%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : CSR147+1 : TPTP v9.3.1. Released v4.1.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% Computer : n007.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 09:46:05 AM UTC 2026
% Result : Theorem 0.07s 0.25s
% Output : Refutation 0.07s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 8
% Syntax : Number of formulae : 27 ( 18 unt; 0 def)
% Number of atoms : 62 ( 2 equ)
% Maximal formula atoms : 6 ( 2 avg)
% Number of connectives : 69 ( 34 ~; 31 |; 2 &)
% ( 0 <=>; 2 =>; 0 <=; 0 <~>)
% Maximal formula depth : 10 ( 3 avg)
% Maximal term depth : 2 ( 1 avg)
% Number of predicates : 7 ( 5 usr; 1 prp; 0-2 aty)
% Number of functors : 5 ( 5 usr; 4 con; 0-1 aty)
% Number of variables : 20 ( 20 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f5,axiom,
s__Human(jim),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',jim_human) ).
fof(f7,axiom,
! [X0,X1,X2] :
( s__Human(X0)
=> ( ( s__age(X0,X1)
& s__age(s__siblingFn(X0),X2)
& greater(X1,X2) )
=> ( s__more_experienced(X0,s__siblingFn(X0))
| s__has_seen_more(s__siblingFn(X0),X0) ) ) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',experience) ).
fof(f9,axiom,
s__age(geoff,n48),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',geoff_48) ).
fof(f10,axiom,
s__age(jim,n54),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',jim_54) ).
fof(f11,axiom,
greater(n54,n48),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',greater_54_48) ).
fof(f12,axiom,
geoff = s__siblingFn(jim),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',geoff_and_jim) ).
fof(f13,axiom,
~ s__has_seen_more(geoff,jim),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',jim_has_seen_more) ).
fof(f14,conjecture,
s__more_experienced(jim,geoff),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',jim_is_experienced) ).
fof(f15,negated_conjecture,
~ s__more_experienced(jim,geoff),
inference(negated_conjecture,[status(cth)],[f14]) ).
fof(f16,plain,
~ s__more_experienced(jim,geoff),
inference(flattening,[],[f15]) ).
fof(f20,plain,
! [X0,X1,X2] :
( s__more_experienced(X0,s__siblingFn(X0))
| s__has_seen_more(s__siblingFn(X0),X0)
| ~ s__age(X0,X1)
| ~ s__age(s__siblingFn(X0),X2)
| ~ greater(X1,X2)
| ~ s__Human(X0) ),
inference(ennf_transformation,[],[f7]) ).
fof(f21,plain,
! [X0,X1,X2] :
( s__more_experienced(X0,s__siblingFn(X0))
| s__has_seen_more(s__siblingFn(X0),X0)
| ~ s__age(X0,X1)
| ~ s__age(s__siblingFn(X0),X2)
| ~ greater(X1,X2)
| ~ s__Human(X0) ),
inference(flattening,[],[f20]) ).
fof(f26,plain,
s__Human(jim),
inference(cnf_transformation,[],[f5]) ).
fof(f28,plain,
! [X2,X0,X1] :
( s__has_seen_more(s__siblingFn(X0),X0)
| ~ greater(X1,X2)
| ~ s__age(s__siblingFn(X0),X2)
| ~ s__age(X0,X1)
| ~ s__Human(X0)
| s__more_experienced(X0,s__siblingFn(X0)) ),
inference(cnf_transformation,[],[f21]) ).
fof(f30,plain,
s__age(geoff,n48),
inference(cnf_transformation,[],[f9]) ).
fof(f31,plain,
s__age(jim,n54),
inference(cnf_transformation,[],[f10]) ).
fof(f32,plain,
greater(n54,n48),
inference(cnf_transformation,[],[f11]) ).
fof(f33,plain,
geoff = s__siblingFn(jim),
inference(cnf_transformation,[],[f12]) ).
fof(f34,plain,
~ s__has_seen_more(geoff,jim),
inference(cnf_transformation,[],[f13]) ).
fof(f35,plain,
~ s__more_experienced(jim,geoff),
inference(cnf_transformation,[],[f16]) ).
fof(f43,plain,
! [X0,X1] :
( s__has_seen_more(geoff,jim)
| ~ greater(X0,X1)
| ~ s__age(geoff,X1)
| ~ s__age(jim,X0)
| ~ s__Human(jim)
| s__more_experienced(jim,geoff) ),
inference(superposition,[],[f28,f33]) ).
fof(f44,plain,
! [X0,X1] :
( ~ greater(X0,X1)
| ~ s__age(geoff,X1)
| ~ s__age(jim,X0)
| ~ s__Human(jim)
| s__more_experienced(jim,geoff) ),
inference(forward_subsumption_resolution,[],[f43,f34]) ).
fof(f45,plain,
! [X0,X1] :
( ~ greater(X0,X1)
| ~ s__age(geoff,X1)
| ~ s__age(jim,X0)
| s__more_experienced(jim,geoff) ),
inference(forward_subsumption_resolution,[],[f44,f26]) ).
fof(f46,plain,
! [X0,X1] :
( ~ greater(X0,X1)
| ~ s__age(geoff,X1)
| ~ s__age(jim,X0) ),
inference(forward_subsumption_resolution,[],[f45,f35]) ).
fof(f47,plain,
( ~ s__age(geoff,n48)
| ~ s__age(jim,n54) ),
inference(resolution,[],[f46,f32]) ).
fof(f48,plain,
~ s__age(jim,n54),
inference(forward_subsumption_resolution,[],[f47,f30]) ).
fof(f49,plain,
$false,
inference(forward_subsumption_resolution,[],[f48,f31]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : CSR147+1 : TPTP v9.3.1. Released v4.1.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.07/0.18 % Computer : n007.cluster.edu
% 0.07/0.18 % Model : x86_64 x86_64
% 0.07/0.18 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.07/0.18 % Memory : 8046.5625MB
% 0.07/0.18 % OS : Linux 6.8.0-71-generic
% 0.07/0.18 % CPULimit : 300
% 0.07/0.18 % WCLimit : 300
% 0.07/0.18 % DateTime : Mon Sep 28 23:35:41 UTC 2026
% 0.07/0.18 % CPUTime :
% 0.07/0.18 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.07/0.21 Running first-order model finding
% 0.07/0.21 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
% 0.07/0.25 % (2966228)Will run a generic schedule for satisfiability detection.
% 0.07/0.25 % (2966237)ott+31_1_sil=16000:lcm=predicate:bce=on:newcnf=on:random_seed=2158858250:i=116_2999 on theBenchmark for (2999ds/116Mi)
% 0.07/0.25 % (2966237) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-2966228-2966237"...
% 0.07/0.25 % (2966237)...printing done.
% 0.07/0.25 % (2966237)Refutation found. Thanks to Tanya!
% 0.07/0.25 % SZS status Theorem for theBenchmark
% 0.07/0.25 % SZS output start Proof for theBenchmark
% See solution above
% 0.07/0.25 % (2966237)------------------------------
% 0.07/0.25 % (2966237)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.07/0.25 % (2966237)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.07/0.25 % (2966237)CaDiCaL version: 2.1.3
% 0.07/0.25 % (2966237)Termination reason: Refutation
% 0.07/0.25 % (2966237)Time elapsed: 0.001 s
% 0.07/0.25 % (2966237)Peak memory usage: 12 MB
% 0.07/0.25 % (2966237)Instructions burned: 1 (million)
% 0.07/0.25 % (2966228)Success in time 0.028 s
% 0.07/0.25 % Vampire exiting
%------------------------------------------------------------------------------