TSTP Solution File: PUZ081_8 by Vampire-SAT---4.8
View Problem
- Process Solution
%------------------------------------------------------------------------------
% File : Vampire-SAT---4.8
% Problem : PUZ081_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 : n005.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 : Tue Apr 30 14:45:46 EDT 2024
% Result : Theorem 0.21s 0.39s
% Output : Refutation 0.21s
% Verified :
% SZS Type : Refutation
% Derivation depth : 24
% Number of leaves : 16
% Syntax : Number of formulae : 76 ( 16 unt; 5 typ; 0 def)
% Number of atoms : 311 ( 59 equ)
% Maximal formula atoms : 6 ( 4 avg)
% Number of connectives : 145 ( 58 ~; 55 |; 19 &)
% ( 5 <=>; 7 =>; 0 <=; 1 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of FOOLs : 207 ( 157 fml; 50 var)
% Number of types : 2 ( 0 usr)
% Number of type conns : 4 ( 3 >; 1 *; 0 +; 0 <<)
% Number of predicates : 12 ( 9 usr; 6 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 63 ( 57 !; 6 ?; 42 :)
% Comments :
%------------------------------------------------------------------------------
tff(func_def_4,type,
bG0: $o ).
tff(func_def_5,type,
bG1: $o ).
tff(func_def_6,type,
bG2: $o > $o ).
tff(func_def_7,type,
bG3: $o > $o ).
tff(pred_def_3,type,
says: ( $i * $o ) > $o ).
tff(f168,plain,
$false,
inference(trivial_inequality_removal,[],[f161]) ).
tff(f161,plain,
$true = $false,
inference(superposition,[],[f92,f150]) ).
tff(f150,plain,
! [X0: $o] : ( $true = (X0) ),
inference(resolution,[],[f148,f95]) ).
tff(f95,plain,
says(zoey,$false),
inference(backward_demodulation,[],[f45,f92]) ).
tff(f45,plain,
says(zoey,bG0),
inference(cnf_transformation,[],[f11]) ).
tff(f11,plain,
says(zoey,bG0),
inference(fool_elimination,[],[f4,f10]) ).
tff(f10,plain,
( knave(mel)
<=> ( $true = bG0 ) ),
introduced(fool_formula_definition,[new_symbols(definition,[bG0])]) ).
tff(f4,axiom,
says(zoey,knave(mel)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',zoey_speaks) ).
tff(f148,plain,
! [X0: $o,X1: $i] :
( ~ says(X1,$false)
| ( $true = (X0) ) ),
inference(duplicate_literal_removal,[],[f145]) ).
tff(f145,plain,
! [X0: $o,X1: $i] :
( ~ says(X1,$false)
| ( $true = (X0) )
| ( $true = (X0) ) ),
inference(superposition,[],[f118,f139]) ).
tff(f139,plain,
! [X0: $o] :
( ( $false = bG2((X0)) )
| ( $true = (X0) ) ),
inference(resolution,[],[f118,f136]) ).
tff(f136,plain,
! [X0: $o] :
( says(mel,(X0))
| ( $false = (X0) ) ),
inference(superposition,[],[f121,f9]) ).
tff(f9,plain,
! [X0: $o] :
( ( $true = (X0) )
| ( $false = (X0) ) ),
introduced(fool_axiom,[]) ).
tff(f121,plain,
says(mel,$true),
inference(backward_demodulation,[],[f46,f117]) ).
tff(f117,plain,
$true = bG1,
inference(subsumption_resolution,[],[f116,f100]) ).
tff(f100,plain,
! [X0: $i] : knight(X0),
inference(trivial_inequality_removal,[],[f97]) ).
tff(f97,plain,
! [X0: $i] :
( ( $true = $false )
| knight(X0) ),
inference(backward_demodulation,[],[f58,f92]) ).
tff(f58,plain,
! [X0: $i] :
( knight(X0)
| ( $true = bG0 ) ),
inference(resolution,[],[f57,f54]) ).
tff(f54,plain,
! [X0: $i,X1: $i] :
( ~ knight(X1)
| knight(X0) ),
inference(resolution,[],[f47,f44]) ).
