{ "openapi": "3.0.1", "info": { "title": "ArXiv Preprint Paper Search", "description": "Search and extract preprint research papers from the ArXiv open-access repository. Query over 2.4 million academic papers across physics, mathematics, computer science, biology, economics, and more with structured JSON output, no API key required.", "version": "3.0", "x-build-id": "Wa0Ph8dCULK26AYa8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ryanclinton~arxiv-paper-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ryanclinton-arxiv-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ryanclinton~arxiv-paper-search/runs": { "post": { "operationId": "runs-sync-ryanclinton-arxiv-paper-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ryanclinton~arxiv-paper-search/run-sync": { "post": { "operationId": "run-sync-ryanclinton-arxiv-paper-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQuery": { "title": "Search Query", "type": "string", "description": "Search query. Supports field prefixes: all: (default), ti: (title), au: (author), abs: (abstract), cat: (category), co: (comment). Combine with AND, OR, ANDNOT.", "default": "all:large language models" }, "category": { "title": "Category", "type": "string", "description": "ArXiv category filter (e.g., cs.AI, cs.CL, math.CO, physics.hep-th, stat.ML). See arxiv.org/category_taxonomy" }, "sortBy": { "title": "Sort By", "enum": [ "relevance", "lastUpdatedDate", "submittedDate" ], "type": "string", "description": "How to sort results", "default": "relevance" }, "sortOrder": { "title": "Sort Order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Sort direction", "default": "descending" }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of papers to return (ArXiv API max per page is 100)", "default": 50 }, "analysisMode": { "title": "Analysis Mode", "enum": [ "general", "literature-review", "cite-check", "trend-watch", "rag" ], "type": "string", "description": "Reweights the per-paper priority score for your task. general (balanced), literature-review (maturity-led), cite-check (publication-status-led), trend-watch (recency-led), rag (RAG-safe + maturity).", "default": "general" }, "outputProfile": { "title": "Output Profile", "enum": [ "minimal", "standard", "full" ], "type": "string", "description": "How many fields each paper record carries. minimal (decision fields only), standard (adds metadata + reasons), full (everything).", "default": "standard" }, "outputMode": { "title": "Output Mode", "enum": [ "papers", "dashboard" ], "type": "string", "description": "papers streams one record per paper plus a research brief and landscape summary. dashboard suppresses per-paper rows and returns a single digest record (charged once).", "default": "papers" }, "emitResearchBrief": { "title": "Emit Research Brief", "type": "boolean", "description": "Add a hero research-brief record: what to read first, reading order, key takeaways, and suggested next queries.", "default": true }, "includeCitationFields": { "title": "Include Citation Fields", "type": "boolean", "description": "Add a deterministic citation block per paper: BibTeX, preferred citation target (published / accepted / arXiv version), citation warning, version-aware note, and APA/MLA-lite strings.", "default": true }, "includeEvidenceLedger": { "title": "Include Evidence Ledger", "type": "boolean", "description": "Add an inspectable evidence object per paper: the status signals, risk signals, and score trace behind the classification. Off by default to keep records lean.", "default": false }, "onlyPeerReviewed": { "title": "Only Peer-Reviewed / Accepted", "type": "boolean", "description": "Keep only papers that are published in a venue or accepted at one (drops preprint-only papers). Dropped counts are disclosed in the summary.", "default": false }, "excludeWithdrawn": { "title": "Exclude Withdrawn", "type": "boolean", "description": "Drop papers whose author comment marks them as withdrawn. Dropped counts are disclosed in the summary.", "default": false }, "requireCode": { "title": "Require Code", "type": "boolean", "description": "Keep only papers with a detected code/repository link (reproducible work). Dropped counts are disclosed in the summary.", "default": false }, "minVersionCount": { "title": "Minimum Version Count", "minimum": 1, "maximum": 20, "type": "integer", "description": "Keep only papers revised at least this many times (e.g. 2 drops single-version preprints). 1 keeps everything.", "default": 1 }, "freshnessFilter": { "title": "Freshness Filter", "enum": [ "any", "cutting-edge", "recent", "established", "older" ], "type": "string", "description": "Keep only papers at least this fresh. any keeps all; cutting-edge keeps <90 days; recent keeps <1 year; established keeps <3 years.", "default": "any" }, "monitorMode": { "title": "Monitor Mode", "type": "boolean", "description": "Track this query across scheduled runs. Stores a per-watchlist baseline and emits a paper-delta record: new papers, and which preprints became published or accepted since the last run. First run captures the baseline.", "default": false }, "watchlistName": { "title": "Watchlist Name", "type": "string", "description": "Names the baseline used by monitor mode. Run the same query under the same watchlist name to track changes over time; use different names for independent watchlists.", "default": "default" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings. Defaults to residential Apify Proxy — ArXiv rate-limits shared datacenter IPs (HTTP 429), so residential is required for reliable runs. Power users can switch to datacenter or disable, accepting possible rate limits.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }