%------------------------------------------------------------------------------
% File : Vampire---5.0.1
% Problem : SYO299_8 : TPTP v9.3.1. Released v8.0.0.
% Transfm : none
% Format : tptp:raw
% Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% Computer : n003.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 02:25:54 PM UTC 2026
% Result : Theorem 3.45s 1.26s
% Output : Refutation 3.45s
% Verified :
% SZS Type : Refutation
% Derivation depth : 12
% Number of leaves : 1
% Syntax : Number of formulae : 14 ( 4 unt; 0 typ; 0 def)
% Number of atoms : 77 ( 39 equ)
% Maximal formula atoms : 8 ( 5 avg)
% Number of connectives : 63 ( 19 ~; 14 |; 10 &)
% ( 15 <=>; 4 =>; 0 <=; 1 <~>)
% Maximal formula depth : 10 ( 6 avg)
% Maximal term depth : 1 ( 1 avg)
% Number of FOOLs : 96 ( 37 fml; 59 var)
% Number of types : 1 ( 0 usr)
% Number of type conns : 0 ( 0 >; 0 *; 0 +; 0 <<)
% Number of predicates : 6 ( 3 usr; 5 prp; 0-2 aty)
% Number of functors : 0 ( 0 usr; 0 con; --- aty)
% Number of variables : 32 ( 19 !; 13 ?; 32 :)
% Comments :
%------------------------------------------------------------------------------
tff(func_def_2,type,
sK0: $o ).
tff(func_def_3,type,
sK1: $o ).
tff(func_def_4,type,
sK2: $o ).
tff(f1,conjecture,
! [X0: $o,X1: $o,X2: $o] :
? [X3: $o] :
( ( ( (X0)
<=> (X1) )
<=> (X2) )
=> ( (X0)
<=> ( (X1)
<=> (X3) ) ) ),
file('/export/starexec/sandbox/benchmark/theBenchmark.p',cTHM51) ).
tff(f2,negated_conjecture,
~ ! [X0: $o,X1: $o,X2: $o] :
? [X3: $o] :
( ( ( (X0)
<=> (X1) )
<=> (X2) )
=> ( (X0)
<=> ( (X1)
<=> (X3) ) ) ),
inference(negated_conjecture,[status(cth)],[f1]) ).
tff(f3,plain,
~ ! [X0: $o,X1: $o,X2: $o] :
? [X3: $o] :
( ( ( (X0)
<=> (X1) )
<=> (X2) )
=> ( (X0)
<=> ( (X1)
<=> (X3) ) ) ),
inference(rectify,[],[f2]) ).
tff(f4,plain,
~ ! [X0: $o,X1: $o,X2: $o] :
? [X3: $o] :
( ( ( (X0) = (X1) )
<=> ( $true = (X2) ) )
=> ( ( $true = (X0) )
<=> ( (X1) = (X3) ) ) ),
inference(fool_elimination,[],[f3]) ).
tff(f5,plain,
? [X0: $o,X1: $o,X2: $o] :
! [X3: $o] :
( ( ( $true = (X0) )
<~> ( (X1) = (X3) ) )
& ( ( (X0) = (X1) )
<=> ( $true = (X2) ) ) ),
inference(ennf_transformation,[],[f4]) ).
tff(f6,plain,
? [X0: $o,X1: $o,X2: $o] :
! [X3: $o] :
( ( ( (X1) != (X3) )
| ( $true != (X0) ) )
& ( ( (X1) = (X3) )
| ( $true = (X0) ) )
& ( ( (X0) = (X1) )
| ( $true != (X2) ) )
& ( ( $true = (X2) )
| ( (X0) != (X1) ) ) ),
inference(nnf_transformation,[],[f5]) ).
tff(f7,plain,
? [X0: $o,X1: $o,X2: $o] :
! [X3: $o] :
( ( ( (X1) != (X3) )
| ( $true != (X0) ) )
& ( ( (X1) = (X3) )
| ( $true = (X0) ) )
& ( ( (X0) = (X1) )
| ( $true != (X2) ) )
& ( ( $true = (X2) )
| ( (X0) != (X1) ) ) ),
inference(flattening,[],[f6]) ).
tff(f8,plain,
! [X3: $o] :
( ( ( sK1 != (X3) )
| ( $true != sK0 ) )
& ( ( sK1 = (X3) )
| ( $true = sK0 ) )
& ( ( sK0 = sK1 )
| ( $true != sK2 ) )
& ( ( $true = sK2 )
| ( sK0 != sK1 ) ) ),
inference(skolemize,[status(esa),new_symbols(skolem,[sK0,sK1,sK2]),skolemize(X0,sK0),skolemize(X1,sK1),skolemize(X2,sK2)],[f7]) ).
tff(f11,plain,
! [X3: $o] :
( ( sK1 = (X3) )
| ( $true = sK0 ) ),
inference(cnf_transformation,[],[f8]) ).
tff(f12,plain,
! [X3: $o] :
( ( sK1 != (X3) )
| ( $true != sK0 ) ),
inference(cnf_transformation,[],[f8]) ).
tff(f15,plain,
$true != sK0,
inference(equality_resolution,[],[f12]) ).
tff(f16,plain,
! [X3: $o] : ( sK1 = (X3) ),
inference(forward_subsumption_resolution,[],[f11,f15]) ).
tff(f19,plain,
$true != sK1,
inference(superposition,[],[f15,f16]) ).
tff(f21,plain,
$false,
inference(forward_subsumption_resolution,[],[f19,f16]) ).
