REVIEW 2 cited by
Safety Case Templates for Autonomous Systems
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This report documents safety assurance argument templates to support the deployment and operation of autonomous systems that include machine learning (ML) components. The document presents example safety argument templates covering: the development of safety requirements, hazard analysis, a safety monitor architecture for an autonomous system including at least one ML element, a component with ML and the adaptation and change of the system over time. The report also presents generic templates for argument defeaters and evidence confidence that can be used to strengthen, review, and adapt the templates as necessary. This report is made available to get feedback on the approach and on the templates. This work was sponsored by the UK Dstl under the R-cloud framework.
Forward citations
Cited by 2 Pith papers
-
Safety Cases: A Scalable Approach to Frontier AI Safety
Structured safety arguments, called safety cases, can help frontier AI companies meet many of the Seoul Frontier AI Safety Commitments, though key methodological and technical gaps remain.
-
A Taxonomy of Real-World Defeaters in Safety Assurance Cases
A systematic review yields a seven-category taxonomy of defeaters in safety assurance cases: logical, contextual, evidence-validity, requirements, structural, adversarial, and uncertainty.
Discussion (0). Continue with ORCID to comment.