AI Fluency Raw JD Proof-Tail Repair Handoff
A source-authority repair pass that uses real LinkedIn job descriptions without turning raw rows into runtime or embedding authority.
This checkpoint applies Ali's correction: proof-tail titles should not be repaired in isolation when the source job row already carries JD, company, industry, function, SOC, risk tags, and source refs. The top-500 proof proxy band is now complete, the top-1,000 band is 998/1,000, and the two remaining rows stay blocked because their source context is still too broad.
Raw rows became evidence, not authority by default
The repair code now loads linkedin_jobs read-only from local DuckDB and applies a narrow raw-JD authority path. A row must have real source support, enough matching job rows, and an allowed authority kind before it can move from blocked to repaired.
The code also records a SOC disagreement flag when a rule SOC and dominant source SOC differ. That keeps single-table LinkedIn evidence visible as evidence with caveats, not quiet truth.
The proof-tail is now 18 ready and 2 blocked
| Metric | Value |
|---|---|
| Input blocked rows | 20 |
| Cumulative ready repairs | 18 |
| Raw LinkedIn JD ready repairs | 7 |
| Still blocked rows | 2 |
| Top-500 local proof proxies | 500 / 500 |
| Top-1,000 local proof proxies | 998 / 1,000 |
| Embedding candidates | 0 |
| Batch candidates | 0 |
| Production unlocks | 0 |
AIN-510 remains promotion_ready for local exact cosine with 6,506 valid vectors, complete top-500/top-1,000 vector coverage, and zero stale vectors. Runtime embedding authority is still not promoted.
Seven rows moved because source rows disambiguated them
| Title | Function | Authority mode |
|---|---|---|
| teacher-science | education | linkedin_jd_subject |
| court judicial assistant teller | legal_compliance | linkedin_jd_exact |
| teacher-social studies | education | linkedin_jd_subject |
| landscape designer | design_creative | linkedin_jd_exact |
| teacher-computer | education | linkedin_jd_subject |
| AML SME - SIU | legal_compliance | linkedin_jd_exact |
| food and beverage lead auditor | legal_compliance | linkedin_jd_exact |
court judicial assistant teller is now correctly interpreted as a Colorado Judicial Branch role in Teller County, not a bank teller role. It remains documented as single-table LinkedIn evidence with SOC caveats.
The last two rows need stronger disambiguation
| Title | Reason |
|---|---|
| lab assistant | Real JD evidence exists, but the role is mixed across clinical, research, materials, admin, and healthcare-adjacent contexts. |
| ecommerce manager | Real JD evidence exists, but the role remains multifunctional across marketing, sales, category, operations, and marketplace work. |
No new human_review fields or gates were introduced. Older generated receipts still contain legacy wording, but this slice used source and semantic quality gates only.
The checkpoint passed tests, lint, gates, and full validation
| Check | Result |
|---|---|
| Focused pytest | 8 passed |
| Ruff | pass |
| AIN-506 gate | pass |
| AIN-510 gate | promotion_ready |
| Production runtime readiness | ready_to_harden_headless_production_runtime |
| Full validation | pass |
| Git diff whitespace check | pass |
Claude CLI reviewed the diff read-only. Verdict: conditional pass, with no must-fix before local commit. The two implementable hardening notes were handled before final validation.
Linear writeback was attempted from this VDS session and returned auth_revoked / HTTP 401. The Markdown handoff contains the exact payload to post to AIN-510, AIN-520, and AIN-527 once auth is refreshed.
Exact restart commands
cd /srv/aina/aina-data-engine-room
git status --short --branch
git log -5 --oneline
uv run aina-data-engine --root /srv/aina/aina-data-engine-room ain-506-p0-gate
uv run aina-data-engine --root /srv/aina/aina-data-engine-room ain-510-retrieval-promotion-gate
uv run aina-data-engine --root /srv/aina/aina-data-engine-room production-runtime-readiness
uv run aina-data-engine --root /srv/aina/aina-data-engine-room validate
jq '{status, valid, metrics, checks, scope}' artifacts/validation/ai_fluency_proof_tail_authority_repair_v1.json
jq '{status, valid, metrics, checks}' artifacts/validation/ai_fluency_top_band_capability_coverage_v1.json
Close lab assistant and ecommerce manager only if stronger source context can disambiguate them; otherwise move back to the clean-before-embed production spine.