{"adoption": {"forks": 178, "observed_at": "2026-08-28T04:04:59.791152+00:00", "stars": 1535}, "canonical_url": "https://ross.abutalabs.com/products/awesome-document-understanding", "card": {"archived": false, "artifact_type": "learning-resource", "description": "A curated list of resources for Document Understanding (DU) topic", "domain": ["machine-learning", "pdf", "awesome-lists", "artificial-intelligence"], "enriched": true, "function": ["ocr", "nlp", "machine-learning", "pdf", "data-science"], "health_score": 20, "homepage": null, "language": null, "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["tstanislawek/awesome-document-understanding"], "name": "tstanislawek/awesome-document-understanding", "platform": [], "pushed_at": "2023-06-02T03:56:06+00:00", "repo": "tstanislawek/awesome-document-understanding", "stars": 1535, "tags": ["awesome-list", "document-understanding", "key-information-extraction", "document-layout-analysis", "document-ai", "intelligent-document-processing", "curated-resources", "natural-language-processing"], "topics": ["awesome-list", "machine-learning", "information-extraction", "key-information-extraction", "document-understanding", "robotic-process-automation", "document-analysis", "document-layout-analysis", "ocr", "natural-language-processing", "deep-learning", "nlp", "awesome", "pdf", "rpa", "pdf-documents", "document-intelligence", "unstructured-data", "intelligent-processing", "document-ai"], "urls": [], "use_cases": ["find datasets for key information extraction from invoices", "learn about document layout analysis models", "discover OCR research papers and tools", "find resources for document question answering", "research intelligent document processing for RPA", "find PDF processing tools for document AI", "explore pre-training datasets for document understanding models"], "what_it_is": "A curated awesome-list of research papers, datasets, tools, and resources for Document Understanding (DU) and Intelligent Document Processing (IDP). It covers topics like key information extraction, document layout analysis, document question answering, and OCR for visually rich documents.", "when_to_avoid": ["you need a working library or tool rather than a list of resources", "you need production-ready document processing software", "you need actively maintained code, since this is a curated link collection"], "when_to_choose": ["you are researching document AI and need a starting point of papers and datasets", "you want to survey the state of the art in key information extraction or OCR", "you need to find datasets for training document understanding models"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-document-understanding", "repo": "tstanislawek/awesome-document-understanding", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:59.791152+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:31:10.524259+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2fc09e4939d0b660771fb711270d820f2fb4cd8b5ba29dee2fb354940785b31a", "fetched_at": "2026-08-28T04:04:59.791152+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tstanislawek/awesome-document-understanding"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1975, "days_push": 1188, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}