# Research Paper Intelligence — OpenAlex Search & AI (`noniner/research-paper-intelligence`) Actor

Search the world's scholarly literature via OpenAlex: top papers, citation counts, authors, institutions and trends for any topic — with an AI summary of the research landscape. For R\&D, competitive tech scouting, academia and biotech/pharma intel.

- **URL**: https://apify.com/noniner/research-paper-intelligence.md
- **Developed by:** [Fredrik Hansson](https://apify.com/noniner) (community)
- **Categories:** AI, Automation
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

$150.00 / 1,000 query analyzeds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

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 Paper Intelligence (OpenAlex + AI)

**Turn any research topic into a ranked reading list and a research-landscape briefing.** Give it a topic — `"large language models"`, `"solid-state batteries"`, `"CRISPR gene editing"` — and the Actor searches the entire OpenAlex scholarly database for the top papers, pulls their citation counts, authors, institutions and venues, and uses OpenAI to summarise the state of the field: the key themes, the seminal papers, and where the research is heading.

You bring the question. It hands back the literature, scored and summarised.

***

### The flow

```
1. Give a research topic        2. OpenAlex search               3. Get papers + AI landscape
   "large language models"  →      (top papers by citations   →     ranked papers · citations ·
   "CRISPR"                         or recency, no API key)          authors · venues · AI summary
```

1. **Enter one or more topics** in `queries`.
2. **The Actor queries OpenAlex** (the open index of 250M+ scholarly works) for the top papers per topic, sorted by citation count or publication date.
3. **You get back** one record per paper (title, year, citations, authors, institution, venue, DOI, open-access status, concepts) **plus** one AI landscape record per topic (key themes, seminal papers, emerging directions, leading institutions, a 2–3 sentence summary).

***

### What you get per query

For every research topic, the Actor:

1. **Searches OpenAlex** for the top `maxPapersPerQuery` works matching the topic, sorted by `cited_by_count` (most influential) or `publication_date` (most recent), optionally filtered to papers published on or after `fromYear`.
2. **Normalises each paper** into a flat record: title, publication year, citation count, author list, first institution, venue, work type, open-access status, DOI, OpenAlex ID, and the top concepts.
3. **Aggregates the set:** total matching works, top authors by appearance, top institutions, top venues, open-access share, and a recent-vs-older year distribution.
4. **Summarises the landscape with AI** (OpenAI `gpt-4o-mini`, a fast and low-cost model), grounded strictly in the retrieved papers — it never invents citation numbers or papers:
   - **`landscapeSummary`** — 2–3 sentences on the state of research.
   - **`keyThemes`** — the dominant sub-topics in the set.
   - **`seminalPapers`** — the foundational / most-cited works, each with a one-line reason.
   - **`emergingDirections`** — where the field appears to be heading.
   - **`leadingInstitutions`** — the institutions publishing the most.

***

### Three ways people use it

- **R\&D and competitive tech scouting** — map a technology area in minutes: who the top labs and institutions are, which papers everyone cites, and what's trending. Pull structured **citation data** and **research papers** for any emerging field without manually combing through the **OpenAlex API**.
- **Literature reviews and academia** — kick-start a **literature review** with a ranked, de-duplicated reading list and a themes breakdown. A fast, programmatic **scholarly search** and a practical **Semantic Scholar alternative** for grabbing top works per topic.
- **Competitive and biotech/pharma intelligence** — track a disease area, drug modality or platform technology: leading institutions, seminal papers, publication momentum, and open-access share — intel for strategy, diligence and scouting teams.

***

### Input

| Field | Type | Notes |
|---|---|---|
| `queries` | array | **Required.** Research topics / keywords, one per line (e.g. `"large language models"`, `"CRISPR"`). |
| `fromYear` | integer | Optional. Only include works published in or after this year. |
| `maxPapersPerQuery` | integer | Papers to fetch and analyze per topic. Default `25` (max `200`). |
| `sortBy` | string | `cited_by_count` (most influential) or `publication_date` (most recent). Default `cited_by_count`. |
| `maxResults` | integer | Max topics to process. Default `100`. |
| `maxConcurrency` | integer | Topics processed in parallel. Default `3`. |
| `model` | string | Override the OpenAI model. Default `gpt-4o-mini`. |

#### Minimal input example

```json
{
  "queries": ["large language models", "CRISPR"],
  "maxPapersPerQuery": 25,
  "sortBy": "cited_by_count"
}
```

***

### Output example

One record per paper:

```json
{
  "query": "large language models",
  "recordType": "paper",
  "title": "Attention Is All You Need",
  "year": 2017,
  "citedByCount": 139482,
  "authors": ["Ashish Vaswani", "Noam Shazeer", "Niki Parmar"],
  "firstInstitution": "Google (United States)",
  "venue": "Neural Information Processing Systems",
  "type": "article",
  "oaStatus": "green",
  "doi": "https://doi.org/10.48550/arxiv.1706.03762",
  "openAlexId": "https://openalex.org/W2963403868",
  "concepts": ["Computer science", "Artificial intelligence", "Transformer"]
}
```

