Campaign — One letter sent by 10 or more people, copied or lightly reworded. One of 26 submissions in its group; the sender added words of their own. See the letter, its submissions and topics.
In short: The comment places on the record that the draft environmental impact statement incorrectly attributes wildfire mitigation to the rescission of the Roadless Rule, contradicts this with Forest Service data on human-caused fires and road proximity, and documents specific tribal objections regarding the lack of required government-to-government consultation and the threat to cultural and subsistence resources in the Tongass National Forest.
Scored with own additions — A family member whose own text beyond the shared letter was scored and combined with the letter's score.
Shaded passages are the ones the analysis quoted as evidence for a dimension: Analytical gapEvidenceLegal
Each dimension is scored 0–3; the eight sum to the substance score out of 24.
A3 weak: Substantive, but easier to set aside.
Owed an answer on Analytical gap, Evidence.
These results are meant to be shared.
How it works. A large language model (an open-weight Qwen3.8 model) reads each substantive comment and copies, word for word, the passages that carry its analytical gap, evidence, request, alternative and connection to the place; it returns no scores. Code grades those passages 0–3 on eight dimensions — evidence, legal grounding, engagement with the environmental analysis, analytical gaps, alternatives, specific requests, position, and local knowledge — with legal grounding taken from a citation scan, not the model. For the strongest tenth on each side, the copied passages are checked against the comment and shown as exhibits. A comment counts as “substantive” when it clears a floor filter — it must show at least one substantive signal (a named entity, a specific citation, a stated analytical deficiency, or first-person testimony), which screens out one-line and purely conclusory submissions before any model scoring.
The full method. Every step, why it is done that way, its known limits and a glossary: Methodologies →
The data. The full canonical dataset — every comment on Docket FS-2025-0001 — is available from Regulations.gov: https://www.regulations.gov/bulkdownload.
Roadless.org — analysis of the public comment docket.
Media inquiries welcome — nicholas@wanderingnature.com.
© 2026 Roadless.org, Wandering Nature, LLC. All rights reserved.