SEC EDGAR Deal-Term Extraction
This is methodology@2026-Q3 as it was on 2026-05-25: the immutable record any signed export stamped methodology@2026-Q3 was computed under. It is intentionally the citation prose, not the current presentation, and it will never change. The methodology has since advanced (current is Methodology M10). Current version · Full version history · Verify an export
We extract structured deal terms from public SEC EDGAR filings for a curated biotech sponsor cohort, retain source provenance, and use aggregate-eligible comparator medians to auto-populate empty rNPV deal structures in engine 2.3. User-entered deal terms always take precedence.
1. What this section covers
PhaseFolio ingests deal-term data from SEC EDGAR for a curated cohort of public biotech sponsors. The extracted fields include upfront cash, near-term and total milestones, royalty ranges, equity consideration, counterparty, asset, indication, effective date, territory, and exclusivity.
v1 extends the v0 ingestion substrate into a canonical read layer and engine integration. Empty rNPV deal structures can now be auto-populated from aggregate SEC comparator medians when enough high-quality comparables exist. User-entered deal structures take precedence: if the user provides any economic deal term, no SEC auto-populate path fires.
2. Data source and legal posture
The source is SEC EDGAR via the SEC's official endpoints (data.sec.gov and www.sec.gov). SEC expressly permits free access and reuse of EDGAR public filing content; PhaseFolio extracts factual deal terms from public filings and surfaces them with source links, short quotes, extraction-risk disclaimers, and no SEC endorsement language.
No AGPL- or other copyleft-licensed code sits in the ingestion path. The pipeline does not depend on the edgartools or sec-edgar-mcp projects.
3. Cohort and forms covered
The current dataset is the AMR-indication biotech sponsor cohort resolved from PhaseFolio's enriched antimicrobial trial dataset. The v1 ingestion path supports Form 8-K and Form 6-K filings filed on or after 2020-01-01. Customer-facing foreign-private-issuer cohort claims and 10-K/10-Q Exhibit 10.x extraction remain separate counsel-review events.
- 8-K Item 1.01: material definitive agreement summaries, used for the counsel-approved auto-populate disclosure.
- 6-K: ingestion-enabled for foreign private issuer coverage; any broader customer-facing FPI claims require supplemental counsel review.
- 10-K/10-Q Exhibit 10.x: out of v1 scope because operative agreement text, redactions, and deduplication require a separate design.
4. Extraction pipeline
- Per-CIK submissions fetch. For each cohort sponsor, the pipeline pulls SEC submissions JSON and filters to supported forms on or after 2020-01-01.
- Cheap deterministic classifier. Each candidate filing is passed through
classifier@2026-05-25-v1to drop obvious non-deal filings before LLM extraction. The Item 1.01 short-circuit applies to 8-K only because 6-K filings do not use the same item numbering. - LLM-assisted structured extraction. Deal candidates are sent to
deal_terms_extractor@2026-05-25-v2, which separates equity dollars from equity share counts and gives platform-broad deals an indication-null path for cohort fallback. - Provenance capture. Every extraction stores field values, source section, a source quote capped at 500 characters, extractor version, raw response, and confidence.
- Review gating. Rows below the confidence threshold are flagged with
needs_review. Aggregate medians exclude unreviewed flagged rows untilreviewed_atis populated by the admin review route.
5. Fields extracted
- Upfront cash in USD millions.
- Near-term milestones and total milestones in USD millions.
- Royalty rate range, including low and high percentages when disclosed.
- Equity component, split into USD value and share count when filings disclose shares rather than dollars.
- Counterparty, licensor, licensee, asset or program, indication, effective date, territory, and exclusivity.
Royalty band conventions such as "low single-digit" and "mid teens" follow defensible industry anchors approximating BIO Industry Analysis 2021 and Tufts CSDD deal-term tables. Re-anchoring requires an extractor version bump.
6. Engine integration (v1 — engine 2.3)
When a user submits an rNPV scenario with an empty deal_structure, engine 2.3 can auto-populate default deal terms from a cascading match against SEC comparators:
- Try indication × deal type. If at least 3 comparable deals exist, use their median economics.