tff(f44,plain,
! [X0: $i,X1: $i] :
( ~ knave(X1)
| ~ knight(X0) ),
inference(cnf_transformation,[],[f24]) ).
tff(f24,plain,
! [X0,X1] :
( ~ knave(X1)
| ~ knight(X0) ),
inference(ennf_transformation,[],[f22]) ).
tff(f22,plain,
~ ? [X0,X1] :
( knave(X1)
& knight(X0) ),
inference(rectify,[],[f7]) ).
tff(f7,negated_conjecture,
~ ? [X2,X3] :
( knave(X3)
& knight(X2) ),
inference(negated_conjecture,[],[f6]) ).
tff(f6,conjecture,
? [X2,X3] :
( knave(X3)
& knight(X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',who_is_knight_and_knave) ).
tff(f47,plain,
! [X0: $i] :
( knave(X0)
| knight(X0) ),
inference(cnf_transformation,[],[f34]) ).
tff(f34,plain,
! [X0] :
( ( ~ knave(X0)
| ~ knight(X0) )
& ( knave(X0)
| knight(X0) ) ),
inference(nnf_transformation,[],[f1]) ).
tff(f1,axiom,
! [X0] :
( knight(X0)
<~> knave(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knights_xor_knaves) ).
tff(f57,plain,
( knight(mel)
| ( $true = bG0 ) ),
inference(resolution,[],[f42,f47]) ).
tff(f42,plain,
( ~ knave(mel)
| ( $true = bG0 ) ),
inference(cnf_transformation,[],[f33]) ).
tff(f33,plain,
( ( knave(mel)
| ( $true != bG0 ) )
& ( ( $true = bG0 )
| ~ knave(mel) ) ),
inference(nnf_transformation,[],[f10]) ).
tff(f116,plain,
! [X0: $i] :
( ( $true = bG1 )
| ~ knight(X0) ),
inference(resolution,[],[f114,f44]) ).
tff(f114,plain,
( knave(zoey)
| ( $true = bG1 ) ),
inference(subsumption_resolution,[],[f39,f102]) ).
tff(f102,plain,
~ knave(mel),
inference(trivial_inequality_removal,[],[f93]) ).
tff(f93,plain,
( ( $true = $false )
| ~ knave(mel) ),
inference(backward_demodulation,[],[f42,f92]) ).
tff(f39,plain,
( ( $true = bG1 )
| knave(mel)
| knave(zoey) ),
inference(cnf_transformation,[],[f32]) ).
tff(f32,plain,
( ( ( ~ knave(mel)
& ~ knave(zoey) )
| ( $true != bG1 ) )
& ( ( $true = bG1 )
| knave(mel)
| knave(zoey) ) ),
inference(flattening,[],[f31]) ).
tff(f31,plain,
( ( ( ~ knave(mel)
& ~ knave(zoey) )
| ( $true != bG1 ) )
& ( ( $true = bG1 )
| knave(mel)
| knave(zoey) ) ),
inference(nnf_transformation,[],[f12]) ).
tff(f12,plain,
( ( ~ knave(mel)
& ~ knave(zoey) )
<=> ( $true = bG1 ) ),
introduced(fool_formula_definition,[new_symbols(definition,[bG1])]) ).
tff(f46,plain,
says(mel,bG1),
inference(cnf_transformation,[],[f13]) ).
tff(f13,plain,
says(mel,bG1),
inference(fool_elimination,[],[f5,f12]) ).
tff(f5,axiom,
says(mel,
( ~ knave(mel)
& ~ knave(zoey) )),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',mel_speaks) ).
tff(f118,plain,
! [X0: $i,X1: $o] :
( ~ says(X0,bG2((X1)))
| ( $true = (X1) ) ),
inference(subsumption_resolution,[],[f49,f100]) ).
tff(f49,plain,
! [X0: $i,X1: $o] :
( ( $true = (X1) )
| ~ says(X0,bG2((X1)))
| ~ knight(X0) ),
inference(cnf_transformation,[],[f26]) ).
tff(f26,plain,
! [X0,X1: $o] :
( ( $true = (X1) )
| ~ says(X0,bG2((X1)))
| ~ knight(X0) ),
inference(flattening,[],[f25]) ).
tff(f25,plain,
! [X0,X1: $o] :
( ( $true = (X1) )
| ~ says(X0,bG2((X1)))
| ~ knight(X0) ),
inference(ennf_transformation,[],[f16]) ).
tff(f16,plain,
! [X0,X1: $o] :
( ( says(X0,bG2((X1)))
& knight(X0) )
=> ( $true = (X1) ) ),
inference(fool_elimination,[],[f14,f15]) ).
tff(f15,plain,
! [X1: $o] :
( ( $true = (X1) )
<=> ( $true = bG2((X1)) ) ),
introduced(fool_formula_definition,[new_symbols(definition,[bG2])]) ).
tff(f14,plain,
! [X0,X1: $o] :
( ( says(X0,(X1))
& knight(X0) )
=> (X1) ),
inference(rectify,[],[f2]) ).
tff(f2,axiom,
! [X0,X1: $o] :
( ( says(X0,(X1))
& knight(X0) )
=> (X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knights_tell_truth) ).
tff(f92,plain,
$false = bG0,
inference(subsumption_resolution,[],[f91,f75]) ).
tff(f75,plain,
! [X0: $i] :
( ~ knight(X0)
| ( $false = bG0 ) ),
inference(resolution,[],[f72,f44]) ).
tff(f72,plain,
( knave(mel)
| ( $false = bG0 ) ),
inference(trivial_inequality_removal,[],[f64]) ).
tff(f64,plain,
( ( $true != $true )
| knave(mel)
| ( $false = bG0 ) ),
inference(superposition,[],[f43,f9]) ).
tff(f43,plain,
( ( $true != bG0 )
| knave(mel) ),
inference(cnf_transformation,[],[f33]) ).
tff(f91,plain,
( ( $false = bG0 )
| knight(zoey) ),
inference(resolution,[],[f89,f47]) ).
tff(f89,plain,
( ~ knave(zoey)
| ( $false = bG0 ) ),
inference(resolution,[],[f65,f82]) ).
tff(f82,plain,
! [X0: $i] :
( ~ says(X0,$true)
| ~ knave(X0) ),
inference(forward_demodulation,[],[f53,f51]) ).
tff(f51,plain,
$true = bG3($true),
inference(equality_resolution,[],[f35]) ).
tff(f35,plain,
! [X0: $o] :
( ( $true = bG3((X0)) )
| ( $true != (X0) ) ),
inference(cnf_transformation,[],[f29]) ).
tff(f29,plain,
! [X0: $o] :
( ( ( $true = (X0) )
| ( $true != bG3((X0)) ) )
& ( ( $true = bG3((X0)) )
| ( $true != (X0) ) ) ),
inference(nnf_transformation,[],[f20]) ).
tff(f20,plain,
! [X0: $o] :
( ( $true = (X0) )
<=> ( $true = bG3((X0)) ) ),
inference(rectify,[],[f18]) ).
tff(f18,plain,
! [X1: $o] :
( ( $true = (X1) )
<=> ( $true = bG3((X1)) ) ),
introduced(fool_formula_definition,[new_symbols(definition,[bG3])]) ).
tff(f53,plain,
! [X0: $i] :
( ~ says(X0,bG3($true))
| ~ knave(X0) ),
inference(equality_resolution,[],[f50]) ).
tff(f50,plain,
! [X0: $i,X1: $o] :
( ( $true != (X1) )
| ~ says(X0,bG3((X1)))
| ~ knave(X0) ),
inference(cnf_transformation,[],[f28]) ).
tff(f28,plain,
! [X0,X1: $o] :
( ( $true != (X1) )
| ~ says(X0,bG3((X1)))
| ~ knave(X0) ),
inference(flattening,[],[f27]) ).
