LLM-Based Safety Case Generation for Baidu Apollo: Are We there Yet?
Bibliographic record
Abstract
Justifying the correct implementation of the non-functional requirements of mission-critical systems is crucial to prevent system failure. The latter could have severe consequences such as the death of people, and financial losses. Assurance cases (e.g., safety cases, security cases) can be used to prevent system failure. They are structured sets of arguments supported by evidence and aiming at demonstrating that a system's non-functional requirements have been correctly implemented. How-ever, although the availability of complete assurance cases is crucial to allow the research community to contribute to the system assurance field, it remains very challenging to access complete assurance cases due to several concerns such as confidentiality issues. Furthermore, assurance cases are usually very large documents. Still, their creation remains a manual, tedious, and error-prone process that heavily relies on domain expertise. Thus, exploring techniques to support their automatic instantiation becomes crucial. To fill these gaps, our experience paper first demonstrates the feasibility of an AMLAS-based design methodology on a case study aiming at manually creating a safety case for the ML-enabled trajectory prediction component of an open-source autonomous driving system i.e. Baidu Apollo. Our paper then reports our experience in using a Large Language Model (LLM) to automatically re-create the same safety case. The lessons we have drawn from this case study provide actionable insights that could benefit researchers and practitioners.
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 | 0.005 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".