%------------------------------------------------------------------------------
% File : Vampire-SAT---5.0.1
% Problem : COM004-1 : TPTP v9.3.1. Released v1.1.0.
% 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 09:40:05 AM UTC 2026
% Result : Unsatisfiable 0.19s 0.27s
% Output : Refutation 0.19s
% Verified :
% SZS Type : Refutation
% Derivation depth : 5
% Number of leaves : 8
% Syntax : Number of formulae : 15 ( 11 unt; 0 def)
% Number of atoms : 25 ( 2 equ)
% Maximal formula atoms : 5 ( 1 avg)
% Number of connectives : 23 ( 13 ~; 10 |; 0 &)
% ( 0 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 12 ( 3 avg)
% Maximal term depth : 3 ( 1 avg)
% Number of predicates : 5 ( 3 usr; 1 prp; 0-2 aty)
% Number of functors : 10 ( 10 usr; 5 con; 0-2 aty)
% Number of variables : 12 ( 12 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
! [X2,X3,X0,X1,X4,X5] :
( ~ failure_node(X1,or(X3,X5))
| ~ failure_node(X0,or(X2,X4))
| failure_node(parent_of(X0,X1),or(X2,X3))
| ~ contradictory(X4,X5)
| ~ siblings(X0,X1) ),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',make_node) ).
fof(f3,axiom,
! [X0] : contradictory(X0,negate(X0)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',x_contradicts_not_x) ).
fof(f4,axiom,
! [X0] : siblings(left_child_of(X0),right_child_of(X0)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',n_left_and_n_right_are_siblings) ).
fof(f5,axiom,
failure_node(n_left,or(empty,atom)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',n_left_is_atom) ).
fof(f6,axiom,
failure_node(n_right,or(empty,negate(atom))),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',n_right_is_not_atom) ).
fof(f7,axiom,
n_left = left_child_of(n),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',n_left_equals_left_child_of_n) ).
fof(f8,axiom,
n_right = right_child_of(n),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',n_right_equals_right_child_of_n) ).
fof(f9,negated_conjecture,
! [X0] : ~ failure_node(X0,or(empty,empty)),
file('/export/starexec/sandbox2/benchmark/theBenchmark.p',goal_is_there_an_empty_node) ).
fof(f11,plain,
siblings(left_child_of(n),n_right),
inference(superposition,[],[f4,f8]) ).
fof(f12,plain,
siblings(n_left,n_right),
inference(forward_demodulation,[],[f11,f7]) ).
fof(f15,plain,
! [X2,X0,X1] :
( ~ failure_node(X0,or(X1,X2))
| failure_node(parent_of(X0,n_right),or(X1,empty))
| ~ contradictory(X2,negate(atom))
| ~ siblings(X0,n_right) ),
inference(resolution,[],[f1,f6]) ).
fof(f30,plain,
( failure_node(parent_of(n_left,n_right),or(empty,empty))
| ~ contradictory(atom,negate(atom))
| ~ siblings(n_left,n_right) ),
inference(resolution,[],[f15,f5]) ).
fof(f33,plain,
( ~ contradictory(atom,negate(atom))
| ~ siblings(n_left,n_right) ),
inference(forward_subsumption_resolution,[],[f30,f9]) ).
fof(f43,plain,
~ siblings(n_left,n_right),
inference(forward_subsumption_resolution,[],[f33,f3]) ).
fof(f44,plain,
$false,
inference(forward_subsumption_resolution,[],[f43,f12]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.02 % Problem : COM004-1 : TPTP v9.3.1. Released v1.1.0.
% 0.00/0.05 % Command : run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.09/0.20 % Computer : n017.cluster.edu
% 0.09/0.20 % Model : x86_64 x86_64
% 0.09/0.20 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.20 % Memory : 8046.5625MB
% 0.09/0.20 % OS : Linux 6.8.0-71-generic
% 0.09/0.20 % CPULimit : 300
% 0.09/0.20 % WCLimit : 300
% 0.09/0.20 % DateTime : Mon Sep 28 21:39:12 UTC 2026
% 0.09/0.20 % CPUTime :
% 0.09/0.20 Running run_vampire /export/starexec/sandbox2/benchmark/theBenchmark.p 300 SAT
% 0.09/0.23 Running first-order model finding
% 0.09/0.23 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
% 0.19/0.27 % (4065020)Will run a generic schedule for satisfiability detection.
% 0.19/0.27 % (4065028)dis+10_1_sil=32000:sp=arity:random_seed=3001515459:i=103:fgj=on_2999 on theBenchmark for (2999ds/103Mi)
% 0.19/0.27 % (4065028) found proof, printing to "/export/starexec/sandbox2/tmp/vampire-proof-4065020-4065028"...
% 0.19/0.27 % (4065028)...printing done.
% 0.19/0.27 % (4065028)Refutation found. Thanks to Tanya!
% 0.19/0.27 % SZS status Unsatisfiable for theBenchmark
% 0.19/0.27 % SZS output start Proof for theBenchmark
% See solution above
% 0.19/0.27 % (4065028)------------------------------
% 0.19/0.27 % (4065028)Version: Vampire 5.0.1 (Release build, commit 5ef7c2677 on 2026-07-16 16:54:09 +0200)
% 0.19/0.27 % (4065028)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 0.19/0.27 % (4065028)CaDiCaL version: 2.1.3
% 0.19/0.27 % (4065028)Termination reason: Refutation
% 0.19/0.27 % (4065028)Time elapsed: 0.001 s
% 0.19/0.27 % (4065028)Peak memory usage: 11 MB
% 0.19/0.27 % (4065028)Instructions burned: 1 (million)
% 0.19/0.27 % (4065020)Success in time 0.027 s
% 0.19/0.27 % Vampire exiting
%------------------------------------------------------------------------------