Work

Basin-Insensitive Reliability: When Riddled Geometry Makes Reproducibility Unattainable, Certification Is the Correct Instrument

Year: 2026

Type: preprint

Abstract: A full preprint synthesizing riddled-basin geometry (Ly & Gong, Nature Machine Intelligence 2026) with PAC-Bayes certification: when training outcomes are unpredictable at the seed level, the correct reliability instrument is a bound that holds for the trained model itself. Measured: a three-round governed distillation arc (0.3%, 2.7%, 1.3% gate-assisted - assistance made acceptance worse), a null uncertainty-exponent measurement with its design flaw named, and the synthesis that certification is basin-independent by construction.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.24043620

Author: Lutar, Stephen P.

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7225454594

Cites:

Cited by:

Related to: 10