{"adoption": {"forks": 565, "observed_at": "2026-08-28T04:09:51.405412+00:00", "stars": 6919}, "canonical_url": "https://ross.abutalabs.com/products/donut", "card": {"archived": false, "artifact_type": "library", "description": "Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022", "domain": ["computer-vision", "machine-learning", "pdf"], "enriched": true, "function": ["ocr", "machine-learning", "deep-learning", "nlp", "computer-vision", "data-generation"], "health_score": 20, "homepage": "https://arxiv.org/abs/2111.15664", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["clovaai/donut"], "name": "clovaai/donut", "platform": ["python", "cross-platform"], "pushed_at": "2024-07-11T15:33:26+00:00", "repo": "clovaai/donut", "stars": 6919, "tags": ["document-understanding", "ocr-free", "document-parsing", "synthetic-data", "transformer", "eccv-2022", "information-extraction", "natural-language-processing", "gpu"], "topics": ["document-ai", "eccv-2022", "multimodal-pre-trained-model", "ocr", "nlp", "computer-vision"], "urls": [], "use_cases": ["extract structured data from invoices without OCR", "parse receipts into JSON", "classify document images", "pretrain a document understanding model on synthetic documents", "build a document parsing pipeline in Python"], "what_it_is": "Donut is an OCR-free end-to-end Transformer model for visual document understanding tasks such as document classification and information extraction. The repository also includes SynthDoG, a synthetic document image generator for flexible multilingual pre-training.", "when_to_avoid": ["you need general-purpose text OCR for plain text extraction", "you lack GPU resources for training or inference", "you need actively developed features or frequent updates"], "when_to_choose": ["you need document information extraction without depending on external OCR engines", "you want to avoid OCR error propagation and reduce OCR compute costs", "you need multilingual or domain-flexible document pre-training via synthetic data"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/donut", "repo": "clovaai/donut", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:51.405412+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:41:26.021818+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d537d720b719352ab2bb2aa0c7904a6974a60bf7f2088e46cf6057f618ac2da3", "fetched_at": "2026-08-28T04:09:51.405412+00:00", "kind": "readme", "missing": false, "url": "https://github.com/clovaai/donut"}, {"content_hash": "bd2fe6bcc1a96fff9dc292d9bcd146f9d9f9219996d4ce9b24e364a6e572c37f", "fetched_at": "2026-08-29T08:37:19.416310+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/2111.15664"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T08:37:19.425885+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T08:37:19.430073+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T08:37:19.431919+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T08:37:19.428349+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1506, "days_push": 783, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}