%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : CSR004+2 : TPTP v9.3.1. Bugfixed v3.1.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% Computer : n018.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 09:41:56 AM UTC 2026
% Result : Theorem 0.20s 1.50s
% Output : Refutation 0.20s
% Verified :
% SZS Type : Refutation
% Derivation depth : 9
% Number of leaves : 6
% Syntax : Number of formulae : 28 ( 14 unt; 2 def)
% Number of atoms : 69 ( 16 equ)
% Maximal formula atoms : 12 ( 2 avg)
% Number of connectives : 69 ( 28 ~; 25 |; 13 &)
% ( 3 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 9 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 6 ( 4 usr; 3 prp; 0-2 aty)
% Number of functors : 6 ( 6 usr; 5 con; 0-1 aty)
% Number of variables : 9 ( 0 sgn 9 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f16,axiom,
! [X0,X1] :
( happens(X0,X1)
<=> ( ( X0 = tapOn
& X1 = n0 )
| ( holdsAt(waterLevel(n3),X1)
& holdsAt(filling,X1)
& X0 = overflow ) ) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',happens_all_defn) ).
fof(f55,axiom,
holdsAt(waterLevel(n3),n3),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',waterLevel_3) ).
fof(f56,axiom,
holdsAt(filling,n3),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',filling_3) ).
fof(f57,conjecture,
happens(overflow,n3),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',overflow_3) ).
fof(f58,negated_conjecture,
~ happens(overflow,n3),
inference(negated_conjecture,[status(cth)],[f57]) ).
fof(f59,plain,
~ happens(overflow,n3),
inference(flattening,[],[f58]) ).
fof(f106,plain,
! [X0,X1] :
( ( happens(X0,X1)
| ( ( tapOn != X0
| n0 != X1 )
& ( ~ holdsAt(waterLevel(n3),X1)
| ~ holdsAt(filling,X1)
| overflow != X0 ) ) )
& ( ( X0 = tapOn
& X1 = n0 )
| ( holdsAt(waterLevel(n3),X1)
& holdsAt(filling,X1)
& X0 = overflow )
| ~ happens(X0,X1) ) ),
inference(nnf_transformation,[],[f16]) ).
fof(f107,plain,
! [X0,X1] :
( ( happens(X0,X1)
| ( ( tapOn != X0
| n0 != X1 )
& ( ~ holdsAt(waterLevel(n3),X1)
| ~ holdsAt(filling,X1)
| overflow != X0 ) ) )
& ( ( X0 = tapOn
& X1 = n0 )
| ( holdsAt(waterLevel(n3),X1)
& holdsAt(filling,X1)
& X0 = overflow )
| ~ happens(X0,X1) ) ),
inference(flattening,[],[f106]) ).
fof(f168,plain,
holdsAt(waterLevel(n3),n3),
inference(cnf_transformation,[],[f55]) ).
fof(f169,plain,
holdsAt(filling,n3),
inference(cnf_transformation,[],[f56]) ).
fof(f170,plain,
~ happens(overflow,n3),
inference(cnf_transformation,[],[f59]) ).
fof(f181,plain,
! [X0,X1] :
( happens(X0,X1)
| ~ holdsAt(waterLevel(n3),X1)
| ~ holdsAt(filling,X1)
| overflow != X0 ),
inference(cnf_transformation,[],[f107]) ).
fof(f237,plain,
! [X1] :
( happens(overflow,X1)
| ~ holdsAt(waterLevel(n3),X1)
| ~ holdsAt(filling,X1) ),
inference(equality_resolution,[],[f181]) ).
fof(f488,plain,
( ~ holdsAt(waterLevel(n3),n3)
| ~ holdsAt(filling,n3) ),
inference(resolution,[],[f237,f170]) ).
fof(f490,definition,
( spl12_19
<=> holdsAt(filling,n3) ),
introduced(definition,[new_symbols(definition,[spl12_19])],[avatar_definition]) ).
fof(f491,plain,
( ~ holdsAt(filling,n3)
| spl12_19 ),
inference(avatar_component_clause,[],[f490]) ).
fof(f493,definition,
( spl12_20
<=> holdsAt(waterLevel(n3),n3) ),
introduced(definition,[new_symbols(definition,[spl12_20])],[avatar_definition]) ).
fof(f494,plain,
( ~ holdsAt(waterLevel(n3),n3)
| spl12_20 ),
inference(avatar_component_clause,[],[f493]) ).
fof(f495,plain,
( ~ spl12_19
| ~ spl12_20 ),
inference(avatar_split_clause,[],[f488,f493,f490]) ).
fof(f496,plain,
( $false
| spl12_19 ),
inference(resolution,[],[f491,f169]) ).
fof(f497,plain,
spl12_19,
inference(avatar_contradiction_clause,[],[f496]) ).
fof(f498,plain,
( $false
| spl12_20 ),
inference(resolution,[],[f494,f168]) ).
