AI-powered scientific paper rankings
Switzerland
Joined April 2026
- Tweets316
- Following187
- Followers5.3K
- Likes324
Kurate.org retweeted
Keeping up with @arxiv is impossible. 500+ preprints a day across dozens of fields.
@KurateOrg scores papers on 16 dimensions (impact, novelty, rigor, surprise, translational...) so you can spot what's worth reading at a glance. Sort, filter & sign up for the weekly newsletter.
Kurate.org retweeted
If AI can reliably help prioritize high-impact research, it could make it much easier for researchers to navigate the growing volume of scientific papers.
The key will be ensuring these rankings complement, rather than replace, expert review.
@KurateOrg AI-powered paper rankings align strongly with expert reviewers according to an independent validation by @MatthiasHafner1 @NicolasOderbolz from Swiss Economics.
Kurate fetches preprints from arXiv across 45+ categories, using LLMs to rank them by scientific impact.
Full report: xitter.cf/robert_lauko/status/20…
@KurateOrg AI-powered paper rankings align strongly with expert reviewers according to an independent validation by @MatthiasHafner1 @NicolasOderbolz from Swiss Economics.
Kurate fetches preprints from arXiv across 45+ categories, using LLMs to rank them by scientific impact.
Kurate.org retweeted
6/ Kurate as a research intelligence platform
We’ll keep improving Kurate by extending the single score ratings into richer dimensions such as reproducibility, difficulty, translational potential, surprisingness, interdisciplinarity and more.
The goal is not to replace deep peer review, but to build a scalable, fast, empirically validated intelligence layer for science.
Stay tuned for more!
Kurate.org retweeted
3/ Kurate was tested in three modes:
- Single Score: directly assign a rating from 0.0 to 10.0 by Claude Opus 4.6 AI to each paper
- Win Rate: pairwise comparisons (matches) using several LLMs aggregated by wins
- TrueSkill: Bayesian ranking from pairwise matches
This allowed Swiss Economics to compare direct scoring vs tournament-style ranking.
All Kurate methods were meaningfully correlated with human expert rankings, but direct scoring (Single Score) was clearly strongest.
Kurate.org retweeted
1/ Swiss Economics (swiss-economics.ch) has validated @KurateOrg's AI scientific paper ranking pipeline against human review data from #ICLR2026.
Full report by @MatthiasHafner1 and @NicolasOderbolz:
swiss-economics.ch/project/i…
Kurate.org is a platform that automatically fetches the latest preprints from @arxiv across 45+ categories (including Machine Learning, Artificial Intelligence, Robotics, Game Theory, Economics, and Physics) and uses LLMs to rank them by scientific impact.
The result: Kurate’s rankings strongly align with expert consensus. Its best method (Spearman correlation 0.71) even exceeds how closely single human reviewers agree with the ground truth (0.56 to 0.68).
Kurate.org retweeted
just got off a call with @robert_lauko (founder of @LiquityProtocol , @KurateOrg ) and my brain is still processing
we talked about kurate, how pairwise llm tournaments are a better signal for paper quality than citation counts. turns out influencerank and kurate are solving basically the same problem from different directions
then we got into liquity. v1 was already one of the cleanest stablecoin designs, no governance, no oracle manipulation surface, purely collateral-driven. v2 (BOLD) took it further, user-set interest rates, multi-collateral, still immutable. the thesis is that trust in a stablecoin comes from mechanism design, not from a team's promises
the people building the most interesting things in defi are the ones who've already broken something and rebuilt it. robert has done that twice
check out kurate if you haven't @KurateOrg
RT @robert_lauko: I'm thrilled to launch a new Frontiers Research Topic: "Blockchain, DeFi and AI: Economic Systems, Intelligent Agents, an…
Kurate.org retweeted
How emergence happens has long been debated amongst physicists, biologists and philosophers alike. quantamagazine.org/the-new-m…
Kurate.org retweeted
Researchers at Columbia University have developed modular robots that can adapt, repair, and even rebuild themselves using a concept called robot metabolism. 🤖
Instead of remaining fixed, these robots can detach, reconnect, and reorganize their own structure based on the task or environment.
If one part is damaged, the system can replace or rearrange itself rather than stopping completely.
This could reshape the future of disaster response, industrial automation, and even space exploration.
The idea of robots that evolve instead of wear out is becoming more than science fiction.
What real-world application do you think will benefit most from this technology?
🎥 Media: @Columbia
⚠️ This content is shared for informational purposes only. CTO Robotics Media is a media platform and does not own or develop the technology shown. Credit belongs to the original creators.
Just posted a paper on arXiv? 📄
Head to kurate.org to see how it scores in our AI-powered impact ranking.
Kurate now covers ~50% of all new arXiv submissions, and growing fast.
#arXiv #OpenScience
Kurate.org retweeted
This sounds like a fantastic resource for staying updated on cutting-edge research. Excited to explore the papers and insights from @kurateorg.
🥇 Congrats to DES Collaboration, T. M. C. Abbott, M. Adamow et al. for ranking #1 Gold in astro-ph.CO Preprints, Week 22, 2026 on Kurate.org!
Their paper, “Constraints on Dynamical Dark Energy from Multiple Probes in the Full Dark Energy Survey,” is highlighted for its strong impact in cosmology, with a Tournament Score of 1553 ± 48 and a 94% win rate on Kurate.org.
#Cosmology #Astrophysics #DarkEnergy #DES #arXiv #Research #KurateOrg #Kuratepapers
🤖 Made with AI
