%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN372+1 : TPTP v9.3.1. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n010.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 01:50:24 PM UTC 2026
% Result : Theorem 2.74s 1.20s
% Output : Refutation 2.74s
% Verified :
% SZS Type : Refutation
% Derivation depth : 11
% Number of leaves : 3
% Syntax : Number of formulae : 23 ( 8 unt; 2 def)
% Number of atoms : 50 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 44 ( 17 ~; 10 |; 6 &)
% ( 2 <=>; 9 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 5 ( 4 usr; 3 prp; 0-1 aty)
% Number of functors : 2 ( 2 usr; 2 con; 0-0 aty)
% Number of variables : 18 ( 0 sgn 8 !; 10 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,conjecture,
! [X0] :
( ? [X1] :
( big_p(X1)
=> big_q(X0) )
=> ? [X1] :
( big_p(X1)
=> big_q(X1) ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',x2123) ).
fof(f2,negated_conjecture,
~ ! [X0] :
( ? [X1] :
( big_p(X1)
=> big_q(X0) )
=> ? [X1] :
( big_p(X1)
=> big_q(X1) ) ),
inference(negated_conjecture,[status(cth)],[f1]) ).
fof(f3,plain,
~ ! [X0] :
( ? [X1] :
( big_p(X1)
=> big_q(X0) )
=> ? [X2] :
( big_p(X2)
=> big_q(X2) ) ),
inference(rectify,[],[f2]) ).
fof(f4,plain,
? [X0] :
( ! [X2] :
( ~ big_q(X2)
& big_p(X2) )
& ? [X1] :
( big_q(X0)
| ~ big_p(X1) ) ),
inference(ennf_transformation,[],[f3]) ).
fof(f5,plain,
? [X0] :
( ! [X1] :
( ~ big_q(X1)
& big_p(X1) )
& ? [X2] :
( big_q(X0)
| ~ big_p(X2) ) ),
inference(rectify,[],[f4]) ).
fof(f6,plain,
( ! [X1] :
( ~ big_q(X1)
& big_p(X1) )
& ( big_q(sK0)
| ~ big_p(sK1) ) ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK0,sK1]),skolemize(X0,sK0),skolemize(X2,sK1)],[f5]) ).
fof(f7,plain,
( big_q(sK0)
| ~ big_p(sK1) ),
inference(cnf_transformation,[],[f6]) ).
fof(f8,plain,
! [X1] : big_p(X1),
inference(cnf_transformation,[],[f6]) ).
fof(f9,plain,
! [X1] : ~ big_q(X1),
inference(cnf_transformation,[],[f6]) ).
fof(f11,definition,
( spl2_1
<=> big_p(sK1) ),
introduced(definition,[new_symbols(definition,[spl2_1])],[avatar_definition]) ).
fof(f12,plain,
( ~ big_p(sK1)
| spl2_1 ),
inference(avatar_component_clause,[],[f11]) ).
fof(f14,definition,
( spl2_2
<=> big_q(sK0) ),
introduced(definition,[new_symbols(definition,[spl2_2])],[avatar_definition]) ).
fof(f15,plain,
( big_q(sK0)
| ~ spl2_2 ),
inference(avatar_component_clause,[],[f14]) ).
fof(f16,plain,
( ~ spl2_1
| spl2_2 ),
inference(avatar_split_clause,[],[f7,f14,f11]) ).
fof(f17,plain,
( $false
| spl2_1 ),
inference(resolution,[],[f12,f8]) ).
fof(f18,plain,
spl2_1,
inference(avatar_contradiction_clause,[],[f17]) ).
fof(f19,plain,
( $false
| ~ spl2_2 ),
inference(resolution,[],[f9,f15]) ).
fof(f20,plain,
~ spl2_2,
inference(avatar_contradiction_clause,[],[f19]) ).
cnf(s1,plain,
( ~ spl2_1
| spl2_2 ),
inference(sat_conversion,[],[f16]) ).
cnf(s2,plain,
spl2_1,
inference(sat_conversion,[],[f18]) ).
cnf(s3,plain,
~ spl2_2,
inference(sat_conversion,[],[f20]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s3,s2]) ).
fof(f21,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYN372+1 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.22 % Computer : n010.cluster.edu
% 0.09/0.22 % Model : x86_64 x86_64
% 0.09/0.22 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.22 % Memory : 8046.5625MB
% 0.09/0.22 % OS : Linux 6.8.0-71-generic
% 0.09/0.22 % CPULimit : 300
% 0.09/0.22 % WCLimit : 300
% 0.09/0.22 % DateTime : Mon Sep 28 15:49:32 UTC 2026
% 0.09/0.22 % CPUTime :
% 0.09/0.22 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.26 Running first-order theorem proving
% 0.09/0.26 Running: /export/starexec/sandbox/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 2.74/1.20 % (2033349)Detected formulas, will run a generic FOF schedule.
% 2.74/1.20 % (2033360)dis-21_1_sil=8000:lcm=predicate:random_seed=3985261684: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)
% 2.74/1.20 % (2033360)First to succeed.
% 2.74/1.20 % (2033360)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-2033349"
% 2.74/1.20 % (2033355)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=1843460306:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 2.74/1.20 % (2033354)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=3896184199:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 2.74/1.20 % (2033356)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=3231946301:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 2.74/1.20 % (2033359)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1616891719:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 2.74/1.20 % (2033357)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=2400922386:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 2.74/1.20 % (2033358)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=111662107:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 2.74/1.20 % (2033358)Also succeeded, but the first one will report.
% 2.74/1.20 % (2033357)Also succeeded, but the first one will report.
% 2.74/1.20 % (2033359)Also succeeded, but the first one will report.
% 2.74/1.20 % (2033360)Refutation found. Thanks to Tanya!
% 2.74/1.20 % SZS status Theorem for theBenchmark
% 2.74/1.20 % SZS output start Proof for theBenchmark
% See solution above
% 2.74/1.20 % (2033360)------------------------------
% 2.74/1.20 % (2033360)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.74/1.20 % (2033360)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.74/1.20 % (2033360)CaDiCaL version: 2.1.3
% 2.74/1.20 % (2033360)Termination reason: Refutation
% 2.74/1.20 % (2033360)Time elapsed: 0.001 s
% 2.74/1.20 % (2033360)Peak memory usage: 89 MB
% 2.74/1.20 % (2033360)------------------------------
% 2.74/1.20 % (2033360)------------------------------
% 2.74/1.20 % (2033349)Success in time 0.299 s
% 2.74/1.20 % Vampire exiting
%------------------------------------------------------------------------------