- Otherwise fall back to indication only. If at least 3 comparable deals exist, use their median economics.
- Otherwise no auto-populate occurs, and the engine falls back to its pre-2.3 default behavior.
Only aggregate-eligible deal terms feed the medians: rows where needs_review = false, or rows that were flagged but later reviewer-cleared. Per-deal administrative display can include flagged rows, but engine medians cannot.
Concrete example: for an antimicrobial × license-in project with no user-entered deal terms, engine 2.3 may auto-populate from a median of 5 AMR license-in deals, such as median upfront of $50M and median royalty range of 8-14%. The dossier discloses the comparator count, match level, cohort, medians, methodology link, and source accessions.
7. Storage and access
Extracted data lives in a private Supabase schema (sec) with filings, deal_terms, ingestion_runs, and cohort_seed tables. Raw filing HTML is retained privately for reproducibility; customer-facing surfaces use source links, accession numbers, and short quotes rather than redistributing raw filing text.
Admin endpoints are gated by X-Admin-Key. The canonical read layer is query_sec_deal_terms for per-deal provenance and query_sec_deal_terms_aggregate for engine medians.
8. What we do not claim
- 8-K and 6-K summaries are not full contracts. They can omit true-up provisions, anti-stacking, step-downs, change-of-control terms, and other operative clauses.
- Redactions are not reconstructed. Current Reg S-K Item 601(b)(10)(iv) permits redaction of specific provisions or terms where the information is customarily and actually treated as private or confidential and is not material. Redacted fields surface as null unless another public filing discloses the same value.
- LLM extraction can be wrong. Values may be incomplete or incorrect, and the source filing controls.
- The cohort is curated, not exhaustive. v1 covers AMR comparators only. NSCLC, RA, modality matching, and Exhibit 10.x extraction are future scopes.
- No SEC endorsement. PhaseFolio is not affiliated with, endorsed by, or certified by the SEC.
9. Versioning
| Artifact | Version | Reason |
|---|---|---|
| Dataset | sec_deal_terms@2026-Q3 | v1 refresh under extractor v2; AMR cohort; 8-K + 6-K ingestion support. |
| Extractor prompt | deal_terms_extractor@2026-05-25-v2 | Equity share/dollar disambiguation and platform-broad indication guidance. |
| Classifier | classifier@2026-05-25-v1 | Deterministic deal pre-filter unchanged. |
| Engine | 2.3.0 | Empty deal-structure scenarios can change when SEC comparator medians are available. |
| Methodology | methodology@2026-Q3 | This page adds v1 read-layer and engine integration disclosure. |
The outgoing v0 methodology remains frozen at /methodology/sec-deal-terms?version=methodology@2026-05-25 and ?version=2026-Q2.
Key facts
| Current methodology | methodology@2026-Q3 |
| Dataset version | sec_deal_terms@2026-Q3 |
| Extractor prompt | deal_terms_extractor@2026-05-25-v2 |
| Classifier | classifier@2026-05-25-v1 |
| Engine integration | Engine 2.3 auto-populates empty deal structures from SEC comparator medians only when N >= 3. |
| Review gate | Aggregate medians exclude unreviewed needs_review rows; reviewer-cleared rows are eligible. |
| User precedence | Any user-entered economic deal term prevents SEC auto-population. |
| Legal posture | Factual extraction from public SEC EDGAR filings with source links, short quotes, extraction-risk disclaimers, and no SEC endorsement language. |
References
01US Securities and Exchange Commission — EDGAR filing access.
02SEC Fair Access Policy — User-Agent and 10 requests/second rate cap.
03Regulation S-K Item 601 — Exhibits and redaction provisions for material agreements.
04BIO Industry Analysis 2021 — Clinical Development Success Rates and Contributing Factors.
05Tufts Center for the Study of Drug Development — deal-term and royalty-rate tables.
Frozen snapshot · methodology version: methodology@2026-Q3 · Last updated: 2026-05-25 · Version history →