%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYO013_8 : TPTP v9.3.1. Released v8.0.0.
% 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 02:24:43 PM UTC 2026
% Result : Theorem 3.63s 1.19s
% Output : Refutation 3.63s
% Verified :
% SZS Type : Refutation
% Derivation depth : 8
% Number of leaves : 3
% Syntax : Number of formulae : 22 ( 9 unt; 0 typ; 2 def)
% Number of atoms : 79 ( 10 equ)
% Maximal formula atoms : 4 ( 3 avg)
% Number of connectives : 33 ( 10 ~; 4 |; 12 &)
% ( 2 <=>; 5 =>; 0 <=; 0 <~>)
% Maximal formula depth : 5 ( 3 avg)
% Maximal term depth : 0 ( 0 avg)
% Number of FOOLs : 34 ( 34 fml; 0 var)
% Number of types : 1 ( 0 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 8 ( 5 usr; 6 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 0 ( 0 !; 0 ?; 0 :)
% Comments :
%------------------------------------------------------------------------------
tff(func_def_0,type,
bG0: $o ).
tff(func_def_3,type,
bG1: $o ).
tff(pred_def_3,type,
p: $o > $o ).
tff(f1,conjecture,
( ( a
& b
& p(a) )
=> p(b) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',conj) ).
tff(f2,negated_conjecture,
~ ( ( a
& b
& p(a) )
=> p(b) ),
inference(negated_conjecture,[status(cth)],[f1]) ).
tff(f3,definition,
( b
<=> ( bG0 = $true ) ),
introduced(definition,[new_symbols(definition,[bG0])],[fool_formula_definition]) ).
tff(f4,definition,
( a
<=> ( $true = bG1 ) ),
introduced(definition,[new_symbols(definition,[bG1])],[fool_formula_definition]) ).
tff(f5,plain,
~ ( ( a
& b
& p(bG1) )
=> p(bG0) ),
inference(fool_elimination,[],[f2,f4,f3]) ).
tff(f6,plain,
( b
=> ( bG0 = $true ) ),
inference(unused_predicate_definition_removal,[],[f3]) ).
tff(f7,plain,
( a
=> ( $true = bG1 ) ),
inference(unused_predicate_definition_removal,[],[f4]) ).
tff(f8,plain,
( ~ p(bG0)
& a
& b
& p(bG1) ),
inference(ennf_transformation,[],[f5]) ).
tff(f9,plain,
( ~ p(bG0)
& a
& b
& p(bG1) ),
inference(flattening,[],[f8]) ).
tff(f10,plain,
( ( bG0 = $true )
| ~ b ),
inference(ennf_transformation,[],[f6]) ).
tff(f11,plain,
( ( $true = bG1 )
| ~ a ),
inference(ennf_transformation,[],[f7]) ).
tff(f12,plain,
p(bG1),
inference(cnf_transformation,[],[f9]) ).
tff(f13,plain,
b,
inference(cnf_transformation,[],[f9]) ).
tff(f14,plain,
a,
inference(cnf_transformation,[],[f9]) ).
tff(f15,plain,
~ p(bG0),
inference(cnf_transformation,[],[f9]) ).
tff(f16,plain,
( ( bG0 = $true )
| ~ b ),
inference(cnf_transformation,[],[f10]) ).
tff(f17,plain,
( ( $true = bG1 )
| ~ a ),
inference(cnf_transformation,[],[f11]) ).
tff(f20,plain,
bG0 = $true,
inference(forward_subsumption_resolution,[],[f16,f13]) ).
tff(f21,plain,
~ p($true),
inference(superposition,[],[f15,f20]) ).
tff(f22,plain,
$true = bG1,
inference(forward_subsumption_resolution,[],[f17,f14]) ).
tff(f23,plain,
p($true),
inference(superposition,[],[f12,f22]) ).
tff(f24,plain,
$false,
inference(forward_subsumption_resolution,[],[f23,f21]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYO013_8 : TPTP v9.3.1. Released v8.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.10/0.18 % Computer : n017.cluster.edu
% 0.10/0.18 % Model : x86_64 x86_64
% 0.10/0.18 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.18 % Memory : 8046.5625MB
% 0.10/0.18 % OS : Linux 6.8.0-71-generic
% 0.10/0.19 % CPULimit : 300
% 0.10/0.19 % WCLimit : 300
% 0.10/0.19 % DateTime : Mon Sep 28 17:16:21 UTC 2026
% 0.10/0.19 % CPUTime :
% 0.10/0.19 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.10/0.22 Running first-order theorem proving
% 0.10/0.22 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
% 3.63/1.19 % (3728432)Detected formulas, will run a generic FOF schedule.
% 3.63/1.19 % (3728439)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=33388958:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.63/1.19 % (3728442)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1383081102:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.63/1.19 % (3728443)dis-21_1_sil=8000:lcm=predicate:random_seed=370523845: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)
% 3.63/1.19 % (3728441)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=3508676249:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.63/1.19 % (3728440)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=225161977:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.63/1.19 % (3728437)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=578523879:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.63/1.19 % (3728438)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=4271866199:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.63/1.19 % (3728441)First to succeed.
% 3.63/1.19 % (3728443)Refutation not found, incomplete strategy
% 3.63/1.19 % (3728443)------------------------------
% 3.63/1.19 % (3728443)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.63/1.19 % (3728443)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.63/1.19 % (3728443)CaDiCaL version: 2.1.3
% 3.63/1.19 % (3728443)Termination reason: Refutation not found, incomplete strategy
% 3.63/1.19 % (3728443)Time elapsed: 0.001 s
% 3.63/1.19 % (3728443)Peak memory usage: 88 MB
% 3.63/1.19 % (3728440)Also succeeded, but the first one will report.
% 3.63/1.19 % (3728442)Also succeeded, but the first one will report.
% 3.63/1.19 % (3728441)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3728432"
% 3.63/1.19 % (3728443)------------------------------
% 3.63/1.19 % (3728443)------------------------------
% 3.63/1.19 % (3728441)Refutation found. Thanks to Tanya!
% 3.63/1.19 % SZS status Theorem for theBenchmark
% 3.63/1.19 % SZS output start Proof for theBenchmark
% See solution above
% 3.63/1.19 % (3728441)------------------------------
% 3.63/1.19 % (3728441)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.63/1.19 % (3728441)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.63/1.19 % (3728441)CaDiCaL version: 2.1.3
% 3.63/1.19 % (3728441)Termination reason: Refutation
% 3.63/1.19 % (3728441)Time elapsed: 0.002 s
% 3.63/1.19 % (3728441)Peak memory usage: 88 MB
% 3.63/1.19 % (3728441)------------------------------
% 3.63/1.19 % (3728441)------------------------------
% 3.63/1.19 % (3728432)Success in time 0.439 s
% 3.63/1.19 % Vampire exiting
%------------------------------------------------------------------------------