Replication Failure and Trivial Baselines in Road-Level Crash Prediction

arXiv:2609.35917v1 Announce Type: new Abstract: Graph neural networks are increasingly applied to road-level crash prediction, but the stability of their reported gains has received little scrutiny. We independently reconstruct the data pipeline of a recent uncertainty-aware model and evaluate eleven of its design decisions across three London boroughs under an expanding-window protocol. Four survive replication on a second borough; seven do not, and four of those reverse sign rather than attenuate. Multi-seed evaluation is decisive: one effect reverses sign between random seeds within a single borough, and the reference architecture exhibits per-borough seed spreads of up to 35.7 points against 4 points for ours. We further compare both networks against a parameter-free baseline that ranks segments by cumulative past crash count. At matched history depth our model is statistically indistinguishable from that baseline ($-0.90$ points, $p=0.61$), and the reference architecture loses to it on 18 of 18 held-out windows ($-17.37$, $p<10^{-6}$). Sweeping the baseline's lookback horizon shows it spans 22.71% to 83.94% accuracy on that variable alone, and that every published figure in this line of work is matched by the baseline at a horizon of one to five years. We argue that the apparent margin of graph networks over historical baselines in this task is substantially an artefact of the short horizons those baselines were computed over, and recommend horizon-matched baselines and multi-seed reporting as minimum practice.

Abstract:Graph neural networks are increasingly applied to road-level crash prediction, but the stability of their reported gains has received little scrutiny. We independently reconstruct the data pipeline of a recent uncertainty-aware model and evaluate eleven of its design decisions across three London boroughs under an expanding-window protocol. Four survive replication on a second borough; seven do not, and four of those reverse sign rather than attenuate. Multi-seed evaluation is decisive: one effect reverses sign between random seeds within a single borough, and the reference architecture exhibits per-borough seed spreads of up to 35.7 points against 4 points for ours. We further compare both networks against a parameter-free baseline that ranks segments by cumulative past crash count. At matched history depth our model is statistically indistinguishable from that baseline ($-0.90$ points, $p=0.61$), and the reference architecture loses to it on 18 of 18 held-out windows ($-17.37$, $p<10^{-6}$). Sweeping the baseline's lookback horizon shows it spans 22.71% to 83.94% accuracy on that variable alone, and that every published figure in this line of work is matched by the baseline at a horizon of one to five years. We argue that the apparent margin of graph networks over historical baselines in this task is substantially an artefact of the short horizons those baselines were computed over, and recommend horizon-matched baselines and multi-seed reporting as minimum practice.

6 pages, 1 figure, 4 tables. Code and reproduction scripts: this https URL

Machine Learning (cs.LG)

arXiv:2609.35917 [cs.LG]

(or arXiv:2609.35917v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.35917 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

Replication Failure and Trivial Baselines in Road-Level Crash Prediction

Related coverage