- Category: web search & research
- Auth: API_KEY
- Composio-managed OAuth available? N/A
- Tools: 21
- Triggers: 0
- Slug:
SEMANTICSCHOLAR - Version: 20261101_00
Tools
Details about a paper
Details about a paper
Slug:
SEMANTICSCHOLAR_DETAILS_ABOUT_A_PAPERRetrieve details for a paper by its ID, with selectable fields. By default the tool requests title, abstract, year, authors, citation and reference counts, URL, venue, publication date, and fields of study; responses are limited to 10 MB.Input Parameters
A comma-separated list of the fields to be returned. The <code>paperId</code> field is always returned. If not specified, returns a useful default set of fields including title, abstract, year, authors, citation metrics, URL, venue, publication date, and fields of study. <p><b>Available fields:</b> paperId, corpusId, externalIds, url, title, abstract, venue, publicationVenue, year, publicationDate, publicationTypes, journal, citationCount, referenceCount, influentialCitationCount, isOpenAccess, openAccessPdf, fieldsOfStudy, s2FieldsOfStudy, authors, citations, references, embedding, tldr</p><p><b>Nested field notation:</b> Use a period (”.”) for fields with subfields:</p><ul> <li><b>authors</b>: Default returns authorId and name. For additional subfields use: authors.url, authors.affiliations, authors.homepage, authors.paperCount, authors.citationCount, authors.hIndex</li> <li><b>citations/references</b>: Default returns paperId and title. For additional subfields use: citations.abstract, citations.year, citations.authors, references.venue, etc.</li> <li><b>embedding</b>: Use embedding.specter_v1 or embedding.specter_v2 for specific versions</li></ul><p><b>Examples:</b></p><ul> <li><code>title,url,year</code> - Basic paper info</li> <li><code>title,authors.url,authors.hIndex</code> - Paper with author metrics</li> <li><code>title,citations.title,citations.year</code> - Paper with citation details</li> <li><code>title,embedding.specter_v2,tldr</code> - Paper with AI summary and embeddings</li></ul>
The following types of IDs are supported: <ul> <li><code><sha></code> - a Semantic Scholar ID, e.g. <code>649def34f8be52c8b66281af98ae884c09aef38b</code></li> <li><code>CorpusId:<id></code> - a Semantic Scholar numerical ID, e.g. <code>CorpusId:215416146</code></li> <li><code>DOI:<doi></code> - a <a href=“http://doi.org”>Digital Object Identifier</a>, e.g. <code>DOI:10.18653/v1/N18-3011</code></li> <li><code>ARXIV:<id></code> - <a href=“https://arxiv.org/“>arXiv.rg</a>, e.g. <code>ARXIV:2106.15928</code></li> <li><code>MAG:<id></code> - Microsoft Academic Graph, e.g. <code>MAG:112218234</code></li> <li><code>ACL:<id></code> - Association for Computational Linguistics, e.g. <code>ACL:W12-3903</code></li> <li><code>PMID:<id></code> - PubMed/Medline, e.g. <code>PMID:19872477</code></li> <li><code>PMCID:<id></code> - PubMed Central, e.g. <code>PMCID:2323736</code></li> <li><code>URL:<url></code> - URL from one of the sites listed below, e.g. <code>URL:https://arxiv.org/abs/2106.15928v1</code></li> </ul> URLs are recognized from the following sites: <ul> <li><a href=“https://www.semanticscholar.org/“>semanticscholar.org</a></li> <li><a href=“https://arxiv.org/“>arxiv.org</a></li> <li><a href=“https://www.aclweb.org”>aclweb.org</a></li> <li><a href=“https://www.acm.org/“>acm.org</a></li> <li><a href=“https://www.biorxiv.org/“>biorxiv.org</a></li> </ul>
Output
Details about a paper s citations
Details about a paper s citations
Slug:
SEMANTICSCHOLAR_DETAILS_ABOUT_A_PAPER_S_CITATIONSRetrieve a paginated list of papers citing a specified paper. Optional fields can include citation contexts, intents, influence indicators, and citing-paper metadata.Input Parameters
A comma-separated list of the fields to be returned. If omitted, only <code>paperId</code> and <code>title</code> of the citing papers are returned. Available fields include: <ul> <li><code>contexts</code> - citation contexts (text snippets)</li> <li><code>intents</code> - citation intent categories</li> <li><code>isInfluential</code> - whether this is an influential citation</li> <li><code>citingPaper.*</code> - fields from the citing paper (e.g., <code>citingPaper.title</code>, <code>citingPaper.year</code>, <code>citingPaper.authors</code>, <code>citingPaper.abstract</code>, <code>citingPaper.citationCount</code>, <code>citingPaper.venue</code>)</li></ul> Examples: <ul> <li><code>fields=contexts,isInfluential,intents</code></li> <li><code>fields=citingPaper.title,citingPaper.year,citingPaper.authors</code></li></ul>
Used for pagination. When returning a list of results, start with the element at this position in the list.
