WebPRM Collection preference data
Checklist-annotated web decision records with page observations, prior actions, one preferred continuation and rejected alternatives for process-reward learning.
AI-assisted editorial review against a primary source. This is a catalog annotation, not an independent reproduction or endorsement.
What is this resource?
- Resource type
- Datasets
- Environment
- web
- Topics
- web-navigation, reward-models, evaluation
- Record publication date
- Not recorded
- Evidence retrieved
- 2026-10-17T02:44:50Z
- Resource ID
- url:8dfc84eb4016204fe70a
What licenses are recorded?
Code, training data, weights, and documents can have different terms. A blank declaration means unknown, not unrestricted use.
- Code
- Not recorded
- Data
- Not recorded
- Document
- Not recorded
- Weights
- Not recorded
Dataset profile
- Supervision
- preferred and rejected continuations, task checklists
- Modalities
- screenshots, text, action history
- Formats
- Parquet
- Splits
- test
Scale and counting units
- 9,460 rows — Hub split named test source
Preserves the publisher’s split label despite the collection’s training purpose. Rows are not individual preference pairs because rejected is a list. Data license is unknown.
Compare source-reviewed profiles
Recorded specifications
- disabled
- false
- download url
- https://huggingface.co/datasets/LangAGI-Lab/WebPRMCollection_preference_pair/tree/main
- gated
- false
- hub id
- LangAGI-Lab/WebPRMCollection_preference_pair
Explore related topics
Scope and limitations
Ten public Parquet shards are present. The card names its split test and reports 9,460 rows; the project’s 40K-plus preference-annotation claim is a different grain and is not substituted for this row count. A row can contain multiple rejected alternatives. No data-license declaration is present.
Related resources
- documented by: Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
Primary evidence and verification
Source retrieval is separate from experiment reproduction. Use the original publication or publisher page when citing claims about the resource.
- editorial primary review
Retrieved 2026-10-17T02:44:50Z. Supports: name, kind, summary, environments, topics, scope, relations, details.
Content fingerprint
9c091c5fc625ce53f53f8262f5cee8d08194e4fd1b8eeed543ff1c3723c823fd - editorial primary review
Retrieved 2026-10-17T02:44:50Z. Supports: identity, release_status, details, licenses.data.
Content fingerprint
28a1d5d12e84fc38515bd3c5031ae0cf315c5f8772b90d982d926b98f2857563 - editorial primary review
Retrieved 2026-10-17T02:44:04Z. Supports: summary, environments.
Content fingerprint
07431058d8b9a71b80e75b7a74a40a8346c1503eec240628459cc4d4e2f0802f
Suggest a correction
Open a source-backed correction. Include this record ID and the original source. Read our editorial policy and coverage boundaries.