The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Many operational cases are documented more than once, at different workflow stages and for different purposes, yet model evaluations normally select one of these records before model comparison begins...
The study investigates whether a model trained on construction‑sector occupational accident narratives can accurately classify accident‑process roles in other sectors and reporting environments. Using 42,244 factual units from 6,040 construction narratives, the authors compared TF‑IDF, frozen pretrained representations, and task‑adapted pretrained models, achieving up to 85.7% balanced accuracy without retraining. The models performed consistently across metallurgy, chemistry‑plastics, and an independent company corpus, though performance varied more on the latter due to differing reporting practices.
arXiv:2607. 29064v1 Announce Type: cross Abstract: Police crash narratives contain information that may supplement structured crash databases, but manual review is labor-intensive and it remains unclear how well large language models (LLMs) reproduce official crash coding.
Medical device recalls are a critical regulatory mechanism for protecting patient safety. The growing volume of FDA recall records presents challenges in post-report recall triage, severity assessment, and root-cause interpretation.
arXiv:2606. 27174v1 Announce Type: new Abstract: Medical device recalls are a critical regulatory mechanism for protecting patient safety.
The paper presents a decision‑aware framework for predicting dementia‑related crash severity that emphasizes auditability and selective deferral. Using 4,781 Texas crash records, the authors evaluate several models—including structured, narrative, fusion, calibrated fusion, BERT‑family, and local large‑language‑model baselines—under a stratified 70/15/15 split. The leakage‑controlled Gemma model achieves the highest macro‑F1 of 0.545, while a calibrated fusion model reaches 0.522 macro‑F1 with an expected calibration error of 0.033; selective deferral further improves performance, raising macro‑F1 to 0.573 at 70% coverage and reducing severity cost to 0.577.