New Framework Uses Cross-Source Reasoning to Improve Author Name Disambiguation in Academic Databases
Researchers have proposed CrossND, a machine learning framework designed to correct errors in author name disambiguation by comparing inconsistent paper-author assignments across multiple data sources. The system combines data refinement, supervised fine-tuning with probabilistic soft logic, and test-time scaling to identify and fix incorrect assignments without human intervention. The work addresses a persistent problem in academic search systems where cumulative errors degrade the reliability of scholarly databases.
Author name disambiguation — the task of correctly attributing academic papers to their true authors — is a longstanding challenge in scholarly information systems, particularly when different databases assign the same papers to different author profiles inconsistently. CrossND, accepted at KDD 2026's Applied Data Science track, introduces a full-stack framework that tackles this problem from a new angle: rather than disambiguating from scratch, it identifies and corrects errors by exploiting disagreements between sources. The pipeline begins with a chain-of-refinement stage that denoises author profiles and produces more accurate paper-author matching probabilities. A supervised fine-tuning step then incorporates these refined signals alongside a probabilistic soft logic module that reasons about which source's assignments are likely incorrect. Finally, test-time scaling is applied to further boost prediction accuracy and robustness. Experiments on real-world datasets show CrossND consistently outperforms 17 baseline methods, suggesting cross-source reasoning is a viable and scalable alternative to costly expert annotation.
What's missing
The abstract does not specify which real-world datasets were used for evaluation, the scale of those datasets, or how CrossND performs across different academic disciplines where naming conventions may vary significantly. It is also unclear how the framework handles cases where all available sources share the same erroneous assignment, leaving no cross-source signal to exploit.
What different sources said
- arXiv cs.CLCenter
Cross-Source Reasoning-based Correction for Author Name Disambiguation
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.