Micro F1
PulseAugur coverage of Micro F1 — every cluster mentioning Micro F1 across labs, papers, and developer communities, ranked by signal.
-
AI classifier shows promise in disaster damage assessment, but road analysis lags
A study evaluating the CLARKE AI classifier for post-disaster damage assessment found that building damage assessment achieved a Micro F1 score of 0.834, demonstrating good geographic transferability across Florida and …
-
New framework improves automated ICD coding using multimodal data and LLM re-ranking
Researchers have developed a novel two-stage framework for automated ICD coding, addressing limitations in current methods. This new approach integrates multimodal patient data, including structured electronic health re…
-
New research paper questions ML evaluation metrics under weak supervision
A new research paper introduces the concept of "evaluation sovereignty" to address issues in machine learning performance measurement, particularly in systems with weakly supervised or inconsistent labels. The paper pro…