%------------------------------------------------------------------------------
%----ORIGINAL SYSTEM OUTPUT
% 0.00/0.03 % Problem : SYO299_8 : TPTP v9.3.1. Released v8.0.0.
% 0.00/0.06 % Command : run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.19 % Computer : n003.cluster.edu
% 0.09/0.19 % Model : x86_64 x86_64
% 0.09/0.19 % CPU : Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz
% 0.09/0.19 % Memory : 8046.5625MB
% 0.09/0.19 % OS : Linux 6.8.0-71-generic
% 0.09/0.19 % CPULimit : 300
% 0.09/0.19 % WCLimit : 300
% 0.09/0.19 % DateTime : Mon Sep 28 17:36:13 UTC 2026
% 0.09/0.20 % CPUTime :
% 0.09/0.20 Running run_vampire /export/starexec/sandbox/benchmark/theBenchmark.p 300 THM
% 0.09/0.23 Running first-order theorem proving
% 0.09/0.23 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
% 3.45/1.26 % (1786447)Detected formulas, will run a generic FOF schedule.
% 3.45/1.26 % (1786500)lrs+11_1_ncem=casc2026/models/loop8.pt:sil=128000:npcc=on:lma=off:spb=units:urr=ec_only:bce=on:s2agt=64:updr=off:random_seed=2069453176:i=134677:sd=20:aac=none:nm=16:ss=included:sgt=10_3000 on theBenchmark for (3000ds/134677Mi)
% 3.45/1.26 % (1786503)dis-1010_2:3_sil=16000:sp=reverse_frequency:random_seed=1034149102:i=119:av=off:ss=axioms_3000 on theBenchmark for (3000ds/119Mi)
% 3.45/1.26 % (1786503)First to succeed.
% 3.45/1.26 % (1786503)Solution written to "/export/starexec/sandbox/tmp/vampire-proof-1786447"
% 3.45/1.26 % (1786501)lrs+1010_1_anc=all:sfv=off:to=kbo:ncem=casc2026/models/loop7.pt:sil=128000:npcc=on:prc=on:sos=all:bsr=unit_only:sac=on:random_seed=2795543428:i=141695:sd=1:nm=32:gsp=on:ss=included_3000 on theBenchmark for (3000ds/141695Mi)
% 3.45/1.26 % (1786499)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=2518790297:i=141193_3000 on theBenchmark for (3000ds/141193Mi)
% 3.45/1.26 % (1786502)lrs+1010_1_to=lpo:sil=32000:sos=on:spb=goal_then_units:bce=on:random_seed=3469719516:i=109:sd=1:ins=1:gsp=on:ss=axioms_3000 on theBenchmark for (3000ds/109Mi)
% 3.45/1.26 % (1786502)Also succeeded, but the first one will report.
% 3.45/1.26 % (1786505)dis-21_1_sil=8000:lcm=predicate:random_seed=1615703801:st=5:avsq=on:i=129:avsqr=1,16:sd=3:aac=none:ep=RS:fsr=off:ss=included_3000 on theBenchmark for (3000ds/129Mi)
% 3.45/1.26 % (1786505)Refutation not found, incomplete strategy
% 3.45/1.26 % (1786505)------------------------------
% 3.45/1.26 % (1786505)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.45/1.26 % (1786505)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.45/1.26 % (1786505)CaDiCaL version: 2.1.3
% 3.45/1.26 % (1786505)Termination reason: Refutation not found, incomplete strategy
% 3.45/1.26 % (1786505)Time elapsed: 0.001 s
% 3.45/1.26 % (1786505)Peak memory usage: 88 MB
% 3.45/1.26 % (1786504)dis-1011_1_sil=16000:fde=unused:s2agt=70:random_seed=3826900387:s2a=on:i=139:gtg=position_3000 on theBenchmark for (3000ds/139Mi)
% 3.45/1.26 % (1786504)Also succeeded, but the first one will report.
% 3.45/1.26 % (1786503)Refutation found. Thanks to Tanya!
% 3.45/1.26 % SZS status Theorem for theBenchmark
% 3.45/1.26 % SZS output start Proof for theBenchmark
% See solution above
% 3.45/1.26 % (1786503)------------------------------
% 3.45/1.26 % (1786503)Version: Vampire 5.0.1 (Release build, commit ea8961452 on 2026-07-16 15:14:34 +0200)
% 3.45/1.26 % (1786503)Linked with Z3 4.14.0.0 3c47fd96cf5645d0c42b2c819d9e9a84380aa721 z3-4.8.4-9178-g3c47fd96c
% 3.45/1.26 % (1786503)CaDiCaL version: 2.1.3
% 3.45/1.26 % (1786503)Termination reason: Refutation
% 3.45/1.26 % (1786503)Time elapsed: 0.002 s
% 3.45/1.26 % (1786503)Peak memory usage: 88 MB
% 3.45/1.26 % (1786503)Instructions burned: 1 (million)
% 3.45/1.26 % (1786503)------------------------------
% 3.45/1.26 % (1786503)------------------------------
% 3.45/1.26 % (1786447)Success in time 0.393 s
% 3.45/1.26 % Vampire exiting
%------------------------------------------------------------------------------