%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ007-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n015.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 12:31:03 PM UTC 2026
% Result : Unsatisfiable 2.17s 1.15s
% Output : Refutation 2.72s
% Verified :
% SZS Type : Refutation
% Derivation depth : 17
% Number of leaves : 31
% Syntax : Number of formulae : 116 ( 15 unt; 12 def)
% Number of atoms : 244 ( 2 equ)
% Maximal formula atoms : 4 ( 2 avg)
% Number of connectives : 249 ( 121 ~; 116 |; 0 &)
% ( 12 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 22 ( 20 usr; 13 prp; 0-2 aty)
% Number of functors : 5 ( 5 usr; 4 con; 0-1 aty)
% Number of variables : 11 ( 0 sgn 11 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f2,axiom,
! [X0] :
( ~ from_venus(X0)
| ~ from_mars(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_from_mars_and_venus) ).
fof(f3,axiom,
! [X0] :
( female(X0)
| male(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',male_or_female) ).
fof(f6,axiom,
! [X0] :
( ~ liar(X0)
| ~ truthteller(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',not_truthteller_and_liar) ).
fof(f10,axiom,
! [X0] :
( ~ a_truth(statement_by(X0))
| truthteller(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',true_statements_made_by_truthtellers) ).
fof(f11,axiom,
! [X0] :
( a_truth(statement_by(X0))
| liar(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',false_statements_made_by_liars) ).
fof(f12,axiom,
! [X0] :
( truthteller(X0)
| ~ female(X0)
| ~ from_venus(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',venusian_female_are_truthtellers) ).
fof(f15,axiom,
! [X0] :
( liar(X0)
| ~ female(X0)
| ~ from_mars(X0) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',marsian_females_are_liars) ).
fof(f16,axiom,
! [X0,X1] :
( ~ says(X0,X1)
| ~ truthteller(X0)
| a_truth(X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',truthtellers_make_true_statements) ).
fof(f17,axiom,
! [X0,X1] :
( ~ says(X0,X1)
| ~ liar(X0)
| ~ a_truth(X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',liars_make_false_statements) ).
fof(f18,axiom,
says(a,a_from_mars),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',a_says_hes_from_mars) ).
fof(f19,axiom,
says(b,a_has_lied),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',b_says_a_lies) ).
fof(f20,axiom,
( ~ from_mars(a)
| a_truth(a_from_mars) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',a_from_mars1) ).
fof(f21,axiom,
( from_mars(a)
| ~ a_truth(a_from_mars) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',a_from_mars2) ).
fof(f22,axiom,
( ~ a_truth(a_from_mars)
| ~ a_truth(statement_by(b)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',a_from_mars3) ).
fof(f23,axiom,
statement_by(a) = a_from_mars,
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',a_states) ).
fof(f24,plain,
a_from_mars = statement_by(a),
inference(reorient_equations,[],[f23]) ).
fof(f27,axiom,
( a_truth(a_from_mars)
| a_truth(statement_by(b)) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',truth_of_bs_statement) ).
fof(f29,axiom,
( ~ male(a)
| female(b) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',different_sex2) ).
fof(f30,negated_conjecture,
( from_mars(b)
| from_mars(a) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',one_from_mars) ).
fof(f31,negated_conjecture,
( from_venus(a)
| from_venus(b) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',one_from_venus) ).
fof(f33,definition,
( spl0_1
<=> from_venus(b) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f34,plain,
( from_venus(b)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f33]) ).
fof(f36,definition,
( spl0_2
<=> from_venus(a) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f37,plain,
( from_venus(a)
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f36]) ).
fof(f38,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f31,f36,f33]) ).
fof(f40,definition,
( spl0_3
<=> from_mars(a) ),
introduced(definition,[new_symbols(definition,[spl0_3])],[avatar_definition]) ).
fof(f41,plain,
( from_mars(a)
| ~ spl0_3 ),
inference(avatar_component_clause,[],[f40]) ).
fof(f43,definition,
( spl0_4
<=> from_mars(b) ),
introduced(definition,[new_symbols(definition,[spl0_4])],[avatar_definition]) ).
fof(f44,plain,
( from_mars(b)
| ~ spl0_4 ),
inference(avatar_component_clause,[],[f43]) ).
fof(f45,plain,
( spl0_3
| spl0_4 ),
inference(avatar_split_clause,[],[f30,f43,f40]) ).
fof(f47,definition,
( spl0_5
<=> female(b) ),
introduced(definition,[new_symbols(definition,[spl0_5])],[avatar_definition]) ).
fof(f48,plain,
( female(b)
| ~ spl0_5 ),
inference(avatar_component_clause,[],[f47]) ).
fof(f50,definition,
( spl0_6
<=> male(a) ),
introduced(definition,[new_symbols(definition,[spl0_6])],[avatar_definition]) ).
