Subasish Das

Can small language models be trusted for aviation safety analysis? A benchmark study across model sizes using real-world incident narratives

Counting the Uncounted: Population-Level Surveillance of Documented Pregnancy and Fetal Harm in Police Crash Narratives with a System One Model (Jev)

Motor-vehicle crashes are a leading cause of traumatic fetal death in the United States, yet no crash database records pregnancy. Existing estimates come from national investigation samples with wide intervals, trauma registries seeing only the injured, or record linkage in a few states. Police narratives record pregna...

CHOIR: heterogeneity-aware conformal prediction for crash injury severity across driver safety strata

This study develops and evaluates a certification layer that gives any fitted severity model a finite-sample, distribution-free coverage guarantee within prespecified safety strata, and adds a declared sensitivity analysis for medically assessed injury and bounds on fatal omission.

Benchmarking System One decision models against trained classifiers and language models for automated decision gates

Software that hands branching decisions to a model needs a declared option and a probability it can threshold. Typed decision models, also called System One models, return such probabilities without generating text, while supervised classifiers and generative language models are the established alternatives. One harnes...

Building Trustworthy Mental Health Benchmarks on Bluesky: A Validation-Aware Weak-Supervision Framework

These findings show that decentralized social media can support reproducible mental health benchmarking, but only when system design, label provenance, validation strategy, and deployment constraints are evaluated together.

Toward Auditable and Calibrated AI for Dementia-Related Crash Severity Prediction: A Selective Deferral Framework to Support Human Review

This study reframes dementia-related crash severity modeling as a decision-aware triage problem in which a system must classify crashes into no-injury/property-damage-only (O), minor or moderate injury (BC), and fatal or severe injury (KA), while also controlling outcome leakage.

Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)

This paper formulates narrative coding as gated, typed decisions answered by Jev, a System One model that returns probabilities over analyst-defined options and generates no text.

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 fiel...