Estimating Uncoded Crash Factors with Tabular Foundation and System One Models: Kumo Tabular and Jev
Abstract
Road safety programs count the coded fields of police crash records, while the officer's narrative, which often records factors the fields omit, is rarely read. A safety office thus cannot tell how much its counts miss or where to review. This study develops and evaluates a system that joins both views of the 5,601,890 Texas crashes from 2017 to 2025 into population estimates with stated validity. An in-context tabular foundation model, Kumo Tabular, reads the coded record of every crash, a calibrated System One model, Jev, reads the narratives of two probability samples, and human judgments recalibrate its probabilities. A multiwave predict-then-debias estimator joins the three tiers, and a second human tier drawn with recorded probabilities checks the estimates by design. For hydroplaning, medical episodes, fatigue, animals, and phone use, the narrative documents more injury crashes than the coded field, 15,074 against 7,340 for phone use, and the human check agrees with all fifteen estimates within its margin. A re-read list ranked by Kumo Tabular finds confirmed discordance 7 to 58 times as often as random reading. At the planning cost of human coding, one further round of human judgments would cut the root mean square relative half-width from 22.0 to 16.2 percent, against 21.2 for reading every narrative. Two calibrated readers of different views, joined by a sampling design, give a safety office counts, a discordance map, a validated re-read list, and a reading budget, with Kumo Tabular reading the table at 15 times the speed of TabPFN 3.5.
Related
- Conformal Prediction and Conditional Coverage for Tabular Foundation Models
- SurvFM enables tabular foundation models for right-censored survival prediction
- Can Tabular Foundation Models Amortize Statistical Inference?
- TGAge: A Phenotypic Aging Clock Based on Tabular Foundation Models and the Gompertz Law for Assisted Living Facility Residents
- PACE: Plug-and-Play Contextual Embedding for Feature Screening with Pretrained Tabular Foundation Models
BibTeX
@misc{rafe2026estimating,
title = {{Estimating Uncoded Crash Factors with Tabular Foundation and System One Models: Kumo Tabular and Jev}},
author = {Amir Rafe and Subasish Das},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10321},
eprint = {2610.10321},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.10321},
}
RIS
TY - UNPB
TI - Estimating Uncoded Crash Factors with Tabular Foundation and System One Models: Kumo Tabular and Jev
AU - Amir Rafe
AU - Subasish Das
PY - 2026
DA - 2026/10/07
PB - arXiv
DO - 10.48550/arxiv.2610.10321
UR - https://arxiv.org/abs/2610.10321
AB - Road safety programs count the coded fields of police crash records, while the officer's narrative, which often records factors the fields omit, is rarely read. A safety office thus cannot tell how much its counts miss or where to review. This study develops and evaluates a system that joins both views of the 5,601,890 Texas crashes from 2017 to 2025 into population estimates with stated validity. An in-context tabular foundation model, Kumo Tabular, reads the coded record of every crash, a calibrated System One model, Jev, reads the narratives of two probability samples, and human judgments recalibrate its probabilities. A multiwave predict-then-debias estimator joins the three tiers, and a second human tier drawn with recorded probabilities checks the estimates by design. For hydroplaning, medical episodes, fatigue, animals, and phone use, the narrative documents more injury crashes than the coded field, 15,074 against 7,340 for phone use, and the human check agrees with all fifteen estimates within its margin. A re-read list ranked by Kumo Tabular finds confirmed discordance 7 to 58 times as often as random reading. At the planning cost of human coding, one further round of human judgments would cut the root mean square relative half-width from 22.0 to 16.2 percent, against 21.2 for reading every narrative. Two calibrated readers of different views, joined by a sampling design, give a safety office counts, a discordance map, a validated re-read list, and a reading budget, with Kumo Tabular reading the table at 15 times the speed of TabPFN 3.5.
ER -