OpenReview reviews and decision API

Use the OpenReview reviews and decision API to retrieve public paper reviews, decisions and author discussion material. Identify a paper forum and optionally filter reply types to inspect public reviews, meta-reviews, decisions, rebuttals and comments, preserving the venue’s score fields and anonymous role labels. Read the feedback the source publishes, compare rating distributions, or inspect how individual experiences relate to an overall score. Scores, dates and reviewer identities follow what the source publishes, including anonymous or abbreviated names where applicable. The detail page provides request and response examples, supported parameters, and usage pricing.

Selected price
$0.002 / billing creditPublished pricing
Sellers / implementations
1 / 1
Requests · 30d
—Loading...
Success rate · 30d
—Loading...

Run sends a real API request. Charges follow the published API contract.

Request parameters
Paper (forum) id or forum URL, e.g. `P42DbV2nuV`.
Optional parameters (6)
Only these reply types, comma-separated, e.g. `official_review,meta_review,decision` (also `official_comment`, `public_comment`, `rebuttal`; names follow the venue).
0 leaves out the bulky `raw` source blocks (often 10-30x smaller).
Comma-separated fields to return, e.g. `posts.id,posts.title`. Call metadata is always included.
1 skips the 24-hour cache and fetches live.
JSON only for this OpenAny product. Omit output or use json; CSV and NDJSON exports are not exposed.
Native CSV/NDJSON record selector; it has no effect on this JSON-only product.

Sample response

"average_rating": 7.33
"cached": false
"count": 22
"counts_by_type": {
  "decision": 1,
  "meta_review": 1,
  "official_comment": 17,
  "official_review": 3
}
"credits_used": 5
"decision": "Accept (Spotlight)"
paper {}
"abstract": "In machine learning practice, early stopping has been widely used to regularize models and can save computational costs by halting the train…"
"author_ids": [
  "~Suqin_Yuan1",
  "~Runqi_Lin1",
  "… 3 more"
]
"authors": [
  "Suqin Yuan",
  "Runqi Lin",
  "… 3 more"
]
"authors_total": 5
bibtexString · text preview
paper.bibtex
@inproceedings{
yuan2025instancedependent,
title={Instance-dependent Early Stopping},
author={Suqin Yuan and Runqi Lin and Lei Feng and Bo H…
"code": null
content {}
"TLDR": "We propose an instance-dependent early stopping method that stops training at the instance level by determining whether the model has fully …"
_bibtexString · text preview
paper.content._bibtex
@inproceedings{
yuan2025instancedependent,
title={Instance-dependent Early Stopping},
author={Suqin Yuan and Runqi Lin and Lei Feng and Bo H…
"abstract": "In machine learning practice, early stopping has been widely used to regularize models and can save computational costs by halting the train…"
"anonymous_url": "I certify that there is no URL (e.g., github page) that could be used to find authors’ identity."
"authorids": [
  "~Suqin_Yuan1",
  "~Runqi_Lin1",
  "… 3 more"
]
"authors": [
  "Suqin Yuan",
  "Runqi Lin",
  "… 3 more"
]
"code_of_ethics": "I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics."
"keywords": [
  "Early Stopping",
  "Supervised Learning",
  "… 4 more"
]
"no_acknowledgement_section": "I certify that there is no acknowledgement section in this submission for double blind review."
"paperhash": "yuan|instancedependent_early_stopping"
"pdf": "/pdf/8fddee1917f5289fe7908965f534e27f36e3f4db.pdf"
"primary_area": "unsupervised, self-supervised, semi-supervised, and supervised representation learning"
"submission_guidelines": "I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide."
"title": "Instance-dependent Early Stopping"
"venue": "ICLR 2025 Spotlight"
"venueid": "ICLR.cc/2025/Conference"
"created": "2024-09-13T00:00:45.058Z"
"domain": "ICLR.cc/2025/Conference"
"forum": "P42DbV2nuV"
"id": "P42DbV2nuV"
"invitation": "ICLR.cc/2025/Conference/-/Submission"
"keywords": [
  "Early Stopping",
  "Supervised Learning",
  "… 4 more"
]
"license": "CC BY 4.0"
"modified": "2025-02-11T13:10:51.446Z"
"number": 2
"pdf_url": "https://openreview.net/pdf/8fddee1917f5289fe7908965f534e27f36e3f4db.pdf"
"primary_area": "unsupervised, self-supervised, semi-supervised, and supervised representation learning"
"published": "2025-01-22T16:09:33.058Z"
"supplementary_material_url": null
"title": "Instance-dependent Early Stopping"
"tldr": "We propose an instance-dependent early stopping method that stops training at the instance level by determining whether the model has fully …"
"url": "https://openreview.net/forum?id=P42DbV2nuV"
"venue": "ICLR 2025 Spotlight"
"venue_id": "ICLR.cc/2025/Conference"
"ratings": [
  6,
  8,
  "… 1 more"
]
replies [3]
[0] {}
"author_role": "Reviewer"
"confidence": 3
content {}
"code_of_conduct": "Yes"
"confidence": 3
"contribution": 3
"flag_for_ethics_review": [
  "No ethics review needed."
]
"presentation": 4
questionsString · text preview
replies[0].content.questions
# Clarification
1. Why did the authors not use FLOPs in their time analysis? Aren’t FLOPs more reliable for this setting? Also, why are ther…
"rating": 8
"soundness": 4
"strengths": "This paper was a very good read. The idea is simple, intuitive and provides a very elegant in-between to curriculum learning, dynamic data p…"
"summary": "This paper introduces instance-dependent early stopping (IES), which refines the idea of early stopping from the entire training dataset to …"
weaknessesString · text preview
replies[0].content.weaknesses
# Reasoning behind second-order information
On one hand I do think that information in Figure 5 is enough to validate using second-order los…
"created": "2024-10-28T15:01:40.659Z"
"decision": null
"forum": "P42DbV2nuV"
"id": "u9wEe6GLM2"
"modified": "2024-11-12T15:59:34.874Z"
"rating": 8
"readers": [
  "everyone"
]
"reply_to": "P42DbV2nuV"
"signature": "ICLR.cc/2025/Conference/Submission2/Reviewer_fBn3"
"title": null
"type": "official_review"
"url": "https://openreview.net/forum?id=P42DbV2nuV&noteId=u9wEe6GLM2"
[1] {}
"author_role": "Reviewer"
"confidence": 4
content {}
"code_of_conduct": "Yes"
"confidence": 4
"contribution": 3
"flag_for_ethics_review": [
  "No ethics review needed."
]
"presentation": 4
"questions": "1. In Figure 1, The rate of excluded samples differs significantly between CIFAR-10 and ImageNet (non-linear vs. linear). What factors might…"
"rating": 8
"soundness": 3
strengthsString · text preview
replies[1].content.strengths
- The paper is well-written, presents an interesting and intuitive idea, and is well-positioned within the existing literature.
- The propos…
"summary": "This paper proposes an early stopping mechanism called Instance-dependent Early Stopping (IES) that takes into account individual instances …"
"weaknesses": "- A crucial missing element in this study is an analysis of the impact of noisy samples within the training set.  It is likely that in the p…"
"created": "2024-11-01T16:23:22.962Z"
"decision": null
"forum": "P42DbV2nuV"
"id": "rXYoKAsjHx"
"modified": "2024-11-28T08:59:34.537Z"
"rating": 8
"readers": [
  "everyone"
]
"reply_to": "P42DbV2nuV"
"signature": "ICLR.cc/2025/Conference/Submission2/Reviewer_1YJ5"
"title": null
"type": "official_review"
"url": "https://openreview.net/forum?id=P42DbV2nuV&noteId=rXYoKAsjHx"
2: "… 20 more"
"review_count": 3
"type_filter": null

