GitHub

Hario Core — Type-safe HAR Model & Transform

A modern, extensible, and type-safe Python library for parsing, transforming, and analyzing HAR (HTTP Archive) files. Built on Pydantic, Hario-Core provides robust validation, flexible transformation, ...
IEEE

Resilient Test-Time Adaptation by Mitigating Batch-Normalization Overfitting

Abstract: Test-time domain adaptation adjusts a source domain model to accommodate previously unseen domain shifts in a target domain during inference. In real-world scenarios, domain shifts ...
GitHub

test_hasher_extended.py

"""Agents might mix case (SELECT vs select). Hasher should ignore it.""" sql_1 = "SELECT * FROM users WHERE id = 1" sql_2 = "select * from users where id = 1" # Note ...
IEEE

Re-Thinking the Effectiveness of Batch Normalization and Beyond

Batch normalization (BN) is used by default in many modern deep neural networks due to its effectiveness in accelerating training convergence and boosting inference performance. Recent studies suggest ...