PubLedge

PubLedge

Open recordkeeping protocol for fact-specific written interpretations between two parties — Joint Interpretation Agreements (JIAs), Regulatory Mitigation Agreements (RMAs), no-action letters, private letter rulings, advisory opinions, and analogous civic instruments (HOA decision logs, co-op governance records, flying-club asset agreements, and the like).

Plain markdown with structured frontmatter. SHA-256 manifest checks provide source-to-manifest consistency. Bound to the Semantic Arts gist upper ontology so records from different authorities can be queried together.

Public and maintained. Package v0.2.5; protocol specification v0.2.0. The MCP server supports the MCP 2026-07-28 stateless core plus the legacy 2024-11-05 handshake. Current npm, MCP Registry, GitHub tag, and GitHub Release observations are recorded in the publication state. Standalone product expansion is parked pending a concrete legal-graph or adopter demand signal.

Who this is for

Regulators, regulated parties, and civic bodies that issue or rely on fact-specific written interpretations and need them recorded in a portable, queryable form.

What problem it solves

Fact-specific interpretations (no-action letters, private rulings, JIAs, HOA decisions) live in scattered, unstructured records that can't be compared across authorities. PubLedge is an open protocol that records them as manifest-checked markdown bound to a shared ontology.

Canonical URL

https://publedge.org/

Part of the PAICE legal graph

PubLedge is one component of the PAICE legal graph (with EveryAILaw, AI Incident Law, and Obligation First). It is intentionally open: code under Apache 2.0, protocol and content under CC BY 4.0, commercial use permitted with attribution. The open siblings are funded by EveryAILaw Pro, the graph's single restricted layer; openness here is a deliberate PBC-charter choice. The canonical model is in the PAICE Foundation INTENT.

What this repo is

Three things in one place:

1. The protocol — the PROTOCOL.md specification and the PRIOR-ART.md survey that motivates it.
2. Utah-shaped reference content — 5 JIA/RMA templates anchored to Utah's AI Policy Act (Utah Code §13-72a) and GenAI safe-harbor (§13-75-104), plus 18 demonstration instruments under data/examples/instruments/ spanning 8 authorities (Utah OAIP, Utah Legislature, Colorado Legislature, SEC, CFPB, IRS Chief Counsel, IRS TEGE, CFTC) and 7 instrument types (JIA, RMA, no-action letter, advisory opinion, private letter ruling, interpretive letter, statute). 35 first-class obligation records under data/examples/obligations/ are mapped to the instruments via data/examples/mapping/index.yml; legal lifecycle is tracked separately from editorial maturity.
3. The published site — rendered HTML under docs/, served by GitHub Pages from main /docs. Regenerate with node scripts/build.js && node scripts/build-extras.js before committing; CI fails if docs/ drifts from sources.

Maintenance scope

Weekly checks flag overdue records and temporal inconsistencies for human review. A separate manual pilot observes three selected official sources and retains inaccessible sources and unresolved findings. It does not renew verification dates, legal statuses, or the wider corpus. Independent missing-run monitoring and recovery email acceptance remain open. See the maintenance pilot for dated evidence and review boundaries.

Machine-readable endpoints

Every record and index is published in parallel HTML + structured form so agents can walk the registry without scraping:

What this repo is not

• Not a regulator. PubLedge does not issue rulings.
• Not a law firm. Templates here are prior art, not legal advice.
• Not a CMS. Editors edit markdown in git.
• Not a blockchain. The integrity layer is plain SHA-256 over plain files.

Quickstart

git clone https://github.com/snapsynapse/publedge.git
cd publedge
./scripts/validate-hashes.sh           # verify integrity
node scripts/validate.js               # cross-reference checks
node scripts/build.js                  # regenerate docs/ entity pages + API
node scripts/build-extras.js           # copy reference HTML, feeds, discovery files

To validate the Obligation-First binding, check out snapsynapse/obligation-first beside this repo or set OBLIGATION_FIRST_DIR, then run npm run validate:of.

After intentional content edits, refresh hashes:

./scripts/validate-hashes.sh --update

CI runs all of the above, plus a pa11y-ci WCAG 2.1 AA pass across every URL in the sitemap, on every push and pull request.

Use PubLedge in five minutes

Choose the surface that matches the job:

1. Browse the instrument registry or open a canonical record such as the SEC CorpFin no-action letter.
2. Query an index without scraping HTML: bash curl -sS https://publedge.org/api/v1/containers.json | jq '.[0]'
3. Fetch a record-shaped JSON representation by appending record.json to its canonical record URL: bash curl -sS https://publedge.org/us/federal/sec-corpfin/nal/2025-001/record.json | jq '.id, .status'
4. Check the publication state for a provider-verified npm version, then add that package version to any stdio-capable client. The example below is for this package version: json { "mcpServers": { "publedge": { "command": "npx", "args": ["-y", "publedge@0.2.5"] } } }
5. Use search to discover records and fetch_by_url when you already have a canonical PubLedge URL. The package exposes the 13 tools listed above. The complete endpoint and capability inventories are at api/v1/index.json, agents.json, and the source-controlled publication state.

Canonical markdown under data/examples/ is the maintained source. Published HTML, API indexes, and each record.json are generated representations and should not be edited directly. Repository checkout instructions operate source code; they are not an install claim. Use the canonical publication state to select a provider-verified package.

Repository layout

The _workshop/ directory documents the design decisions behind the layout above. Read _workshop/TAXONOMY.md, _workshop/SITEMAP.md, and _workshop/CONTENT-GUIDE.md before proposing structural changes.

Contributing an instrument

1. Pick template under _templates/jia/ or _templates/rma/.
2. Replace every {{variable_name}} with applicable values.
3. Set id to {jurisdiction}-{authority}-{type}-{YYYY-NNN} (e.g. us-ut-oaip-rma-2025-003). Filename must match: us-ut-oaip-rma-2025-003.md.
4. Set legal status: proposed and editorial_status: draft. Add parties under parties:.
5. Place file under data/examples/instruments/.
6. Run ./scripts/validate-hashes.sh --update to refresh MANIFEST.yaml.
7. Run node scripts/build.js && node scripts/build-extras.js to verify site regenerates cleanly.
8. Open a pull request.

See CONTRIBUTING.md for full conventions including obligation entries, source PDFs, and OCR workflow.

License

PubLedge is dual-licensed:

• Content (markdown, YAML, HTML) — CC-BY 4.0
• Code (scripts, schemas, build tooling) — Apache 2.0

See LICENSE for the split. Vendored snapshots retain their upstream licenses; the pinned gist core ontology is CC-BY 4.0 (Semantic Arts). Full credits in ATTRIBUTION.md.

Built on

• Knowledge as Code — the four-role entity pattern (Authority / Container / Secondary / Primary) PubLedge inherits.
• gist (Semantic Arts) — open upper ontology bound to PubLedge entities.
• Every AI Law — preferred source for statute-anchor URLs in statute_anchors[].
• skill-provenance — hash-mechanism pattern adapted for validate-hashes.sh. PubLedge does not adopt the full skill-provenance protocol.

Status and roadmap

See ROADMAP.md for phasing and _workshop/ROADMAP.md for the original workshop plan.