# Semantic Scholar Research Paper Tracker (`gochujang/semantic-scholar-papers`) Actor

Search, browse, and track academic papers using the Semantic Scholar API. Get citations, authors, abstracts, and PDFs for AI, biology, medicine, and more. No API key required.

- **URL**: https://apify.com/gochujang/semantic-scholar-papers.md
- **Developed by:** [Hojun Lee](https://apify.com/gochujang) (community)
- **Categories:** Business
- **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $1.00 / 1,000 item processeds

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

### Semantic Scholar Research Paper Tracker — Academic Papers, Citations & Authors

Search and track academic research papers using the **Semantic Scholar** public API. If its keyword search is unavailable or rate-limited, search mode falls back to the keyless OpenAlex Works API. Author, paper-ID, and recommendation modes still use Semantic Scholar only. No API key required.

OpenAlex fallback rows keep the same output field names and link to OpenAlex. Semantic Scholar-specific fields such as `influential_citation_count` and `arxiv_id` are null when OpenAlex does not provide them; `pdf_url` is null unless a direct PDF URL is available.

Covers all major research domains: AI/ML, computer science, biology, medicine, physics, economics, and more.

### What You Get

For each paper, the actor returns:

- **Title, abstract** (up to 1000 characters), **year, publication date**
- **Venue / journal** name
- **Authors** (up to 10, with author IDs)
- **Citation count, reference count, influential citation count**
- **Fields of study** (Computer Science, Medicine, Biology, etc.)
- **Open access PDF URL** when freely available
- **External IDs** — DOI, ArXiv ID, PubMed ID
- **Direct URL** to the paper on Semantic Scholar, or OpenAlex for fallback rows
- **Publication type** — Journal Article, Conference Paper, Preprint, etc.

### Modes

| Mode | Description | Key Input |
|------|-------------|-----------|
| `search` | Keyword search across all papers | `query` |
| `author` | Browse papers by a specific author | `authorQuery` |
| `paper` | Look up specific papers by ID | `paperIds` |
| `recommendations` | Find papers similar to a seed paper | `paperIds[0]` |

### Input Parameters

| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `mode` | string | `"search"` | Fetch mode (see table above) |
| `query` | string | `"large language models"` | Keyword query for search mode |
| `limit` | integer | `20` | Max papers to return (max 500) |
| `sort` | string | `"relevance"` | Sort by: `relevance`, `citationCount`, `year` |
| `fieldsOfStudy` | string | — | Filter: `"Computer Science"` or `"Medicine,Biology"` |
| `yearRange` | string | — | Year filter: `"2024"`, `"2020-2024"`, `"2022-"` |
| `openAccessOnly` | boolean | `false` | Only papers with free PDF |
| `authorQuery` | string | — | Author name for author mode |
| `paperIds` | array | `[]` | ArXiv IDs, S2 IDs, or DOIs |

### Sample Output

```json
{
  "paper_id": "204e3073870fae3d05bcbc2f6a8e263d9b72e776",
  "title": "Attention Is All You Need",
  "abstract": "The dominant sequence transduction models are based on complex recurrent or convolutional neural networks...",
  "year": 2017,
  "publication_date": "2017-06-12",
  "venue": "Neural Information Processing Systems",
  "publication_types": ["Conference"],
  "fields_of_study": ["Computer Science"],
  "authors": [
    {"id": "1234", "name": "Ashish Vaswani"},
    {"id": "5678", "name": "Noam Shazeer"}
  ],
  "citation_count": 95420,
  "reference_count": 38,
  "influential_citation_count": 8450,
  "is_open_access": true,
  "pdf_url": "https://arxiv.org/pdf/1706.03762",
  "doi": "10.48550/arXiv.1706.03762",
  "arxiv_id": "1706.03762",
  "url": "https://www.semanticscholar.org/paper/204e3073...",
  "fetched_at": "2025-01-15T12:00:00Z"
}
```

### Examples

**Search for recent AI papers with open access PDF:**

```json
{
  "mode": "search",
  "query": "transformer language model fine-tuning",
  "limit": 50,
  "sort": "citationCount",
  "fieldsOfStudy": "Computer Science",
  "yearRange": "2022-",
  "openAccessOnly": true
}
```

**Get all papers by Geoffrey Hinton (sorted by citations):**

```json
{
  "mode": "author",
  "authorQuery": "Geoffrey Hinton",
  "limit": 100
}
```

**Look up specific papers by ArXiv ID:**

```json
{
  "mode": "paper",
  "paperIds": ["2303.08774", "2307.09288", "1706.03762"]
}
```

