{ "openapi": "3.0.1", "info": { "title": "arXiv Preprints API", "description": "Search arXiv, bioRxiv and medRxiv preprints, or look up arXiv IDs and DOIs. One row per preprint with title, abstract, categories, version, dates, links and licence. No author fields. Independent tool, not affiliated with arXiv, bioRxiv or medRxiv.", "version": "0.0", "x-build-id": "UOVxW7yvKDBuVkuRg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/conserving_celerytop~preprint-papers-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-conserving_celerytop-preprint-papers-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/conserving_celerytop~preprint-papers-api/runs": { "post": { "operationId": "runs-sync-conserving_celerytop-preprint-papers-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/conserving_celerytop~preprint-papers-api/run-sync": { "post": { "operationId": "run-sync-conserving_celerytop-preprint-papers-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "Search queries", "maxItems": 50, "type": "array", "description": "Enter one search per line, in plain words, for example: retrieval augmented generation, or \"graph neural network\" AND molecules. AND, OR and ANDNOT work, and quotes mark a phrase. On arXiv you can also use field prefixes such as ti:, abs: and cat:. Leave empty to list preprints by category or date.", "items": { "type": "string" } }, "servers": { "title": "Servers", "type": "array", "description": "Which servers to search. Identifier lookups try the right server by themselves.", "items": { "type": "string", "enum": [ "arxiv", "biorxiv", "medrxiv" ], "enumTitles": [ "arXiv", "bioRxiv", "medRxiv" ] }, "default": [ "arxiv", "biorxiv", "medrxiv" ] }, "searchIn": { "title": "Search in", "enum": [ "title_abstract", "everywhere" ], "type": "string", "description": "Where plain search words must appear on arXiv. Title and abstract gives on-topic results. bioRxiv and medRxiv are always matched in title and abstract.", "default": "title_abstract" }, "ids": { "title": "arXiv ids or DOIs", "maxItems": 1000, "type": "array", "description": "Enter one identifier per line: an arXiv id such as 1706.03762 or hep-th/9901001, an arXiv link, or a bioRxiv or medRxiv DOI such as 10.1101/2020.03.01.972935. A link to the preprint page also works. An identifier that matches nothing returns one not_found row. Filters do not apply to lookups.", "items": { "type": "string" } }, "dateFrom": { "title": "Date from", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "First day, as YYYY-MM-DD, for example 2025-01-31. On arXiv it filters the date of the first version. bioRxiv and medRxiv read the last 30 days when you give no dates." }, "dateTo": { "title": "Date to", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Last day, as YYYY-MM-DD. bioRxiv and medRxiv accept a window of at most 366 days." }, "arxivCategories": { "title": "arXiv categories", "type": "array", "description": "Keep arXiv preprints in these categories, one per line, for example cs.LG, hep-th or math.*. Applies to arXiv only.", "items": { "type": "string" } }, "biorxivCategories": { "title": "bioRxiv and medRxiv subject areas", "type": "array", "description": "Keep bioRxiv and medRxiv preprints in these subject areas, one per line, for example Neuroscience or Infectious Diseases. Applies to bioRxiv and medRxiv only.", "items": { "type": "string" } }, "sort": { "title": "Sort by", "enum": [ "relevance", "newest", "recently_updated" ], "type": "string", "description": "Order of arXiv results. bioRxiv and medRxiv rows always come newest first, because their API has no ranking.", "default": "relevance" }, "includeAbstract": { "title": "Include abstract", "type": "boolean", "description": "Add the abstract text to each row. arXiv states that its descriptive metadata is free to use under CC0. bioRxiv and medRxiv authors keep the copyright of their text, and each row shows the licence. Switch this off if you only need metadata.", "default": true }, "abstractMaxChars": { "title": "Abstract max characters", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Cut each abstract to this many characters. Use 0 for the full abstract.", "default": 0 }, "maxPerSearch": { "title": "Max results per search", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop one search on one server after this many rows. Each query and each server counts as one search. Leave empty for no extra cap: only Max results applies." }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Return at most this many rows in total, across all searches and lookups, including not_found rows. Each row returned is one charged result.", "default": 100 } } }, "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 } } } } } } } } } }