%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : PLA022-2 : TPTP v9.3.1. Released v1.1.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n003.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 12:27:44 PM UTC 2026
% Result : Unsatisfiable 3.71s 1.51s
% Output : Refutation 3.71s
% Verified :
% SZS Type : Refutation
% Derivation depth : 12
% Number of leaves : 16
% Syntax : Number of formulae : 42 ( 12 unt; 2 def)
% Number of atoms : 112 ( 0 equ)
% Maximal formula atoms : 6 ( 2 avg)
% Number of connectives : 153 ( 83 ~; 68 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 9 ( 4 avg)
% Maximal term depth : 4 ( 1 avg)
% Number of predicates : 5 ( 4 usr; 3 prp; 0-2 aty)
% Number of functors : 13 ( 13 usr; 6 con; 0-2 aty)
% Number of variables : 35 ( 0 sgn 35 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X2,X0,X1] :
( holds(and(X0,X1),X2)
| ~ holds(X0,X2)
| ~ holds(X1,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',and_definition) ).
fof(f2,axiom,
! [X0,X1] :
( holds(holding(X0),do(pickup(X0),X1))
| ~ holds(empty,X1)
| ~ holds(clear(X0),X1)
| ~ differ(X0,table) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pickup_1) ).
fof(f4,axiom,
! [X2,X3,X0,X1] :
( holds(on(X0,X1),do(pickup(X2),X3))
| ~ holds(on(X0,X1),X3)
| ~ differ(X0,X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pickup_3) ).
fof(f5,axiom,
! [X2,X0,X1] :
( holds(clear(X0),do(pickup(X1),X2))
| ~ holds(clear(X0),X2)
| ~ differ(X0,X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',pickup_4) ).
fof(f7,axiom,
! [X2,X0,X1] :
( ~ holds(holding(X0),X2)
| holds(on(X0,X1),do(putdown(X0,X1),X2))
| ~ holds(clear(X1),X2) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',putdown_2) ).
fof(f9,axiom,
! [X2,X3,X0,X1,X4] :
( holds(on(X0,X1),do(putdown(X2,X3),X4))
| ~ holds(on(X0,X1),X4) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',putdown_4) ).
fof(f11,axiom,
! [X0,X1] :
( differ(X0,X1)
| ~ differ(X1,X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',symmetry_of_differ) ).
fof(f13,axiom,
differ(a,c),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',differ_a_c) ).
fof(f15,axiom,
differ(a,table),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',differ_a_table) ).
fof(f24,axiom,
holds(on(c,d),s0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',initial_state3) ).
fof(f26,axiom,
holds(clear(a),s0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',initial_state5) ).
fof(f28,axiom,
holds(clear(c),s0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',initial_state7) ).
fof(f29,axiom,
holds(empty,s0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',initial_state8) ).
fof(f31,negated_conjecture,
! [X0] : ~ holds(and(on(a,c),on(c,d)),X0),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',prove_ACD) ).
fof(f32,plain,
! [X0] :
( ~ holds(on(a,c),X0)
| ~ holds(on(c,d),X0) ),
inference(resolution,[],[f1,f31]) ).
fof(f37,plain,
! [X2,X0,X1] :
( holds(on(X0,X1),do(putdown(X0,X1),do(pickup(X0),X2)))
| ~ holds(clear(X1),do(pickup(X0),X2))
| ~ holds(empty,X2)
| ~ holds(clear(X0),X2)
| ~ differ(X0,table) ),
inference(resolution,[],[f7,f2]) ).
fof(f39,plain,
! [X0] :
( ~ holds(clear(c),do(pickup(a),X0))
| ~ holds(empty,X0)
| ~ holds(clear(a),X0)
| ~ differ(a,table)
| ~ holds(on(c,d),do(putdown(a,c),do(pickup(a),X0))) ),
inference(resolution,[],[f37,f32]) ).
