PulseAugur
EN
LIVE 06:17:06

Language models prove mathematical conjectures on new OEIS Open benchmark

By PulseAugur Editorial · [2 sources] ·

Researchers have developed OEIS Open, a new benchmark designed to evaluate how many mathematical conjectures language models can prove. The benchmark, based on 492 open conjectures from the On-Line Encyclopedia of Integer Sequences formalized in Lean, allows generic language models to attempt proofs autonomously. Initial results show that LMs can resolve a significant portion of these conjectures at a modest cost, with one model scoring 44% on a subset of the benchmark using a $200 budget per attempt. AI

IMPACT Demonstrates potential for LMs to autonomously resolve open research conjectures, potentially accelerating mathematical discovery.

RANK_REASON The cluster describes a new benchmark and research paper evaluating language models on mathematical conjectures.

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Language models prove mathematical conjectures on new OEIS Open benchmark

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster describes a new benchmark and research paper evaluating language models on mathematical conjectures.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
48 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Tom Adamczewski ·

    OEIS Open: How many conjectures can language models turn into theorems?

    arXiv:2608.11941v1 Announce Type: new Abstract: We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conjectures had previously been attempted only with a bespoke agent, our open-source …

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    OEIS Open: How many conjectures can language models turn into theorems?

    We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conjectures had previously been attempted only with a bespoke agent, our open-source evaluation code runs any generic language model …

RELATED ENTITIES

RELATED TOPICS