PLGen Syntax Specification

The open standard for
provenance declaration

Version: 1.0 Status: Draft Published: 2026-02-17 License: CC BY 4.0

Overview

PLGen is a plain-text syntax for declaring the provenance of AI-assisted content. It is human-readable, tool-parseable, and implementation-agnostic. Any tool — a CLI, a website, a browser extension — can read or write a valid .plgen file using this specification.

Think of it like Markdown: a simple set of rules that does useful work across many contexts without requiring special software to understand.

Design Principle PLGen is a disclosure format, not a quality certification. It makes no judgment about how much AI assistance is "too much." It simply asks: what happened, and who is accountable?

File Format

Fields

Field Type Description
@provenance directive Version declaration. Must be line 1. Required
author string Full name of the human accountable for the content. Required
date YYYY-MM-DD Date of completion or publication. Required
human integer 0–100 Percentage of human contribution. Must sum to 100 with ai. Required
ai integer 0–100 Percentage of AI contribution. Must sum to 100 with human. Required
tools string AI tool(s) used. Comma-separated if multiple. Optional
shared-by string Name of person republishing content they did not originally create. Optional
updated YYYY-MM-DD Date of most recent substantive revision. Optional
note string Single plain-language sentence describing the collaboration. Optional
ref URL or citation Source referenced during creation. Repeatable for multiple sources. Optional

Example

# PLGen v1.0 — provenance-label.org/spec
@provenance 1.0
author: Shelton Davis
date: 2026-02-17
human: 65
ai: 35
tools: Claude Sonnet 4.6
note: Concept and direction human. Draft and structure AI. Edited for voice.
ref: https://provenance-label.org/spec

Output Formats

Any valid implementation must support at minimum the --short and --long output formats. --json is recommended for tool integrations.

--short

Single-line badge. For inline use, footers, social posts.

--long

Full disclosure block. For articles, documentation, reports.

--json

Machine-readable export for tool integrations and APIs.

Short output
PL v1.0 | Shelton Davis | 2026-02-17 | Human 65% · AI 35% · Claude Sonnet 4.6
Long output
─────────────────────────────────────
PROVENANCE LABEL v1.0
─────────────────────────────────────
Author:   Shelton Davis
Date:     2026-02-17
Human:    65%
AI:       35%
Tools:    Claude Sonnet 4.6
Note:     Concept and direction human.
          Draft and structure AI.
          Edited for voice.
─────────────────────────────────────
provenance-label.org/spec
JSON output
{
  "plgen": "1.0",
  "author": "Shelton Davis",
  "date": "2026-02-17",
  "human": 65,
  "ai": 35,
  "tools": "Claude Sonnet 4.6",
  "note": "Concept and direction human. Draft and structure AI. Edited for voice."
}

Validation Rules

Registry (Coming)

Submitted labels will receive a permanent short ID — for example, PL-000312 — that can be embedded in content. Anyone can look up a label ID at provenance-label.org/r/PL-000312 to verify the original, timestamped disclosure.

How the registry works
1. Generate a .plgen file using any valid tool
2. Submit to provenance-label.org/submit
3. Receive a unique PL-ID for your label
4. Embed PL-ID in your content
5. Anyone can verify at provenance-label.org/r/[PL-ID]

Creator profiles: provenance-label.org/[author-name]
→ All labels by that author, in chronological order

Versioning

The @provenance directive specifies the spec version. Major version changes indicate breaking format changes. Minor version changes are backwards-compatible additions. Implementations should specify the version they support.

Building on PLGen

This specification is licensed CC BY 4.0. Anyone can build implementations — CLI tools, website generators, browser extensions, GitHub Actions, editor plugins — as long as they reference this spec. Implementation code is licensed MIT.

To propose changes to the spec, open an issue on the GitHub repository.