Response result

Response structure

Inferred from examples
  • average_ratingnumber
  • cachedboolean
  • countinteger
  • counts_by_typeobject
    • decisioninteger
    • meta_reviewinteger
    • official_commentinteger
    • official_reviewinteger
  • credits_usedinteger
  • decisionstring
  • paperobject
    • abstractstring
    • author_idsstring[]
    • authorsstring[]
    • authors_totalinteger
    • bibtexstring
    • codenull
    • contentobject
      • TLDRstring
      • _bibtexstring
      • abstractstring
      • anonymous_urlstring
      • authoridsstring[]
      • authorsstring[]
      • code_of_ethicsstring
      • keywordsstring[]
      • no_acknowledgement_sectionstring
      • paperhashstring
      • pdfstring
      • primary_areastring
      • submission_guidelinesstring
      • titlestring
      • venuestring
      • venueidstring
    • createdstring
    • domainstring
    • forumstring
    • idstring
    • invitationstring
    • keywordsstring[]
    • licensestring
    • modifiedstring
    • numberinteger
    • pdf_urlstring
    • primary_areastring
    • publishedstring
    • supplementary_material_urlnull
    • titlestring
    • tldrstring
    • urlstring
    • venuestring
    • venue_idstring
  • ratings(integer | string)[]
  • replies(object | string)[]
    • author_rolestring
    • confidenceinteger
    • contentobject
      • code_of_conductstring
      • confidenceinteger
      • contributioninteger
      • flag_for_ethics_reviewstring[]
      • presentationinteger
      • questionsstring
      • ratinginteger
      • soundnessinteger
      • strengthsstring
      • summarystring
      • weaknessesstring
    • createdstring
    • decisionnull
    • forumstring
    • idstring
    • modifiedstring
    • ratinginteger
    • readersstring[]
    • reply_tostring
    • signaturestring
    • titlenull
    • typestring
    • urlstring
  • review_countinteger
  • type_filternull

Loading related APIs…

Common questions

Do I need a separate key for every provider?

Use your OpenAny API key for standard API access. Read it from OPENANY_API_KEY in your environment and keep it out of prompts, source code and logs.

Are these providers interchangeable?

No. Each offering has its own inputs, pricing and response contract. Selecting a catalog offering does not establish automatic routing or fallback. Confirm the service contract before calling.

How is this API billed?

API-key calls use your shared balance at the selected implementation's published rate. Check the billing unit and request-specific pricing rules before making a paid call. Recorded usage determines the final charge under that contract.

Where do the price and contract come from?

The selected implementation publishes its provider, request contract, revision and billing rules through OpenAny's public API catalog. A revision number identifies a contract version, not a price update date. A price update timestamp is not supplied; do not treat a page date as one.

How do OpenAny Balance and x402 differ?

OpenAny Balance uses an API key and one shared balance. Card, USDC and x402 top-ups, card auto top-up and USDC subscriptions fund that balance; available routes appear on the Credits page. Direct x402 is a separate pay-per-request flow, available only on listings that show it and requiring an authorized payment client.

Does Playground send a paid request?

Yes. After you sign in, Run sends a real API request using an active OpenAny API key. Charges follow the published API contract and use your shared balance. Selecting an implementation, editing inputs and viewing sample responses do not send requests.

Use OpenReview reviews and decision API with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.