Tag
BACON proposes a four-stage pipeline that combines budgeted human labels with multiple AI judge outputs to produce calibrated item-level surrogate predictions, supporting both population-level estimation and individual-level scoring with improved accuracy and reduced bias.
This paper presents a systematic comparative study of KV-cache compression schemes (TurboQuant and SpectralQuant), introduces a statistical validation methodology, and offers regime-specific recommendations for efficient transformer inference.
This academic paper identifies and characterizes Simpson's paradox in behavioral curve modeling, demonstrating how aggregation systematically distorts parametric estimates of user dynamics due to survival bias. The authors validate this distortion across datasets like Goodreads and Amazon Electronics and propose hierarchical peak estimation methods to mitigate the issue.