fof(f40,plain,
! [X0] :
( ~ holds(on(c,d),do(putdown(a,c),do(pickup(a),X0)))
| ~ holds(empty,X0)
| ~ holds(clear(a),X0)
| ~ holds(clear(c),do(pickup(a),X0)) ),
inference(forward_subsumption_resolution,[],[f39,f15]) ).
fof(f42,plain,
! [X0] :
( ~ holds(on(c,d),do(pickup(a),X0))
| ~ holds(clear(a),X0)
| ~ holds(clear(c),do(pickup(a),X0))
| ~ holds(empty,X0) ),
inference(resolution,[],[f40,f9]) ).
fof(f45,plain,
! [X0] :
( ~ holds(clear(a),X0)
| ~ holds(clear(c),do(pickup(a),X0))
| ~ holds(empty,X0)
| ~ holds(on(c,d),X0)
| ~ differ(c,a) ),
inference(resolution,[],[f42,f4]) ).
fof(f47,definition,
( spl0_1
<=> differ(c,a) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f48,plain,
( differ(c,a)
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f47]) ).
fof(f49,plain,
( ~ differ(c,a)
| spl0_1 ),
inference(avatar_component_clause,[],[f47]) ).
fof(f51,definition,
( spl0_2
<=> ! [X0] :
( ~ holds(clear(a),X0)
| ~ holds(on(c,d),X0)
| ~ holds(empty,X0)
| ~ holds(clear(c),do(pickup(a),X0)) ) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f52,plain,
( ! [X0] :
( ~ holds(clear(c),do(pickup(a),X0))
| ~ holds(on(c,d),X0)
| ~ holds(empty,X0)
| ~ holds(clear(a),X0) )
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f51]) ).
fof(f53,plain,
( ~ spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f45,f51,f47]) ).
fof(f54,plain,
( ~ differ(a,c)
| spl0_1 ),
inference(resolution,[],[f49,f11]) ).
fof(f55,plain,
( $false
| spl0_1 ),
inference(forward_subsumption_resolution,[],[f54,f13]) ).
fof(f56,plain,
spl0_1,
inference(avatar_contradiction_clause,[],[f55]) ).
fof(f69,plain,
( ! [X0] :
( ~ holds(on(c,d),X0)
| ~ holds(empty,X0)
| ~ holds(clear(a),X0)
| ~ holds(clear(c),X0)
| ~ differ(c,a) )
| ~ spl0_2 ),
inference(resolution,[],[f52,f5]) ).
fof(f71,plain,
( ! [X0] :
( ~ holds(empty,X0)
| ~ holds(on(c,d),X0)
| ~ holds(clear(a),X0)
| ~ holds(clear(c),X0) )
| ~ spl0_1
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f69,f48]) ).
fof(f88,plain,
( ~ holds(on(c,d),s0)
| ~ holds(clear(a),s0)
| ~ holds(clear(c),s0)
| ~ spl0_1
| ~ spl0_2 ),
inference(resolution,[],[f71,f29]) ).
fof(f89,plain,
( ~ holds(clear(a),s0)
| ~ holds(clear(c),s0)
| ~ spl0_1
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f88,f24]) ).
fof(f90,plain,
( ~ holds(clear(c),s0)
| ~ spl0_1
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f89,f26]) ).
fof(f91,plain,
( $false
| ~ spl0_1
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f90,f28]) ).
fof(f92,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(avatar_contradiction_clause,[],[f91]) ).
cnf(s1,plain,
( ~ spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f53]) ).
cnf(s2,plain,
spl0_1,
inference(sat_conversion,[],[f56]) ).
cnf(s6,plain,
( ~ spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f92]) ).
cnf(s8,plain,
~ spl0_2,
inference(rat,[],[s6,s2]) ).
cnf(s9,plain,
$false,
inference(rat,[],[s1,s8,s2]) ).
