Translate v2

v24.3-joint-lexeme-dose29-s3598-20260715

Current runtime-verified Kuku Yalanji research candidate for closed-set lexical reconstruction and separately labelled sentence drafts

runtime verified research candidate

The governed training-overlapping lexical gate and every frozen development retention check passed. ADVANCE authorizes further research, not unrestricted deployment: the model remains 0/43 exact on the elder diagnostic and lacks speaker-diverse human evaluation.

v21.2-claude-balanced-replay-guarded-20260714

Current Kuku Yalanji research model of record: frozen v21.2 weights with validated guarded decoding; CPU inference is intentionally unloaded

research only

Retain the exact published v21.2 weights and guarded decoder as reproducible research artifacts, but do not load them for public CPU inference while natural elder-register transfer remains unsolved. The homepage uses separately labelled dictionary-context prompting until a stronger RunPod candidate clears the frozen linguistic and safety gates and receives appropriate speaker review.

v23.0-attested-narrative-adaptation-failed

Rejected three-seed attested-narrative adaptation retained as compact negative evidence

negative result

Do not promote. Seed 73 improved the held-out Text 3 corpus chrF++ point estimate by 0.6414, below the preregistered +1.0 floor; its paired interval crossed zero, untagged synthetic repetition worsened, and isolated lexical reconstruction fell to 46/297.

v22.0-step-matched-replay-3120-failed

Rejected one-variable replay-exposure experiment retained as negative evidence

negative result

Do not promote. Step 3,120 failed the frozen greedy checkpoint gate because tagged synthetic repeated-segment rows were 37 against a maximum of 25, and paired comparison showed lower tagged synthetic, untagged synthetic, and dictionary-usage agreement than the final v21.2 step 4,155 checkpoint.

v21.2-claude-balanced-replay-v2-candidate

Historical v21.2 weights release; superseded for serving by the guarded-policy release without changing weights

research only

Balanced replay preserves synthetic performance while materially recovering dictionary-usage and Bible retention relative to v21.1. Natural elder-register transfer remains unsolved, and synthetic morpheme loops remain a hard safety failure; serve only as a clearly labelled research draft pending speaker review.

v21.1-codex-synthetic-direct-v2-candidate

Kuku Yalanji translation model v2 candidate

research only

The model learned the synthetic treatment and remained stable without the task tag, but elder-shared, dictionary-usage, and Bible controls regressed severely. Preserve as a research artifact; keep retrieval-first routing and require balanced replay plus speaker review before promotion.

v20.0-full-candidate-corpus-gvn

Full-candidate-corpus diagnostic artifact

internal proof

Full-corpus v20 fixed the length-compression failure and completed the 35k-row diagnostic, but it is not a faithful general model: Bible heldout stays near 39 chrF, heldout usage is 43.26 chrF, and elder-shared sentence pairs regressed to 0/43 exact.

v19.0-balanced-replay-from-v12-gvn

Balanced replay artifact

internal proof

Restores near-v12 Bible heldout while adding elder sentence-pair/usage signal, but does not replace v10 usage or v12 Bible routing.

v18.0-usage-elder-sentence-continuation-from-v10

Elder sentence-pair memorization proof artifact

internal proof

Exactly memorized all elder-shared sentence pairs, but regressed Bible and did not beat v10 on heldout usage.

v15.0-soft-lexical-hint-bible-gvn-token

Lexical-hint diagnostic

negative result

Reproduced train rows strongly, but did not beat v12 on heldout Bible.

v13.0-retrieval-context-bible-gvn-token

Retrieval-prefix diagnostic

negative result

Retrieval context as an NLLB source prefix was harmful; heldout Bible dropped sharply.

v12.0-tagged-direct-plus-reference-bible-gvn-token

Current Bible draft fallback

route candidate

Best Bible draft heldout score before v19, but still zero exact heldout reproduction.

v11.0-byt5-bible-control-32row

Byte-model control

negative result

Failed the tiny overfit/control path; NLLB/LoRA remains the proven memorizing path for now.

v10.0-tagged-bible-plus-glossary-usage-tpi

Current usage/general draft fallback

route candidate

Best heldout usage signal so far; weaker Bible than v12/v19.

v9.8-tagged-bible-plus-db-usage-tpi

First DB-usage multitask diagnostic

internal proof

Memorized DB train examples but did not generalize well to word-id heldout usage.

v9.7-tagged-direct-plus-reference-bible-tpi

Reference-conditioning baseline

internal proof

Established tagged Bible direct/reference training as viable, but still zero exact heldout reproduction.

v8.0-diagnostic-gates-summary

Pipeline proof gate

internal proof

Proved tokenizer/LoRA/training/merge path could memorize; shifted problem from plumbing to data/task/generalization.

0.7.0-full-tpi-proxy-1.3b

kuku_yalanji_ebible_parallel_v0.1.0

internal proof

No verdict recorded.

0.4.0-full-gvn-token

kuku_yalanji_ebible_parallel_v0.1.0

internal proof

No verdict recorded.

0.1.0-smoke

kuku_yalanji_ebible_parallel_smoke_v0.1.0

internal proof

No verdict recorded.

0.1.0-baseline

kuku_yalanji_ebible_parallel_v0.1.0

training ready

No verdict recorded.

1.0.0-rc1

First leakage-controlled Mi'gmaq dictionary-example research candidate

research only

Machine-integrity gates pass, but linguistic-quality promotion does not: frozen-test chrF++ is 21.43 with 0/742 exact matches and material lexical/content failures. Permit only a visibly warned research preview pending qualified Mi'gmaq review.