The following types of IDs are supported: <ul> <li><code><sha></code> - a Semantic Scholar ID, e.g. <code>649def34f8be52c8b66281af98ae884c09aef38b</code></li> <li><code>CorpusId:<id></code> - a Semantic Scholar numerical ID, e.g. <code>CorpusId:215416146</code></li> <li><code>DOI:<doi></code> - a <a href=“http://doi.org”>Digital Object Identifier</a>, e.g. <code>DOI:10.18653/v1/N18-3011</code></li> <li><code>ARXIV:<id></code> - <a href=“https://arxiv.org/“>arXiv.rg</a>, e.g. <code>ARXIV:2106.15928</code></li> <li><code>MAG:<id></code> - Microsoft Academic Graph, e.g. <code>MAG:112218234</code></li> <li><code>ACL:<id></code> - Association for Computational Linguistics, e.g. <code>ACL:W12-3903</code></li> <li><code>PMID:<id></code> - PubMed/Medline, e.g. <code>PMID:19872477</code></li> <li><code>PMCID:<id></code> - PubMed Central, e.g. <code>PMCID:2323736</code></li> <li><code>URL:<url></code> - URL from one of the sites listed below, e.g. <code>URL:https://arxiv.org/abs/2106.15928v1</code></li> </ul> URLs are recognized from the following sites: <ul> <li><a href=“https://www.semanticscholar.org/“>semanticscholar.org</a></li> <li><a href=“https://arxiv.org/“>arxiv.org</a></li> <li><a href=“https://www.aclweb.org”>aclweb.org</a></li> <li><a href=“https://www.acm.org/“>acm.org</a></li> <li><a href=“https://www.biorxiv.org/“>biorxiv.org</a></li> </ul>
Output
Details about a paper s references
Details about a paper s references
Slug:
SEMANTICSCHOLAR_DETAILS_ABOUT_A_PAPER_S_REFERENCESRetrieves the list of references cited by a specific paper in the Semantic Scholar database. This endpoint allows users to explore the scholarly context of a publication by accessing its bibliography. It’s particularly useful for understanding the foundation of a paper’s research, tracing the development of ideas, or conducting literature reviews. The tool returns details about the cited papers, which may include their titles, authors, publication dates, and Semantic Scholar IDs. It should be used when analyzing a paper’s sources or investigating the connections between different academic works. Note that this endpoint only provides outgoing references (papers cited by the specified paper) and not incoming citations (papers that cite the specified paper).Input Parameters
A comma-separated list of the fields to be returned for each reference. If omitted, only paperId and title are returned for each cited paper. Available fields include: <ul><li><code>contexts</code> - Text snippets where the reference appears in the citing paper</li><li><code>intents</code> - Citation intent categories (e.g., ‘methodology’, ‘background’)</li><li><code>contextsWithIntent</code> - Combined context and intent objects</li><li><code>isInfluential</code> - Boolean indicating if this is a highly influential citation</li><li><code>citedPaper.<field></code> - Nested fields for the cited paper (use period notation)</li></ul>For citedPaper fields, use period notation: citedPaper.title, citedPaper.year, citedPaper.authors, citedPaper.abstract, citedPaper.venue, citedPaper.citationCount, citedPaper.referenceCount, etc.
Examples: <ul><li><code>contexts,isInfluential</code> - Get citation contexts and influence flag</li><li><code>citedPaper.title,citedPaper.year,citedPaper.authors</code> - Get cited paper metadata</li><li><code>contexts,isInfluential,citedPaper.title,citedPaper.abstract</code> - Combined request</li></ul>
Examples: <ul><li><code>contexts,isInfluential</code> - Get citation contexts and influence flag</li><li><code>citedPaper.title,citedPaper.year,citedPaper.authors</code> - Get cited paper metadata</li><li><code>contexts,isInfluential,citedPaper.title,citedPaper.abstract</code> - Combined request</li></ul>
Used for pagination. When returning a list of results, start with the element at this position in the list.