fof(f51,plain,
( ~ male(a)
| spl0_6 ),
inference(avatar_component_clause,[],[f50]) ).
fof(f52,plain,
( spl0_5
| ~ spl0_6 ),
inference(avatar_split_clause,[],[f29,f50,f47]) ).
fof(f57,definition,
( spl0_8
<=> female(a) ),
introduced(definition,[new_symbols(definition,[spl0_8])],[avatar_definition]) ).
fof(f58,plain,
( ~ female(a)
| spl0_8 ),
inference(avatar_component_clause,[],[f57]) ).
fof(f61,definition,
( spl0_9
<=> a_truth(statement_by(b)) ),
introduced(definition,[new_symbols(definition,[spl0_9])],[avatar_definition]) ).
fof(f62,plain,
( a_truth(statement_by(b))
| ~ spl0_9 ),
inference(avatar_component_clause,[],[f61]) ).
fof(f64,definition,
( spl0_10
<=> a_truth(a_from_mars) ),
introduced(definition,[new_symbols(definition,[spl0_10])],[avatar_definition]) ).
fof(f65,plain,
( a_truth(a_from_mars)
| ~ spl0_10 ),
inference(avatar_component_clause,[],[f64]) ).
fof(f66,plain,
( spl0_9
| spl0_10 ),
inference(avatar_split_clause,[],[f27,f64,f61]) ).
fof(f67,plain,
( ~ a_truth(statement_by(b))
| spl0_9 ),
inference(avatar_component_clause,[],[f61]) ).
fof(f68,plain,
( ~ a_truth(a_from_mars)
| spl0_10 ),
inference(avatar_component_clause,[],[f64]) ).
fof(f69,plain,
( ~ spl0_9
| ~ spl0_10 ),
inference(avatar_split_clause,[],[f22,f64,f61]) ).
fof(f70,plain,
( ~ spl0_10
| spl0_3 ),
inference(avatar_split_clause,[],[f21,f40,f64]) ).
fof(f72,plain,
( spl0_10
| ~ spl0_3 ),
inference(avatar_split_clause,[],[f20,f40,f64]) ).
fof(f74,plain,
( ~ a_truth(statement_by(a))
| spl0_10 ),
inference(superposition,[],[f68,f24]) ).
fof(f76,plain,
( ~ from_mars(a)
| ~ spl0_2 ),
inference(resolution,[],[f2,f37]) ).
fof(f78,plain,
( male(a)
| spl0_8 ),
inference(resolution,[],[f3,f58]) ).
fof(f79,plain,
( $false
| spl0_6
| spl0_8 ),
inference(forward_subsumption_resolution,[],[f78,f51]) ).
fof(f80,plain,
( spl0_6
| spl0_8 ),
inference(avatar_contradiction_clause,[],[f79]) ).
fof(f83,plain,
( truthteller(b)
| ~ spl0_9 ),
inference(resolution,[],[f10,f62]) ).
fof(f84,plain,
( liar(a)
| spl0_10 ),
inference(resolution,[],[f11,f74]) ).
fof(f86,plain,
( ~ truthteller(a)
| spl0_10 ),
inference(resolution,[],[f84,f6]) ).
fof(f87,plain,
( ~ female(a)
| ~ from_venus(a)
| spl0_10 ),
inference(resolution,[],[f86,f12]) ).
fof(f88,plain,
( ~ female(a)
| ~ spl0_2
| spl0_10 ),
inference(forward_subsumption_resolution,[],[f87,f37]) ).
fof(f89,plain,
( ~ spl0_8
| ~ spl0_2
| spl0_10 ),
inference(avatar_split_clause,[],[f88,f64,f36,f57]) ).
fof(f90,plain,
( ~ spl0_3
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f76,f36,f40]) ).
fof(f91,plain,
( ~ from_mars(b)
| ~ spl0_1 ),
inference(resolution,[],[f34,f2]) ).
fof(f92,plain,
( $false
| ~ spl0_1
| ~ spl0_4 ),
inference(forward_subsumption_resolution,[],[f91,f44]) ).
fof(f93,plain,
( ~ spl0_1
| ~ spl0_4 ),
inference(avatar_contradiction_clause,[],[f92]) ).
fof(f95,plain,
( liar(b)
| spl0_9 ),
inference(resolution,[],[f67,f11]) ).
fof(f96,plain,
( ~ truthteller(b)
| spl0_9 ),
inference(resolution,[],[f95,f6]) ).
fof(f98,plain,
( ~ female(b)
| ~ from_venus(b)
| spl0_9 ),
inference(resolution,[],[f96,f12]) ).
fof(f99,plain,
( ~ female(b)
| ~ spl0_1
| spl0_9 ),
inference(forward_subsumption_resolution,[],[f98,f34]) ).
