Paper Rankings.across live arXiv categories.
Search and explore AI-assisted scientific preprint rankings. Kurate helps researchers explore ranked papers using category-based leaderboards and AI-assisted paper comparison.
Validation Report by Swiss Economics (ICLR 2026 correlation)Top Papers
Explore newly ranked papers and active research categories.
Newly Ranked Papers
Latest papers added to the live Kurate ranking pipeline.
+40 more categories
18,957 papers across all remaining fields.
What Kurate supports today.
A ranking and discovery layer for scientific preprints. The capabilities below reflect what is currently live on the platform.
AI-assisted comparison
Papers are compared using AI-assisted pairwise evaluation to produce category-level rankings.
Category-based leaderboards
Papers are organised within live arXiv categories so rankings can be read in their proper field context.
Score: comparative tournament ranking
Score is the comparative tournament-based ranking score derived from AI-assisted paper comparisons within a category.
Rating: standalone scientific impact (1 to 10)
Rating is a standalone scientific impact rating on a 1 to 10 scale. It is independent of the tournament and does not come from pairwise comparison.
Gap: percentile difference between Score and Rating
Gap shows how far the comparative Score sits from the standalone Rating, expressed as a percentile difference between the two signals. A high positive Gap may indicate a hyped topic or a paper that oversells its contribution despite methodological weaknesses. A high negative Gap may point to a methodologically strong paper in a niche area that is harder to distinguish in head-to-head matchups.
Recent rankings & search
Recently ranked papers and updated categories are surfaced on the homepage, with search and time-period filtering across papers.
Planned features under active development. These are not yet part of the live platform.
- Extended novelty, significance, and other metrics
- Field-level validation reporting
- Non-tournament ranking mechanisms
- Cross-model agreement metrics
A discovery workflow for fast-moving scientific literature.
Kurate compares papers using AI-assisted evaluation and produces category-based rankings that help researchers identify work worth closer inspection.
Collect papers
Kurate gathers scientific preprints from supported arXiv categories.
Evaluate papers
Papers are reviewed, rated, and compared through AI-assisted pairwise evaluation within each category. Three independent AI models judge each pair to produce robust rankings.
Score, Rating, Gap
Pairwise comparisons produce a tournament-based Score using TrueSkill. Each paper also receives a standalone Rating (1 to 10) based on scientific impact, independent of the tournament. Gap measures how far the two signals diverge for a given paper.
Explore rankings
Browse ranked papers by category, time period, or search to find work worth closer reading.
Scientific papers are difficult to compare across unrelated fields.
A robotics paper, a quantum physics paper, and an economics paper may all be important, but they should not be interpreted through the same field assumptions. Kurate uses category-based leaderboards so papers are ranked within more meaningful research contexts.
Field context matters
A paper's significance is easier to interpret when compared with other papers from the same arXiv category.
Broad rankings hide specialised work
Important papers in smaller technical fields may be missed when discovery depends only on general popularity or social attention.
Category filters improve discovery
Move directly into the arXiv category you care about and inspect ranked papers within that context.
A ranking layer for scientific preprints.
Kurate adds a ranking layer on top of preprint discovery, combining category-based leaderboards with AI-assisted comparison so users can explore work that may deserve closer reading.
Built for researchers, students, supervisors, labs, institutions, and analysts.
Researchers
Follow fast-moving fields, identify ranked preprints, and discover papers that may not yet have citation visibility.
Postgraduate students
Scan active arXiv categories, find relevant preprints for literature discovery, and follow which topics are moving quickly.
Research supervisors
Recommend recent ranked papers, monitor category activity, and identify emerging work for discussion.
Research groups & labs
Track category activity, compare ranked papers within a field, and support reading-group paper selection.
Institutions
Monitor emerging scientific areas and where attention is forming across research categories.
Science communicators
Identify ranked papers that may become important and follow early signals in the scientific literature.
A discovery layer, not a replacement for peer review.
Kurate rankings are discovery signals, not peer review. They are intended to help users prioritise papers for closer reading. Users should still inspect the paper, methodology, evidence, assumptions, limitations, and field context before forming conclusions.
Methodology, scope, and how to interpret Kurate signals.
Practical answers about what the platform does, how rankings are produced, and how they should be used in research workflows.