The following types of IDs are supported: <ul> <li><code><sha></code> - a Semantic Scholar ID, e.g. <code>649def34f8be52c8b66281af98ae884c09aef38b</code></li> <li><code>CorpusId:<id></code> - a Semantic Scholar numerical ID, e.g. <code>CorpusId:215416146</code></li> <li><code>DOI:<doi></code> - a <a href=“http://doi.org”>Digital Object Identifier</a>, e.g. <code>DOI:10.18653/v1/N18-3011</code></li> <li><code>ARXIV:<id></code> - <a href=“https://arxiv.org/“>arXiv.rg</a>, e.g. <code>ARXIV:2106.15928</code></li> <li><code>MAG:<id></code> - Microsoft Academic Graph, e.g. <code>MAG:112218234</code></li> <li><code>ACL:<id></code> - Association for Computational Linguistics, e.g. <code>ACL:W12-3903</code></li> <li><code>PMID:<id></code> - PubMed/Medline, e.g. <code>PMID:19872477</code></li> <li><code>PMCID:<id></code> - PubMed Central, e.g. <code>PMCID:2323736</code></li> <li><code>URL:<url></code> - URL from one of the sites listed below, e.g. <code>URL:https://arxiv.org/abs/2106.15928v1</code></li> </ul> URLs are recognized from the following sites: <ul> <li><a href=“https://www.semanticscholar.org/“>semanticscholar.org</a></li> <li><a href=“https://arxiv.org/“>arxiv.org</a></li> <li><a href=“https://www.aclweb.org”>aclweb.org</a></li> <li><a href=“https://www.acm.org/“>acm.org</a></li> <li><a href=“https://www.biorxiv.org/“>biorxiv.org</a></li> </ul>
Output
Get dataset download links
Get dataset download links
Slug:
SEMANTICSCHOLAR_GET_DATASETTool to get download links for a specific dataset within a release. Use when you need to download Semantic Scholar dataset files from S3. Returns pre-signed URLs for all dataset partitions.Input Parameters
ID of the release. Use ‘latest’ for the most recent release, or a specific date in YYYY-MM-DD format (e.g., ‘2024-12-31’)
Name of the dataset to retrieve. Common dataset names include: ‘papers’, ‘abstracts’, ‘authors’, ‘citations’, ‘embeddings’
Output
Get dataset diffs
Get dataset diffs
Slug:
SEMANTICSCHOLAR_GET_DATASET_DIFFSGet download links for incremental diffs between dataset releases. Returns a list of diffs required to update a dataset from start_release to end_release, enabling efficient dataset synchronization. Use when you need to update a local dataset copy without re-downloading the entire dataset.Input Parameters
Name of the dataset to retrieve diffs for. Common datasets include ‘papers’, ‘authors’, ‘citations’, ‘abstracts’, etc.
ID of the ending release. Use date format YYYY-MM-DD (e.g., ‘2025-01-15’) or ‘latest’ for the most recent release.
ID of the starting release. Use date format YYYY-MM-DD (e.g., ‘2024-12-31’) or ‘latest’ for the most recent release.
Output
Get details for multiple papers at once
Get details for multiple papers at once
Slug:
SEMANTICSCHOLAR_GET_DETAILS_FOR_MULTIPLE_PAPERS_AT_ONCERetrieve detailed information for multiple academic papers in a single API call using the Semantic Scholar paper batch endpoint. This endpoint efficiently fetches data for up to 500 papers at once, significantly reducing the number of individual API requests needed. Key features: - Accepts multiple paper ID formats (Semantic Scholar ID, CorpusId, DOI, ArXiv, PMID, etc.) - Customizable field selection to retrieve only needed data - Papers not found return null in the corresponding array position - Results maintain the same order as input IDs - Supports nested field queries (e.g., authors.name, citations.title) Use this endpoint when you have a list of known paper IDs and want to retrieve their details simultaneously, rather than making individual requests for each paper.Input Parameters
A list of paper IDs to retrieve (maximum 500 IDs per request). Supports multiple ID formats: Semantic Scholar Paper ID (e.g., ‘649def34f8be52c8b66281af98ae884c09aef38b’), CorpusId (e.g., ‘CorpusId:37220927’), DOI (e.g., ‘10.1038/nature14539’), ArXiv ID (e.g., ‘arXiv:1706.03762’), PubMed ID (e.g., ‘PMID:29446767’), PubMed Central ID (e.g., ‘PMCID:PMC5833129’), MAG ID, ACL ID, or paper URL. Papers not found will return null in the response array.
A comma-separated list of the fields to be returned. See the contents of Response Schema below for a list of all available fields that can be returned. The <code>paperId</code> field is always returned. If the fields parameter is omitted, only the <code>paperId</code> and <code>title</code> will be returned. <p>Use a period (“.”) for fields that have version numbers or subfields, such as the <code>embedding</code>, <code>authors</code>, <code>citations</code>, and <code>references</code> fields: <ul> <li>When requesting <code>authors</code>, the <code>authorId</code> and <code>name</code> subfields are returned by default. To request other subfields, use the format <code>author.url,author.paperCount</code>, etc. See the Response Schema below for available subfields.</li> <li>When requesting <code>citations</code> and <code>references</code>, the <code>paperId</code> and <code>title</code> subfields are returned by default. To request other subfields, use the format <code>citations.title,citations.abstract</code>, etc. See the Response Schema below for available subfields.</li> <li>When requesting <code>embedding</code>, the default <a href=“https://github.com/allenai/specter”>Spector embedding version</a> is v1. Specify <code>embedding.specter_v2</code> to select v2 embeddings.</li> </ul> Examples: <ul> <li><code>fields=title,url</code></li> <li><code>fields=title,embedding.specter_v2</code></li> <li><code>fields=title,authors,citations.title,citations.abstract</code></li> </ul>
Output
Get paper recommendations
Get paper recommendations
Slug:
SEMANTICSCHOLAR_GET_PAPER_RECOMMENDATIONSTool to get paper recommendations based on positive and negative example papers. Use when you need to find papers similar to ones you like (positive examples) and optionally dissimilar to ones you don’t like (negative examples). The recommendation engine analyzes the provided examples and returns relevant papers from the Semantic Scholar database.Input Parameters
Comma-separated list of fields to return for each recommended paper. If not specified, only paperId and title are returned. Available fields include: paperId, corpusId, externalIds, url, title, abstract, venue, publicationVenue, year, referenceCount, citationCount, influentialCitationCount, isOpenAccess, openAccessPdf, fieldsOfStudy, s2FieldsOfStudy, publicationTypes, publicationDate, journal, citationStyles, authors, embedding, tldr. Use dot notation for nested fields (e.g., ‘authors.authorId’, ‘citations.title’).
Array of paper IDs that represent negative examples (papers you don’t want similar recommendations for). This is optional and helps refine recommendations by excluding similar papers. Accepts the same ID formats as positive_paper_ids.
Array of paper IDs that represent positive examples (papers you like and want similar recommendations for). Supported ID formats include: Semantic Scholar ID (e.g., ‘649def34f8be52c8b66281af98ae884c09aef38b’), CorpusId (e.g., ‘CorpusId:215416146’), DOI (e.g., ‘DOI:10.18653/v1/N18-3011’), ArXiv (e.g., ‘ARXIV:2106.15928’), MAG (e.g., ‘MAG:112218234’), ACL (e.g., ‘ACL:W12-3903’), PMID (e.g., ‘PMID:19872477’), PMCID (e.g., ‘PMCID:2323736’), or URL from supported sites.
Output
Get recommendations for paper
Get recommendations for paper
Slug:
SEMANTICSCHOLAR_GET_RECOMMENDATIONS_FOR_PAPERTool to get recommended papers for a single positive example paper. Use when you need to find papers similar to a given paper based on Semantic Scholar’s recommendation algorithm.Input Parameters
Comma-separated list of fields to return for each recommended paper. paperId is always included. Available fields: title, abstract, year, authors, venue, publicationDate, citationCount, referenceCount, fieldsOfStudy, openAccessPdf, url, embedding, citations, references. Use dot notation for nested fields (e.g., ‘authors.authorId’, ‘citations.title’). Examples: ‘title,year,authors’ or ‘title,abstract,citationCount,url’
Paper ID to find recommendations for. Supports various ID formats: <sha> (Semantic Scholar ID), CorpusId:<id>, DOI:<doi>, ARXIV:<id>, MAG:<id>, ACL:<id>, PMID:<id>, PMCID:<id>, URL:<url>. Example: ‘ArXiv:1810.04805’ or ‘649def34f8be52c8b66281af98ae884c09aef38b’
Output
Get dataset release information
Get dataset release information
Slug:
SEMANTICSCHOLAR_GET_RELEASETool to retrieve metadata for a specific Semantic Scholar dataset release. Returns release information including available datasets with their descriptions. Use when you need to discover what datasets are available in a release or get release documentation.Input Parameters
ID of the release in date format (e.g., ‘2023-08-01’) or ‘latest’ for the most recent release
Output
List available dataset releases
List available dataset releases
Paper relevance search (Deprecated)
Paper relevance search (Deprecated)
Slug:
SEMANTICSCHOLAR_PAPER_RELEVANCE_SEARCHDEPRECATED: Use SEMANTICSCHOLAR_SEARCH_PAPERS instead. The SearchPapers endpoint allows users to search for academic papers within the Semantic Scholar database. It provides a powerful way to discover relevant scientific literature based on user-defined search criteria. This endpoint should be used when researchers, students, or developers need to find papers related to specific topics, authors, or time periods. The search functionality supports various query parameters to refine and customize the search results, making it suitable for both broad exploratory searches and targeted inquiries. However, users should be aware that the search is limited to papers indexed by Semantic Scholar, and very recent publications might not be immediately available. The endpoint returns a list of papers matching the search criteria, along with selected metadata fields, facilitating efficient literature review and analysis.Input Parameters
Restricts results to the given publication year or range of years (inclusive).
Examples: <ul> <li><code>2019</code> in 2019</li> <li><code>2016-2020</code> as early as 2016 or as late as 2020</li> <li><code>2010-</code> during or after 2010</li> <li><code>-2015</code> before or during 2015</li> </ul>
Examples: <ul> <li><code>2019</code> in 2019</li> <li><code>2016-2020</code> as early as 2016 or as late as 2020</li> <li><code>2010-</code> during or after 2010</li> <li><code>-2015</code> before or during 2015</li> </ul>
Maximum number of results to return per request (must be <= 100). Total results capped at 1,000.
Plain-text search query for papers (no special query syntax supported). Use spaces instead of hyphens in search terms. Example: ‘machine learning’ or ‘neural networks’
Restricts results to papers published in the given venues, formatted as a comma-separated list.
Input could also be an ISO4 abbreviation. Examples include: <ul> <li>Nature</li> <li>New England Journal of Medicine</li> <li>Radiology</li> <li>N. Engl. J. Med.</li> </ul> Example: <code>Nature,Radiology</code> will return papers from venues Nature and/or Radiology.
Input could also be an ISO4 abbreviation. Examples include: <ul> <li>Nature</li> <li>New England Journal of Medicine</li> <li>Radiology</li> <li>N. Engl. J. Med.</li> </ul> Example: <code>Nature,Radiology</code> will return papers from venues Nature and/or Radiology.
Comma-separated list of fields to return. paperId is always included; if omitted, only paperId and title are returned. Available fields include: title, abstract, year, authors, venue, publicationDate, citationCount, referenceCount, fieldsOfStudy, openAccessPdf, url, embedding.specter_v2, citations, references. Use dot notation for subfields (e.g., ‘authors.authorId’, ‘citations.title’). Examples: ‘title,abstract,year’ or ‘title,authors,citationCount,url’
Pagination offset: skip this many results before returning data. Use with limit for pagination.
Restricts results to papers in the given fields of study, formatted as a comma-separated list: <ul> <li>Computer Science</li> <li>Medicine</li> <li>Chemistry</li> <li>Biology</li> <li>Materials Science</li> <li>Physics</li> <li>Geology</li> <li>Psychology</li> <li>Art</li> <li>History</li> <li>Geography</li> <li>Sociology</li> <li>Business</li> <li>Political Science</li> <li>Economics</li> <li>Philosophy</li> <li>Mathematics</li> <li>Engineering</li> <li>Environmental Science</li> <li>Agricultural and Food Sciences</li> <li>Education</li> <li>Law</li> <li>Linguistics</li> </ul> Example: <code>Physics,Mathematics</code> will return papers with either Physics or Mathematics in their list of fields-of-study.
Restricts results to only include papers with a public PDF. This parameter does not accept any values.
Restricts results to only include papers with at least this many citations. Must be a non-negative integer. Example: 200
Restricts results to any of the following paper publication types: <ul> <li>Review</li> <li>JournalArticle</li> <li>CaseReport</li> <li>ClinicalTrial</li> <li>Conference</li> <li>Dataset</li> <li>Editorial</li> <li>LettersAndComments</li> <li>MetaAnalysis</li> <li>News</li> <li>Study</li> <li>Book</li> <li>BookSection</li> </ul> Use a comma-separated list to include papers with any of the listed publication types.
Example: <code>Review,JournalArticle</code> will return papers with publication types Review and/or JournalArticle.
Example: <code>Review,JournalArticle</code> will return papers with publication types Review and/or JournalArticle.
Restricts results to the given range of publication dates or years (inclusive). Accepts the format <code><startDate>:<endDate></code> with each date in <code>YYYY-MM-DD</code> format.
Each term is optional, allowing for specific dates, fixed ranges, or open-ended ranges. In addition, prefixes are suported as a shorthand, e.g. <code>2020-06</code> matches all dates in June 2020.
Specific dates are not known for all papers, so some records returned with this filter will have a <code>null</code> value for </code>publicationDate</code>. <code>year</code>, however, will always be present. For records where a specific publication date is not known, they will be treated as if published on January 1st of their publication year.
Examples: <ul> <li><code>2019-03-05</code> on March 3rd, 2019</li> <li><code>2019-03</code> during March 2019</li> <li><code>2019</code> during 2019</li> <li><code>2016-03-05:2020-06-06</code> as early as March 5th, 2016 or as late as June 6th, 2020</li> <li><code>1981-08-25:</code> on or after August 25th, 1981</li> <li><code>:2015-01</code> before or on January 31st, 2015</li> <li><code>2015:2020</code> between January 1st, 2015 and December 31st, 2020</li> </ul>
Each term is optional, allowing for specific dates, fixed ranges, or open-ended ranges. In addition, prefixes are suported as a shorthand, e.g. <code>2020-06</code> matches all dates in June 2020.
Specific dates are not known for all papers, so some records returned with this filter will have a <code>null</code> value for </code>publicationDate</code>. <code>year</code>, however, will always be present. For records where a specific publication date is not known, they will be treated as if published on January 1st of their publication year.
Examples: <ul> <li><code>2019-03-05</code> on March 3rd, 2019</li> <li><code>2019-03</code> during March 2019</li> <li><code>2019</code> during 2019</li> <li><code>2016-03-05:2020-06-06</code> as early as March 5th, 2016 or as late as June 6th, 2020</li> <li><code>1981-08-25:</code> on or after August 25th, 1981</li> <li><code>:2015-01</code> before or on January 31st, 2015</li> <li><code>2015:2020</code> between January 1st, 2015 and December 31st, 2020</li> </ul>
Output
Paper title search
Paper title search
Slug:
Limitations: <ul> <li>Will only return the single highest match result.</li> </ul> </ul>
SEMANTICSCHOLAR_PAPER_TITLE_SEARCHBehaves similarly to <code>/paper/search</code>, but is intended for retrieval of a single paper based on closest title match to given query. Examples: <ul> <li><code>https://api.semanticscholar.org/graph/v1/paper/search/match?query=Construction of the Literature Graph in Semantic Scholar</code></li> <ul> <li>Returns a single paper that is the closest title match.</li> <li>Each paper has its paperId, title, and matchScore as well as any other requested fields.</li> </ul> <li><code>https://api.semanticscholar.org/graph/v1/paper/search/match?query=totalGarbageNonsense</code></li> <ul> <li>Returns with a 404 error and a “Title match not found” message.</li> </ul> </ul> Limitations: <ul> <li>Will only return the single highest match result.</li> </ul> </ul>
Input Parameters
Restricts results to the given publication year or range of years (inclusive).