fof(f110,plain,
( ~ truthteller(b)
| a_truth(a_has_lied) ),
inference(resolution,[],[f16,f19]) ).
fof(f113,plain,
( ~ liar(a)
| ~ a_truth(a_from_mars) ),
inference(resolution,[],[f17,f18]) ).
fof(f115,plain,
( ~ liar(b)
| ~ a_truth(a_has_lied) ),
inference(resolution,[],[f17,f19]) ).
fof(f118,plain,
( ~ liar(a)
| ~ spl0_10 ),
inference(forward_subsumption_resolution,[],[f113,f65]) ).
fof(f120,plain,
( ~ female(a)
| ~ from_mars(a)
| ~ spl0_10 ),
inference(resolution,[],[f118,f15]) ).
fof(f123,plain,
( ~ female(a)
| ~ spl0_3
| ~ spl0_10 ),
inference(forward_subsumption_resolution,[],[f120,f41]) ).
fof(f124,plain,
( ~ spl0_8
| ~ spl0_3
| ~ spl0_10 ),
inference(avatar_split_clause,[],[f123,f64,f40,f57]) ).
fof(f140,definition,
( spl0_14
<=> a_truth(a_has_lied) ),
introduced(definition,[new_symbols(definition,[spl0_14])],[avatar_definition]) ).
fof(f143,definition,
( spl0_15
<=> truthteller(b) ),
introduced(definition,[new_symbols(definition,[spl0_15])],[avatar_definition]) ).
fof(f144,plain,
( ~ truthteller(b)
| spl0_15 ),
inference(avatar_component_clause,[],[f143]) ).
fof(f145,plain,
( spl0_14
| ~ spl0_15 ),
inference(avatar_split_clause,[],[f110,f143,f140]) ).
fof(f148,definition,
( spl0_16
<=> liar(b) ),
introduced(definition,[new_symbols(definition,[spl0_16])],[avatar_definition]) ).
fof(f149,plain,
( ~ liar(b)
| spl0_16 ),
inference(avatar_component_clause,[],[f148]) ).
fof(f150,plain,
( ~ spl0_14
| ~ spl0_16 ),
inference(avatar_split_clause,[],[f115,f148,f140]) ).
fof(f162,plain,
( $false
| ~ spl0_9
| spl0_15 ),
inference(forward_subsumption_resolution,[],[f144,f83]) ).
fof(f163,plain,
( ~ spl0_9
| spl0_15 ),
inference(avatar_contradiction_clause,[],[f162]) ).
fof(f165,plain,
( ~ female(b)
| ~ from_mars(b)
| spl0_16 ),
inference(resolution,[],[f149,f15]) ).
fof(f171,plain,
( ~ from_mars(b)
| ~ spl0_5
| spl0_16 ),
inference(forward_subsumption_resolution,[],[f165,f48]) ).
fof(f172,plain,
( $false
| ~ spl0_4
| ~ spl0_5
| spl0_16 ),
inference(forward_subsumption_resolution,[],[f171,f44]) ).
fof(f173,plain,
( ~ spl0_4
| ~ spl0_5
| spl0_16 ),
inference(avatar_contradiction_clause,[],[f172]) ).
fof(f174,plain,
( $false
| ~ spl0_1
| ~ spl0_5
| spl0_9 ),
inference(forward_subsumption_resolution,[],[f99,f48]) ).
fof(f175,plain,
( ~ spl0_1
| ~ spl0_5
| spl0_9 ),
inference(avatar_contradiction_clause,[],[f174]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f38]) ).
cnf(s2,plain,
( spl0_3
| spl0_4 ),
inference(sat_conversion,[],[f45]) ).
cnf(s3,plain,
( spl0_5
| ~ spl0_6 ),
inference(sat_conversion,[],[f52]) ).
cnf(s5,plain,
( spl0_9
| spl0_10 ),
inference(sat_conversion,[],[f66]) ).
cnf(s6,plain,
( ~ spl0_9
| ~ spl0_10 ),
inference(sat_conversion,[],[f69]) ).
cnf(s7,plain,
( spl0_3
| ~ spl0_10 ),
inference(sat_conversion,[],[f70]) ).
cnf(s8,plain,
( ~ spl0_3
| spl0_10 ),
inference(sat_conversion,[],[f72]) ).
cnf(s9,plain,
( spl0_6
| spl0_8 ),
inference(sat_conversion,[],[f80]) ).
cnf(s10,plain,
( ~ spl0_2
| ~ spl0_8
| spl0_10 ),
inference(sat_conversion,[],[f89]) ).
cnf(s11,plain,
( ~ spl0_2
| ~ spl0_3 ),
inference(sat_conversion,[],[f90]) ).
