TSTP Solution File: PUZ083_8 by Vampire-SAT---4.8
View Problem
- Process Solution
%------------------------------------------------------------------------------
% File : Vampire-SAT---4.8
% Problem : PUZ083_8 : TPTP v8.1.2. Released v8.0.0.
% Transfm : none
% Format : tptp:raw
% Command : vampire --mode casc_sat -m 16384 --cores 7 -t %d %s
% Computer : n020.cluster.edu
% Model : x86_64 x86_64
% CPU : Intel(R) Xeon(R) CPU E5-2620 v4 2.10GHz
% Memory : 8042.1875MB
% OS : Linux 3.10.0-693.el7.x86_64
% CPULimit : 300s
% WCLimit : 300s
% DateTime : Sun May 5 08:50:31 EDT 2024
% Result : Theorem 0.23s 0.39s
% Output : Refutation 0.23s
% Verified :
% SZS Type : Refutation
% Derivation depth : 15
% Number of leaves : 17
% Syntax : Number of formulae : 64 ( 9 unt; 5 typ; 0 def)
% Number of atoms : 325 ( 60 equ)
% Maximal formula atoms : 6 ( 5 avg)
% Number of connectives : 158 ( 65 ~; 64 |; 9 &)
% ( 10 <=>; 10 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of FOOLs : 236 ( 178 fml; 58 var)
% Number of types : 2 ( 0 usr)
% Number of type conns : 4 ( 3 >; 1 *; 0 +; 0 <<)
% Number of predicates : 14 ( 11 usr; 10 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 29 ( 26 !; 3 ?; 29 :)
% Comments :
%------------------------------------------------------------------------------
tff(func_def_3,type,
bG0: $o > $o ).
tff(func_def_4,type,
bG1: $o > $o ).
tff(func_def_5,type,
bG2: $o ).
tff(func_def_6,type,
sK3: $o ).
tff(pred_def_1,type,
says: ( $i * $o ) > $o ).
tff(f144,plain,
$false,
inference(avatar_sat_refutation,[],[f43,f48,f53,f109,f140,f143]) ).
tff(f143,plain,
( ~ spl4_8
| spl4_2 ),
inference(avatar_split_clause,[],[f121,f40,f128]) ).
tff(f128,plain,
( spl4_8
<=> says(peter,$true) ),
introduced(avatar_definition,[new_symbols(naming,[spl4_8])]) ).
tff(f40,plain,
( spl4_2
<=> says(peter,bG1($true)) ),
introduced(avatar_definition,[new_symbols(naming,[spl4_2])]) ).
tff(f121,plain,
( ~ says(peter,$true)
| spl4_2 ),
inference(forward_demodulation,[],[f42,f33]) ).
tff(f33,plain,
$true = bG1($true),
inference(equality_resolution,[],[f26]) ).
tff(f26,plain,
! [X0: $o] :
( ( $true = bG1((X0)) )
| ( $true != (X0) ) ),
inference(cnf_transformation,[],[f21]) ).
tff(f21,plain,
! [X0: $o] :
( ( ( $true = (X0) )
| ( $true != bG1((X0)) ) )
& ( ( $true = bG1((X0)) )
| ( $true != (X0) ) ) ),
inference(nnf_transformation,[],[f10]) ).
tff(f10,plain,
! [X0: $o] :
( ( $true = (X0) )
<=> ( $true = bG1((X0)) ) ),
introduced(fool_formula_definition,[new_symbols(definition,[bG1])]) ).
tff(f42,plain,
( ~ says(peter,bG1($true))
| spl4_2 ),
inference(avatar_component_clause,[],[f40]) ).
tff(f140,plain,
( spl4_8
| ~ spl4_1 ),
inference(avatar_split_clause,[],[f139,f36,f128]) ).
tff(f36,plain,
( spl4_1
<=> ( $true = bG2 ) ),
introduced(avatar_definition,[new_symbols(naming,[spl4_1])]) ).
tff(f139,plain,
( says(peter,$true)
| ~ spl4_1 ),
inference(backward_demodulation,[],[f31,f37]) ).
tff(f37,plain,
( ( $true = bG2 )
| ~ spl4_1 ),
inference(avatar_component_clause,[],[f36]) ).
tff(f31,plain,
says(peter,bG2),
inference(cnf_transformation,[],[f12]) ).
tff(f12,plain,
says(peter,bG2),
inference(fool_elimination,[],[f9,f11,f10]) ).
tff(f11,plain,
( ! [X0: $o] :
( says(peter,bG1((X0)))
=> ( $true != (X0) ) )
<=> ( $true = bG2 ) ),
introduced(fool_formula_definition,[new_symbols(definition,[bG2])]) ).
tff(f9,plain,
says(peter,
! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) )),
inference(rectify,[],[f1]) ).
tff(f1,axiom,
says(peter,
! [X0: $o] :
( says(peter,(X0))
=> ~ (X0) )),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',ax1) ).
tff(f109,plain,
( spl4_1
| ~ spl4_3
| ~ spl4_4 ),
inference(avatar_contradiction_clause,[],[f108]) ).
tff(f108,plain,
( $false
| spl4_1
| ~ spl4_3
| ~ spl4_4 ),
inference(trivial_inequality_removal,[],[f107]) ).
tff(f107,plain,
( ( $true = $false )
| spl4_1
| ~ spl4_3
| ~ spl4_4 ),
inference(superposition,[],[f64,f87]) ).
tff(f87,plain,
( ! [X0: $o] : ( $true = (X0) )
| spl4_1
| ~ spl4_3
| ~ spl4_4 ),
inference(subsumption_resolution,[],[f84,f66]) ).
tff(f66,plain,
( says(peter,$false)
| spl4_1 ),
inference(backward_demodulation,[],[f31,f64]) ).
tff(f84,plain,
( ! [X0: $o] :
( ~ says(peter,$false)
| ( $true = (X0) ) )
| ~ spl4_3
| ~ spl4_4 ),
inference(duplicate_literal_removal,[],[f83]) ).
tff(f83,plain,
( ! [X0: $o] :
( ~ says(peter,$false)
| ( $true = (X0) )
| ( $true = (X0) ) )
| ~ spl4_3
| ~ spl4_4 ),
inference(superposition,[],[f30,f72]) ).
tff(f72,plain,
( ! [X0: $o] :
( ( $false = bG0((X0)) )
| ( $true = (X0) ) )
| ~ spl4_3
| ~ spl4_4 ),
inference(subsumption_resolution,[],[f71,f55]) ).
tff(f55,plain,
( says(peter,$true)
| ~ spl4_3
| ~ spl4_4 ),
inference(forward_demodulation,[],[f54,f33]) ).
tff(f54,plain,
( says(peter,bG1($true))
| ~ spl4_3
| ~ spl4_4 ),
inference(forward_demodulation,[],[f52,f47]) ).
tff(f47,plain,
( ( $true = sK3 )
| ~ spl4_3 ),
inference(avatar_component_clause,[],[f45]) ).
tff(f45,plain,
( spl4_3
<=> ( $true = sK3 ) ),
introduced(avatar_definition,[new_symbols(naming,[spl4_3])]) ).
tff(f52,plain,
( says(peter,bG1(sK3))
| ~ spl4_4 ),
inference(avatar_component_clause,[],[f50]) ).
tff(f50,plain,
( spl4_4
<=> says(peter,bG1(sK3)) ),
introduced(avatar_definition,[new_symbols(naming,[spl4_4])]) ).
tff(f71,plain,
! [X0: $o] :
( ~ says(peter,$true)
| ( $true = (X0) )
| ( $false = bG0((X0)) ) ),
inference(superposition,[],[f30,f5]) ).
tff(f5,plain,
! [X0: $o] :
( ( $true = (X0) )
| ( $false = (X0) ) ),
introduced(fool_axiom,[]) ).