Examples: <ul> <li><code>2019</code> in 2019</li> <li><code>2016-2020</code> as early as 2016 or as late as 2020</li> <li><code>2010-</code> during or after 2010</li> <li><code>-2015</code> before or during 2015</li> </ul>
Examples: <ul> <li><code>2019</code> in 2019</li> <li><code>2016-2020</code> as early as 2016 or as late as 2020</li> <li><code>2010-</code> during or after 2010</li> <li><code>-2015</code> before or during 2015</li> </ul>
A plain-text search query string. * No special query syntax is supported. See our <a href=“https://medium.com/ai2-blog/building-a-better-search-engine-for-semantic-scholar-ea23a0b661e7”>blog post</a> for a description of our search relevance algorithm.
Restricts results to papers published in the given venues, formatted as a comma-separated list.
Input could also be an ISO4 abbreviation. Examples include: <ul> <li>Nature</li> <li>New England Journal of Medicine</li> <li>Radiology</li> <li>N. Engl. J. Med.</li> </ul> Example: <code>Nature,Radiology</code> will return papers from venues Nature and/or Radiology.
Input could also be an ISO4 abbreviation. Examples include: <ul> <li>Nature</li> <li>New England Journal of Medicine</li> <li>Radiology</li> <li>N. Engl. J. Med.</li> </ul> Example: <code>Nature,Radiology</code> will return papers from venues Nature and/or Radiology.
A comma-separated list of the fields to be returned. See the contents of the <code>data</code> array in Response Schema below for a list of all available fields that can be returned. The <code>paperId</code> field is always returned. If the fields parameter is omitted, only the <code>paperId</code> and <code>title</code> will be returned. <p>Use a period (“.”) for fields that have version numbers or subfields, such as the <code>embedding</code>, <code>authors</code>, <code>citations</code>, and <code>references</code> fields: <ul> <li>When requesting <code>authors</code>, the <code>authorId</code> and <code>name</code> subfields are returned by default. To request other subfields, use the format <code>author.url,author.paperCount</code>, etc. See the Response Schema below for available subfields.</li> <li>When requesting <code>citations</code> and <code>references</code>, the <code>paperId</code> and <code>title</code> subfields are returned by default. To request other subfields, use the format <code>citations.title,citations.abstract</code>, etc. See the Response Schema below for available subfields.</li> <li>When requesting <code>embedding</code>, the default <a href=“https://github.com/allenai/specter”>Spector embedding version</a> is v1. Specify <code>embedding.specter_v2</code> to select v2 embeddings.</li> </ul> Examples: <ul> <li><code>fields=title,url</code></li> <li><code>fields=title,embedding.specter_v2</code></li> <li><code>fields=title,authors,citations.title,citations.abstract</code></li> </ul>
Restricts results to papers in the given fields of study, formatted as a comma-separated list: <ul> <li>Computer Science</li> <li>Medicine</li> <li>Chemistry</li> <li>Biology</li> <li>Materials Science</li> <li>Physics</li> <li>Geology</li> <li>Psychology</li> <li>Art</li> <li>History</li> <li>Geography</li> <li>Sociology</li> <li>Business</li> <li>Political Science</li> <li>Economics</li> <li>Philosophy</li> <li>Mathematics</li> <li>Engineering</li> <li>Environmental Science</li> <li>Agricultural and Food Sciences</li> <li>Education</li> <li>Law</li> <li>Linguistics</li> </ul> Example: <code>Physics,Mathematics</code> will return papers with either Physics or Mathematics in their list of fields-of-study.
Restricts results to only include papers with a public PDF. This parameter does not accept any values.
Restricts results to only include papers with at least this many citations. Must be a non-negative integer. Example: 200
Restricts results to any of the following paper publication types: <ul> <li>Review</li> <li>JournalArticle</li> <li>CaseReport</li> <li>ClinicalTrial</li> <li>Conference</li> <li>Dataset</li> <li>Editorial</li> <li>LettersAndComments</li> <li>MetaAnalysis</li> <li>News</li> <li>Study</li> <li>Book</li> <li>BookSection</li> </ul> Use a comma-separated list to include papers with any of the listed publication types.
Example: <code>Review,JournalArticle</code> will return papers with publication types Review and/or JournalArticle.
Example: <code>Review,JournalArticle</code> will return papers with publication types Review and/or JournalArticle.
Restricts results to the given range of publication dates or years (inclusive). Accepts the format <code><startDate>:<endDate></code> with each date in <code>YYYY-MM-DD</code> format.
Each term is optional, allowing for specific dates, fixed ranges, or open-ended ranges. In addition, prefixes are suported as a shorthand, e.g. <code>2020-06</code> matches all dates in June 2020.
Specific dates are not known for all papers, so some records returned with this filter will have a <code>null</code> value for </code>publicationDate</code>. <code>year</code>, however, will always be present. For records where a specific publication date is not known, they will be treated as if published on January 1st of their publication year.
Examples: <ul> <li><code>2019-03-05</code> on March 3rd, 2019</li> <li><code>2019-03</code> during March 2019</li> <li><code>2019</code> during 2019</li> <li><code>2016-03-05:2020-06-06</code> as early as March 5th, 2016 or as late as June 6th, 2020</li> <li><code>1981-08-25:</code> on or after August 25th, 1981</li> <li><code>:2015-01</code> before or on January 31st, 2015</li> <li><code>2015:2020</code> between January 1st, 2015 and December 31st, 2020</li> </ul>
Each term is optional, allowing for specific dates, fixed ranges, or open-ended ranges. In addition, prefixes are suported as a shorthand, e.g. <code>2020-06</code> matches all dates in June 2020.
Specific dates are not known for all papers, so some records returned with this filter will have a <code>null</code> value for </code>publicationDate</code>. <code>year</code>, however, will always be present. For records where a specific publication date is not known, they will be treated as if published on January 1st of their publication year.
Examples: <ul> <li><code>2019-03-05</code> on March 3rd, 2019</li> <li><code>2019-03</code> during March 2019</li> <li><code>2019</code> during 2019</li> <li><code>2016-03-05:2020-06-06</code> as early as March 5th, 2016 or as late as June 6th, 2020</li> <li><code>1981-08-25:</code> on or after August 25th, 1981</li> <li><code>:2015-01</code> before or on January 31st, 2015</li> <li><code>2015:2020</code> between January 1st, 2015 and December 31st, 2020</li> </ul>
Output
Search Bulk Papers
Search Bulk Papers
Slug:
SEMANTICSCHOLAR_SEARCH_BULK_PAPERSTool to perform bulk search for academic papers. Intended for bulk retrieval of basic paper data without search relevance scoring. Use when you need to retrieve large sets of papers with optional text filtering and various criteria. Supports token-based pagination for efficient fetching of up to 10 million papers (use Datasets API for larger needs).Input Parameters
Sort results by field:order. Available fields: paperId, publicationDate, citationCount. Default field is paperId, default order is asc. Ties broken by paperId. Records with null sort values appear at end regardless of order. Examples: ‘publicationDate:asc’ (oldest first), ‘citationCount:desc’ (most cited first), ‘paperId’ (ID order).
Publication year or year range filter (inclusive). Examples: ‘2019’ (year 2019), ‘2016-2020’ (range), ‘2010-’ (on or after 2010), ‘-2015’ (before or on 2015).
Optional text query matched against paper title and abstract. All terms are stemmed in English. By default, all query terms must be present. Supports boolean operators: + (AND), | (OR), - (NOT), "" (phrase), * (prefix match), () (precedence), N (fuzzy match with edit distance N, default 2). When omitted, returns all papers (subject to filters). Examples: ‘fish ladder’ (both terms), ‘fish | ladder’ (either term), ‘“fish ladder”’ (exact phrase), ‘fish’ (fuzzy match), ‘(fish ladder) | outflow’ (boolean logic).
Pagination token from previous response. Used to fetch the next batch of papers. Each response returns a new token when more results are available.
Comma-separated list of venue names. ISO4 abbreviations supported. Papers from any listed venue are returned. Examples: Nature, New England Journal of Medicine, Radiology, N. Engl. J. Med.
Comma-separated list of fields to return. paperId is always returned. If omitted, only paperId and title are returned. Available fields: title, abstract, venue, publicationVenue, year, publicationDate, authors, externalIds, url, referenceCount, citationCount, influentialCitationCount, isOpenAccess, openAccessPdf, fieldsOfStudy, s2FieldsOfStudy, publicationTypes, journal, citationStyles, corpusId.
Comma-separated list of fields of study. Papers in any listed field are returned. Available fields: Computer Science, Medicine, Chemistry, Biology, Materials Science, Physics, Geology, Psychology, Art, History, Geography, Sociology, Business, Political Science, Economics, Philosophy, Mathematics, Engineering, Environmental Science, Agricultural and Food Sciences, Education, Law, Linguistics.
Restricts results to papers with a public PDF. This parameter does not accept any values - its presence activates the filter.
Comma-separated list of publication types to include. Available types: Review, JournalArticle, CaseReport, ClinicalTrial, Conference, Dataset, Editorial, LettersAndComments, MetaAnalysis, News, Study, Book, BookSection. Papers matching any listed type are returned.
Date or year range filter (inclusive) in format <startDate>:<endDate>. Each date in YYYY-MM-DD format. Each term optional for open-ended ranges. Prefixes supported (e.g., 2020-06 matches June 2020). Papers without specific dates treated as published January 1st of their year. Examples: ‘2019-03-05’ (specific date), ‘2019-03’ (March 2019), ‘2019’ (year 2019), ‘2016-03-05:2020-06-06’ (date range), ‘1981-08-25:’ (on or after), ‘:2015-01’ (before or on), ‘2015:2020’ (year range).
Output
Search papers by relevance
Search papers by relevance
Slug:
SEMANTICSCHOLAR_SEARCH_PAPERSTool to search for academic papers by relevance in the Semantic Scholar database. Use when searching for papers on specific topics, keywords, or research areas. Returns papers ordered by relevance score with support for extensive filtering by publication type, date, venue, field of study, and citation metrics.Input Parameters
Filter by publication year or year range (inclusive). Examples: ‘2019’ (in 2019), ‘2016-2020’ (from 2016 to 2020), ‘2010-’ (2010 or after), ‘-2015’ (2015 or before)
Plain-text search query string. No special query syntax is supported. Use spaces instead of hyphens in search terms. Example: ‘machine learning’ or ‘neural networks’
Comma-separated list of publication venues to filter by. Can use full names or ISO4 abbreviations. Examples: ‘Nature’, ‘New England Journal of Medicine’, ‘N. Engl. J. Med.’, ‘Nature,Radiology’
Comma-separated list of fields to return. paperId is always returned. If omitted, only paperId and title are returned. Available fields: title, abstract, year, venue, publicationDate, authors, citationCount, referenceCount, influentialCitationCount, isOpenAccess, openAccessPdf, fieldsOfStudy, s2FieldsOfStudy, publicationTypes, publicationVenue, journal, externalIds, url, embedding, citations, references, tldr. Use dot notation for subfields (e.g., ‘authors.authorId,authors.name’, ‘citations.title’, ‘embedding.specter_v2’). Examples: ‘title,abstract,year’ or ‘title,authors,citationCount,url’
Pagination offset: number of results to skip before returning data. Used with limit for pagination
Comma-separated list of fields of study to filter by. Available fields: Computer Science, Medicine, Chemistry, Biology, Materials Science, Physics, Geology, Psychology, Art, History, Geography, Sociology, Business, Political Science, Economics, Philosophy, Mathematics, Engineering, Environmental Science, Agricultural and Food Sciences, Education, Law, Linguistics. Example: ‘Physics,Mathematics’
Minimum number of citations required. Restricts results to papers with at least this many citations. Must be non-negative
Comma-separated list of publication types to filter by. Available types: Review, JournalArticle, CaseReport, ClinicalTrial, Conference, Dataset, Editorial, LettersAndComments, MetaAnalysis, News, Study, Book, BookSection. Example: ‘Review,JournalArticle’
Filter by publication date or year range (inclusive). Format: ‘<startDate>:<endDate>’ with dates in YYYY-MM-DD format. Each term is optional for open-ended ranges. Prefixes supported (e.g., ‘2020-06’ for June 2020). Examples: ‘2019-03-05’ (specific date), ‘2019-03’ (March 2019), ‘2019’ (entire 2019), ‘2016-03-05:2020-06-06’ (date range), ‘1981-08-25:’ (on or after), ‘:2015-01’ (before or on), ‘2015:2020’ (year range)
Output
Suggest paper query completions
Suggest paper query completions
Slug:
SEMANTICSCHOLAR_SUGGEST_PAPER_QUERY_COMPLETIONSGet autocomplete suggestions for paper queries. Returns a list of papers matching the partial query string, useful for interactive search experiences. Each suggestion includes the paper ID, title, and authors with publication year. Example: For query “machine learning”, returns papers like “Machine learning - a probabilistic perspective” by Murphy, 2012.Input Parameters
Plain-text partial query string for autocomplete suggestions. Must be at least 3 characters long. Will be truncated to first 100 characters.
Output
Text snippet search
Text snippet search
Slug:
SEMANTICSCHOLAR_TEXT_SNIPPET_SEARCHSearch for text snippets matching a plain-text query in academic papers. Results are ranked by relevance and include paper information and a score; excerpts are drawn from titles, abstracts, and body text. Filter by author, year, or venue, choose snippet fields, and set a result limit (default 10, maximum 1,000).Input Parameters
Maximum number of snippet results to return. Must be between 1 and 1000. Default is 10. Use smaller limits for faster responses.
Plain-text search query to find matching text snippets in academic papers. No special query syntax is supported - just use natural language. Example: ‘machine learning neural networks’
Comma-separated list of snippet fields to include in the response. Available fields: text, snippetKind, section, snippetOffset, annotations. If not specified, all fields are returned by default.
Filter results to papers by specific authors. Provide comma-separated author names (fuzzy matching supported). Uses AND logic - all authors must match. Maximum 10 authors.
Filter results to only snippets from specific papers. Provide a comma-separated list of paper IDs (supports multiple ID formats: corpusId, DOI, arXiv ID, etc.). Maximum ~100 paper IDs.
Filter results by academic field. Comma-separated list of fields like ‘Computer Science’, ‘Medicine’, ‘Physics’, etc.
Filter results to papers with at least this many citations. Useful for finding influential papers. Example: ‘10’ or ‘100’
Filter results by publication date range. Supports ranges like ‘2020-2023’ or specific years like ‘2022’.