tff(f27,plain,
! [X0,X1: $o] :
( ( $true != (X1) )
| ~ says(X0,bG3((X1)))
| ~ knave(X0) ),
inference(ennf_transformation,[],[f23]) ).
tff(f23,plain,
! [X0,X1: $o] :
( ( says(X0,bG3((X1)))
& knave(X0) )
=> ( $true != (X1) ) ),
inference(flattening,[],[f19]) ).
tff(f19,plain,
! [X0,X1: $o] :
( ( says(X0,bG3((X1)))
& knave(X0) )
=> ( $true != (X1) ) ),
inference(fool_elimination,[],[f17,f18]) ).
tff(f17,plain,
! [X0,X1: $o] :
( ( says(X0,(X1))
& knave(X0) )
=> ~ (X1) ),
inference(rectify,[],[f3]) ).
tff(f3,axiom,
! [X0,X1: $o] :
( ( says(X0,(X1))
& knave(X0) )
=> ~ (X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knaves_lie) ).
tff(f65,plain,
( says(zoey,$true)
| ( $false = bG0 ) ),
inference(superposition,[],[f45,f9]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.03/0.13 % Problem : PUZ081_8 : TPTP v8.1.2. Released v8.0.0.
% 0.03/0.14 % Command : vampire --mode casc_sat -m 16384 --cores 7 -t %d %s
% 0.14/0.36 % Computer : n005.cluster.edu
% 0.14/0.36 % Model : x86_64 x86_64
% 0.14/0.36 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.14/0.36 % Memory : 8042.1875MB
% 0.14/0.36 % OS : Linux 3.10.0-693.el7.x86_64
% 0.14/0.36 % CPULimit : 300
% 0.14/0.36 % WCLimit : 300
% 0.14/0.36 % DateTime : Tue Apr 30 01:56:41 EDT 2024
% 0.14/0.36 % CPUTime :
% 0.14/0.36 % (16456)Running in auto input_syntax mode. Trying TPTP
% 0.21/0.38 % (16457)fmb+10_1_fmbas=off:fmbsr=1.3:nm=2_1451 on theBenchmark for (1451ds/0Mi)
% 0.21/0.38 % (16459)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)
% 0.21/0.38 % (16461)dis+1_20_av=off:lcm=predicate:nm=2:nwc=2.0_396 on theBenchmark for (396ds/0Mi)
% 0.21/0.38 % (16458)fmb+10_1_bce=on:fmbas=expand:fmbksg=on:fmbsr=1.3_569 on theBenchmark for (569ds/0Mi)
% 0.21/0.38 % (16460)fmb+10_1_bce=on:fmbas=expand:fmbksg=on:fmbsr=1.3:gsp=on:nm=4_470 on theBenchmark for (470ds/0Mi)
% 0.21/0.38 Detected minimum model sizes of [1,1]
% 0.21/0.38 Detected maximum model sizes of [2,2]
% 0.21/0.38 % (16463)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)
% 0.21/0.38 % (16462)dis+11_4:5_nm=4_216 on theBenchmark for (216ds/0Mi)
% 0.21/0.38 TRYING [1,1]
% 0.21/0.38 Detected minimum model sizes of [1,1]
% 0.21/0.38 Detected maximum model sizes of [2,2]
% 0.21/0.38 TRYING [1,1]
% 0.21/0.38 Detected minimum model sizes of [1,1]
% 0.21/0.38 Detected maximum model sizes of [2,2]
% 0.21/0.38 TRYING [1,1]
% 0.21/0.38 TRYING [1,2]
% 0.21/0.38 TRYING [1,2]
% 0.21/0.38 Detected minimum model sizes of [1,1]
% 0.21/0.38 Detected maximum model sizes of [2,2]
% 0.21/0.38 TRYING [2,2]
% 0.21/0.38 TRYING [1,1]
% 0.21/0.38 TRYING [1,2]
% 0.21/0.38 TRYING [2,2]
% 0.21/0.38 Cannot enumerate next child to try in an incomplete setup
% 0.21/0.38 % (16457)Refutation not found, incomplete strategy% (16457)------------------------------
% 0.21/0.38 % (16457)Version: Vampire 4.8 (commit 8e9376e55 on 2024-01-18 13:49:33 +0100)
% 0.21/0.38 % (16457)Termination reason: Refutation not found, incomplete strategy
% 0.21/0.38
