Reads Hugging Face paper pages as markdown and queries the papers API for authors, linked models/datasets/spaces, GitHub, and project URLs. Use when the user shares an hf.co/papers or arXiv URL or ID, or asks to summarize an AI paper on that index. Not for keyword arXiv search (arxiv), sentence-transformers training, or model-card eval tables (hugging-face-evaluation).
Reads Hugging Face paper pages as markdown and queries the papers API for authors, linked models/datasets/spaces, GitHub, and project URLs. Use when the user shares an hf.co/papers or arXiv URL or ID, or asks to summarize an AI paper on that index. Not for keyword arXiv search (arxiv), sentence-transformers training, or model-card eval tables (hugging-face-evaluation).
Hugging Face Paper pages (hf.co/papers) is a platform built on top of arXiv (arxiv.org) for AI and computer science research papers. Users submit papers at hf.co/papers/submit, which features them on the Daily Papers feed (hf.co/papers). Each day, users upvote and comment on papers. Each paper page allows authors to:
Claim their paper by clicking their name in the authors field. The paper then appears on their Hugging Face profile.
Link associated model checkpoints, datasets, and Spaces by including the HF paper or arXiv URL in the model card, dataset card, or Space README.
Link the GitHub repository and/or project page URLs.
Link the HF organization. The paper page then appears on the organization page.
When someone mentions an HF paper or arXiv abstract/PDF URL in a model card, dataset card, or Space README, the paper is automatically indexed. Not all indexed papers are submitted to Daily Papers—submission is for promotion. Papers can only be submitted to Daily Papers within 14 days of their arXiv publication date.
When to Use
User shares a Hugging Face paper page URL (e.g. https://huggingface.co/papers/2602.08025)
User shares a Hugging Face markdown paper page URL (e.g. https://huggingface.co/papers/2602.08025.md)
User shares an arXiv URL (e.g. https://arxiv.org/abs/2602.08025 or https://arxiv.org/pdf/2602.08025)
User mentions an arXiv ID (e.g. 2602.08025)
User asks you to summarize, explain, or analyze an AI research paper
Prerequisites
Network access to https://huggingface.co and https://arxiv.org.
curl available on the host. On Windows PowerShell, curl is an alias for Invoke-WebRequest by default; use curl.exe to invoke the real curl binary, or use Invoke-RestMethod as an alternative.
HF_TOKEN environment variable set when calling write endpoints (claim authorship, index paper, update links). Public read endpoints require no authentication.
Windows PowerShell notes
Use curl.exe instead of curl to avoid the PowerShell alias for Invoke-WebRequest.
For HF_TOKEN, set it in the current session:
$env:HF_TOKEN = "YOUR_TOKEN_HERE"
In PowerShell, use double quotes for JSON bodies and escape inner double quotes, or use a here-string.
Procedure
Step 1 — Parse the paper ID
Extract the arXiv ID from whatever the user provides:
Input
Paper ID
https://huggingface.co/papers/2602.08025
2602.08025
https://huggingface.co/papers/2602.08025.md
2602.08025
https://arxiv.org/abs/2602.08025
2602.08025
https://arxiv.org/pdf/2602.08025
2602.08025
2602.08025v1
2602.08025v1
2602.08025
2602.08025
Use the extracted ID in any of the API endpoints below.
paperId (string, required): arXiv paper identifier being claimed
claimAuthorId (string): author entry on the paper being claimed, 24-char hex ID
targetUserId (string): HF user who should receive the claim, 24-char hex ID
Response: paper authorship claim result, including the claimed paper ID
Step 10 — Update paper links
Update the project page, GitHub repository, or submitting organization. The requester must be the paper author, the Daily Papers submitter, or a papers admin.
organizationId (string, nullable): organization ID, 24-char hex ID
projectPage (string, nullable): project page URL
Response: empty JSON object on success
Pitfalls
404 on https://huggingface.co/papers/{PAPER_ID} or .md endpoint: the paper is not indexed on Hugging Face paper pages yet. Fall back to arXiv (https://arxiv.org/abs/{PAPER_ID} or https://arxiv.org/pdf/{PAPER_ID}).
404 on /api/papers/{PAPER_ID}: the paper may not be indexed on Hugging Face paper pages yet.
Paper ID not found: verify the extracted arXiv ID, including any version suffix (e.g. v1).
PowerShell curl alias: on Windows, curl defaults to Invoke-WebRequest. Always use curl.exe to invoke the real curl binary, or use Invoke-RestMethod with equivalent parameters.
JSON quoting in PowerShell: single-quoted JSON strings with curl.exe work reliably. If using double quotes, inner double quotes must be escaped or use a here-string.
Write endpoints require auth: claim authorship, index paper, and update paper links all require Authorization: Bearer $HF_TOKEN. Public read endpoints do not.
POST /api/papers/{paperId}/links uses the HF paper object ID, not the arXiv ID. Using the arXiv ID here will fail.
arXiv ID pattern for indexing: must match ^\d{4}\.\d{4,5}$. Versioned IDs (e.g. 2602.08025v1) are not accepted by the index endpoint.
Not all arXiv papers have an HTML version: the .md endpoint may fall back to the HF paper page HTML, which is less detailed than the arXiv HTML.
Daily Papers submission window: papers can only be submitted to Daily Papers within 14 days of their arXiv publication date.
Verification
Verify a paper is indexed and fetchable as markdown:
