{ "openapi": "3.0.1", "info": { "title": "Semantic Scholar Scraper — Papers, Authors & Citations", "description": "Search Semantic Scholar papers and authors, retrieve abstracts, TLDRs, citation counts, references, citing papers, external IDs, and open-access PDF metadata for literature reviews and AI-agent research workflows. Uses the public Academic Graph API. Charged $0.001 per returned record.", "version": "1.0", "x-build-id": "J9hVat6oaqb3JPekz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/muhammadafzal~semantic-scholar-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-muhammadafzal-semantic-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/muhammadafzal~semantic-scholar-scraper/runs": { "post": { "operationId": "runs-sync-muhammadafzal-semantic-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/muhammadafzal~semantic-scholar-scraper/run-sync": { "post": { "operationId": "run-sync-muhammadafzal-semantic-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "operation": { "title": "Operation", "enum": [ "searchPapers", "getPaper", "searchAuthors", "getAuthor", "getCitations", "getReferences" ], "type": "string", "description": "Use this to choose the Academic Graph API action. Accepted values are searchPapers, getPaper, searchAuthors, getAuthor, getCitations, and getReferences. Defaults to searchPapers.", "default": "searchPapers" }, "query": { "title": "Search query", "type": "string", "description": "Use this for paper or author search terms such as \"retrieval augmented generation\" or \"Geoffrey Hinton\". Defaults to \"machine learning\". This is not a paper ID; use paperId for one-paper and graph operations.", "default": "machine learning" }, "paperId": { "title": "Paper identifier", "type": "string", "description": "Use this for getPaper, getCitations, or getReferences with a Semantic Scholar paperId, DOI, arXiv ID, or CorpusID. Defaults to a known paper ID for a working prefill. This is not an author ID.", "default": "649def34f8be52c8b66281af98ae884c09aef38b" }, "authorId": { "title": "Author identifier", "type": "string", "description": "Use this for getAuthor with a Semantic Scholar author ID. Defaults to an empty value. This is not a paper ID or a free-text author name; use searchAuthors for names.", "default": "" }, "fields": { "title": "Paper fields", "type": "array", "description": "Use this to select paper fields returned by the API. Defaults to core metadata plus abstract, TLDR, citations, and open-access PDF. Use fewer fields for faster, smaller agent responses.", "items": { "type": "string" }, "default": [ "paperId", "externalIds", "url", "title", "abstract", "venue", "year", "publicationDate", "authors", "citationCount", "referenceCount", "openAccessPdf", "fieldsOfStudy", "publicationTypes", "tldr" ] }, "limit": { "title": "Maximum records", "minimum": 1, "maximum": 100, "type": "integer", "description": "Use this to cap returned dataset rows and cost. Enter 1–100 for search, citation, or reference operations. Defaults to 10 and is not a guarantee that matching records exist.", "default": 10 }, "offset": { "title": "Result offset", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Use this to page through search, citation, or reference results. Enter a non-negative offset; for example, 100 starts after the first 100 records. Defaults to 0.", "default": 0 }, "year": { "title": "Publication year filter", "type": "string", "description": "Use this to filter paper search by year or range, such as \"2023\" or \"2020-2024\". Defaults to an empty value, meaning no year filter. This does not filter author search.", "default": "" }, "minCitationCount": { "title": "Minimum citation count", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Use this to keep only papers with at least this many citations. Defaults to 0. This applies to paper search only and can reduce broad result sets.", "default": 0 }, "openAccessPdfOnly": { "title": "Open-access PDFs only", "type": "boolean", "description": "Use this to keep only paper search results with an open-access PDF. Defaults to false. This applies to paper search only and is not a full-text download option.", "default": false } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }