%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PUZ001+1 : TPTP v9.3.1. Released v2.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n008.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 12:31:02 PM UTC 2026
% Result : Theorem 3.58s 1.49s
% Output : Refutation 3.58s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 14
% Syntax : Number of formulae : 66 ( 23 unt; 3 def)
% Number of atoms : 120 ( 28 equ)
% Maximal formula atoms : 4 ( 1 avg)
% Number of connectives : 105 ( 51 ~; 42 |; 2 &)
% ( 3 <=>; 7 =>; 0 <=; 0 <~>)
% Maximal formula depth : 6 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 9 ( 7 usr; 4 prp; 0-2 aty)
% Number of functors : 5 ( 5 usr; 4 con; 0-1 aty)
% Number of variables : 35 ( 0 sgn 33 !; 2 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
? [X0] :
( lives(X0)
& killed(X0,agatha) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_1) ).
fof(f5,axiom,
! [X0] :
( lives(X0)
=> ( X0 = agatha
| X0 = butler
| X0 = charles ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_3) ).
fof(f6,axiom,
! [X0,X1] :
( killed(X0,X1)
=> hates(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_4) ).
fof(f7,axiom,
! [X0,X1] :
( killed(X0,X1)
=> ~ richer(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_5) ).
fof(f8,axiom,
! [X0] :
( hates(agatha,X0)
=> ~ hates(charles,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_6) ).
fof(f9,axiom,
! [X0] :
( X0 != butler
=> hates(agatha,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_7) ).
fof(f10,axiom,
! [X0] :
( ~ richer(X0,agatha)
=> hates(butler,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_8) ).
fof(f11,axiom,
! [X0] :
( hates(agatha,X0)
=> hates(butler,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_9) ).
fof(f12,axiom,
! [X0] :
? [X1] : ~ hates(X0,X1),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_10) ).
fof(f13,axiom,
agatha != butler,
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55_11) ).
fof(f14,conjecture,
killed(agatha,agatha),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pel55) ).
fof(f15,negated_conjecture,
~ killed(agatha,agatha),
inference(negated_conjecture,[status(cth)],[f14]) ).
fof(f16,plain,
~ killed(agatha,agatha),
inference(flattening,[],[f15]) ).
fof(f17,plain,
! [X0] :
( X0 = agatha
| X0 = butler
| X0 = charles
| ~ lives(X0) ),
inference(ennf_transformation,[],[f5]) ).
fof(f18,plain,
! [X0] :
( X0 = agatha
| X0 = butler
| X0 = charles
| ~ lives(X0) ),
inference(flattening,[],[f17]) ).
fof(f19,plain,
! [X0,X1] :
( hates(X0,X1)
| ~ killed(X0,X1) ),
inference(ennf_transformation,[],[f6]) ).
fof(f20,plain,
! [X0,X1] :
( ~ richer(X0,X1)
| ~ killed(X0,X1) ),
inference(ennf_transformation,[],[f7]) ).
fof(f21,plain,
! [X0] :
( ~ hates(charles,X0)
| ~ hates(agatha,X0) ),
inference(ennf_transformation,[],[f8]) ).
fof(f22,plain,
! [X0] :
( hates(agatha,X0)
| butler = X0 ),
inference(ennf_transformation,[],[f9]) ).
fof(f23,plain,
! [X0] :
( hates(butler,X0)
| richer(X0,agatha) ),
inference(ennf_transformation,[],[f10]) ).
fof(f24,plain,
! [X0] :
( hates(butler,X0)
| ~ hates(agatha,X0) ),
inference(ennf_transformation,[],[f11]) ).
fof(f25,plain,
( lives(sK0)
& killed(sK0,agatha) ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK0]),skolemize(X0,sK0)],[f1]) ).
fof(f26,plain,
! [X0] : ~ hates(X0,sK1(X0)),
inference(skolemize,[status(esa),new_symbols(skolem,[sK1]),skolemize(X1,sK1(X0))],[f12]) ).
fof(f27,plain,
killed(sK0,agatha),
inference(cnf_transformation,[],[f25]) ).
fof(f28,plain,
lives(sK0),
inference(cnf_transformation,[],[f25]) ).
fof(f32,plain,
! [X0] :
( ~ lives(X0)
| butler = X0
| charles = X0
| agatha = X0 ),
inference(cnf_transformation,[],[f18]) ).
fof(f33,plain,
! [X0,X1] :
( hates(X0,X1)
| ~ killed(X0,X1) ),
inference(cnf_transformation,[],[f19]) ).
fof(f34,plain,
! [X0,X1] :
( ~ richer(X0,X1)
| ~ killed(X0,X1) ),
inference(cnf_transformation,[],[f20]) ).
fof(f35,plain,
! [X0] :
( ~ hates(charles,X0)
| ~ hates(agatha,X0) ),
inference(cnf_transformation,[],[f21]) ).
fof(f36,plain,
! [X0] :
( hates(agatha,X0)
| butler = X0 ),
inference(cnf_transformation,[],[f22]) ).
fof(f37,plain,
! [X0] :
( richer(X0,agatha)
| hates(butler,X0) ),
inference(cnf_transformation,[],[f23]) ).
fof(f38,plain,
! [X0] :
( hates(butler,X0)
| ~ hates(agatha,X0) ),
inference(cnf_transformation,[],[f24]) ).
fof(f39,plain,
! [X0] : ~ hates(X0,sK1(X0)),
inference(cnf_transformation,[],[f26]) ).
fof(f40,plain,
agatha != butler,
inference(cnf_transformation,[],[f13]) ).
fof(f41,plain,
~ killed(agatha,agatha),
inference(cnf_transformation,[],[f16]) ).
fof(f43,plain,
! [X0] :
( ~ killed(charles,X0)
| ~ hates(agatha,X0) ),
inference(resolution,[],[f35,f33]) ).
fof(f45,plain,
! [X0] :
( hates(butler,X0)
| ~ killed(X0,agatha) ),
inference(resolution,[],[f37,f34]) ).
fof(f48,plain,
~ hates(agatha,sK1(butler)),
inference(resolution,[],[f38,f39]) ).
fof(f52,plain,
( butler = sK0
| charles = sK0
| agatha = sK0 ),
inference(resolution,[],[f32,f28]) ).
fof(f54,definition,
( spl2_1
<=> agatha = sK0 ),
introduced(definition,[new_symbols(definition,[spl2_1])],[avatar_definition]) ).
fof(f56,plain,
( agatha = sK0
| ~ spl2_1 ),
inference(avatar_component_clause,[],[f54]) ).
fof(f58,definition,
( spl2_2
<=> charles = sK0 ),
introduced(definition,[new_symbols(definition,[spl2_2])],[avatar_definition]) ).
fof(f60,plain,
( charles = sK0
| ~ spl2_2 ),
inference(avatar_component_clause,[],[f58]) ).
fof(f62,definition,
( spl2_3
<=> butler = sK0 ),
introduced(definition,[new_symbols(definition,[spl2_3])],[avatar_definition]) ).
fof(f64,plain,
( butler = sK0
| ~ spl2_3 ),
inference(avatar_component_clause,[],[f62]) ).
fof(f65,plain,
( spl2_1
| spl2_2
| spl2_3 ),
inference(avatar_split_clause,[],[f52,f62,f58,f54]) ).
fof(f66,plain,
( killed(charles,agatha)
| ~ spl2_2 ),
inference(superposition,[],[f27,f60]) ).
fof(f68,plain,
( ~ hates(agatha,agatha)
| ~ spl2_2 ),
inference(resolution,[],[f66,f43]) ).
fof(f69,plain,
~ killed(sK1(butler),agatha),
inference(resolution,[],[f45,f39]) ).
fof(f72,plain,
butler = sK1(butler),
inference(resolution,[],[f48,f36]) ).
fof(f74,plain,
( agatha = butler
| ~ spl2_2 ),
inference(resolution,[],[f68,f36]) ).
fof(f76,plain,
( $false
| ~ spl2_2 ),
inference(forward_subsumption_resolution,[],[f74,f40]) ).
fof(f77,plain,
~ spl2_2,
inference(avatar_contradiction_clause,[],[f76]) ).
fof(f79,plain,
( killed(butler,agatha)
| ~ spl2_3 ),
inference(superposition,[],[f27,f64]) ).
fof(f81,plain,
~ killed(butler,agatha),
inference(superposition,[],[f69,f72]) ).
fof(f85,plain,
( $false
| ~ spl2_3 ),
inference(forward_subsumption_resolution,[],[f81,f79]) ).
fof(f86,plain,
~ spl2_3,
inference(avatar_contradiction_clause,[],[f85]) ).
fof(f88,plain,
( killed(agatha,agatha)
| ~ spl2_1 ),
inference(superposition,[],[f27,f56]) ).
fof(f90,plain,
( $false
| ~ spl2_1 ),
inference(forward_subsumption_resolution,[],[f88,f41]) ).
fof(f91,plain,
~ spl2_1,
inference(avatar_contradiction_clause,[],[f90]) ).
cnf(s1,plain,
( spl2_1
| spl2_2
| spl2_3 ),
inference(sat_conversion,[],[f65]) ).
cnf(s2,plain,
~ spl2_2,
inference(sat_conversion,[],[f77]) ).
cnf(s3,plain,
~ spl2_3,
inference(sat_conversion,[],[f86]) ).