tff(f30,plain,
! [X0: $o] :
( ~ says(peter,bG0((X0)))
| ( $true = (X0) ) ),
inference(cnf_transformation,[],[f16]) ).
tff(f16,plain,
! [X0: $o] :
( ( $true = (X0) )
| ~ says(peter,bG0((X0))) ),
inference(ennf_transformation,[],[f14]) ).
tff(f14,plain,
! [X0: $o] :
( says(peter,bG0((X0)))
=> ( $true = (X0) ) ),
inference(flattening,[],[f8]) ).
tff(f8,plain,
~ ~ ! [X0: $o] :
( says(peter,bG0((X0)))
=> ( $true = (X0) ) ),
inference(fool_elimination,[],[f6,f7]) ).
tff(f7,plain,
! [X0: $o] :
( ( $true = (X0) )
<=> ( $true = bG0((X0)) ) ),
introduced(fool_formula_definition,[new_symbols(definition,[bG0])]) ).
tff(f6,plain,
~ ~ ! [X0: $o] :
( says(peter,(X0))
=> (X0) ),
inference(rectify,[],[f3]) ).
tff(f3,negated_conjecture,
~ ~ ! [X0: $o] :
( says(peter,(X0))
=> (X0) ),
inference(negated_conjecture,[],[f2]) ).
tff(f2,conjecture,
~ ! [X0: $o] :
( says(peter,(X0))
=> (X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',thm) ).
tff(f64,plain,
( ( $false = bG2 )
| spl4_1 ),
inference(trivial_inequality_removal,[],[f61]) ).
tff(f61,plain,
( ( $true != $true )
| ( $false = bG2 )
| spl4_1 ),
inference(superposition,[],[f38,f5]) ).
tff(f38,plain,
( ( $true != bG2 )
| spl4_1 ),
inference(avatar_component_clause,[],[f36]) ).
tff(f53,plain,
( spl4_4
| spl4_1 ),
inference(avatar_split_clause,[],[f23,f36,f50]) ).
tff(f23,plain,
( ( $true = bG2 )
| says(peter,bG1(sK3)) ),
inference(cnf_transformation,[],[f20]) ).
tff(f20,plain,
( ( ! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG1((X0))) )
| ( $true != bG2 ) )
& ( ( $true = bG2 )
| ( ( $true = sK3 )
& says(peter,bG1(sK3)) ) ) ),
inference(skolemisation,[status(esa),new_symbols(skolem,[sK3])],[f18,f19]) ).
tff(f19,plain,
( ? [X1: $o] :
( ( $true = (X1) )
& says(peter,bG1((X1))) )
=> ( ( $true = sK3 )
& says(peter,bG1(sK3)) ) ),
introduced(choice_axiom,[]) ).
tff(f18,plain,
( ( ! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG1((X0))) )
| ( $true != bG2 ) )
& ( ( $true = bG2 )
| ? [X1: $o] :
( ( $true = (X1) )
& says(peter,bG1((X1))) ) ) ),
inference(rectify,[],[f17]) ).
tff(f17,plain,
( ( ! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG1((X0))) )
| ( $true != bG2 ) )
& ( ( $true = bG2 )
| ? [X0: $o] :
( ( $true = (X0) )
& says(peter,bG1((X0))) ) ) ),
inference(nnf_transformation,[],[f15]) ).
tff(f15,plain,
( ! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG1((X0))) )
<=> ( $true = bG2 ) ),
inference(ennf_transformation,[],[f13]) ).
tff(f13,plain,
( ! [X0: $o] :
( says(peter,bG1((X0)))
=> ( $true != (X0) ) )
<=> ( $true = bG2 ) ),
inference(flattening,[],[f11]) ).
tff(f48,plain,
( spl4_3
| spl4_1 ),
inference(avatar_split_clause,[],[f24,f36,f45]) ).
