APIReference

List papers by category

Browse papers by category or semantic field. Use this to explore papers without a search query.

Does not count toward paper quota.

For full-text search, use GET /search instead.

GET
/papers

Authorization

ApiKeyAuth
x-api-key<token>

API key for authentication. Get yours at https://sciencestack.ai/settings/api

Format: sk_live_... or sk_test_...

In: header

Query Parameters

field?string

Semantic field to filter by (e.g., machine-learning, nlp, computer-vision). Required if category is not provided.

category?string

arXiv category filter. Comma-separated for multiple (e.g., cs.LG,cs.CL). Required if field is not provided.

sort?string

Sort order for results:

  • recent: Most recently published first (default)
  • citations: Most cited first
Default"recent"
Value in"recent" | "citations"
limit?integer

Maximum results to return

Default20
Rangevalue <= 100
offset?integer

Pagination offset

Default0
from?string

Only return papers published on or after this date. ISO 8601 format (e.g., 2025-01-01 or 2025-01-01T00:00:00Z).

Formatdate
to?string

Only return papers published before this date. ISO 8601 format (e.g., 2025-02-01 or 2025-02-01T00:00:00Z).

Formatdate

Response Body

application/json

application/json

application/json

curl -X GET "https://sciencestack.ai/api/v1/papers?field=machine-learning&category=cs.LG&from=2025-01-01&to=2025-02-01"
{
  "data": [
    {
      "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
      "title": "string",
      "arxivId": "string",
      "authors": [
        "string"
      ],
      "abstract": "string",
      "tldr": "string",
      "published": "2019-08-24T14:15:22Z",
      "citationCount": 0,
      "primaryCategory": "string"
    }
  ],
  "pagination": {
    "offset": 0,
    "limit": 0,
    "hasMore": true
  },
  "_version": "string"
}
{
  "error": {
    "code": "INVALID_QUERY",
    "message": "Query parameter \"q\" is required"
  }
}
{
  "error": {
    "code": "UNAUTHORIZED",
    "message": "Invalid API key"
  }
}

Search papers

Search papers across the catalog. This is the primary discovery endpoint. **Does not count toward paper quota.** Search behavior (in order of precedence): 1. Exact arXiv ID match: `1706.03762` or `1706.03762v7` 2. Full-text search on title + abstract 3. Author name search (fallback) 4. Fuzzy title match (last resort for typos)

Get paper metadata

Get paper metadata by arXiv ID or internal UUID. Optionally include additional fields like TOC, summaries, figures, etc.