Plus one landscape record per topic:

```json
{
  "query": "large language models",
  "recordType": "landscape",
  "totalResults": 184203,
  "papersAnalyzed": 25,
  "topAuthors": [{ "name": "Yoshua Bengio", "count": 3 }],
  "topInstitutions": [{ "name": "Google (United States)", "count": 5 }],
  "topVenues": [{ "name": "Neural Information Processing Systems", "count": 4 }],
  "keyThemes": ["Transformer architectures", "Pretraining and fine-tuning", "In-context learning"],
  "seminalPapers": [
    { "title": "Attention Is All You Need", "year": 2017, "citedByCount": 139482, "why": "Introduced the Transformer, the architecture underlying modern LLMs." }
  ],
  "emergingDirections": ["Reasoning and tool use", "Efficient / small language models"],
  "landscapeSummary": "Research on large language models is dominated by Transformer-based architectures and large-scale pretraining..."
}
```

***

### Pay-per-event pricing

This Actor uses **pay-per-event** billing with a single event:

| Event | Charged when | Price |
|---|---|---|
| `query-analyzed` | Once per research topic searched across OpenAlex and summarized with AI. | $0.15 |

The Actor logs its OpenAI token usage and estimated AI cost at the end of every run, so the event price stays safely above the model cost.

***

### Data source

Paper data comes from [**OpenAlex**](https://openalex.org) — a fully open, free index of the world's scholarly works (papers, authors, institutions, venues and citation counts). No API key is required. The Actor uses OpenAlex's polite pool (sends a `mailto`) and respects their usage guidelines. The AI layer uses OpenAI to summarise the retrieved papers.

***

### Setup

The AI landscape summary calls the OpenAI API. Set the environment variable / secret **`OPENAI_API_KEY`** on the Actor. The OpenAlex search itself needs no key.

***

### Use it from an AI agent (Apify MCP server)

This Actor is available through the [Apify MCP server](https://mcp.apify.com), so AI agents (Claude, ChatGPT, or anything that speaks MCP) can call it as a tool — hand it a topic and read back the top papers and the research-landscape summary — with no custom integration code.

***

### Run it locally

```bash
npm install
## put your input in storage/key_value_stores/default/INPUT.json
export OPENAI_API_KEY=sk-...
apify run -p
```

***

### Related actors

- [GitHub Repo Analyzer](https://apify.com/noniner/github-repo-analyzer) — Analyze any GitHub repository: stars, activity, contributors and an AI health assessment.
- [AI Web Extractor](https://apify.com/noniner/ai-web-extractor) — Turn any URL plus a plain-English prompt into structured JSON.
- [Google News Scraper](https://apify.com/noniner/google-news-scraper) — Pull news articles and headlines for any topic or query.
- [SEC Filings Extractor](https://apify.com/noniner/sec-filings-extractor) — Extract and structure data from SEC filings.

***

**Part of the [No Niner](https://noniner.io) toolkit** — no-code web scraping, enrichment & AI data tools, all pay-per-use. Browse the full set at **[noniner.io](https://noniner.io)**.

# Actor input Schema

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

Research topics or keywords to search the OpenAlex scholarly database for. One per line.

## `fromYear` (type: `integer`):

Only include works published in or after this year. Leave empty for all years.

## `maxPapersPerQuery` (type: `integer`):

How many papers to fetch and analyze per research topic.

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

Rank papers by citation count (most influential) or by publication date (most recent).

## `maxResults` (type: `integer`):

Max research topics to process. One pay-per-event charge per topic analyzed.

## `maxConcurrency` (type: `integer`):

How many topics to process in parallel.

## `model` (type: `string`):

Override the model (default gpt-4o-mini).

## Actor input object example

```json
{
  "queries": [
    "large language models",
    "CRISPR"
  ],
  "maxPapersPerQuery": 25,
  "sortBy": "cited_by_count",
  "maxResults": 100,
  "maxConcurrency": 3
}
```

# Actor output Schema

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

All paper and landscape records in the default dataset.

# 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": [
        "large language models",
        "CRISPR"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("noniner/research-paper-intelligence").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": [
        "large language models",
        "CRISPR",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("noniner/research-paper-intelligence").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": [
    "large language models",
    "CRISPR"
  ]
}' |
apify call noniner/research-paper-intelligence --silent --output-dataset

```

## MCP server setup

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

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/DiT5oJSYoog845vhD/builds/Y59wrfYKkwYF8nbKq/openapi.json