# Research Radar — Papers, Preprints & Patents (`tacps126/research-radar`) Actor

Search OpenAlex, arXiv, PubMed, Europe PMC and patents at once: one deduplicated, newest-first feed of papers and patents with abstracts, authors, DOIs and PDFs. Only-new alerts, RSS feed, optional AI summaries on your own key. From $3 per 1,000 results.

- **URL**: https://apify.com/tacps126/research-radar.md
- **Developed by:** [Tapaswai Ashok Choudhary](https://apify.com/tacps126) (community)
- **Categories:** AI, News, Business
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.40 / 1,000 results

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## Research Radar — Papers, Preprints & Patents

Search **OpenAlex, arXiv, PubMed, Europe PMC and patent records at once** and get one clean, deduplicated, newest-first list of papers, preprints and patents — with abstracts, authors and affiliations, DOIs, PDF links, citation counts and open-access status. Schedule it with *Only new results* and it becomes a research alert; follow it as an **RSS/Atom feed**; add **AI summaries and multilingual search** on your own AI key.

**Built for** R\&D and innovation teams watching a technology, IP and patent professionals tracking prior art, pharma and biotech scouting new findings, investors and analysts following a field, librarians, and AI agents that need fresh research.

### Why this radar

- **Many sources, one record each.** The same paper found by OpenAlex, PubMed and Europe PMC comes back once, with the best fields from each and a `foundIn` list. Matching uses DOIs, PubMed / PMC / arXiv ids and normalized titles.
- **Fresh first.** Results are sorted newest first; filter by *Published within N days* or a start date.
- **Research alerts.** Schedule it with *Only new results*: each run returns only what earlier runs didn't deliver, so you pay only for new papers.
- **RSS / Atom feed.** Call the Actor's Standby URL with `&format=atom` and paste it into Feedly, Slack, Teams, Inoreader or Zapier. Repeat polls within 30 minutes are served from memory — no new search, no new charge.
- **AI summaries and multilingual search (optional).** Get a short plain-language summary of each result, or search your query translated into other languages (e.g. German, Japanese, Chinese). Use Apify's built-in AI (no key, billed to your Apify account) or your own Anthropic, OpenAI, Gemini, OpenRouter, Groq, Mistral, DeepSeek or local model. The Actor charges nothing extra for AI.
- **Influence, not just volume.** Each paper carries its citations per year, a **field-normalized impact** (1.0 = the world average for papers of the same field and year) and a *top 1% / top 10%* flag. Sort by *Most cited* or *Highest impact* to find the work that matters.
- **Retractions left out.** Retracted papers are dropped by default (or kept and flagged, if you ask).
- **Ready to share and cite.** Every run saves a readable **digest** (`REPORT`: newest and most influential per query) and **`CITATIONS.bib`** for Zotero, Mendeley, EndNote or LaTeX.
- **Official open APIs only.** No browser, no scraping of protected pages — fast, reliable runs.

### How to use it

1. Enter one or more **search queries** (`solid state battery`, `CRISPR base editing`, `"retrieval augmented generation"`).
2. Pick **sources** (all five are on by default) and optionally **Published within (days)**.
3. Press **Start**. For alerts, turn on **Only new results** and add a schedule (daily or weekly).

Example input:

```json
{
  "queries": ["solid state battery", "sulfide electrolyte"],
  "postedWithinDays": 30,
  "maxItems": 200,
  "onlyNew": true
}
```

### Output

| Field | Description |
|-------|-------------|
| `type` | `paper`, `preprint` or `patent` |
| `title`, `abstract` | As published |
| `authors` | `[{name, affiliation, orcid, country}]` when the source has them |
| `publishedAt` | Publication date (YYYY-MM-DD) |
| `venue` | Journal, server (arXiv) or repository |
| `doi`, `url`, `pdfUrl` | Identifiers and links (PDF when openly available) |
| `openAccess`, `citations`, `language`, `keywords` | When known |
| `citationsPerYear` | Citations divided by years since publication |
| `fieldNormalizedImpact`, `citationRank` | Impact against papers of the same field and year (1.0 = average); `top 1%` / `top 10%` |
| `retracted` | `true` for retracted papers (only with *Include retracted*) |
| `ids` | `openalex`, `pmid`, `pmcid`, `arxiv`, `europepmc` |
| `patent` | For patents: `number`, `kind`, `country`, `applicationNumber`, `filingDate`, `priorityDate`, `classifications` (IPC/CPC), `applicants` |
| `foundIn` | Every source that returned it |
| `query`, `matchedQuery`, `queryLanguage` | Which of your queries found it (and the translation, for multilingual search) |
| `aiSummary` | With *AI summaries* on |

The key-value store also holds `REPORT` (a Markdown digest to read or forward) and `CITATIONS` (BibTeX).

