{ "openapi": "3.0.1", "info": { "title": "arXiv & PubMed Paper Search: Abstracts, DOI, MeSH, PDF Links", "description": "Search research papers on arXiv and PubMed through their official APIs: title, abstract, authors, dates, DOI, journal, arXiv categories, MeSH terms and PDF links. Keyword, category, date or ID/DOI lookup, duplicates merged, only-new monitoring. $1 per 1,000 papers.", "version": "1.0", "x-build-id": "dtCgGTNeYJq5rO8IH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/manageable_gully~arxiv-pubmed-paper-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-manageable_gully-arxiv-pubmed-paper-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/manageable_gully~arxiv-pubmed-paper-search/runs": { "post": { "operationId": "runs-sync-manageable_gully-arxiv-pubmed-paper-search", "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/manageable_gully~arxiv-pubmed-paper-search/run-sync": { "post": { "operationId": "run-sync-manageable_gully-arxiv-pubmed-paper-search", "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": { "query": { "title": "Search query", "type": "string", "description": "Keywords to search for, e.g. retrieval augmented generation. Use \"quotes\" for exact phrases. Advanced syntax is passed through: arXiv field prefixes (ti:, au:, abs:, cat:) and PubMed tags (asthma[MeSH], review[pt], Smith J[au])." }, "source": { "title": "Where to search", "enum": [ "both", "arxiv", "pubmed" ], "type": "string", "description": "arXiv is searched through the official arXiv API, PubMed through NCBI's official E-utilities.", "default": "both" }, "arxivCategories": { "title": "arXiv categories", "type": "array", "description": "Optional. Limit arXiv results to these categories (any of them), e.g. cs.CL, cs.AI, cs.LG, q-bio.GN, astro-ph, stat.ML. A top-level archive like cs or math covers all its subcategories. Without a query, returns the newest papers in these categories.", "items": { "type": "string" } }, "dateFrom": { "title": "Published from", "type": "string", "description": "Optional. Only papers submitted (arXiv) or published (PubMed) on or after this date." }, "dateTo": { "title": "Published until", "type": "string", "description": "Optional. Only papers submitted/published on or before this date." }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "newest" ], "type": "string", "description": "Use 'Newest first' for monitoring and for 'only new papers' runs.", "default": "relevance" }, "maxResults": { "title": "Max papers per source", "minimum": 1, "maximum": 10000, "type": "integer", "description": "How many papers to fetch from each source (up to 10,000; PubMed allows 9,999 per search). Papers you look up by ID are always all returned.", "default": 50 }, "ids": { "title": "Paper IDs, DOIs or links", "type": "array", "description": "Optional. arXiv IDs (2005.11401, hep-th/9711200, arxiv.org links), PubMed IDs (33301246, pubmed links), PMCIDs (PMC7745181) or DOIs. DOIs are looked up on PubMed first, then on Crossref. Up to 10,000.", "items": { "type": "string" } }, "onlyNew": { "title": "Only new papers (monitoring)", "type": "boolean", "description": "Remember which papers this search already returned and output only papers you have not seen before. Already-seen papers are free. Schedule the run daily/weekly with sort 'Newest first' to get a literature alert.", "default": false }, "stateKey": { "title": "Monitoring name", "type": "string", "description": "Optional name for the 'only new' memory, e.g. crispr-weekly. By default it is derived from the search, so changing the query starts a fresh memory." }, "dedupe": { "title": "Merge duplicates", "type": "boolean", "description": "Keep one record per paper when it appears in both arXiv and PubMed (same DOI or title). The kept record lists the other copy in alsoFoundIn. Duplicates are never charged.", "default": true }, "includeAbstract": { "title": "Include abstracts", "type": "boolean", "description": "Turn off for smaller datasets with metadata only.", "default": true }, "includeAffiliations": { "title": "Include affiliations", "type": "boolean", "description": "Add the authors' institutions as published in the paper record (e-mail addresses are removed).", "default": false }, "crossrefFallback": { "title": "Look up other DOIs on Crossref", "type": "boolean", "description": "For DOIs that are not in PubMed or arXiv (e.g. conference papers), fetch the metadata from the public Crossref API.", "default": true }, "ncbiApiKey": { "title": "NCBI API key (optional)", "type": "string", "description": "Optional free key from your NCBI account. Raises PubMed's limit from 3 to 10 requests per second, which speeds up very large PubMed runs." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }