Open Issues Need Help
View All on GitHub README demo GIF: Streamlit click-through on a hallucinated field about 4 hours ago
documentation good first issue
Trust layer for document→JSON extraction: calibrated per-field confidence, source grounding, and abstention on top of any extractor (+ VerifyDocBench eval harness)
Python
#benchmark#calibration#conformal-prediction#document-ai#document-extraction#hallucination-detection#llm#ocr#selective-prediction#trustworthy-ai
Array-leaf alignment (greedy matching) in JSON scoring about 4 hours ago
good first issue
Trust layer for document→JSON extraction: calibrated per-field confidence, source grounding, and abstention on top of any extractor (+ VerifyDocBench eval harness)
Python
#benchmark#calibration#conformal-prediction#document-ai#document-extraction#hallucination-detection#llm#ocr#selective-prediction#trustworthy-ai