%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYN057-1 : TPTP v9.3.1. Released v1.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n009.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 01:49:09 PM UTC 2026
% Result : Unsatisfiable 3.93s 1.23s
% Output : Refutation 3.93s
% Verified :
% SZS Type : Refutation
% Derivation depth : 10
% Number of leaves : 9
% Syntax : Number of formulae : 27 ( 10 unt; 2 def)
% Number of atoms : 53 ( 0 equ)
% Maximal formula atoms : 4 ( 1 avg)
% Number of connectives : 60 ( 34 ~; 24 |; 0 &)
% ( 2 <=>; 0 =>; 0 <=; 0 <~>)
% Maximal formula depth : 7 ( 3 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of predicates : 8 ( 7 usr; 3 prp; 0-1 aty)
% Number of functors : 2 ( 2 usr; 2 con; 0-0 aty)
% Number of variables : 9 ( 0 sgn 9 !; 0 ?)
% Comments :
%------------------------------------------------------------------------------
fof(f1,axiom,
big_f(a),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause_1) ).
fof(f2,axiom,
~ big_g(a),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause_2) ).
fof(f3,axiom,
! [X0] :
( big_h(X0)
| ~ big_f(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause_3) ).
fof(f4,axiom,
! [X0] :
( big_f(X0)
| ~ big_i(X0)
| ~ big_j(X0) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause_4) ).
fof(f5,axiom,
! [X0,X1] :
( ~ big_h(X0)
| big_g(X0)
| ~ big_i(X1)
| ~ big_h(X1) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause_5) ).
fof(f6,negated_conjecture,
big_j(b),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause_6) ).
fof(f7,negated_conjecture,
big_i(b),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',clause_7) ).
fof(f9,definition,
( spl0_1
<=> ! [X1] :
( ~ big_i(X1)
| ~ big_h(X1) ) ),
introduced(definition,[new_symbols(definition,[spl0_1])],[avatar_definition]) ).
fof(f10,plain,
( ! [X1] :
( ~ big_i(X1)
| ~ big_h(X1) )
| ~ spl0_1 ),
inference(avatar_component_clause,[],[f9]) ).
fof(f12,definition,
( spl0_2
<=> ! [X0] :
( ~ big_h(X0)
| big_g(X0) ) ),
introduced(definition,[new_symbols(definition,[spl0_2])],[avatar_definition]) ).
fof(f13,plain,
( ! [X0] :
( ~ big_h(X0)
| big_g(X0) )
| ~ spl0_2 ),
inference(avatar_component_clause,[],[f12]) ).
fof(f14,plain,
( spl0_1
| spl0_2 ),
inference(avatar_split_clause,[],[f5,f12,f9]) ).
fof(f15,plain,
( ! [X0] :
( big_g(X0)
| ~ big_f(X0) )
| ~ spl0_2 ),
inference(resolution,[],[f3,f13]) ).
fof(f16,plain,
( ~ big_f(a)
| ~ spl0_2 ),
inference(resolution,[],[f15,f2]) ).
fof(f17,plain,
( $false
| ~ spl0_2 ),
inference(forward_subsumption_resolution,[],[f16,f1]) ).
fof(f18,plain,
~ spl0_2,
inference(avatar_contradiction_clause,[],[f17]) ).
fof(f19,plain,
( ~ big_h(b)
| ~ spl0_1 ),
inference(resolution,[],[f10,f7]) ).
fof(f20,plain,
( ~ big_f(b)
| ~ spl0_1 ),
inference(resolution,[],[f19,f3]) ).
fof(f21,plain,
( ~ big_i(b)
| ~ big_j(b)
| ~ spl0_1 ),
inference(resolution,[],[f20,f4]) ).
fof(f22,plain,
( ~ big_j(b)
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f21,f7]) ).
fof(f23,plain,
( $false
| ~ spl0_1 ),
inference(forward_subsumption_resolution,[],[f22,f6]) ).
fof(f24,plain,
~ spl0_1,
inference(avatar_contradiction_clause,[],[f23]) ).
cnf(s1,plain,
( spl0_1
| spl0_2 ),
inference(sat_conversion,[],[f14]) ).
cnf(s2,plain,
~ spl0_2,
inference(sat_conversion,[],[f18]) ).
cnf(s3,plain,
~ spl0_1,
inference(sat_conversion,[],[f24]) ).
cnf(s4,plain,
$false,
inference(rat,[],[s1,s2,s3]) ).
fof(f25,plain,
$false,
inference(avatar_sat_refutation,[],[s4]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYN057-1 : TPTP v9.3.1. Released v1.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.12/0.19 % Computer : n009.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 : Mon Sep 28 15:27:00 UTC 2026
% 0.12/0.19 % CPUTime :
% 0.12/0.19 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.12/0.23 Running first-order theorem proving
% 0.12/0.23 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
% 3.93/1.23 % (3147479)Input is clausal, will run a generic CNF schedule.
% 3.93/1.23 % (3147499)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=2982212079:i=140167_3000 on theBenchmark for (3000ds/140167Mi)
% 3.93/1.23 % (3147502)lrs+10_1_sil=8000:sp=occurrence:random_seed=1170319218:i=107:sd=3:ss=axioms:sgt=8_3000 on theBenchmark for (3000ds/107Mi)
% 3.93/1.23 % (3147500)lrs+10_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:urr=on:br=off:random_seed=1170103434:i=132376:av=off_3000 on theBenchmark for (3000ds/132376Mi)
% 3.93/1.23 % (3147504)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=2148717527:s2a=on:i=180:gtg=position_3000 on theBenchmark for (3000ds/180Mi)
% 3.93/1.23 % (3147503)dis-1002_1_to=lpo:sil=16000:fd=off:random_seed=2279997957:st=1.5:i=114:aac=none:ins=7:ss=axioms:fsd=on_3000 on theBenchmark for (3000ds/114Mi)
% 3.93/1.23 % (3147501)lrs+1002_1_ncem=casc2026/models/loop8.pt:sil=128000:tgt=ground:npcc=on:sp=reverse_frequency:spb=intro:random_seed=3769365663:i=137899:s2at=10:gtgl=3:kws=precedence:add=on:bd=preordered:gtg=position_3000 on theBenchmark for (3000ds/137899Mi)
% 3.93/1.23 % (3147502)Also succeeded, but the first one will report.
% 3.93/1.23 % (3147504)First to succeed.
% 3.93/1.23 % (3147503)Also succeeded, but the first one will report.
% 3.93/1.23 % (3147504)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-3147479"
% 3.93/1.23 % (3147505)dis-21_1_sil=8000:lcm=predicate:random_seed=3435429030:st=5:avsq=on:i=117:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_3000 on theBenchmark for (3000ds/117Mi)
% 3.93/1.23 % (3147505)Also succeeded, but the first one will report.
% 3.93/1.23 % (3147504)Refutation found. Thanks to Tanya!
% 3.93/1.23 % SZS status Unsatisfiable for theBenchmark
% 3.93/1.23 % SZS output start Proof for theBenchmark
% See solution above
% 3.93/1.23 % (3147504)------------------------------
% 3.93/1.23 % (3147504)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.93/1.23 % (3147504)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.93/1.23 % (3147504)CaDiCaL version: 2.1.3
% 3.93/1.23 % (3147504)Termination reason: Refutation
% 3.93/1.23 % (3147504)Time elapsed: 0.003 s
% 3.93/1.23 % (3147504)Peak memory usage: 89 MB
% 3.93/1.23 % (3147504)Instructions burned: 1 (million)
% 3.93/1.23 % (3147504)------------------------------
% 3.93/1.23 % (3147504)------------------------------
% 3.93/1.23 % (3147479)Success in time 0.468 s
% 3.93/1.23 % Vampire exiting
%------------------------------------------------------------------------------