TSTP Solution File: PUZ021-1 by Vampire-SAT---4.8
View Problem
- Process Solution
%------------------------------------------------------------------------------
% File : Vampire-SAT---4.8
% Problem : PUZ021-1 : TPTP v8.1.2. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : vampire --mode casc_sat -m 16384 --cores 7 -t %d %s
% Computer : n010.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 08:49:37 EDT 2024
% Result : Unsatisfiable 0.21s 0.46s
% Output : Refutation 0.21s
% Verified :
% SZS Type : Refutation
% Derivation depth : 11
% Number of leaves : 18
% Syntax : Number of formulae : 60 ( 5 unt; 0 def)
% Number of atoms : 137 ( 0 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 126 ( 49 ~; 72 |; 0 &)
% ( 5 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 4 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of predicates : 8 ( 7 usr; 6 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 1 con; 0-2 aty)
% Number of variables : 76 ( 76 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f2406,plain,
$false,
inference(avatar_sat_refutation,[],[f91,f284,f380,f2347,f2349,f2405]) ).
fof(f2405,plain,
~ spl0_72,
inference(avatar_contradiction_clause,[],[f2404]) ).
fof(f2404,plain,
( $false
| ~ spl0_72 ),
inference(subsumption_resolution,[],[f2386,f2339]) ).
fof(f2339,plain,
( ! [X0] : a_truth(X0,knight(me))
| ~ spl0_72 ),
inference(avatar_component_clause,[],[f2338]) ).
fof(f2338,plain,
( spl0_72
<=> ! [X0] : a_truth(X0,knight(me)) ),
introduced(avatar_definition,[new_symbols(naming,[spl0_72])]) ).
fof(f2386,plain,
( ! [X0] : ~ a_truth(rich(X0),knight(me))
| ~ spl0_72 ),
inference(resolution,[],[f2339,f3]) ).
fof(f3,axiom,
! [X0,X1] :
( ~ a_truth(poor(X0),X1)
| ~ a_truth(rich(X0),X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_rich_and_poor) ).
fof(f2349,plain,
( spl0_1
| spl0_72
| spl0_4 ),
inference(avatar_split_clause,[],[f2348,f88,f2338,f36]) ).
fof(f36,plain,
( spl0_1
<=> ! [X0] : says(me,X0) ),
introduced(avatar_definition,[new_symbols(naming,[spl0_1])]) ).
fof(f88,plain,
( spl0_4
<=> a_truth(knave(me),knight(me)) ),
introduced(avatar_definition,[new_symbols(naming,[spl0_4])]) ).
fof(f2348,plain,
( ! [X0,X1] :
( a_truth(X0,knight(me))
| says(me,X1) )
| spl0_4 ),
inference(subsumption_resolution,[],[f2326,f18]) ).
fof(f18,plain,
! [X0] :
( ~ a_truth(knight(me),X0)
| says(me,X0) ),
inference(resolution,[],[f17,f1]) ).
fof(f1,axiom,
! [X0,X1] :
( ~ a_truth(knave(X0),X1)
| ~ a_truth(knight(X0),X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_knight_and_knave) ).
fof(f17,plain,
! [X0] :
( a_truth(knave(me),X0)
| says(me,X0) ),
inference(resolution,[],[f13,f9]) ).
fof(f9,axiom,
! [X2,X0,X1] :
( ~ a_truth(and(X0,X1),X2)
| a_truth(X0,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',conjunction1) ).
fof(f13,axiom,
! [X0] :
( a_truth(and(knave(me),rich(me)),X0)
| says(me,X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_statement_exists2) ).
fof(f2326,plain,
( ! [X0,X1] :
( a_truth(X0,knight(me))
| a_truth(knight(me),X1)
| says(me,X1) )
| spl0_4 ),
inference(resolution,[],[f667,f131]) ).
fof(f131,plain,
! [X2,X0,X1] :
( says(X0,and(knight(me),X1))
| a_truth(knight(X0),X2)
| says(me,X2) ),
inference(resolution,[],[f64,f18]) ).
fof(f64,plain,
! [X2,X3,X0,X1] :
( says(X0,and(X1,X2))
| a_truth(knight(X0),X3)
| a_truth(X1,X3) ),
inference(resolution,[],[f19,f9]) ).
fof(f19,plain,
! [X2,X0,X1] :
( a_truth(X0,X1)
| says(X2,X0)
| a_truth(knight(X2),X1) ),
inference(resolution,[],[f8,f2]) ).
fof(f2,axiom,
! [X0,X1] :
( a_truth(knave(X0),X1)
| a_truth(knight(X0),X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knight_or_knave) ).
fof(f8,axiom,
! [X2,X0,X1] :
( ~ a_truth(knave(X0),X2)
| a_truth(X1,X2)
| says(X0,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knaves_lie2) ).
fof(f667,plain,
( ! [X0,X1] :
( ~ says(me,and(X0,X1))
| a_truth(X1,knight(me)) )
| spl0_4 ),
inference(resolution,[],[f304,f10]) ).
fof(f10,axiom,
! [X2,X0,X1] :
( ~ a_truth(and(X0,X1),X2)
| a_truth(X1,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',conjunction2) ).
fof(f304,plain,
( ! [X0] :
( a_truth(X0,knight(me))
| ~ says(me,X0) )
| spl0_4 ),
inference(resolution,[],[f294,f5]) ).
fof(f5,axiom,
! [X2,X0,X1] :
( ~ a_truth(knight(X0),X2)
| a_truth(X1,X2)
| ~ says(X0,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knights_tell_truth1) ).
fof(f294,plain,
( a_truth(knight(me),knight(me))
| spl0_4 ),
inference(resolution,[],[f90,f2]) ).
fof(f90,plain,
( ~ a_truth(knave(me),knight(me))
| spl0_4 ),
inference(avatar_component_clause,[],[f88]) ).
fof(f2347,plain,
( spl0_8
| spl0_72
| spl0_4 ),
inference(avatar_split_clause,[],[f2325,f88,f2338,f322]) ).
fof(f322,plain,
( spl0_8
<=> ! [X0] : a_truth(knight(me),X0) ),
introduced(avatar_definition,[new_symbols(naming,[spl0_8])]) ).
fof(f2325,plain,
( ! [X0,X1] :
( a_truth(X0,knight(me))
| a_truth(knight(me),X1) )
| spl0_4 ),
inference(resolution,[],[f667,f144]) ).
fof(f144,plain,
! [X2,X0,X1] :
( says(X0,and(knight(X0),X1))
| a_truth(knight(X0),X2) ),
inference(factoring,[],[f64]) ).
fof(f380,plain,
( ~ spl0_1
| spl0_4
| ~ spl0_8 ),
inference(avatar_contradiction_clause,[],[f373]) ).
fof(f373,plain,
( $false
| ~ spl0_1
| spl0_4
| ~ spl0_8 ),
inference(resolution,[],[f355,f90]) ).
fof(f355,plain,
( ! [X0,X1] : a_truth(X0,X1)
| ~ spl0_1
| ~ spl0_8 ),
inference(subsumption_resolution,[],[f351,f37]) ).
fof(f37,plain,
( ! [X0] : says(me,X0)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f36]) ).
fof(f351,plain,
( ! [X0,X1] :
( a_truth(X0,X1)
| ~ says(me,X0) )
| ~ spl0_8 ),
inference(resolution,[],[f323,f5]) ).
fof(f323,plain,
( ! [X0] : a_truth(knight(me),X0)
| ~ spl0_8 ),
inference(avatar_component_clause,[],[f322]) ).
fof(f284,plain,
( ~ spl0_4
| spl0_3 ),
inference(avatar_split_clause,[],[f281,f84,f88]) ).
fof(f84,plain,
( spl0_3
<=> a_truth(rich(me),knight(me)) ),
introduced(avatar_definition,[new_symbols(naming,[spl0_3])]) ).
fof(f281,plain,
( ~ a_truth(knave(me),knight(me))
| spl0_3 ),
inference(resolution,[],[f258,f86]) ).
fof(f86,plain,
( ~ a_truth(rich(me),knight(me))
| spl0_3 ),
inference(avatar_component_clause,[],[f84]) ).
fof(f258,plain,
! [X0] :
( a_truth(rich(me),X0)
| ~ a_truth(knave(me),X0) ),
inference(resolution,[],[f179,f4]) ).
fof(f4,axiom,
! [X0,X1] :
( a_truth(poor(X0),X1)
| a_truth(rich(X0),X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',rich_or_poor) ).
fof(f179,plain,
! [X0] :
( ~ a_truth(poor(me),X0)
| ~ a_truth(knave(me),X0) ),
inference(resolution,[],[f166,f7]) ).
fof(f7,axiom,
! [X2,X0,X1] :
( ~ says(X0,X1)
| ~ a_truth(X1,X2)
| ~ a_truth(knave(X0),X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knaves_lie1) ).
fof(f166,plain,
says(me,poor(me)),
inference(duplicate_literal_removal,[],[f165]) ).
fof(f165,plain,
( says(me,poor(me))
| says(me,poor(me)) ),
inference(resolution,[],[f49,f16]) ).
fof(f16,plain,
! [X0] :
( a_truth(rich(me),X0)
| says(me,X0) ),
inference(resolution,[],[f13,f10]) ).
fof(f49,plain,
! [X0] :
( ~ a_truth(rich(X0),poor(X0))
| says(me,poor(X0)) ),
inference(resolution,[],[f33,f3]) ).
fof(f33,plain,
! [X0] :
( a_truth(X0,X0)
| says(me,X0) ),
inference(factoring,[],[f20]) ).
fof(f20,plain,
! [X0,X1] :
( a_truth(X0,X1)
| says(me,X0)
| says(me,X1) ),
inference(resolution,[],[f8,f17]) ).
fof(f91,plain,
( ~ spl0_3
| ~ spl0_4 ),
inference(avatar_split_clause,[],[f82,f88,f84]) ).
fof(f82,plain,
( ~ a_truth(knave(me),knight(me))
| ~ a_truth(rich(me),knight(me)) ),
inference(resolution,[],[f73,f11]) ).
fof(f11,axiom,
! [X2,X0,X1] :
( a_truth(and(X0,X1),X2)
| ~ a_truth(X0,X2)
| ~ a_truth(X1,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',conjunction3) ).
fof(f73,plain,
~ a_truth(and(knave(me),rich(me)),knight(me)),
inference(resolution,[],[f72,f12]) ).
fof(f12,axiom,
! [X0] :
( ~ says(me,X0)
| ~ a_truth(and(knave(me),rich(me)),X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',prove_statement_exists1) ).
fof(f72,plain,
! [X0] : says(X0,knight(X0)),
inference(subsumption_resolution,[],[f71,f6]) ).
fof(f6,axiom,
! [X2,X0,X1] :
( ~ a_truth(knight(X0),X2)
| says(X0,X1)
| ~ a_truth(X1,X2) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',knights_tell_truth2) ).
fof(f71,plain,
! [X0,X1] :
( a_truth(knight(X0),X1)
| says(X0,knight(X0)) ),
inference(factoring,[],[f19]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.07/0.13 % Problem : PUZ021-1 : TPTP v8.1.2. Released v1.0.0.
% 0.07/0.14 % Command : vampire --mode casc_sat -m 16384 --cores 7 -t %d %s
% 0.15/0.35 % Computer : n010.cluster.edu
% 0.15/0.35 % Model : x86_64 x86_64
% 0.15/0.35 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.15/0.35 % Memory : 8042.1875MB
% 0.15/0.35 % OS : Linux 3.10.0-693.el7.x86_64
% 0.15/0.35 % CPULimit : 300
% 0.15/0.35 % WCLimit : 300
% 0.15/0.35 % DateTime : Fri May 3 18:01:53 EDT 2024
% 0.15/0.36 % CPUTime :
% 0.15/0.36 % (22438)Running in auto input_syntax mode. Trying TPTP
% 0.15/0.38 % (22441)fmb+10_1_bce=on:fmbas=expand:fmbksg=on:fmbsr=1.3_569 on theBenchmark for (569ds/0Mi)
% 0.15/0.38 % (22443)fmb+10_1_bce=on:fmbas=expand:fmbksg=on:fmbsr=1.3:gsp=on:nm=4_470 on theBenchmark for (470ds/0Mi)
% 0.15/0.38 % (22440)fmb+10_1_fmbas=off:fmbsr=1.3:nm=2_1451 on theBenchmark for (1451ds/0Mi)
% 0.15/0.38 % (22444)dis+1_20_av=off:lcm=predicate:nm=2:nwc=2.0_396 on theBenchmark for (396ds/0Mi)
% 0.15/0.38 % (22442)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)
% 0.15/0.38 % (22445)dis+11_4:5_nm=4_216 on theBenchmark for (216ds/0Mi)
% 0.15/0.38 % (22446)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)
% 0.15/0.38 Detected minimum model sizes of [1,1]
% 0.15/0.38 TRYING [1]
% 0.15/0.38 Detected maximum model sizes of [max,1]
% 0.15/0.38 TRYING [1,1]
% 0.15/0.38 Detected minimum model sizes of [1,1]
% 0.15/0.38 Detected maximum model sizes of [max,1]
% 0.15/0.38 TRYING [1]
% 0.15/0.38 TRYING [1,1]
% 0.15/0.38 TRYING [2]
% 0.15/0.38 TRYING [2,1]
% 0.15/0.38 TRYING [2]
% 0.15/0.38 TRYING [2,1]
% 0.15/0.38 TRYING [3]
% 0.15/0.38 TRYING [3,1]
% 0.15/0.38 TRYING [3]
% 0.15/0.38 TRYING [3,1]
% 0.15/0.38 TRYING [4]
% 0.15/0.38 TRYING [4,1]
% 0.15/0.38 TRYING [4,1]
% 0.15/0.38 TRYING [4]
% 0.15/0.38 TRYING [5]
% 0.15/0.38 TRYING [5,1]
% 0.15/0.38 TRYING [5,1]
% 0.15/0.39 TRYING [5]
% 0.15/0.39 TRYING [6]
% 0.15/0.39 TRYING [6,1]
% 0.15/0.39 TRYING [6,1]
% 0.15/0.39 TRYING [6]
% 0.15/0.40 TRYING [7]
% 0.21/0.40 TRYING [7,1]
% 0.21/0.40 TRYING [7,1]
% 0.21/0.40 TRYING [7]
% 0.21/0.42 TRYING [8]
% 0.21/0.42 TRYING [8,1]
% 0.21/0.42 TRYING [8,1]
% 0.21/0.43 TRYING [8]
% 0.21/0.44 TRYING [9]
% 0.21/0.45 TRYING [9,1]
% 0.21/0.45 TRYING [9,1]
% 0.21/0.46 % (22445)First to succeed.
% 0.21/0.46 % (22445)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-22438"
% 0.21/0.46 % (22445)Refutation found. Thanks to Tanya!
% 0.21/0.46 % SZS status Unsatisfiable for theBenchmark
% 0.21/0.46 % SZS output start Proof for theBenchmark
% See solution above
% 0.21/0.46 % (22445)------------------------------
% 0.21/0.46 % (22445)Version: Vampire 4.8 (commit 3a798227e on 2024-05-03 07:42:47 +0200)
% 0.21/0.46 % (22445)Termination reason: Refutation
% 0.21/0.46
% 0.21/0.46 % (22445)Memory used [KB]: 1636
% 0.21/0.46 % (22445)Time elapsed: 0.083 s
% 0.21/0.46 % (22445)Instructions burned: 155 (million)
% 0.21/0.46 % (22438)Success in time 0.099 s
%------------------------------------------------------------------------------