cnf(s12,plain,
( ~ spl0_1
| ~ spl0_4 ),
inference(sat_conversion,[],[f93]) ).
cnf(s13,plain,
( ~ spl0_3
| ~ spl0_8
| ~ spl0_10 ),
inference(sat_conversion,[],[f124]) ).
cnf(s20,plain,
( spl0_14
| ~ spl0_15 ),
inference(sat_conversion,[],[f145]) ).
cnf(s21,plain,
( ~ spl0_14
| ~ spl0_16 ),
inference(sat_conversion,[],[f150]) ).
cnf(s25,plain,
( ~ spl0_9
| spl0_15 ),
inference(sat_conversion,[],[f163]) ).
cnf(s27,plain,
( ~ spl0_4
| ~ spl0_5
| spl0_16 ),
inference(sat_conversion,[],[f173]) ).
cnf(s28,plain,
( ~ spl0_1
| ~ spl0_5
| spl0_9 ),
inference(sat_conversion,[],[f175]) ).
cnf(s38,plain,
~ spl0_2,
inference(rat,[],[s27,s21,s3,s20,s9,s25,s10,s5,s2,s7,s11]) ).
cnf(s39,plain,
spl0_1,
inference(rat,[],[s1,s38]) ).
cnf(s40,plain,
~ spl0_4,
inference(rat,[],[s12,s39]) ).
cnf(s41,plain,
spl0_3,
inference(rat,[],[s2,s40]) ).
cnf(s42,plain,
spl0_10,
inference(rat,[],[s8,s41]) ).
cnf(s45,plain,
~ spl0_9,
inference(rat,[],[s6,s42]) ).
cnf(s46,plain,
~ spl0_8,
inference(rat,[],[s13,s41,s42]) ).
cnf(s52,plain,
~ spl0_5,
inference(rat,[],[s28,s39,s45]) ).
cnf(s53,plain,
spl0_6,
inference(rat,[],[s9,s46]) ).
cnf(s54,plain,
$false,
inference(rat,[],[s3,s53,s52]) ).
fof(f188,plain,
$false,
inference(avatar_sat_refutation,[],[s54]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PUZ007-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.37 % Computer : n015.cluster.edu
% 0.09/0.37 % Model : x86_64 x86_64
% 0.09/0.37 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.37 % Memory : 8046.5625MB
% 0.09/0.37 % OS : Linux 6.8.0-71-generic
% 0.09/0.37 % CPULimit : 300
% 0.09/0.37 % WCLimit : 300
% 0.09/0.37 % DateTime : Sun Sep 27 22:32:16 UTC 2026
% 0.09/0.37 % CPUTime :
% 0.09/0.37 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.40 Running first-order theorem proving
% 0.09/0.41 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
% 2.17/1.15 % (2079784)Input is clausal, will run a generic CNF schedule.
% 2.17/1.15 % (2079793)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=1198754027:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 2.17/1.15 % (2079793)First to succeed.
% 2.17/1.15 % (2079793)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-2079784"
% 2.17/1.15 % (2079789)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=3272284660:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 2.17/1.15 % (2079795)dis-21_1_sil=8000:lcm=predicate:random_seed=3595122866:st=5:avsq=on:i=117:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_2999 on theBenchmark for (2999ds/117Mi)
% 2.17/1.15 % (2079790)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=132255836:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 2.17/1.15 % (2079792)lrs+10_1_sil=8000:sp=occurrence:random_seed=3368715861:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 2.17/1.15 % (2079791)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=2584105647:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 2.17/1.15 % (2079794)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=486748021:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 2.17/1.15 % (2079795)Also succeeded, but the first one will report.
% 2.17/1.15 % (2079792)Also succeeded, but the first one will report.
% 2.17/1.15 % (2079794)Also succeeded, but the first one will report.
% 2.17/1.15 % (2079793)Refutation found. Thanks to Tanya!
% 2.17/1.15 % SZS status Unsatisfiable for theBenchmark
% 2.17/1.15 % SZS output start Proof for theBenchmark
% See solution above
% 2.72/1.34 % (2079793)------------------------------
% 2.72/1.34 % (2079793)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 2.72/1.34 % (2079793)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 2.72/1.34 % (2079793)CaDiCaL version: 2.1.3
% 2.72/1.34 % (2079793)Termination reason: Refutation
% 2.72/1.34 % (2079793)Time elapsed: 0.003 s
% 2.72/1.34 % (2079793)Peak memory usage: 89 MB
% 2.72/1.34 % (2079793)Instructions burned: 5 (million)
% 2.72/1.34 % (2079793)------------------------------
% 2.72/1.34 % (2079793)------------------------------
% 2.72/1.34 % (2079784)Success in time 0.299 s
% 2.72/1.34 % Vampire exiting
%------------------------------------------------------------------------------