The utility of cognitive testing to predict real world commercial driving risk
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Driving is a complex task which requires numerous cognitive and sensorimotor skills to be performed safely. On-road driver evaluation can identify unsafe drivers but can also be expensive, risky, and time-consuming. Poor performance on off-road measures of cognition and sensorimotor control has been shown to predict on-road performance in privately-licensed light vehicle drivers, but commercial drivers have not yet been studied despite such vehicles generally being larger and heavier, thus increasing risks from unsafe driving. Commercially-licensed truck, bus, and light vehicle drivers undertook the tablet-based Vitals cognitive screening tool, which measures reaction time, judgement, memory, and sensorimotor control, and also undertook an on-road driving evaluation using their vehicle. Accuracy and reliability of the Vitals tasks on predicting road test outcomes were investigated using a trichotomous classifier (pass, fail, borderline), and task performance was analyzed depending on vehicle type and road test outcome. Performance on the Vitals tasks predicted on-road performance across all vehicle types. Participants who failed their on-road evaluation also demonstrated lower success on the Judgement task, fewer correctly replicated shapes on the Memory task, and less time on-target in the Control task compared to those who passed. Performance on cognitive and sensorimotor tasks is a good predictor of future driving performance and driver safety for commercially-licensed drivers. Regardless of vehicle type, stakeholders can use cognitive measures from the Vitals assessment to identify an increased driving risk. Use of the Vitals as a screening tool prior to on-road evaluation can benefit both drivers and evaluators.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it