% 0.21/0.38 % (16457)Memory used [KB]: 733
% 0.21/0.38 % (16457)Time elapsed: 0.005 s
% 0.21/0.38 % (16457)Instructions burned: 5 (million)
% 0.21/0.38 % (16457)------------------------------
% 0.21/0.38 % (16457)------------------------------
% 0.21/0.38 TRYING [2,2]
% 0.21/0.38 Cannot enumerate next child to try in an incomplete setup
% 0.21/0.38 % (16458)Refutation not found, incomplete strategy% (16458)------------------------------
% 0.21/0.38 % (16458)Version: Vampire 4.8 (commit 8e9376e55 on 2024-01-18 13:49:33 +0100)
% 0.21/0.38 % (16458)Termination reason: Refutation not found, incomplete strategy
% 0.21/0.38
% 0.21/0.38 % (16458)Memory used [KB]: 734
% 0.21/0.38 % (16458)Time elapsed: 0.005 s
% 0.21/0.38 % (16458)Instructions burned: 5 (million)
% 0.21/0.38 % (16458)------------------------------
% 0.21/0.38 % (16458)------------------------------
% 0.21/0.38 Cannot enumerate next child to try in an incomplete setup
% 0.21/0.38 % (16460)Refutation not found, incomplete strategy% (16460)------------------------------
% 0.21/0.38 % (16460)Version: Vampire 4.8 (commit 8e9376e55 on 2024-01-18 13:49:33 +0100)
% 0.21/0.38 % (16460)Termination reason: Refutation not found, incomplete strategy
% 0.21/0.38
% 0.21/0.38 % (16460)Memory used [KB]: 735
% 0.21/0.38 % (16460)Time elapsed: 0.005 s
% 0.21/0.38 % (16460)Instructions burned: 5 (million)
% 0.21/0.38 % (16460)------------------------------
% 0.21/0.38 % (16460)------------------------------
% 0.21/0.39 TRYING [1,2]
% 0.21/0.39 % (16461)First to succeed.
% 0.21/0.39 TRYING [2,2]
% 0.21/0.39 Cannot enumerate next child to try in an incomplete setup
% 0.21/0.39 % (16463)Refutation not found, incomplete strategy% (16463)------------------------------
% 0.21/0.39 % (16463)Version: Vampire 4.8 (commit 8e9376e55 on 2024-01-18 13:49:33 +0100)
% 0.21/0.39 % (16463)Termination reason: Refutation not found, incomplete strategy
% 0.21/0.39
% 0.21/0.39 % (16463)Memory used [KB]: 734
% 0.21/0.39 % (16463)Time elapsed: 0.005 s
% 0.21/0.39 % (16463)Instructions burned: 5 (million)
% 0.21/0.39 % (16463)------------------------------
% 0.21/0.39 % (16463)------------------------------
% 0.21/0.39 % (16462)Also succeeded, but the first one will report.
% 0.21/0.39 % (16461)Refutation found. Thanks to Tanya!
% 0.21/0.39 % SZS status Theorem for theBenchmark
% 0.21/0.39 % SZS output start Proof for theBenchmark
% See solution above
% 0.21/0.39 % (16461)------------------------------
% 0.21/0.39 % (16461)Version: Vampire 4.8 (commit 8e9376e55 on 2024-01-18 13:49:33 +0100)
% 0.21/0.39 % (16461)Termination reason: Refutation
% 0.21/0.39
% 0.21/0.39 % (16461)Memory used [KB]: 768
% 0.21/0.39 % (16461)Time elapsed: 0.007 s
% 0.21/0.39 % (16461)Instructions burned: 8 (million)
% 0.21/0.39 % (16461)------------------------------
% 0.21/0.39 % (16461)------------------------------
% 0.21/0.39 % (16456)Success in time 0.021 s
%------------------------------------------------------------------------------