docs(translation): #202 EN post-release campaign plan — planning-only, 0 CSV write - #809
Merged
Conversation
…, 0 CSV write Structures the post-v0.9.0 EN translation campaign as a plan doc (DoD: docs-only, no CSV writes). The campaign itself stays deferred post-release (arbitrage jsboige). Empirical inventory computed live from the prod CSVs at master cf8cb0d: - Fallacies Simple_name_en: 61/1408 filled (1347 empty, 96% margin) - Fallacies political_example_en: 35/1408 filled (1373 empty, 98% margin) - Both fields ARE used in active templates (Cards/Fallacies/Argumentum_Fallacies_Face_*.json, Cards/Memo/Argumentum_Memo_*.json — confirmed via grep) → real rendered-card impact. - All other EN datasets at/near 100% (#795 proved core prose is clean). The doc designs: - gpt-5.5 prompt per field (/v1/responses, reasoning.effort=low, empty-only, cell-by-cell verified) reusing the existing DatasetUpdater scaffold ("Translate Fallacies to English empty-only 0-shot" task pattern). - 5 gated tranches (T1/T2 Simple_name_en pilot+bulk, T3/T4 political_example_en pilot+bulk, T5 trivial Virtues hierarchy residual), ~2725 calls total. - Post-tag execution order; explicit out-of-scope (no bulk re-translation, no link_* = #192, no #804 Phase 4 regen, #415 history-rewrite INTERDICTED). Dispatch y20p0t [PRIMAIRE] #202-prep. Co-Authored-By: Claude-Code <noreply@anthropic.com>
jsboige
added a commit
that referenced
this pull request
Jul 15, 2026
…teria (docs-only) (#810) Companion to 202-en-campaign-plan.md (#809). Defines the byte-exact spot-check criteria ai-01 applies per pilot tranche before a bulk GO, so campaign execution is turnkey once the register decision (A/B) lands. 6 checks per 20-cell pilot: 1. Empty-only invariant (byte-exact, HARD — 0 clobber) 2. Meaning fidelity vs text_fr/desc_fr (semantic, sample >=5) 3. Register/style (field-specific: Simple_name <=5 words; political_example neutral/non-defamatory, matches ratified A/B) 4. MT-garbage sweep (3-dim, per-token counts — memo false-zero) 5. Language purity (0 FR/RU leakage in new outputs) 6. Encoding/round-trip (CRLF+BOM, no quoting drift — memo byte-exact-insertion) GO/REVISE/NO-GO thresholds; hard gates = clobber + encoding drift. Post-bulk regression gate: re-run #795 drift audit + byte-check ALL lang columns (zh #761 lesson) + rendered-source freshness (clobber harvests). #202 execution stays deferred post-v0.9.0 (jsboige arbitration). Docs-only, 0 CSV write, 0 code change. Dispatch mf4nyb [SECONDAIRE]. Co-authored-by: Your <your.email@example.com> Co-authored-by: Claude-Code <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Planning-only doc structuring the post-v0.9.0 EN translation campaign (epic #202, dispatch
y20p0t[PRIMAIRE]).DoD met: docs-only, 0 CSV write, 0 code change. The campaign itself stays deferred post-release (arbitrage jsboige) — this PR only structures it.
Why
#795proved the EN core prose (text/desc/example) is 100% clean — there is nothing to gain from a bulk re-translation (risk of regression only). But two Fallacies fields are materially under-filled and ARE used in active templates, so they have real rendered-card impact:Simple_name_enpolitical_example_enAll other EN datasets are at/near 100%.
Plan summary (full detail in the doc)
/v1/responses,reasoning.effort=low, empty-only (never overwrite), cell-by-cell verified.DatasetUpdater"Translate Fallacies to English empty-only 0-shot" task pattern + two sibling tasks (Simple_name_en,political_example_en).CsvPromptSystemEn.txtstyle;political_example_enneeds a jsboige register decision (A international vs B FR-context).link_*work (that's feat(translations): multi-pass quality improvement for EN/RU/PT (beyond initial translation) #192, Wikipedia API, separate)Verification
cf8cb0d8(2026-07-15).Cards/Fallacies/Argumentum_Fallacies_Face_*.json,Cards/Memo/Argumentum_Memo_*.json).— po-2024 (dispatch
y20p0t, planning-only GO)