fof(f93,plain,
$false,
inference(avatar_sat_refutation,[],[s9]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : PLA022-2 : TPTP v9.3.1. Released v1.1.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.14/0.39 % Computer : n003.cluster.edu
% 0.14/0.39 % Model : x86_64 x86_64
% 0.14/0.39 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.14/0.39 % Memory : 8046.5625MB
% 0.14/0.39 % OS : Linux 6.8.0-71-generic
% 0.14/0.39 % CPULimit : 300
% 0.14/0.39 % WCLimit : 300
% 0.14/0.39 % DateTime : Sun Sep 27 22:12:11 UTC 2026
% 0.14/0.39 % CPUTime :
% 0.14/0.39 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.14/0.43 Running first-order theorem proving
% 0.14/0.43 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
% 3.71/1.51 % (968682)Input is clausal, will run a generic CNF schedule.
% 3.71/1.51 % (968788)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=529049924:i=140167_2999 on theBenchmark for (2999ds/140167Mi)
% 3.71/1.51 % (968791)lrs+10_1_sil=8000:sp=occurrence:random_seed=1301122113:i=107:sd=3:ss=axioms:sgt=8_2999 on theBenchmark for (2999ds/107Mi)
% 3.71/1.51 % (968793)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=1627591070:s2a=on:i=180:gtg=position_2999 on theBenchmark for (2999ds/180Mi)
% 3.71/1.51 % (968794)dis-21_1_sil=8000:lcm=predicate:random_seed=1744943669: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)
% 3.71/1.51 % (968790)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=1060541798:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_2999 on theBenchmark for (2999ds/137899Mi)
% 3.71/1.51 % (968789)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=3378737613:i=132376:av=off_2999 on theBenchmark for (2999ds/132376Mi)
% 3.71/1.51 % (968792)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=4015200638:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_2999 on theBenchmark for (2999ds/114Mi)
% 3.71/1.51 % (968792)Refutation not found, incomplete strategy
% 3.71/1.51 % (968792)------------------------------
% 3.71/1.51 % (968792)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.71/1.51 % (968792)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.71/1.51 % (968792)CaDiCaL version: 2.1.3
% 3.71/1.51 % (968792)Termination reason: Refutation not found, incomplete strategy
% 3.71/1.51 % (968792)Time elapsed: 0.001 s
% 3.71/1.51 % (968792)Peak memory usage: 87 MB
% 3.71/1.51 % (968791)Refutation not found, incomplete strategy
% 3.71/1.51 % (968791)------------------------------
% 3.71/1.51 % (968791)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.71/1.51 % (968791)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.71/1.51 % (968791)CaDiCaL version: 2.1.3
% 3.71/1.51 % (968791)Termination reason: Refutation not found, incomplete strategy
% 3.71/1.51 % (968791)Time elapsed: 0.001 s
% 3.71/1.51 % (968791)Peak memory usage: 87 MB
% 3.71/1.51 % (968791)Instructions burned: 1 (million)
% 3.71/1.51 % (968793)First to succeed.
% 3.71/1.51 % (968793)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-968682"
% 3.71/1.51 % (968794)Also succeeded, but the first one will report.
% 3.71/1.51 % (968791)------------------------------
% 3.71/1.51 % (968791)------------------------------
% 3.71/1.51 % (968793)Refutation found. Thanks to Tanya!
% 3.71/1.51 % SZS status Unsatisfiable for theBenchmark
% 3.71/1.51 % SZS output start Proof for theBenchmark
% See solution above
% 3.71/1.51 % (968793)------------------------------
% 3.71/1.51 % (968793)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.71/1.51 % (968793)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.71/1.51 % (968793)CaDiCaL version: 2.1.3
% 3.71/1.51 % (968793)Termination reason: Refutation
% 3.71/1.51 % (968793)Time elapsed: 0.004 s
% 3.71/1.51 % (968793)Peak memory usage: 88 MB
% 3.71/1.51 % (968793)Instructions burned: 4 (million)
% 3.71/1.51 % (968793)------------------------------
% 3.71/1.51 % (968793)------------------------------
% 3.71/1.51 % (968682)Success in time 0.434 s
% 3.71/1.51 % Vampire exiting
%------------------------------------------------------------------------------