You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Automated evaluation and observability harness for production RAG systems. Gates CI/CD against regressions with precision/recall/F1 scoring, dual-signal faithfulness auditing (embeddings + LLM judge), cold/warm latency profiling, and side-by-side configuration benchmarking.
Selective prediction for fetal ultrasound plane classification by pairing a ResNet-18 with diffusion reconstruction uncertainty and softmax confidence for calibrated human-AI deferral. Includes an honest ablation of uncertainty methods.