{"adoption": {"forks": 193, "observed_at": "2026-08-28T04:06:03.624745+00:00", "stars": 1999}, "canonical_url": "https://ross.abutalabs.com/products/omnidocbench", "card": {"archived": false, "artifact_type": "dataset", "description": "[CVPR 2025] A Comprehensive Benchmark for Document Parsing and Evaluation", "domain": ["computer-vision", "pdf", "machine-learning"], "enriched": true, "function": ["benchmarking", "ocr", "pdf"], "health_score": 77, "homepage": "https://opendatalab.com/omnidocbench", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["opendatalab/OmniDocBench"], "name": "opendatalab/OmniDocBench", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-27T09:24:57+00:00", "repo": "opendatalab/OmniDocBench", "stars": 1999, "tags": ["document-parsing", "pdf-parsing", "benchmark-dataset", "layout-detection", "table-recognition", "formula-recognition", "cvpr-2025", "evaluation", "natural-language-processing", "datasets"], "topics": [], "urls": [], "use_cases": ["evaluate pdf document parsing models", "benchmark ocr accuracy on real-world documents", "compare table recognition and formula recognition tools", "measure layout detection quality on annotated pdf pages", "test end-to-end document-to-markdown conversion quality"], "what_it_is": "OmniDocBench is a comprehensive benchmark dataset and evaluation toolkit for document parsing, containing 1,651 annotated PDF pages across 10 document types, 5 layouts, and 5 languages. It includes rich block- and span-level annotations (text, tables, formulas, reading order) plus end-to-end and module-level evaluation code with metrics like TEDS, BLEU, and mAP.", "when_to_avoid": ["you need a production document parser rather than an evaluation benchmark", "your documents fall outside its covered types, layouts, or languages", "you need training data rather than evaluation data"], "when_to_choose": ["you need a high-quality annotated dataset to evaluate document parsing systems", "you want standardized metrics (TEDS, BLEU, METEOR, mAP) for comparing parsers", "you need coverage of diverse document types like papers, reports, newspapers, and handwriting"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/omnidocbench", "repo": "opendatalab/OmniDocBench", "role": "main", "score": 64}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:03.624745+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:02:10.989538+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e773dc4736756fe432e05b049ffd7f4db361705473c23aacf0c56e74dbd06ad0", "fetched_at": "2026-08-28T04:06:03.624745+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opendatalab/OmniDocBench"}, {"content_hash": "0f12c7c923abdd834c327a029d835af3ec51539d15607023f9047277ee234be6", "fetched_at": "2026-08-29T10:42:02.154924+00:00", "kind": "homepage", "missing": false, "url": "https://opendatalab.com/omnidocbench"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 94, "longevity": 49, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 688, "days_push": 37, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 64, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}