data science

Selection-Aware Stress Testing for Interactive Agents

This work introduces Selection-Aware Semantic Stress Testing (\SASST{}), which learns a task reweighting from pre-execution features on discovery tasks and evaluates the same paired comparison on separate confirmation tasks.

When the Martingale Never Stops Firing: Anytime-Valid Gating on Real Forecast Streams

Anytime-valid methods proposed for dependent data should be accompanied by null-calibration controls and mechanism traces, and Huber-style gating of the filter's own updates cuts isolated-spike degradation by an order of magnitude with no dataset specific tuning.

Confounding Masquerading as Improvement: A Systematic Evaluation of Offline Reinforcement Learning for Stroke Antithrombotic Treatment in a 129,000-Patient Registry

This work conducts a systematic, partially crossed evaluation of five offline RL algorithm families and 14 reward designs in 44,894 post-2018 acute ischemic stroke patients from a nationwide registry, and provides an empirically motivated six-step evaluation checklist.

Learning PDE Time-Stepping with Neural Cellular Automata

This paper proposes a trainable Neural Cellular Automata (NCA) based surrogate model for learning long time PDE dynamics that achieves the lowest long-horizon relative errors on the majority of the experiments.

Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation

CAS (causal active sequential experimentation), which targets evaluation to model-workload pairs and repeats the test as evidence accumulates, to ask whether one assignment stays optimal across every quality table consistent with the evidence.

SS-ESOAP: Self-Scaled Adaptive Preconditioning for Physics-Informed Learning

Method is introduced, which augments SOAP-style preconditioning with a scalar secant-energy correction adapted to Kronecker geometry and an adaptive basis update followed by variance-state downscaling, and is positioned as a scalable option for stiff, high-accuracy physics-informed training, rather than a uniform repla...

PathGuide: Dynamic Classifier-Free Guidance via On-Policy Transport Alignment

This work introduces PathGuide, a framework that reformulates scalar CFG selection as an on-policy transport problem and derives a selection criterion with a direct path-correctness interpretation that yields a strictly quadratic local objective with an efficient, closed-form selector for each solver interval.

A Vision-Based Approach for Human Activity Intensity Estimation Using Kinematic Features

A novel activity intensity score (AIS) framework that provides a nonintrusive and continuous measure of activity intensity by analyzing video data and enables robust, real-time measurement of movement intensity for applications ranging from healthcare and workplace ergonomics to sports analytics and adaptive HVAC contr...

Is management commitment a necessity after all in software process improvement?

Literature and practice has established that the lack of management commitment has been one of the top reasons for a failed SPI (software process improvement) initiative. The paper reports results from an ongoing study aimed at clarifying the role and the meaning of management commitment in SPI initiatives. Results fro...

Rethinking the Concept of Commitment in Software Process Improvement

It is shown that current thinking relies on models of commitment that are flawed in both academic and practical sense and four misconceptions are identified in current thinking.

Commitment development in software process improvement: critical misconceptions

Commitment in software process improvement - in search of the process