2711274)Success in time 0.437 s
% 3.73/6.56 % Vampire exiting
%------------------------------------------------------------------------------