Distribution-free certification framework for crash-severity prediction
A distribution-free certification framework for trustworthy crash-severity prediction
This provides a new method for ensuring the reliability of AI models used in critical applications like crash severity prediction, which is important for safety and decision-making.
Researchers developed a certification layer that wraps crash-severity models, providing distribution-free guarantees.
It works with any severity model unmodified and uses the ordinal nature of crash severity outcomes.On 5.
2 million Texas records across seven base models spanning four decades, the framework attached identical validity and certified a model-independent floor on set width for vulnerable road users.
A distribution-free certification framework for trustworthy crash-severity prediction
Crash-severity models inform screening, dispatch and site prioritization, yet are deployed without a finite-sample statement of what one prediction means. Off-the-shelf guarantees fail here, because the features that make crash severity distinctive defeat them: the KABCO outcome is ordinal, the recorded label is a field assessment agreeing with medical severity about half the time, erring in a structured way, and deployment crosses jurisdictions and years calibration never saw. We develop a certification layer that wraps any severity model unmodified, with distribution-free guarantees using this structure: contiguous ordinal sets that read as "B or worse"; per-class validity for any pre-declared partition, with an oracle efficiency characterization; transfer of coverage to unobserved true severity through a declared reporting band, with a worst-case sharpness result; a one-sided certificate under deployment shift; and severity-weighted risk control. The guarantees compose with an attributable slack budget. The same analysis bounds what certification can achieve. A certified set's informativeness is governed by a functional of the true law that no base model can evade and that cannot be lower-bounded distribution-free; given a declared misreporting channel identified from record-linkage data, a nonvacuous lower bound on that floor becomes computable. On 5.2 million Texas records across seven base models spanning four decades, the layer attaches identical validity and certifies, on the vulnerable road users, a model-independent floor on set width that no base model beats, separating it from a remainder that stays bounded but distribution-free unidentifiable. The framework is released as an open-source package with theorem-level tests.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include crash-severity, trustworthy AI.
Source attribution: curated from arXiv cs.LG (@Amir Rafe, Subasish Das).
