Orchestrating Black-Box Schema Converters: An Empirical Study of Automated, Quality-Ranked Conversion Across Heterogeneous Schema Languages
2026-06-26T08:51:53Z•9810fb2174363974389488124a36fedb976710183af5f039743ec078910e3343
AI coding agentsConcoLixirDynFaultLLM oracleLLM-generated specificationsLLM-labelled codeSafety-Aware Mutation TestingSchema Conversion OrchestratorVeriFastaugmentation with dilutionautonomous drivingcode reviewconcolic testingdeep learning fault diagnosiseye trackinghuman contributorsmutation equivalencemutation testingopen sourceorchestrationquantum softwareschema conversionschema languagesseparation logictranspiler-based equivalence (TBE)
What happened
This RSS parse bundles a set of new empirical and tool papers in software engineering and program analysis. Highlights include: an orchestrator for automated, quality-ranked schema conversions across JSON Schema/XSD/SHACL that produced usable outputs for 43/60 tasks; a large-scale causal study showing AI coding agent adoption reduces human contributor density and newcomer share (staggered DiD on 11,097 GitHub repos); a proposal for Safety-Aware Mutation Testing (SAMT) that injects temporally bounded message-level faults for autonomous driving systems; an evaluation of LLMs generating VeriFast/
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_cs_se
- Record identifier
- 9810fb2174363974389488124a36fedb976710183af5f039743ec078910e3343
- Enrichment time
- 2026-06-26T08:51:53Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.