arXiv:2606. 28815v1 Announce Type: cross Abstract: Mathswitch is an open-source project that imports mathematical concept records from sources such as Wikidata, Wikipedia, MathWorld, Encyclopedia of Mathematics, nLab, ProofWiki, and Agda-Unimath, and links records that refer to the same concept.
arXiv:2607. 24512v1 Announce Type: new Abstract: Mathematical models are central to formalizing research problems, yet their documentation often falls short of FAIR principles.
arXiv:2607. 25959v1 Announce Type: cross Abstract: Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation.
arXiv:2609.01182v1 Announce Type: new Abstract: Flagship language models appear saturated on benchmarks like MMLU (Hendrycks et al., 2021), scoring above 90% - yet benchmarks test only what the exper...
arXiv:2606. 29894v1 Announce Type: cross Abstract: As agentic AI systems tackle more complex mathematical tasks, they increasingly rely on information retrieval (IR) to search problem databases, theorem libraries, and educational resources.
The paper introduces a method for evaluating the intrinsic interestingness of mathematical theorems by comparing the length of their proofs to the length of their statements. It trains a 27B language model to predict proof difficulty, enabling the generation and selection of more interesting theorems while significantly reducing overlap with existing Mathlib. The approach allows iterative expansion of a self‑building, machine‑verified mathematical library guided by quantifiable metrics.
The paper introduces an epistemically and formally grounded ensemble (EFG) of large language model judges to evaluate autoformalization tasks in formal mathematics. It defines four criteria—logical preservation, mathematical consistency, formal quality, and formal validity—to provide a transparent, multi‑granular assessment. Experiments show that this ensemble outperforms coarse‑grained models, offering a scalable and interpretable proxy for evaluating formal mathematical reasoning.
WiCleanData is a refined version of Wikidata that eliminates type inconsistencies and constraint violations. The authors built an automated pipeline that cleans the taxonomy with language‑model assistance, aggregates type constraints hierarchically, and filters facts to ensure no type violations remain. The resulting knowledge graph is publicly available through a web interface for easy exploration and downstream use.
arXiv:2608. 10644v1 Announce Type: new Abstract: Extraction produces candidate entities and relationships; writing them into a graph is where identity is decided, and identity decisions are destructive in a way extraction errors are not.
arXiv:2608. 20106v1 Announce Type: new Abstract: We introduce OenoBench, a wine-domain knowledge benchmark of 3,266 multiple-choice questions across six pillars (regions, grape varieties, viticulture, winemaking, producers, business) and four difficulty tiers.
The paper argues that large language models (LLMs) organize their internal mathematical reasoning by reusable reasoning approaches rather than by the benchmark topics they are tested on. Using a generation‑replay protocol, the authors extract activation‑importance signatures from eight models across five math sources, cluster these signatures, and find that the resulting groups align more closely with reasoning approaches than with topics. The study shows that changing the requested reasoning approach shifts cluster assignments, while paraphrasing the prompt does not, underscoring the primacy of approach over topic in LLM reasoning.
The zbMATH Open Knowledge Graph is a large-scale RDF knowledge graph that spans more than 250 years of mathematical scholarship. It goes beyond traditional bibliographic metadata by incorporating expert-curated semantic content such as reviews, keywords, subject classifications, software references, and disambiguated authorship. With 34 million entities and 168 million RDF triples, the graph enables fine-grained, historically grounded exploration of mathematical concepts, research fields, and scholarly relationships over time.
arXiv:2606. 11430v1 Announce Type: cross Abstract: Mathematical knowledge is split between bibliographic databases (e.