**Get recommendations similar to GPT-4 paper:**

```json
{
  "mode": "recommendations",
  "paperIds": ["8ca62fdf4c276ea3052dc96dcfd8ee96ca425a48"],
  "limit": 30
}
```

### Use Cases

- **Literature review automation** — pull all papers on a topic sorted by impact
- **Citation tracking** — monitor how many times a paper has been cited over time
- **Researcher profiling** — analyze a scientist's publication history and h-index
- **AI research monitoring** — track new LLM, multimodal, or agent papers weekly
- **Investment research** — find scientific evidence for tech/biotech investment theses
- **Grant and publication discovery** — find open-access papers for research reports
- **Academic data pipelines** — feed paper data into RAG systems or knowledge graphs

### Pricing

Pay-per-event: **$0.001 per paper returned** (~$0.02 for the default 20 papers, $0.50 for 500 papers).

### FAQ

**How many papers does Semantic Scholar cover?**
Over 200 million papers across all academic disciplines, with strong coverage of STEM fields and growing social science/humanities coverage.

**Are there rate limits?**
Semantic Scholar may rate-limit unauthenticated traffic. Search retries 429 responses with bounded backoff, then uses OpenAlex if Semantic Scholar remains unavailable.

**How current is the data?**
Semantic Scholar continuously ingests new papers. ArXiv preprints typically appear within days of posting; journal articles within weeks of publication.

**Can I get the full paper text?**
Only abstracts are returned directly. The `pdf_url` field provides a link to the full PDF when the paper is open access.

**What ArXiv ID formats are supported?**
Both formats work: `"1706.03762"` (numeric) and `"arXiv:1706.03762"`. For DOIs, pass the full DOI string.

***

### Related actors

- [PubMed Medical Papers Tracker](https://apify.com/gochujang/pubmed-papers-tracker) — Biomedical literature from PubMed to complement Semantic Scholar's broader paper index
- [Patent Search Tracker](https://apify.com/gochujang/patent-search-tracker) — US patents citing academic papers found via Semantic Scholar
- [Open Library Search](https://apify.com/gochujang/open-library-search) — Book catalog to supplement academic paper research workflows

### Feedback

If this actor powers your research workflows, a review helps others find it: [Leave a review on Apify Store](https://apify.com/gochujang/semantic-scholar-papers#reviews)

***

**Keywords:** Semantic Scholar API scraper, academic paper search, citation tracker, research paper extractor, AI ML paper search, biology research papers, open access PDF finder, paper abstract extractor, author citation count, DOI extractor academic, scientific literature search, machine learning papers tracker, Semantic Scholar dataset, academic research monitor

# Actor input Schema

## `mode` (type: `string`):

How to find papers: 'search' by keyword, 'author' by author name, 'paper' by specific IDs, 'recommendations' for similar papers.

## `query` (type: `string`):

Keyword query for search mode (e.g. 'large language models' or 'CRISPR gene editing').

## `limit` (type: `integer`):

Maximum papers to return (max 500).

## `sort` (type: `string`):

How to sort search results.

## `fieldsOfStudy` (type: `string`):

Comma-separated fields to filter by (e.g. 'Computer Science,Mathematics'). Options: Computer Science, Medicine, Biology, Physics, Economics, etc.

## `yearRange` (type: `string`):

Year filter: '2024' for single year, '2020-2024' for range, '2020-' for since 2020.

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

Only return papers with freely available PDF.

## `authorQuery` (type: `string`):

Author name to look up (for 'author' mode). E.g. 'Geoffrey Hinton' or 'Yoshua Bengio'.

## `paperIds` (type: `array`):

Specific paper IDs (for 'paper' and 'recommendations' modes). Supports Semantic Scholar IDs, ArXiv IDs (e.g. '2303.08774'), and DOIs.

## Actor input object example

```json
{
  "mode": "search",
  "query": "large language models",
  "limit": 20,
  "sort": "relevance",
  "openAccessOnly": false,
  "paperIds": []
}
```

# Actor output Schema

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

No description

# 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 = {};

// Run the Actor and wait for it to finish
const run = await client.actor("gochujang/semantic-scholar-papers").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 = {}

# Run the Actor and wait for it to finish
run = client.actor("gochujang/semantic-scholar-papers").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 '{}' |
apify call gochujang/semantic-scholar-papers --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,gochujang/semantic-scholar-papers"
        }
    }
}
```

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/nfWO1qlJEVYhw0ibP/builds/woVBeyPfZvFKWgnGZ/openapi.json