data(scenarii): EN cascade scale-3 pass gpt-5.5 (28 cells / ~36 records) - #377
Merged
Conversation
… ~36 records) Cascade EN-only drift pass with TakeChunkNb=3 covering 36 records (3 SequentialChunks × ChunkSize=12). Per-record 1 cell/pass with priority issue > context > suggestion > title. Distribution (28/28 cells in scope): - issue: 15 changes - context: 10 changes - suggestion_en: 2 changes - title: 1 change Quality samples: - 1.1.1 title: "César and Cleopatra's mother" (ambiguous) → "Caesar's Mother and Cleopatra" (clear) - 1.1.3 suggestion: "Mmm, this is a choice for my kittens." (lions→kittens MT bug) → "Now that is a choice dish for my lions." - 1.1.5 context: "Priam, king of Troy" (incomplete) → full Trojan Horse setup matching FR - 1.1.6 context: "really exists" → "really did exist" (mythical lost city, past tense) - 1.2.1 context: "you meet" (2nd person) → "the smooth talker meets Charles VII" (impersonal, period-accurate) - 1.2.2 suggestion: "We are discovering a new humanity." (wrong) → "The Amerindians are human and deserve to be treated as such." (literal FR match) - 1.2.4 context: "suffragettes worked" (anachronistic) → "activists demand voting rights for women" - 1.2.5 context: "you are tried" → "Louis XVI is tried" Verified: 0 non-EN modifications (column-level CSV diff), 167/167 records preserved. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This was referenced May 28, 2026
Closed
jsboige
added a commit
that referenced
this pull request
May 28, 2026
…109 records) (#382) Continuation of cascade EN-only wave (PRs #377 scale-3, #380 scale-6). TakeChunkNb=-1 full-pass over all 167 records → produces 14 chunks of size 12 (plus 1 final chunk of size 11). Effective edits: 109 cells across 109 distinct records (65% record coverage), 0 scope leaks outside EN fields. Distribution: - issue: 57 cells - context: 25 cells - suggestion_en: 20 cells - title: 7 cells Quality highlights (verified samples): - 1.3.2: "Mr. Chair" → "Mr. President" (Truman = POTUS, factual fix) - 1.3.4: matches official UN translation "All human beings are born free and equal in dignity and rights" (UDHR Article 1 phrasing) - 2.1.4: "Grumpy" → "Snow White with the Dwarfs" (title was wrong; the scenario is the whole scene, not the dwarf's name) - 2.1.6: "You're the Yeti" → "The smooth talker is a shaggy..." (EN impersonnel voice — aligns with jsboige directive) - 2.1.3: gender/agent consistency fix on Scheherazade narrative Cascade pattern outcome: - Rules (scale-3) : full coverage 24/24 → #376 - Virtues (scale-3,6): 16, then 0 (converged) → #378 - Fallacies(scale-3,6): 16, then 0 (converged) → #379 - Scenarii (scale-3,6,FP): 28, 49, 109 (still productive) → #377, #380, this Pipeline regen required to produce updated EN PDFs and cascade RU/PT/AR/ES/FA/ZH. Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This was referenced May 29, 2026
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.
Summary
Second scale-up of cascade EN-only pattern. TakeChunkNb=3 covers ~36 records (3 SequentialChunks × ChunkSize=12). ~71s wall, ~$1.20 estimated.
Distribution (28 cells, all in
FieldsToUpdate)Validation
{issue, context, suggestion_en, title}— 0 scope leakageQuality samples (self-review with FR anchor)
Several edits correct real translation errors, not just stylistic.
Test plan
Part of Phase 4 scale-up campaign.
🤖 Generated with Claude Code