%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : NUM761_8 : TPTP v9.3.1. Released v8.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n006.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 12:25:39 PM UTC 2026
% Result : Theorem 0.17s 0.46s
% Output : Refutation 0.17s
% Verified :
% SZS Type : Refutation
% Derivation depth : 11
% Number of leaves : 7
% Syntax : Number of formulae : 38 ( 16 unt; 0 typ; 2 def)
% Number of atoms : 70 ( 0 equ)
% Maximal formula atoms : 3 ( 1 avg)
% Number of connectives : 60 ( 28 ~; 25 |; 0 &)
% ( 2 <=>; 5 =>; 0 <=; 0 <~>)
% Maximal formula depth : 8 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of types : 2 ( 1 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 5 ( 4 usr; 3 prp; 0-2 aty)
% Number of functors : 5 ( 5 usr; 4 con; 0-2 aty)
% Number of variables : 40 ( 0 sgn 40 !; 0 ?; 40 :)
% Comments :
%------------------------------------------------------------------------------
tff(type_def_5,type,
frac: $tType ).
tff(func_def_0,type,
x: frac ).
tff(func_def_1,type,
y: frac ).
tff(func_def_2,type,
z: frac ).
tff(func_def_3,type,
u: frac ).
tff(func_def_4,type,
pf: ( frac * frac ) > frac ).
tff(pred_def_1,type,
moref: ( frac * frac ) > $o ).
tff(pred_def_2,type,
eq: ( frac * frac ) > $o ).
tff(f1,axiom,
( ~ moref(x,y)
=> eq(x,y) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',m) ).
tff(f2,axiom,
moref(z,u),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',n) ).
tff(f4,axiom,
! [X0: frac,X1: frac,X2: frac,X3: frac] :
( eq(X0,X1)
=> ( moref(X2,X3)
=> moref(pf(X0,X2),pf(X1,X3)) ) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',satz62g) ).
tff(f5,axiom,
! [X0: frac,X1: frac,X2: frac,X3: frac] :
( moref(X0,X1)
=> ( moref(X2,X3)
=> moref(pf(X0,X2),pf(X1,X3)) ) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',satz64) ).
tff(f6,conjecture,
moref(pf(x,z),pf(y,u)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',satz65a) ).
tff(f7,negated_conjecture,
~ moref(pf(x,z),pf(y,u)),
inference(negated_conjecture,[status(cth)],[f6]) ).
tff(f10,plain,
~ moref(pf(x,z),pf(y,u)),
inference(flattening,[],[f7]) ).
tff(f11,plain,
( eq(x,y)
| moref(x,y) ),
inference(ennf_transformation,[],[f1]) ).
tff(f13,plain,
! [X0: frac,X1: frac,X2: frac,X3: frac] :
( moref(pf(X0,X2),pf(X1,X3))
| ~ moref(X2,X3)
| ~ eq(X0,X1) ),
inference(ennf_transformation,[],[f4]) ).
tff(f14,plain,
! [X0: frac,X1: frac,X2: frac,X3: frac] :
( moref(pf(X0,X2),pf(X1,X3))
| ~ moref(X2,X3)
| ~ eq(X0,X1) ),
inference(flattening,[],[f13]) ).
tff(f15,plain,
! [X0: frac,X1: frac,X2: frac,X3: frac] :
( moref(pf(X0,X2),pf(X1,X3))
| ~ moref(X2,X3)
| ~ moref(X0,X1) ),
inference(ennf_transformation,[],[f5]) ).
tff(f16,plain,
! [X0: frac,X1: frac,X2: frac,X3: frac] :
( moref(pf(X0,X2),pf(X1,X3))
| ~ moref(X2,X3)
| ~ moref(X0,X1) ),
inference(flattening,[],[f15]) ).
tff(f17,plain,
( moref(x,y)
| eq(x,y) ),
inference(cnf_transformation,[],[f11]) ).
tff(f18,plain,
moref(z,u),
inference(cnf_transformation,[],[f2]) ).
tff(f19,plain,
! [X2: frac,X3: frac,X0: frac,X1: frac] :
( ~ eq(X0,X1)
| ~ moref(X2,X3)
| moref(pf(X0,X2),pf(X1,X3)) ),
inference(cnf_transformation,[],[f14]) ).
tff(f20,plain,
! [X2: frac,X3: frac,X0: frac,X1: frac] :
( ~ moref(X0,X1)
| ~ moref(X2,X3)
| moref(pf(X0,X2),pf(X1,X3)) ),
inference(cnf_transformation,[],[f16]) ).
tff(f21,plain,
~ moref(pf(x,z),pf(y,u)),
inference(cnf_transformation,[],[f10]) ).
