2026-09-08 報 release. 8 September 2026

Bucket tables for 47 languages in registry v1.5.0

Model-generated candidates now reach out-of-vocabulary misspellings in 45 more languages, and eight languages were rejected on measurement with full evidence ladders.

Forty-five new bucket-table siblings of 10 to 12 MB each let semanticSuggest embed the out-of-vocabulary n-grams the vocabulary lacks, in every language the fidelity gates passed. French rose from 0.696 to 1.000, Spanish from 0.667 to 1.000, and Russian from 0.623 to 1.000 in out-of-vocabulary resolution on real-corpus probes.
Eight languages (ar, cs, fa, he, ja, pl, vi, zh) were rejected on measurement, with the gates never weakened; full ladder evidence is committed for a future decision. Serbian and Swedish ship at K=65536 with a recorded size deviation.
The registry now holds 213 resources at revision 7, and the playground picks up every addition automatically.