{"adoption": {"forks": 776, "observed_at": "2026-08-28T04:10:28.144010+00:00", "stars": 9049}, "canonical_url": "https://ross.abutalabs.com/products/bytedance-dolphin", "card": {"archived": false, "artifact_type": "library", "description": "The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.", "domain": ["pdf", "computer-vision", "artificial-intelligence", "files"], "enriched": true, "function": ["ocr", "parser", "pdf", "machine-learning", "computer-vision", "nlp"], "health_score": 64, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["bytedance/Dolphin"], "name": "bytedance/Dolphin", "platform": ["python", "cross-platform"], "pushed_at": "2026-03-25T06:34:12+00:00", "repo": "bytedance/Dolphin", "stars": 9049, "tags": ["document-parsing", "layout-analysis", "vision-language-model", "pdf-converter", "table-recognition", "formula-recognition", "natural-language-processing", "gpu"], "topics": ["document-analysis", "layout-analysis", "ocr", "parser", "pdf", "pdf-converter", "pdf-parser", "python", "vlm-ocr"], "urls": [], "use_cases": ["parse scanned pdf documents into structured text", "extract tables and formulas from document images", "convert photographed documents to markdown", "analyze document layout and reading order", "ocr for complex document pages", "batch convert pdfs to structured data"], "what_it_is": "Dolphin is ByteDance's open-source document image parsing model that converts document images and PDFs into structured content using a two-stage layout-analysis and element-parsing architecture. It handles text, tables, formulas, figures, and code blocks in both digital-born and photographed documents.", "when_to_avoid": ["you only need plain OCR text extraction without layout structure", "you cannot run GPU inference for the vision-language model", "you need a fully permissive license (license is not standard MIT-verified)"], "when_to_choose": ["you need structured parsing of mixed document elements like tables, formulas, and figures", "you want a lightweight model with parallel element-wise parsing for efficiency", "you need to handle both digital and photographed documents"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bytedance-dolphin", "repo": "bytedance/Dolphin", "role": "main", "score": 52}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:28.144010+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:24:03.021308+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3827ac3c7e681b42d6da1c1c235443587fbd69e6c5407a79f91e814fb87742d5", "fetched_at": "2026-08-28T04:10:28.144010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bytedance/Dolphin"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 74, "longevity": 34, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+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": 477, "days_push": 161, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 52, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}