cnf(s4,plain,
~ spl2_1,
inference(sat_conversion,[],[f91]) ).
cnf(s5,plain,
$false,
inference(rat,[],[s1,s3,s2,s4]) ).
fof(f92,plain,
$false,
inference(avatar_sat_refutation,[],[s5]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : PUZ001+1 : TPTP v9.3.1. Released v2.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.39 % Computer : n008.cluster.edu
% 0.10/0.39 % Model : x86_64 x86_64
% 0.10/0.39 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.10/0.39 % Memory : 8046.5625MB
% 0.10/0.39 % OS : Linux 6.8.0-71-generic
% 0.10/0.39 % CPULimit : 300
% 0.10/0.39 % WCLimit : 300
% 0.10/0.39 % DateTime : Sun Sep 27 22:28:09 UTC 2026
% 0.10/0.39 % CPUTime :
% 0.10/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.10/0.42 Running first-order theorem proving
% 0.10/0.42 Running: /export/starexec/sandbox/solver/bin/vampire --input_syntax tptp --output_axiom_names on --mode casc -m 16384 --cores 7 -t 300 /export/starexec/sandbox/benchmark/theBenchmark.p
% 3.58/1.49 % (1662269)Detected formulas, will run a generic FOF schedule.
% 3.58/1.49 % (1662278)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=1360510906:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 3.58/1.49 % (1662278)Refutation not found, incomplete strategy
% 3.58/1.49 % (1662278)------------------------------
% 3.58/1.49 % (1662278)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.58/1.49 % (1662278)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.58/1.49 % (1662278)CaDiCaL version: 2.1.3
% 3.58/1.49 % (1662278)Termination reason: Refutation not found, incomplete strategy
% 3.58/1.49 % (1662278)Time elapsed: 0.001 s
% 3.58/1.49 % (1662278)Peak memory usage: 87 MB
% 3.58/1.49 % (1662277)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=710070848:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 3.58/1.49 % (1662274)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=3553257957:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 3.58/1.49 % (1662275)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=3800086257:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 3.58/1.49 % (1662280)dis-21_1_sil=8000:lcm=predicate:random_seed=3588844396: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)
% 3.58/1.49 % (1662276)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=2625633673:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 3.58/1.49 % (1662277)Refutation not found, incomplete strategy
% 3.58/1.49 % (1662277)------------------------------
% 3.58/1.49 % (1662277)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.58/1.49 % (1662277)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.58/1.49 % (1662277)CaDiCaL version: 2.1.3
% 3.58/1.49 % (1662277)Termination reason: Refutation not found, incomplete strategy
% 3.58/1.49 % (1662277)Time elapsed: 0.001 s
% 3.58/1.49 % (1662277)Peak memory usage: 87 MB
% 3.58/1.49 % (1662280)Refutation not found, incomplete strategy
% 3.58/1.49 % (1662280)------------------------------
% 3.58/1.49 % (1662280)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.58/1.49 % (1662280)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.58/1.49 % (1662280)CaDiCaL version: 2.1.3
% 3.58/1.49 % (1662280)Termination reason: Refutation not found, incomplete strategy
% 3.58/1.49 % (1662280)Time elapsed: 0.001 s
% 3.58/1.49 % (1662280)Peak memory usage: 88 MB
% 3.58/1.49 % (1662279)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1500461616:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 3.58/1.49 % (1662279)First to succeed.
% 3.58/1.49 % (1662279)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-1662269"
% 3.58/1.49 % (1662278)------------------------------
% 3.58/1.49 % (1662278)------------------------------
% 3.58/1.49 % (1662280)------------------------------
% 3.58/1.49 % (1662280)------------------------------
% 3.58/1.49 % (1662277)------------------------------
% 3.58/1.49 % (1662277)------------------------------
% 3.58/1.49 % (1662279)Refutation found. Thanks to Tanya!
% 3.58/1.49 % SZS status Theorem for theBenchmark
% 3.58/1.49 % SZS output start Proof for theBenchmark
% See solution above
% 3.58/1.49 % (1662279)------------------------------
% 3.58/1.49 % (1662279)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.58/1.49 % (1662279)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.58/1.49 % (1662279)CaDiCaL version: 2.1.3
% 3.58/1.49 % (1662279)Termination reason: Refutation
% 3.58/1.49 % (1662279)Time elapsed: 0.004 s
% 3.58/1.49 % (1662279)Peak memory usage: 89 MB
% 3.58/1.49 % (1662279)Instructions burned: 3 (million)
% 3.58/1.49 % (1662279)------------------------------
% 3.58/1.49 % (1662279)------------------------------
% 3.58/1.49 % (1662269)Success in time 0.433 s
% 3.58/1.49 % Vampire exiting
%------------------------------------------------------------------------------