Get multiple paper overviews (Pro+)
Get overviews for multiple papers in a single request.
Requires Pro tier or higher.
Does not count toward paper quota (free peeks, batched).
- Maximum 10 papers per request
- Partial failures return successful results plus errors array
Authorization
ApiKeyAuth API key for authentication. Get yours at https://sciencestack.ai/settings/api
Format: sk_live_... or sk_test_...
In: header
Query Parameters
Comma-separated paper IDs (arXiv IDs or UUIDs)
Response Body
application/json
application/json
application/json
application/json
curl -X GET "https://sciencestack.ai/api/v1/papers/overview?ids=1706.03762%2C2108.07258%2C2303.08774"{
"data": [
{
"paperId": "0dc1dcb2-991d-5ff2-b67c-af0a863ad32f",
"arxivId": "1706.03762v7",
"data": {
"title": "Attention Is All You Need",
"arxivId": "1706.03762v7",
"authors": [
"Ashish Vaswani",
"Noam Shazeer",
"Niki Parmar",
"Jakob Uszkoreit",
"Llion Jones",
"Aidan N. Gomez",
"Lukasz Kaiser",
"Illia Polosukhin"
],
"abstract": "The dominant sequence transduction models are based on complex recurrent or convolutional neural networks...",
"published": "2017-06-12T17:57:34",
"aiSummary": "The Transformer paper addresses the inefficiency of recurrent/convolutional sequence transduction models...",
"toc": [
{
"section": "1",
"nodeId": "sec:1",
"title": "Introduction",
"depth": 1
},
{
"section": "3",
"nodeId": "sec:3",
"title": "Model Architecture",
"depth": 1
}
],
"figures": [
{
"nodeId": "fig:1",
"number": "1",
"caption": "The Transformer - model architecture."
}
],
"tables": [
{
"nodeId": "tab:1",
"number": "1",
"caption": "Maximum path lengths, per-layer complexity..."
}
]
}
},
{
"paperId": "ce3e6ee3-404c-5e70-b198-e8517510bd50",
"arxivId": "2108.07258v3",
"data": {
"title": "On the Opportunities and Risks of Foundation Models",
"arxivId": "2108.07258v3",
"authors": [
"Rishi Bommasani",
"Drew A. Hudson",
"Ehsan Adeli",
"et al."
],
"abstract": "AI is undergoing a paradigm shift with the rise of models (e.g., BERT, DALL-E, GPT-3)...",
"published": "2021-08-16T17:50:08"
}
},
{
"paperId": "0b753398-6439-522f-868a-b5a00c2e99b7",
"arxivId": "2303.08774v6",
"data": {
"title": "GPT-4 Technical Report",
"arxivId": "2303.08774v6",
"authors": [
"OpenAI",
"Josh Achiam",
"Steven Adler",
"et al."
],
"abstract": "We report the development of GPT-4, a large-scale, multimodal model...",
"published": "2023-03-15T17:15:04"
}
}
],
"errors": [],
"_version": "1.0.0"
}{
"error": {
"code": "INVALID_REQUEST",
"message": "Maximum 10 paper IDs per request"
}
}{
"error": {
"code": "UNAUTHORIZED",
"message": "Invalid API key"
}
}{
"error": {
"code": "UPGRADE_REQUIRED",
"message": "Pro plan required for batch overview. Upgrade at https://sciencestack.ai/settings/api"
}
}Get paper overview
Get everything an agent needs in one call: metadata, TOC, AI summaries, and lists of all figures, tables, equations, and theorems. **Does not count toward paper quota** (free peek). - **Free**: metadata, TOC, figures/tables/equations lists - **Pro+**: + `aiSummary`, `sectionSummaries`
Get paper nodes
Get nodes with optional filtering. Use this for fine-grained access to paper structure. Paper content is stored as a tree of typed nodes: sections, equations, figures, tables, etc. Filter by type to get specific elements: - `?types=equation` - all equations with LaTeX - `?types=table` - all tables with content - `?types=math_env` - all theorems, lemmas, proofs - `?types=algorithm` - all algorithms **Multi-node support:** Fetch multiple specific nodes in one request: - `?nodeIds=eq:1,eq:2,fig:1` - get equations 1, 2 and figure 1 - `?nodeIds=sec:3,sec:4` - get sections 3 and 4 with all content For a quick overview of what's in a paper (including figure image URLs), use `/overview` (free). **Counts toward paper quota** on first access.