%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN356+1 : TPTP v9.3.1. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n014.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 01:50:21 PM UTC 2026
% Result : Theorem 0.18s 1.14s
% Output : Refutation 0.18s
% Verified :
% SZS Type : Refutation
% Derivation depth : 12
% Number of leaves : 3
% Syntax : Number of formulae : 26 ( 12 unt; 2 def)
% Number of atoms : 64 ( 0 equ)
% Maximal formula atoms : 8 ( 2 avg)
% Number of connectives : 57 ( 19 ~; 14 |; 16 &)
% ( 2 <=>; 6 =>; 0 <=; 0 <~>)
% Maximal formula depth : 9 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 5 ( 4 usr; 3 prp; 0-2 aty)
% Number of functors : 2 ( 2 usr; 2 con; 0-0 aty)
% Number of variables : 22 ( 0 sgn 22 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,conjecture,
( ( big_r(a,b)
& ! [X0,X1] :
( big_r(X0,X1)
=> ( big_r(X1,X0)
& big_q(X0,X1) ) )
& ! [X2,X3] :
( big_q(X2,X3)
=> big_q(X2,X2) ) )
=> ( big_q(a,a)
& big_q(b,b) ) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',x2107) ).
fof(f2,negated_conjecture,
~ ( ( big_r(a,b)
& ! [X0,X1] :
( big_r(X0,X1)
=> ( big_r(X1,X0)
& big_q(X0,X1) ) )
& ! [X2,X3] :
( big_q(X2,X3)
=> big_q(X2,X2) ) )
=> ( big_q(a,a)
& big_q(b,b) ) ),
inference(negated_conjecture,[status(cth)],[f1]) ).
fof(f3,plain,
( ( ~ big_q(a,a)
| ~ big_q(b,b) )
& big_r(a,b)
& ! [X0,X1] :
( ( big_r(X1,X0)
& big_q(X0,X1) )
| ~ big_r(X0,X1) )
& ! [X2,X3] :
( big_q(X2,X2)
| ~ big_q(X2,X3) ) ),
inference(ennf_transformation,[],[f2]) ).
fof(f4,plain,
( ( ~ big_q(a,a)
| ~ big_q(b,b) )
& big_r(a,b)
& ! [X0,X1] :
( ( big_r(X1,X0)
& big_q(X0,X1) )
| ~ big_r(X0,X1) )
& ! [X2,X3] :
( big_q(X2,X2)
| ~ big_q(X2,X3) ) ),
inference(flattening,[],[f3]) ).
fof(f5,plain,
! [X2,X3] :
( ~ big_q(X2,X3)
| big_q(X2,X2) ),
inference(cnf_transformation,[],[f4]) ).
fof(f6,plain,
! [X0,X1] :
( ~ big_r(X0,X1)
| big_q(X0,X1) ),
inference(cnf_transformation,[],[f4]) ).
fof(f7,plain,
! [X0,X1] :
( ~ big_r(X0,X1)
| big_r(X1,X0) ),
inference(cnf_transformation,[],[f4]) ).
fof(f8,plain,
big_r(a,b),
inference(cnf_transformation,[],[f4]) ).
fof(f9,plain,
( ~ big_q(a,a)
| ~ big_q(b,b) ),
inference(cnf_transformation,[],[f4]) ).
fof(f11,definition,
( spl0_1
<=> big_q(b,b) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f13,plain,
( ~ big_q(b,b)
| spl0_1 ),
inference(avatar_component_clause,[],[f11]) ).
fof(f15,definition,
( spl0_2
<=> big_q(a,a) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f18,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f9,f15,f11]) ).
fof(f19,plain,
big_q(a,b),
inference(resolution,[],[f6,f8]) ).
fof(f20,plain,
big_q(a,a),
inference(resolution,[],[f19,f5]) ).
fof(f21,plain,
spl0_2,
inference(avatar_split_clause,[],[f20,f15]) ).
fof(f23,plain,
big_r(b,a),
inference(resolution,[],[f7,f8]) ).
fof(f25,plain,
big_q(b,a),
inference(resolution,[],[f23,f6]) ).
fof(f26,plain,
big_q(b,b),
inference(resolution,[],[f25,f5]) ).
fof(f27,plain,
( $false
| spl0_1 ),
inference(forward_subsumption_resolution,[],[f26,f13]) ).
fof(f28,plain,
spl0_1,
inference(avatar_contradiction_clause,[],[f27]) ).
cnf(s1,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f18]) ).
cnf(s2,plain,
spl0_2,
inference(sat_conversion,[],[f21]) ).
cnf(s3,plain,
spl0_1,
inference(sat_conversion,[],[f28]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s2,s3]) ).
fof(f29,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : SYN356+1 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.04 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.11/0.16 % Computer : n014.cluster.edu
% 0.11/0.16 % Model : x86_64 x86_64
% 0.11/0.16 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.11/0.16 % Memory : 8046.5625MB
% 0.11/0.16 % OS : Linux 6.8.0-71-generic
% 0.11/0.16 % CPULimit : 300
% 0.11/0.16 % WCLimit : 300
% 0.11/0.16 % DateTime : Mon Sep 28 15:47:45 UTC 2026
% 0.11/0.16 % CPUTime :
% 0.11/0.16 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.11/0.20 Running first-order theorem proving
% 0.11/0.20 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
% 0.18/1.14 % (1884323)Detected formulas, will run a generic FOF schedule.
% 0.18/1.14 % (1884331)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=3395662281:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 0.18/1.14 % (1884331)First to succeed.
% 0.18/1.14 % (1884331)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-1884323"
% 0.18/1.14 % (1884330)lrs+1010_1_anc=all:sfv=off:to=kbo:ncem=casc2026/models/loop7.pt:sil=128000:npcc=on:prc=on:sos=all:bsr=unit_only:sac=on:random_seed=4042894161:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 0.18/1.14 % (1884329)lrs+11_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:lma=off:spb=units:urr=ec_only:bce=on:s2agt=64:updr=off:random_seed=1298293566:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 0.18/1.14 % (1884328)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=2310802124:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 0.18/1.14 % (1884334)dis-21_1_sil=8000:lcm=predicate:random_seed=102666606:st=5:avsq=on:i=129:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/129Mi)
% 0.18/1.14 % (1884333)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1620957555:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 0.18/1.14 % (1884332)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=4190585218:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 0.18/1.14 % (1884332)Also succeeded, but the first one will report.
% 0.18/1.14 % (1884334)Also succeeded, but the first one will report.
% 0.18/1.14 % (1884333)Also succeeded, but the first one will report.
% 0.18/1.14 % (1884331)Refutation found. Thanks to Tanya!
% 0.18/1.14 % SZS status Theorem for theBenchmark
% 0.18/1.14 % SZS output start Proof for theBenchmark
% See solution above
% 0.18/1.14 % (1884331)------------------------------
% 0.18/1.14 % (1884331)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.18/1.14 % (1884331)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.18/1.14 % (1884331)CaDiCaL version: 2.1.3
% 0.18/1.14 % (1884331)Termination reason: Refutation
% 0.18/1.14 % (1884331)Time elapsed: 0.001 s
% 0.18/1.14 % (1884331)Peak memory usage: 89 MB
% 0.18/1.14 % (1884331)Instructions burned: 1 (million)
% 0.18/1.14 % (1884331)------------------------------
% 0.18/1.14 % (1884331)------------------------------
% 0.18/1.14 % (1884323)Success in time 0.3 s
% 0.18/1.14 % Vampire exiting
%------------------------------------------------------------------------------