fof(f499,plain,
spl12_20,
inference(avatar_contradiction_clause,[],[f498]) ).
cnf(s24,plain,
( ~ spl12_19
| ~ spl12_20 ),
inference(sat_conversion,[],[f495]) ).
cnf(s25,plain,
spl12_19,
inference(sat_conversion,[],[f497]) ).
cnf(s26,plain,
spl12_20,
inference(sat_conversion,[],[f499]) ).
cnf(s27,plain,
$false,
inference(rat,[],[s24,s26,s25]) ).
fof(f500,plain,
$false,
inference(avatar_sat_refutation,[],[s27]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : CSR004+2 : TPTP v9.3.1. Bugfixed v3.1.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.18 % Computer : n018.cluster.edu
% 0.09/0.18 % Model : x86_64 x86_64
% 0.09/0.18 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.18 % Memory : 8046.5625MB
% 0.09/0.18 % OS : Linux 6.8.0-71-generic
% 0.09/0.18 % CPULimit : 300
% 0.09/0.18 % WCLimit : 300
% 0.09/0.18 % DateTime : Mon Sep 28 22:07:25 UTC 2026
% 0.09/0.19 % CPUTime :
% 0.09/0.19 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 THM
% 0.09/0.22 Running first-order theorem proving
% 0.09/0.22 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
% 0.20/1.50 % (3844982)Detected formulas, will run a generic FOF schedule.
% 0.20/1.50 % (3845002)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=2451529903:i=141193_2999 on theBenchmark for (2999ds/141193Mi)
% 0.20/1.50 % (3845008)dis-21_1_sil=8000:lcm=predicate:random_seed=2257494070: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)
% 0.20/1.50 % (3845008)First to succeed.
% 0.20/1.50 % (3845008)Solution written to "/export/starexec/sandbox2/tmp/vampire-proof-3844982"
% 0.20/1.50 % (3845006)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=4045280078:i=119:av=off:ss=axioms_2999 on theBenchmark for (2999ds/119Mi)
% 0.20/1.50 % (3845003)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=2976938338:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_2999 on theBenchmark for (2999ds/134677Mi)
% 0.20/1.50 % (3845005)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=2625588416:i=109:sd=1:ins=1:gsp=on:ss=axioms_2999 on theBenchmark for (2999ds/109Mi)
% 0.20/1.50 % (3845004)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=2608327141:i=141695:sd=1:nm=32:gsp=on:ss=included_2999 on theBenchmark for (2999ds/141695Mi)
% 0.20/1.50 % (3845006)Refutation not found, incomplete strategy
% 0.20/1.50 % (3845006)------------------------------
% 0.20/1.50 % (3845006)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.20/1.50 % (3845006)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.20/1.50 % (3845006)CaDiCaL version: 2.1.3
% 0.20/1.50 % (3845006)Termination reason: Refutation not found, incomplete strategy
% 0.20/1.50 % (3845006)Time elapsed: 0.003 s
% 0.20/1.50 % (3845006)Peak memory usage: 88 MB
% 0.20/1.50 % (3845006)Instructions burned: 1 (million)
% 0.20/1.50 % (3845005)Refutation not found, incomplete strategy
% 0.20/1.50 % (3845005)------------------------------
% 0.20/1.50 % (3845005)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.20/1.50 % (3845005)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.20/1.50 % (3845005)CaDiCaL version: 2.1.3
% 0.20/1.50 % (3845005)Termination reason: Refutation not found, incomplete strategy
% 0.20/1.50 % (3845005)Time elapsed: 0.002 s
% 0.20/1.50 % (3845005)Peak memory usage: 88 MB
% 0.20/1.50 % (3845007)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3621704696:s2a=on:i=139:gtg=position_2999 on theBenchmark for (2999ds/139Mi)
% 0.20/1.50 % (3845007)Also succeeded, but the first one will report.
% 0.20/1.50 % (3845008)Refutation found. Thanks to Tanya!
% 0.20/1.50 % SZS status Theorem for theBenchmark
% 0.20/1.50 % SZS output start Proof for theBenchmark
% See solution above
% 0.20/1.50 % (3845008)------------------------------
% 0.20/1.50 % (3845008)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 0.20/1.50 % (3845008)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.20/1.50 % (3845008)CaDiCaL version: 2.1.3
% 0.20/1.50 % (3845008)Termination reason: Refutation
% 0.20/1.50 % (3845008)Time elapsed: 0.009 s
% 0.20/1.50 % (3845008)Peak memory usage: 89 MB
% 0.20/1.50 % (3845008)Instructions burned: 8 (million)
% 0.20/1.50 % (3845008)------------------------------
% 0.20/1.50 % (3845008)------------------------------
% 0.20/1.50 % (3844982)Success in time 0.584 s
% 0.20/1.50 % Vampire exiting
%------------------------------------------------------------------------------