Generated: 2026-04-27 16:11 UTC
Source: Pano cluster combined audit (/tmp/combined_audit.json)
Per-stage coverage at-a-glance
| Stage | Entities | Pct | Threshold |
|---|---|---|---|
Background (>=300 chars) | 72 / 75 | 96.0% | substantive prose |
Investors (>=1) | 51 / 75 | 68.0% | at least 1 named investor |
Goals (>=4) | 75 / 75 | 100% | 4 of 5 expected |
Goals clean (>=4) | 73 / 75 | 97.3% | label well-formed |
RIOHs (>=4) | 75 / 75 | 100% | post-fix |
News (>=4) | 72 / 75 | 96.0% | Serper /news harvest |
Press (>=4) | 69 / 75 | 92.0% | press_release Serper |
SEC (>=2) | 68 / 75 | 90.7% | SEC EDGAR via search |
| Headcount total | 20 / 75 | 26.7% | populated total field |
| Headcount trend | 17 / 75 | 22.7% | populated trend field |
Coverage gaps to address
Tier 1 — substantive blockers
- Headcount stage is undercovered (20/75 + 17/75 trend). The
org_chartGemma stage runs but emitsheadcountasNonefor the majority of entities. Likely cause: Gemma defaults to null when not confident; we accept null rather than re-prompting. Fix: add a separate Serper query layer specifically for"<entity> headcount" OR "<entity> employees" OR site:linkedin.com/company/<slug>and parse with regex. - Investor coverage at 68% — 24 entities have zero investors captured. Investigation: the investor stage targets organizations only, so all 12 person-entities skip it (-12). Of the remaining 63 organizations, 12 still show 0 investors. Likely public companies (SEC-only) or VC-funds that don't have visible investor stacks.
Tier 2 — minor coverage gaps
- 3 entities have <300-char backgrounds (Codametrix, Optum Bank, Optum Care). Codametrix has 10 chars — failed background generation, needs reprocessing.
- 6 entities have <4 press releases. Likely Israeli-domiciled or person-entities without press lineage.
- 7 entities have <2 SEC filings. Expected for private foreign-domiciled or sub-scale entities.
Tier 3 — observation only
- News coverage at 96% is essentially saturated; the missing 3 are person-entities with weak news presence
- Goals/RIOH coverage at 100% post-fix, validates the parser refactor
Coverage by entity-type
- Organization (63 entities): all stages populated except investors/headcount
- Person (12 entities): background, goals, RIOH all clean; investors/org/headcount stages skipped by design
Stage success ranking
- Goals (100%) — most reliable stage post-refactor
- RIOHs (100%) — most reliable post-fix
- News (96%) — saturated; Serper /news endpoint works well
- Background (96%) — 1-2 outliers
- Press (92%) — second-tier
- SEC (91%) — second-tier
- Goals-clean (97%) — minor parser artifacts
- Investors (68%) — by-design gap for persons + public companies
- Headcount-total (27%) — major coverage gap
- Headcount-trend (23%) — major coverage gap
Recommended action sequencing
- Build dedicated headcount Serper layer (3-line fix in
parallel_deep_research.py) — biggest coverage gain available - Force-refresh Codametrix background — single-entity issue with disproportionate impact on
nym_medical_coding_industry_report - Add coverage panel to the dashboard — render this matrix at
/admin/coverageso it's visible during continuous-cycle ops - Defer person-entity investor coverage — by-design 0%; not a real gap Co-Authored-By: Oz oz-agent@warp.dev