tff(f24,plain,
( ( $true = bG2 )
| ( $true = sK3 ) ),
inference(cnf_transformation,[],[f20]) ).
tff(f43,plain,
( ~ spl4_1
| ~ spl4_2 ),
inference(avatar_split_clause,[],[f32,f40,f36]) ).
tff(f32,plain,
( ~ says(peter,bG1($true))
| ( $true != bG2 ) ),
inference(equality_resolution,[],[f25]) ).
tff(f25,plain,
! [X0: $o] :
( ( $true != (X0) )
| ~ says(peter,bG1((X0)))
| ( $true != bG2 ) ),
inference(cnf_transformation,[],[f20]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.07/0.13 % Problem : PUZ083_8 : TPTP v8.1.2. Released v8.0.0.
% 0.07/0.15 % Command : vampire --mode casc_sat -m 16384 --cores 7 -t %d %s
% 0.16/0.36 % Computer : n020.cluster.edu
% 0.16/0.36 % Model : x86_64 x86_64
% 0.16/0.36 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.16/0.36 % Memory : 8042.1875MB
% 0.16/0.36 % OS : Linux 3.10.0-693.el7.x86_64
% 0.16/0.36 % CPULimit : 300
% 0.16/0.36 % WCLimit : 300
% 0.16/0.36 % DateTime : Fri May 3 18:04:08 EDT 2024
% 0.16/0.36 % CPUTime :
% 0.16/0.36 % (1665)Running in auto input_syntax mode. Trying TPTP
% 0.16/0.38 % (1667)fmb+10_1_bce=on:fmbas=expand:fmbksg=on:fmbsr=1.3_569 on theBenchmark for (569ds/0Mi)
% 0.16/0.38 % (1666)fmb+10_1_fmbas=off:fmbsr=1.3:nm=2_1451 on theBenchmark for (1451ds/0Mi)
% 0.16/0.38 % (1670)dis+1_20_av=off:lcm=predicate:nm=2:nwc=2.0_396 on theBenchmark for (396ds/0Mi)
% 0.16/0.38 % (1671)dis+11_4:5_nm=4_216 on theBenchmark for (216ds/0Mi)
% 0.16/0.38 % (1669)fmb+10_1_bce=on:fmbas=expand:fmbksg=on:fmbsr=1.3:gsp=on:nm=4_470 on theBenchmark for (470ds/0Mi)
% 0.16/0.38 % (1668)dis-2_2:3_amm=sco:anc=none:bce=on:fsr=off:gsp=on:nm=16:nwc=1.2:nicw=on:sac=on:sp=weighted_frequency_476 on theBenchmark for (476ds/0Mi)
% 0.16/0.38 % (1672)fmb+10_1_fmbas=off:fmbsr=1.3:nm=2:si=on:rtra=on:rawr=on:rp=on:fmbksg=on_1451 on theBenchmark for (1451ds/0Mi)
% 0.16/0.38 Detected minimum model sizes of [1,1]
% 0.16/0.38 Detected minimum model sizes of [1,1]
% 0.16/0.38 Detected maximum model sizes of [1,2]
% 0.16/0.38 Detected maximum model sizes of [1,2]
% 0.16/0.38 Detected minimum model sizes of [1,1]
% 0.16/0.38 Detected maximum model sizes of [1,2]
% 0.16/0.38 Detected minimum model sizes of [1,1]
% 0.16/0.38 Detected maximum model sizes of [1,2]
% 0.16/0.38 TRYING [1,1]
% 0.16/0.38 TRYING [1,1]
% 0.16/0.38 TRYING [1,1]
% 0.16/0.38 TRYING [1,1]
% 0.16/0.38 TRYING [1,2]
% 0.16/0.38 TRYING [1,2]
% 0.16/0.38 TRYING [1,2]
% 0.16/0.38 TRYING [1,2]
% 0.16/0.38 Cannot enumerate next child to try in an incomplete setup
% 0.16/0.38 Cannot enumerate next child to try in an incomplete setup
% 0.16/0.38 Cannot enumerate next child to try in an incomplete setup
% 0.16/0.38 % (1666)Refutation not found, incomplete strategy% (1666)------------------------------
% 0.16/0.38 % (1666)Version: Vampire 4.8 (commit 3a798227e on 2024-05-03 07:42:47 +0200)
% 0.16/0.38 % (1666)Termination reason: Refutation not found, incomplete strategy
% 0.16/0.38
% 0.16/0.38 % (1666)Memory used [KB]: 729
% 0.16/0.38 Cannot enumerate next child to try in an incomplete setup
% 0.16/0.38 % (1666)Time elapsed: 0.004 s
% 0.16/0.38 % (1666)Instructions burned: 4 (million)
% 0.16/0.38 % (1672)Refutation not found, incomplete strategy% (1672)------------------------------
% 0.16/0.38 % (1672)Version: Vampire 4.8 (commit 3a798227e on 2024-05-03 07:42:47 +0200)
% 0.16/0.38 % (1667)Refutation not found, incomplete strategy% (1667)------------------------------
% 0.16/0.38 % (1667)Version: Vampire 4.8 (commit 3a798227e on 2024-05-03 07:42:47 +0200)
% 0.16/0.38 % (1672)Termination reason: Refutation not found, incomplete strategy
% 0.16/0.38 % (1667)Termination reason: Refutation not found, incomplete strategy
% 0.16/0.38
% 0.16/0.38
% 0.16/0.38 % (1672)Memory used [KB]: 730
% 0.16/0.38 % (1667)Memory used [KB]: 730
% 0.16/0.38 % (1672)Time elapsed: 0.004 s
% 0.16/0.38 % (1667)Time elapsed: 0.004 s
% 0.16/0.38 % (1672)Instructions burned: 4 (million)
% 0.16/0.38 % (1669)Refutation not found, incomplete strategy% (1669)------------------------------
% 0.16/0.38 % (1669)Version: Vampire 4.8 (commit 3a798227e on 2024-05-03 07:42:47 +0200)
% 0.16/0.38 % (1667)Instructions burned: 4 (million)
% 0.16/0.38 % (1669)Termination reason: Refutation not found, incomplete strategy
% 0.16/0.38
% 0.16/0.38 % (1669)Memory used [KB]: 730
% 0.16/0.38 % (1669)Time elapsed: 0.004 s
% 0.16/0.38 % (1669)Instructions burned: 4 (million)
% 0.23/0.38 % (1666)------------------------------
% 0.23/0.38 % (1666)------------------------------
% 0.23/0.38 % (1672)------------------------------
% 0.23/0.38 % (1672)------------------------------
% 0.23/0.38 % (1669)------------------------------
% 0.23/0.38 % (1669)------------------------------
% 0.23/0.38 % (1667)------------------------------
% 0.23/0.38 % (1667)------------------------------
% 0.23/0.38 % (1668)Also succeeded, but the first one will report.
% 0.23/0.38 % (1671)First to succeed.
% 0.23/0.38 % (1670)Also succeeded, but the first one will report.
% 0.23/0.39 % (1671)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-1665"
% 0.23/0.39 % (1671)Refutation found. Thanks to Tanya!
% 0.23/0.39 % SZS status Theorem for theBenchmark
% 0.23/0.39 % SZS output start Proof for theBenchmark
% See solution above
% 0.23/0.39 % (1671)------------------------------
% 0.23/0.39 % (1671)Version: Vampire 4.8 (commit 3a798227e on 2024-05-03 07:42:47 +0200)
% 0.23/0.39 % (1671)Termination reason: Refutation
% 0.23/0.39
% 0.23/0.39 % (1671)Memory used [KB]: 775
% 0.23/0.39 % (1671)Time elapsed: 0.006 s
% 0.23/0.39 % (1671)Instructions burned: 6 (million)
% 0.23/0.39 % (1665)Success in time 0.02 s
%------------------------------------------------------------------------------