Language agnostic automatic scenario tagging in ASAM OpenLABEL
Bibliographic record
Abstract
Automated driving system (ADS) testing for the purposes of validation and verification (V&V) has seen a shift towards scenario focused testing.This puts an emphasis on the quality of selected testing scenarios to prove ADS safety, rather than attempting to justify safety by the number of miles driven.In line with this, there has been a rush from industry and the research community alike to derive a plethora of scenario description languages (SDLs).Scenario storage solutions have emerged as the number of developers wishing to engage in testing increases.An essential component of scenario storage is the correct, complete and appropriate labeling of scenarios, so that scenarios can be filtered and searched for effectively.Scenario labeling or tagging is typically a manual and language specific process, which can be time-consuming and error-prone.We address this problem using a standard approach to labelling scenarios, utilizing the ASAM OpenLABEL standard.This allows for consistent scenario searching and filtering across databases.This paper proposes a methodology for automatic label extraction that is language agnostic and can be adapted to suit any SDL.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.005 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.071 | 0.057 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".