Semantic Scholar Release Data API

openapi: 3.0.0
info:
  title: Academic Graph Author Data Release Data API
  version: '1.0'
  description: "Fetch paper and author data from the Semantic Scholar Academic Graph (S2AG).\n        <br><br>\n        Some things to note:\n        <ul>\n        <li>If you are using an API key, it must be set in the header <code>x-api-key</code> (case-sensitive).</li>\n        <li>We have two different IDs for a single paper:\n          <ul>\n            <li><code>paperId</code> - string - The primary way to identify papers when using our website or this API</li>\n            <li><code>corpusId</code> - int64 - A second way to identify papers. Our datasets use corpusId when pointing to papers.</li>\n          </ul>\n        </li>\n        <li>Other useful resources<ul>\n        <li><a href=\"https://www.semanticscholar.org/product/api\">Overview</a></li>\n        <li><a href=\"https://github.com/allenai/s2-folks/\">allenai/s2-folks</a></li>\n        <li><a href=\"https://github.com/allenai/s2-folks/blob/main/FAQ.md\">FAQ</a> in allenai/s2folks</li>\n        </ul></li>\n        "
servers:
- url: https://api.semanticscholar.org/graph/v1
tags:
- name: Release Data
paths:
  /release/:
    get:
      summary: List of Available Releases
      operationId: get_releases
      tags:
      - Release Data
      description: Releases are identified by a date stamp such as "2023-08-01". Each release contains full data for each dataset.
      responses:
        '200':
          description: List of Available Releases
          content:
            application/json:
              schema:
                type: array
                items:
                  type: string
                  description: Release ids in the form of date stamps
                  example: '2022-01-17'
  /release/{release_id}:
    get:
      summary: List of Datasets in a Release
      operationId: get_release
      tags:
      - Release Data
      description: Metadata describing a particular release, including a list of datasets available.
      responses:
        '200':
          description: Contents of the release with the given ID
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Release%20Metadata'
  /release/{release_id}/dataset/{dataset_name}:
    get:
      summary: Download Links for a Dataset
      operationId: get_dataset
      tags:
      - Release Data
      description: 'Datasets are partitioned and stored on S3. Clients can retrieve them by requesting this list

        of pre-signed download urls and fetching all the partitions.'
      responses:
        '200':
          description: Description and download links for the given dataset within the given release
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Dataset%20Metadata'