### Sources

| Source | Covers |
|--------|--------|
| **OpenAlex** | 250M+ scholarly works in every field (journals, conferences, books, preprints) |
| **arXiv** | Preprints in physics, computer science, maths, quantitative biology and finance, statistics, engineering |
| **PubMed** | Biomedical and life-science literature |
| **Europe PMC** | Life-science literature and preprints (bioRxiv, medRxiv, Research Square…) |
| **Patents** | Patent records indexed by Europe PMC (strongest for life sciences and medical devices) |
| **Crossref** (optional) | DOI metadata from publishers |

Broader patent coverage (USPTO full text, EPO) is planned.

### Pricing

**$3 per 1,000 results** (each paper or patent counts once, however many sources found it) plus a small start fee per run. Duplicates and, with *Only new results*, already-delivered items are free. AI summaries and translations are billed by Apify's AI gateway or your own provider at their prices. See the **Pricing** tab, and set a maximum charge per run to cap spend.

### Tips

- Use several specific queries rather than one broad one; results are merged.
- Queries match titles and abstracts, so papers that only mention your words in passing stay out.
- For a literature review, set *Sort by* to *Highest impact* with *Published within* 1,100 days: the most influential work of the last three years, deduplicated, with BibTeX.
- For a weekly alert, set *Published within* to 8 days and schedule weekly with *Only new results*.
- A free [OpenAlex key](https://openalex.org/settings/api) gives your runs their own daily budget.

### Use from AI agents

The Actor is also an MCP tool (Standby `/mcp`), and part of the [webdata-tools-mcp](https://github.com/tacps126/webdata-tools-mcp) server.

# Actor input Schema

## `queries` (type: `array`):

Keywords or phrases, one per line. Each is searched in every source you pick. Boolean operators (AND, OR, NOT) and quotes work in most sources.

## `sources` (type: `array`):

Where to search. Results found in several sources are merged into one record (`foundIn` lists them).

## `postedWithinDays` (type: `integer`):

Only results published in the last N days. Leave empty for any time.

## `dateFrom` (type: `string`):

Only results published on or after this date.

## `openAccessOnly` (type: `boolean`):

Only papers you can read for free (patents are always included).

## `sortBy` (type: `string`):

Newest first suits alerts; the other two surface the most influential work.

## `includeRetracted` (type: `boolean`):

Retracted papers are left out by default. Turn on to keep them (flagged `retracted`).

## `maxItemsPerSource` (type: `integer`):

Most results each source returns for each query, before merging.

## `maxItems` (type: `integer`):

Most results delivered in total (after merging).

## `onlyNew` (type: `boolean`):

Schedule the Actor and each run returns only papers and patents earlier runs didn't deliver — a research alert you pay for only when something new appears.

## `stateKey` (type: `string`):

Optional: name this monitor to keep its history even if you change the queries.

## `summarize` (type: `boolean`):

Add a short plain-language summary to each result, written by the AI model of your choice on your own API key (you pay your provider directly; nothing extra here).

## `summaryLanguage` (type: `string`):

e.g. English, German, Japanese. Default English.

## `languages` (type: `array`):

Translate each query into these languages (e.g. de, fr, zh, ja) with your AI key and search those too — finds work published in other languages.

## `aiProvider` (type: `string`):

Which AI does the analysis. Apify needs no key: the model runs through Apify's OpenRouter proxy and is billed to your Apify account. Any other provider uses your own key and bills you there.

## `aiApiKey` (type: `string`):

Your own key for the provider above (not needed for Apify). Sent only to that provider, never stored.

## `aiModel` (type: `string`):

Model name. Apify: an OpenRouter id like anthropic/claude-sonnet-… or google/gemini-… (default: the newest Claude Haiku listed, a light model since it runs once per result). Anthropic: default claude-opus-5-5. Others: required.

## `aiBaseUrl` (type: `string`):

Only for "Other OpenAI-compatible API", e.g. http://localhost:11434/v1 for Ollama.

## `openalexApiKey` (type: `string`):

A free OpenAlex key gives your runs their own daily budget instead of the shared one. Get it at openalex.org/settings/api.

## Actor input object example

```json
{
  "queries": [
    "solid state battery"
  ],
  "sources": [
    "openalex",
    "arxiv",
    "pubmed",
    "europepmc",
    "patents"
  ],
  "postedWithinDays": 30,
  "openAccessOnly": false,
  "sortBy": "newest",
  "includeRetracted": false,
  "maxItemsPerSource": 50,
  "maxItems": 200,
  "onlyNew": false,
  "summarize": false,
  "aiProvider": "apify"
}
```

# Actor output Schema

## `results` (type: `string`):

The produced items (default dataset items).

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "queries": [
        "solid state battery"
    ],
    "postedWithinDays": 30
};

// Run the Actor and wait for it to finish
const run = await client.actor("tacps126/research-radar").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "queries": ["solid state battery"],
    "postedWithinDays": 30,
}

# Run the Actor and wait for it to finish
run = client.actor("tacps126/research-radar").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "queries": [
    "solid state battery"
  ],
  "postedWithinDays": 30
}' |
apify call tacps126/research-radar --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,tacps126/research-radar"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/3xgmUjFKtflPA8Wuu/builds/XWOykYDbreXdl7fpr/openapi.json