verifydoc good first issues (Python)

Guarantee-respecting genuine-VLM conformal (nominal alpha, doc-clustered, multiplicity-corrected) 9 days ago

help wanted calibration stale

0

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

Ablation: does provenance beat non-provenance conditioning covariates? 9 days ago

help wanted calibration stale

bhaskargurram-ai/verifydoc

0

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

Add >=3 local/open extractors: PaddleOCR-VL, dots.ocr (vLLM), and open VLMs 9 days ago

help wanted adapters stale

bhaskargurram-ai/verifydoc

0

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

Document-clustered CIs + across-split dispersion on every headline table 10 days ago

help wanted eval stale

bhaskargurram-ai/verifydoc

0

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

Grow VerifyDocBench: DocILE, SROIE, full multilingual XFUND, invoices 10 days ago

help wanted benchmark stale

bhaskargurram-ai/verifydoc

0

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

Learned-fusion feature importance / interpretability about 2 months ago

good first issue eval

bhaskargurram-ai/verifydoc

0

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

Trust-gated agentic layer: accuracy-at-fixed-compute evaluation about 2 months ago

enhancement help wanted

bhaskargurram-ai/verifydoc

0

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

Alternative ambiguity-penalty modes (softmax / entropy) about 2 months ago

good first issue calibration

bhaskargurram-ai/verifydoc

0

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

Formalize the "when does provenance-conditioning help" characterization about 2 months ago

enhancement help wanted

bhaskargurram-ai/verifydoc

0

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

Human-labeled gold slice + inter-annotator agreement for free-text fields about 2 months ago

help wanted benchmark

bhaskargurram-ai/verifydoc

0

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

CLI test coverage (tests/test_cli.py) about 2 months ago

good first issue

bhaskargurram-ai/verifydoc

0

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

MCP registry + awesome-mcp-servers submission about 2 months ago

good first issue

bhaskargurram-ai/verifydoc

0

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

Batch/folder processing CLI: verifydoc batch <dir> about 2 months ago

good first issue

bhaskargurram-ai/verifydoc

0

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 2 months ago

good first issue

bhaskargurram-ai/verifydoc

0

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

parse_number: strip alphabetic currency codes (RM, Rp, USD) about 2 months ago

bug good first issue

bhaskargurram-ai/verifydoc

0

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

Adaptive-k budget control for consensus confidence about 2 months ago

enhancement good first issue

bhaskargurram-ai/verifydoc

0

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

DocILE + XFUND dataset loaders about 2 months ago

enhancement good first issue

bhaskargurram-ai/verifydoc

0

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

Loaders + license audit: FUNSD, SROIE, DocILE, XFUND about 2 months ago

enhancement good first issue

bhaskargurram-ai/verifydoc

0

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

VerifyDocBench v1: CORD slice with gold source boxes about 2 months ago

enhancement good first issue

bhaskargurram-ai/verifydoc

0

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

README demo GIF: Streamlit click-through on a hallucinated field 2 months ago

documentation good first issue

bhaskargurram-ai/verifydoc

0

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

bhaskargurram-ai/verifydoc

Open Issues Need Help