few-shot anomaly referencing

This study addresses the critical issue that existing selective prediction methods in signal domains—such as anomalous sound detection and AI-generated image forensics—often yield a false sense of security due to the use of uncalibrated thresholds, resulting in actual error rates that substantially exceed users’ prescribed risk budgets. The work presents the first systematic audit of four distribution-free calibration rules (NAIVE, Hoeffding, Clopper–Pearson, and Betting) regarding their risk control performance on both real and synthetic data. Findings reveal that NAIVE exceeds the risk budget in 49–73% of experiments; Clopper–Pearson and Betting achieve zero violations under exchangeability but suffer 9–30% violation rates when deployed in grouped settings where exchangeability fails. Group-wise thresholding restores valid risk control at the cost of reduced coverage. The study underscores the pivotal role of tight confidence bounds for effective coverage and identifies uncalibrated thresholds as the root cause of risk miscontrol.

This study addresses the lack of rigorous statistical guarantees in sequential sampling for auditing by formulating it as a sequential hypothesis test under sampling without replacement from a finite population. It defines null and alternative hypotheses based on a tolerable deviation rate and constructs exact stopping and decision rules that provide a priori control over both Type I and Type II error probabilities. The work introduces the first sequential audit sampling framework supporting one-sided, two-stage, and truncated designs. Exact boundaries are derived using finite-population error probabilities and efficiently calibrated via Monte Carlo simulation under the least favorable deviation rate. This approach not only ensures pre-specified error control but also accurately estimates expected sample sizes, making it suitable for attribute sampling and tests of controls.

In industrial quality inspection, anomaly detection suffers from poor robustness due to high noise levels and sparse defective samples. To address this, we propose Iterative Refinement of Pseudo-labels (IRP), a self-supervised method that alternately evaluates sample credibility and removes misleading instances under feature-space consistency constraints—effectively purifying the training set dynamically without human annotations and generating high-fidelity self-supervised signals. IRP introduces the novel paradigm of “iterative data refinement,” significantly enhancing model robustness against label noise and cross-domain generalization capability. Evaluated on KSDD2 and MVTec AD benchmarks, IRP consistently outperforms existing unsupervised and self-supervised methods. Notably, under high-noise conditions, it achieves substantial improvements in detection accuracy and reduces false positive rates by over 25%.

This work addresses the challenge of quantifying prediction uncertainty in generative biomolecular design, where feedback covariate shift undermines conventional uncertainty estimation. We propose the first conformal prediction framework tailored to closed-loop design paradigms. Departing from standard i.i.d. assumptions, our method imposes no structural constraints on either the design algorithm or the regression model, delivering finite-sample statistically valid confidence sets for arbitrary black-box design pipelines. Key innovations include quantile-regression-driven adaptive conformal prediction, explicit modeling of feedback-induced distributional shift, and robust error calibration. Evaluated on protein and small-molecule design tasks, our approach achieves ≥94.8% empirical coverage at the 95% nominal confidence level—substantially outperforming standard conformal methods (which drop to as low as 72%)—while maintaining high predictive accuracy.

This study addresses the stagnation of enterprise AI initiatives in regulated financial institutions due to the absence of quantifiable evaluation criteria. Focusing on six document-intensive workflows, it systematically compares AI system performance across four model families and three tool configurations, distinguishing between demonstration and production environments. For the first time, it links deployment feasibility with human review rates. The authors propose a production-grade evaluation framework encompassing accuracy, reproducibility, traceability, and informative confidence, integrating multi-model comparison, confidence signals, source citation, and self-verification mechanisms. Experiments reveal that 56.1% of the 72 evaluated configurations meet production readiness thresholds. Incorporating source citation and confidence estimation reduces human review requirements to 49%, and adding self-verification further lowers this to 44%, albeit at the cost of reduced error tolerance.