Pith. sign in

REVIEW 3 cited by

Scope Compliance Uncertainty Estimate

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.10801 v1 pith:4D7YTADA submitted 2023-12-17 cs.AI cs.LG

classification cs.AIcs.LG
keywords modelsafetyaffectapplicationsapproachbeenbinarycomputational
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The zeitgeist of the digital era has been dominated by an expanding integration of Artificial Intelligence~(AI) in a plethora of applications across various domains. With this expansion, however, questions of the safety and reliability of these methods come have become more relevant than ever. Consequently, a run-time ML model safety system has been developed to ensure the model's operation within the intended context, especially in applications whose environments are greatly variable such as Autonomous Vehicles~(AVs). SafeML is a model-agnostic approach for performing such monitoring, using distance measures based on statistical testing of the training and operational datasets; comparing them to a predetermined threshold, returning a binary value whether the model should be trusted in the context of the observed data or be deemed unreliable. Although a systematic framework exists for this approach, its performance is hindered by: (1) a dependency on a number of design parameters that directly affect the selection of a safety threshold and therefore likely affect its robustness, (2) an inherent assumption of certain distributions for the training and operational sets, as well as (3) a high computational complexity for relatively large sets. This work addresses these limitations by changing the binary decision to a continuous metric. Furthermore, all data distribution assumptions are made obsolete by implementing non-parametric approaches, and the computational speed increased by introducing a new distance measure based on the Empirical Characteristics Functions~(ECF).

Discussion (0). Sign in to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Q-SafeML: Safety Assessment of Quantum Machine Learning via Quantum Distance Metrics

    cs.LG 2025-09 reject novelty 5.0 of 10

    Q-SafeML applies quantum distance metrics, such as trace distance and fidelity, to compare correct and incorrect predictions of quantum classifiers, offering a way to flag unsafe or unreliable QML behavior.

  2. Incorporating Failure of Machine Learning in Dynamic Probabilistic Safety Assurance

    cs.AI 2025-06 conditional novelty 5.0 of 10

    SafeML's out-of-distribution detection is fed into a Bayesian network so that unreliable ML perception shifts an autonomous platoon into a fallback safety state.

  3. Safer Skin Lesion Classification with Global Class Activation Probability Map Evaluation and SafeML

    cs.CV 2025-08 conditional novelty 4.0 of 10

    A pixel-level argmax over per-class Grad-CAM maps, combined with a selective predictor, is proposed to detect unreliable skin lesion classifications.

Pith tools