tff(f22,plain,
( ~ moref(x,y)
| eq(x,y) ),
inference(consistent_polarity_flipping,[],[f17]) ).
tff(f23,plain,
~ moref(z,u),
inference(consistent_polarity_flipping,[],[f18]) ).
tff(f24,plain,
! [X2: frac,X3: frac,X0: frac,X1: frac] :
( ~ moref(pf(X0,X2),pf(X1,X3))
| moref(X2,X3)
| ~ eq(X0,X1) ),
inference(consistent_polarity_flipping,[],[f19]) ).
tff(f25,plain,
! [X2: frac,X3: frac,X0: frac,X1: frac] :
( ~ moref(pf(X0,X2),pf(X1,X3))
| moref(X2,X3)
| moref(X0,X1) ),
inference(consistent_polarity_flipping,[],[f20]) ).
tff(f26,plain,
moref(pf(x,z),pf(y,u)),
inference(consistent_polarity_flipping,[],[f21]) ).
tff(f28,definition,
( spl0_1
<=> eq(x,y) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
tff(f32,definition,
( spl0_2
<=> moref(x,y) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
tff(f34,plain,
( ~ moref(x,y)
| spl0_2 ),
inference(avatar_component_clause,[],[f32]) ).
tff(f35,plain,
( spl0_1
| ~ spl0_2 ),
inference(avatar_split_clause,[],[f22,f32,f28]) ).
tff(f36,plain,
( moref(z,u)
| ~ eq(x,y) ),
inference(resolution,[],[f24,f26]) ).
tff(f37,plain,
~ eq(x,y),
inference(forward_subsumption_resolution,[],[f36,f23]) ).
tff(f38,plain,
~ spl0_1,
inference(avatar_split_clause,[],[f37,f28]) ).
tff(f39,plain,
( moref(z,u)
| moref(x,y) ),
inference(resolution,[],[f25,f26]) ).
tff(f40,plain,
moref(x,y),
inference(forward_subsumption_resolution,[],[f39,f23]) ).
tff(f41,plain,
( $false
| spl0_2 ),
inference(forward_subsumption_resolution,[],[f40,f34]) ).
tff(f42,plain,
spl0_2,
inference(avatar_contradiction_clause,[],[f41]) ).
cnf(s1,plain,
( spl0_1
| ~ spl0_2 ),
inference(sat_conversion,[],[f35]) ).
cnf(s2,plain,
~ spl0_1,
inference(sat_conversion,[],[f38]) ).
cnf(s3,plain,
spl0_2,
inference(sat_conversion,[],[f42]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s3,s2]) ).
tff(f43,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : NUM761_8 : TPTP v9.3.1. Released v8.0.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.13/0.39 % Computer : n006.cluster.edu
% 0.13/0.39 % Model : x86_64 x86_64
% 0.13/0.39 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.13/0.39 % Memory : 8046.5625MB
% 0.13/0.39 % OS : Linux 6.8.0-71-generic
% 0.13/0.39 % CPULimit : 300
% 0.13/0.39 % WCLimit : 300
% 0.13/0.39 % DateTime : Sun Sep 27 21:19:26 UTC 2026
% 0.13/0.39 % CPUTime :
% 0.13/0.39 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.13/0.42 Running first-order model finding
% 0.13/0.42 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
% 0.17/0.46 % (3324216)Will run a generic schedule for satisfiability detection.
% 0.17/0.46 % (3324222)% WARNING: option uhcvi not known.
% 0.17/0.46 % (3324222)dis+11_61:31_drc=ordering:lsd=5:bsr=unit_only:rp=on:newcnf=on:random_seed=436804489:i=135531:add=off:rawr=on_2999 on theBenchmark for (2999ds/135531Mi)
% 0.17/0.46 % (3324222) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-3324216-3324222"...
% 0.17/0.46 % (3324222)...printing done.
% 0.17/0.46 % (3324222)Refutation found. Thanks to Tanya!
% 0.17/0.46 % SZS status Theorem for theBenchmark
% 0.17/0.46 % SZS output start Proof for theBenchmark
% See solution above
% 0.17/0.46 % (3324222)------------------------------
% 0.17/0.46 % (3324222)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.17/0.46 % (3324222)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.17/0.46 % (3324222)CaDiCaL version: 2.1.3
% 0.17/0.46 % (3324222)Termination reason: Refutation
% 0.17/0.46 % (3324222)Time elapsed: 0.001 s
% 0.17/0.46 % (3324222)Peak memory usage: 12 MB
% 0.17/0.46 % (3324222)Instructions burned: 1 (million)
% 0.17/0.46 % (3324216)Success in time 0.028 s
% 0.17/0.46 % Vampire exiting
%------------------------------------------------------------------------------