Skip to content

docs(taxonomy): #141 crossLink DatasetUpdater adaptation (additive proposal + sample, gated) - #673

Merged
jsboige merged 1 commit into
masterfrom
docs/141-crosslink-datasetupdater-adaptation
Jul 4, 2026
Merged

docs(taxonomy): #141 crossLink DatasetUpdater adaptation (additive proposal + sample, gated)#673
jsboige merged 1 commit into
masterfrom
docs/141-crosslink-datasetupdater-adaptation

Conversation

@jsboige

@jsboige jsboige commented Jul 4, 2026

Copy link
Copy Markdown
Contributor

Summary

Secondaire of dispatch l0wt63 (ai-01). Additive proposal for #141's remaining engineering artifact — the crossLink DatasetUpdater task that lets the Stage-3 expert-gate output flow into Cards/ drift-free. Docs-only proposal + sample; gated post-tag. 0 Cards/ write, 0 AssetConverter C# change (prompt/config are text in the doc, not materialized files).

#141 state recap (code=truth)

Scope item Status
Text enrichment (desc/example × 8 langs, non-card) ✅ DONE (100%)
"Adapt the GPT-4 script" ✅ DONE (DatasetUpdater = modern counterpart)
AIF cross-ref generation ✅ DELIVERED (#626: 1232/1232, 0 fab)
AIF expert adjudication (Stage-3) ⚖️ PENDING (expert gate)
crossLink DatasetUpdater task (this proposal) 📝 STAGED

The closure recommendation is explicit: remaining #141 work is "judgment, not engineering, owned by the expert gate." This stages the one engineering artifact that follows the gate, so the handoff is mechanical once jsboige adjudicates.

What the proposal stages (as text, not files)

  1. Task config skeletonEnabled=false, mirrors the 7 existing configs. Key flags:
  2. Prompt designPromptCrossLinkSystem framing with closed verb + decimal_path set
  3. Échantillon — 3 rows from the committed sidecar 141-aif-candidates-sample.csv showing the ratified-output shape (high-conf 0.95 ratifiable, mid-tail 0.55 defers)
  4. Staged flow — gated post-tag + post-Stage-3-ratification, drift-free method fix(i18n): #192 passe 2 — harmonize 24 Virtues term-structure cells (RTL/CJK consistency) #595

Why a proposal now, not the code

What this PR does NOT do

❌ No Cards/ write · ❌ No AssetConverter C# change · ❌ No gpt-5.5 call · ❌ No auto-ratification (anti-fab "Walton scheme = WARN").

Relates #141, #609, #620, #623, #626, #130, #136, #498, #595. Base a41cbda6.

🤖 Worker po-2024 (dispatch l0wt63, secondaire)

…oposal + sample, gated)

Secondaire dispatch l0wt63 (ai-01). Additive proposal for #141's remaining
engineering artifact: the crossLink DatasetUpdater task that lets the Stage-3
expert-gate output flow into Cards/ drift-free.

State recap (code=truth): #141 text-enrichment DONE (100% x8 langs), AIF
cross-ref DELIVERED through Stage-3 (#626: 1232/1232, 0 fab), 'adapt the GPT-4
script' DONE (DatasetUpdater = modern counterpart, SDK v2.10.0/gpt-5.5). Closure-rec
says remaining work is expert-gate judgment, not engineering. This stages the ONE
engineering artifact that follows the gate.

Proposal contents (text in doc, NOT materialized files):
- Task config skeleton (Enabled=false, mirrors the 7 existing configs)
  - UseFunctionCalling=true (closed-set anti-fab, the #626-validated design)
  - SkipNonEmpty=true (preserves the 12 expert-adjudicated existing-AIF nodes)
  - ChunkSize=1 (per-node relationship judgement)
- Prompt design (PromptCrossLinkSystem sample framing, closed verb+path set)
- Sample (echantillon) drawn from committed sidecar 141-aif-candidates-sample.csv
- Staged flow gated post-tag + post-Stage-3-ratification

Gated: 0 Cards/ write, 0 AssetConverter C# change (pre-tag freeze honored per
closure-rec). Same method as scale-ups #497-499 (proposal doc + sample first,
prod-write separate gated step).

Relates #141 #626 #130 #136 #498 #595. Base a41cbda.

Co-Authored-By: Claude-Code <noreply@anthropic.com>
@jsboige
jsboige merged commit 88c4d78 into master Jul 4, 2026
3 checks passed
@jsboige
jsboige deleted the docs/141-crosslink-datasetupdater-adaptation branch July 4, 2026 05:09
jsboige added a commit that referenced this pull request Jul 4, 2026
…ated from #626) (#677)

* docs(taxonomy): #141 crossLink enrichment sample run (real output curated from #626)

Primaire of dispatch `lofjtd` (ai-01). Concrete before/after sample for the
#141 crossLink enrichment staged by proposal #673.

The enrichment was already run in #626 (fullscale gpt-5.5 closed-set pass over
1232 non-card nodes, 3850 candidate links, 0 fabrication warnings). Rather than
re-spend gpt-5.5 credits to reproduce existing output, this doc curates a
7-node representative sample from #626's real output and shows before/after,
quality, and cost.

- Before (prod taxonomy CSV): 11242/11264 crossLink_* cells empty (99.8%)
- Sample: 7 non-card nodes, depth 0-7, confidence 0.38-0.98
- Quality (21 links): mean conf 0.70, 11/21 ratifiable (>=0.70), 0 fab warnings
- Surfaces the multi-target serialization question for the Stage-3 expert gate
  (5/7 nodes have >=1 verb with multiple candidates; cell convention = 1 target)

0 prod Cards/ write, 0 AssetConverter C# change, 0 fresh gpt-5.5 call, 0
auto-ratification. Gated post-tag + post-Stage-3.

Co-Authored-By: Claude-Code <noreply@anthropic.com>

* docs(taxonomy): #141 add target-existence validation to sample-run (#677 update)

Idle tick follow-up on #677. Adds a "Target-existence validation" section
confirming the second axis of #626 0-fabrication claim: every one of the 3850
crossLinks targets actually exists in the prod taxonomy (0/3850 orphans, 0/1232
nodes), and all #626 source_dps are present in prod (0/1232 missing).

Independent code=truth verification of the closed-set design quality bar.
Includes a format-conversion anti-false-finding note (naive comma->dot replace
produces a spurious 74% orphan rate; correct conversion splits each digit).

Co-Authored-By: Claude-Code <noreply@anthropic.com>

---------

Co-authored-by: Your <your.email@example.com>
Co-authored-by: Claude-Code <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant