%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : LCL117-1 : 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 : n002.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 11:51:16 AM UTC 2026
% Result : Unsatisfiable 4.11s 1.69s
% Output : Refutation 4.11s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 5
% Syntax : Number of formulae : 22 ( 8 unt; 2 def)
% Number of atoms : 39 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 39 ( 22 ~; 15 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 4 ( 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 : 17 ( 0 sgn 17 !; 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(X2,X0)))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',yqm) ).
fof(f3,negated_conjecture,
~ is_a_theorem(equivalent(equivalent(equivalent(a,b),equivalent(a,c)),equivalent(c,b))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_qyf) ).
fof(f4,plain,
! [X2,X0,X1] :
( is_a_theorem(equivalent(equivalent(X2,X1),equivalent(X2,X0)))
| ~ is_a_theorem(equivalent(X0,X1)) ),
inference(resolution,[],[f2,f1]) ).
fof(f5,plain,
! [X2,X0,X1] :
( is_a_theorem(equivalent(X2,X0))
| ~ is_a_theorem(equivalent(X2,X1))
| ~ is_a_theorem(equivalent(X0,X1)) ),
inference(resolution,[],[f4,f1]) ).
fof(f6,plain,
! [X0] :
( ~ is_a_theorem(equivalent(equivalent(equivalent(a,b),equivalent(a,c)),X0))
| ~ is_a_theorem(equivalent(equivalent(c,b),X0)) ),
inference(resolution,[],[f5,f3]) ).
fof(f10,plain,
! [X0,X1] :
( ~ is_a_theorem(equivalent(equivalent(c,b),X0))
| ~ is_a_theorem(equivalent(equivalent(equivalent(a,b),equivalent(a,c)),X1))
| ~ is_a_theorem(equivalent(X0,X1)) ),
inference(resolution,[],[f6,f5]) ).
fof(f31,plain,
! [X0] :
( ~ is_a_theorem(equivalent(equivalent(c,b),equivalent(equivalent(a,b),equivalent(a,c))))
| ~ is_a_theorem(equivalent(equivalent(equivalent(a,b),equivalent(a,c)),X0)) ),
inference(factoring,[],[f10]) ).
fof(f33,definition,
( spl0_1
<=> ! [X0] : ~ is_a_theorem(equivalent(equivalent(equivalent(a,b),equivalent(a,c)),X0)) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f34,plain,
( ! [X0] : ~ is_a_theorem(equivalent(equivalent(equivalent(a,b),equivalent(a,c)),X0))
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f33]) ).
fof(f36,definition,
( spl0_2
<=> is_a_theorem(equivalent(equivalent(c,b),equivalent(equivalent(a,b),equivalent(a,c)))) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f37,plain,
( ~ is_a_theorem(equivalent(equivalent(c,b),equivalent(equivalent(a,b),equivalent(a,c))))
| spl0_2 ),
inference(avatar_component_clause,[],[f36]) ).
fof(f38,plain,
( spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f31,f36,f33]) ).
fof(f39,plain,
( $false
| spl0_2 ),
inference(resolution,[],[f37,f2]) ).
fof(f42,plain,
spl0_2,
inference(avatar_contradiction_clause,[],[f39]) ).
fof(f43,plain,
( $false
| ~ spl0_1 ),
inference(resolution,[],[f34,f2]) ).
fof(f47,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f43]) ).
cnf(s1,plain,
( spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f38]) ).
cnf(s2,plain,
spl0_2,
inference(sat_conversion,[],[f42]) ).
cnf(s3,plain,
~ spl0_1,
inference(sat_conversion,[],[f47]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s2,s3]) ).
fof(f48,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : LCL117-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.16/0.40 % Computer : n002.cluster.edu
% 0.16/0.40 % Model : x86_64 x86_64
% 0.16/0.40 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.16/0.40 % Memory : 8046.5625MB
% 0.16/0.40 % OS : Linux 6.8.0-71-generic
% 0.16/0.40 % CPULimit : 300
% 0.16/0.40 % WCLimit : 300
% 0.16/0.40 % DateTime : Sun Sep 27 15:25:36 UTC 2026
% 0.16/0.41 % CPUTime :
% 0.16/0.41 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.16/0.45 Running first-order theorem proving
% 0.16/0.45 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
% 4.11/1.69 % (3667618)Input is clausal, will run a generic CNF schedule.
% 4.11/1.69 % (3667623)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=4006339920:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 4.11/1.69 % (3667629)dis-21_1_sil=8000:lcm=predicate:random_seed=2956155199: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)
% 4.11/1.69 % (3667629)First to succeed.
% 4.11/1.69 % (3667629)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3667618"
% 4.11/1.69 % (3667625)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=3025103202:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 4.11/1.69 % (3667627)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=245190902:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 4.11/1.69 % (3667626)lrs+10_1_sil=8000:sp=occurrence:random_seed=2100851539:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 4.11/1.69 % (3667628)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=2224201088:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 4.11/1.69 % (3667624)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=2522391131:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 4.11/1.69 % (3667628)Also succeeded, but the first one will report.
% 4.11/1.69 % (3667626)Also succeeded, but the first one will report.
% 4.11/1.69 % (3667627)Also succeeded, but the first one will report.
% 4.11/1.69 % (3667629)Refutation found. Thanks to Tanya!
% 4.11/1.69 % SZS status Unsatisfiable for theBenchmark
% 4.11/1.69 % SZS output start Proof for theBenchmark
% See solution above
% 4.11/1.69 % (3667629)------------------------------
% 4.11/1.69 % (3667629)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 4.11/1.69 % (3667629)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 4.11/1.69 % (3667629)CaDiCaL version: 2.1.3
% 4.11/1.69 % (3667629)Termination reason: Refutation
% 4.11/1.69 % (3667629)Time elapsed: 0.003 s
% 4.11/1.69 % (3667629)Peak memory usage: 89 MB
% 4.11/1.69 % (3667629)Instructions burned: 2 (million)
% 4.11/1.69 % (3667629)------------------------------
% 4.11/1.69 % (3667629)------------------------------
% 4.11/1.69 % (3667618)Success in time 0.49 s
% 4.11/1.69 % Vampire exiting
%------------------------------------------------------------------------------