Every campaign, by how it reached the agency: choose Individual Submission or Bulk Upload.
A campaign is an organised effort by a group to get people to weigh in on the rule. The group writes a letter or a petition, asks its supporters to add their names or their own words, and gets the result to the agency. However it arrives, it is one campaign. It can arrive in two ways, and each is counted its own way.
The count is of entries, not people. A posted comment carries no name, so a person who posted the letter and also signed the petition is two entries, and cannot be matched.
The campaigns whose supporters posted the letter themselves, largest first by how many times it was posted. Each counts as one unique comment, however many posted it. Where the group behind a campaign is known, it is named, with how we know; otherwise the campaign is named by how its letter opens.
Each campaign's organisation where known, its letter, how many submitted it, its position and ratings, and the topics it raises.
“Dear Secretary Rollins: I wish to express my strong opposition to the U.S. Forest Service's proposal to rescind the Roadless Area…”Named in the letter: Dozens of volunteers with the Potomac Appalachian Trail Club maintain 61 trails in two districts on the George Washington National Forest
Letter FS-2025-0001-351304 · 77 versions · 63 added their own words · names George Washington National Forest
“Dear Secretary Rollins: I wish to express my strong opposition to the U.S. Forest Service's proposal to rescind the Roadless Area…”Named in the letter: Dozens of volunteers with the Potomac Appalachian Trail Club maintain 61 trails in two districts on the George Washington National Forest
Letter FS-2025-0001-596365 · 25 versions · 22 added their own words · names George Washington National Forest
These results are meant to be shared.
How it works. Position and topic classification is performed by a large language model (the open-weight Qwen3.8 27B) that reads each comment and labels its position — supports, opposes, or neutral — and the topics it raises. Copies and campaigns are found by hashes of the text and the overlap of six-to-eight-word phrases, grouped into text families; every unique figure counts one family once. Sentence embeddings (Qwen3) find reworded templates, shown under Organized campaigns, and cross-check the families; lexical, syntactic and stylometric features (TF-IDF, spaCy) score each comment’s originality for review. Neither decides a copy count. The full method is on the Methodologies page of roadless.org.
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's bulk download, the canonical source: https://www.regulations.gov/bulkdownload. Download the CSV directly (Regulations.gov keeps this link working until October 18, 2026): https://bulk-downloads.regulations.gov/mv4-z8fw-q5jx.csv.
Roadless.org — analysis of the public comment docket.
Media inquiries welcome — nicholas@wanderingnature.com.
© 2026 Roadless.org, Wandering Nature, LLC. All rights reserved.