%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : DAT020_1 : TPTP v9.3.1. Released v5.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n017.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 09:47:58 AM UTC 2026
% Result : Theorem 0.12s 0.27s
% Output : Refutation 0.12s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 3
% Syntax : Number of formulae : 17 ( 10 unt; 0 typ; 0 def)
% Number of atoms : 34 ( 9 equ)
% Maximal formula atoms : 6 ( 2 avg)
% Number of connectives : 29 ( 12 ~; 12 |; 4 &)
% ( 1 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 8 ( 3 avg)
% Maximal term depth : 4 ( 1 avg)
% Number arithmetic : 44 ( 0 atm; 0 fun; 34 num; 10 var)
% Number of types : 3 ( 1 usr; 1 ari; 0 dat; 0 cdt)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 3 ( 1 usr; 1 prp; 0-2 aty)
% Number of functors : 7 ( 3 usr; 5 con; 0-2 aty)
% Number of variables : 14 ( 14 !; 0 ?; 14 :)
% Comments :
%------------------------------------------------------------------------------
tff(type_def_5,type,
collection: $tType ).
tff(func_def_0,type,
empty: collection ).
tff(func_def_1,type,
add: ( $int * collection ) > collection ).
tff(func_def_2,type,
remove: ( $int * collection ) > collection ).
tff(pred_def_1,type,
in: ( $int * collection ) > $o ).
tff(f1,axiom,
! [X0: $int] : ~ in(X0,empty),
file('/export/starexec/sandbox2/benchmark/Axioms/DAT002_0.ax',ax1) ).
tff(f4,axiom,
! [X0: $int,X1: collection,X2: $int] :
( ( in(X0,X1)
| ( X0 = X2 ) )
<=> in(X0,add(X2,X1)) ),
file('/export/starexec/sandbox2/benchmark/Axioms/DAT002_0.ax',ax4) ).
tff(f6,conjecture,
~ in(4,add(1,add(3,add(5,empty)))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',co1) ).
tff(f7,negated_conjecture,
~ ~ in(4,add(1,add(3,add(5,empty)))),
inference(negated_conjecture,[status(cth)],[f6]) ).
tff(f8,plain,
in(4,add(1,add(3,add(5,empty)))),
inference(flattening,[],[f7]) ).
tff(f9,plain,
! [X0: $int,X1: collection,X2: $int] :
( ( in(X0,X1)
| ( X0 = X2 )
| ~ in(X0,add(X2,X1)) )
& ( in(X0,add(X2,X1))
| ( ~ in(X0,X1)
& ( X0 != X2 ) ) ) ),
inference(nnf_transformation,[],[f4]) ).
tff(f10,plain,
! [X0: $int,X1: collection,X2: $int] :
( ( in(X0,X1)
| ( X0 = X2 )
| ~ in(X0,add(X2,X1)) )
& ( in(X0,add(X2,X1))
| ( ~ in(X0,X1)
& ( X0 != X2 ) ) ) ),
inference(flattening,[],[f9]) ).
tff(f13,plain,
! [X0: $int] : ~ in(X0,empty),
inference(cnf_transformation,[],[f1]) ).
tff(f18,plain,
! [X2: $int,X0: $int,X1: collection] :
( ~ in(X0,add(X2,X1))
| ( X0 = X2 )
| in(X0,X1) ),
inference(cnf_transformation,[],[f10]) ).
tff(f22,plain,
in(4,add(1,add(3,add(5,empty)))),
inference(cnf_transformation,[],[f8]) ).
tff(f29,plain,
( ( 4 = 1 )
| in(4,add(3,add(5,empty))) ),
inference(resolution,[],[f18,f22]) ).
tff(f34,plain,
in(4,add(3,add(5,empty))),
inference(evaluation,[],[f29]) ).
tff(f35,plain,
( ( 4 = 3 )
| in(4,add(5,empty)) ),
inference(resolution,[],[f34,f18]) ).
tff(f37,plain,
in(4,add(5,empty)),
inference(evaluation,[],[f35]) ).
tff(f44,plain,
( ( 4 = 5 )
| in(4,empty) ),
inference(resolution,[],[f37,f18]) ).
tff(f47,plain,
in(4,empty),
inference(evaluation,[],[f44]) ).
tff(f48,plain,
$false,
inference(forward_subsumption_resolution,[],[f47,f13]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : DAT020_1 : TPTP v9.3.1. Released v5.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.12/0.19 % Computer : n017.cluster.edu
% 0.12/0.19 % Model : x86_64 x86_64
% 0.12/0.19 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.12/0.19 % Memory : 8046.5625MB
% 0.12/0.19 % OS : Linux 6.8.0-71-generic
% 0.12/0.19 % CPULimit : 300
% 0.12/0.19 % WCLimit : 300
% 0.12/0.19 % DateTime : Tue Sep 29 00:01:07 UTC 2026
% 0.12/0.20 % CPUTime :
% 0.12/0.20 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.12/0.23 Running first-order model finding
% 0.12/0.23 Running: /export/starexec/sandbox2/solver/bin/vampire-ho --input_syntax tptp --output_axiom_names on --mode casc --intent sat -m 16384 --cores 7 -t 300 /export/starexec/sandbox2/benchmark/theBenchmark.p
% 0.12/0.27 % (4146008)Will run a generic schedule for satisfiability detection.
% 0.12/0.27 % (4146018)ott+1_1_to=lpo:sil=16000:sp=reverse_arity:erd=off:random_seed=2531145361:i=131_2999 on theBenchmark for (2999ds/131Mi)
% 0.12/0.27 % (4146018) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-4146008-4146018"...
% 0.12/0.27 % (4146018)...printing done.
% 0.12/0.27 % (4146018)Refutation found. Thanks to Tanya!
% 0.12/0.27 % SZS status Theorem for theBenchmark
% 0.12/0.27 % SZS output start Proof for theBenchmark
% See solution above
% 0.12/0.27 % (4146018)------------------------------
% 0.12/0.27 % (4146018)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.12/0.27 % (4146018)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.12/0.27 % (4146018)CaDiCaL version: 2.1.3
% 0.12/0.27 % (4146018)Termination reason: Refutation
% 0.12/0.27 % (4146018)Time elapsed: 0.001 s
% 0.12/0.27 % (4146018)Peak memory usage: 11 MB
% 0.12/0.27 % (4146018)Instructions burned: 2 (million)
% 0.12/0.27 % (4146008)Success in time 0.032 s
% 0.12/0.27 % Vampire exiting
%------------------------------------------------------------------------------