{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3LCHIT7FYHXM6DUASVPUCHA3XO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3f3e53475258f1b87f64798338c41e36fa6fcf35184ce7b6b8681d3116db5f47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T02:14:10Z","title_canon_sha256":"82285a5b2ad48f34d92c2129da2d5f2f609456792d462a63c6650508507b1e8e"},"schema_version":"1.0","source":{"id":"2507.05595","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05595","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05595v1","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05595","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"3LCHIT7FYHXM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"3LCHIT7FYHXM6DUA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"3LCHIT7F","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:281b164b4f0a07f493c87a5b86c031a12ed1643fbe35b716e3c149d99238591e","target":"graph","created_at":"2026-05-17T23:39:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The benchmarks used to claim competitiveness are representative of real-world use and do not contain undisclosed advantages in data selection or evaluation protocol."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PaddleOCR 3.0 releases compact open-source models for OCR, document structure parsing, and information extraction that rival billion-parameter VLMs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PaddleOCR 3.0 shows models under 100 million parameters match billion-parameter vision-language models on OCR and document tasks."}],"snapshot_sha256":"5b7bb728d226f207f09de66fbe1e3e5ed12ebd36b3da08755f5b5e1c7c217569"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"13c3883d9c10bcc093169782c3a59b98b59c67df633d38156ca0c44e32b29619"},"paper":{"abstract_excerpt":"This technical report introduces PaddleOCR 3.0, an Apache-licensed open-source toolkit for OCR and document parsing. To address the growing demand for document understanding in the era of large language models, PaddleOCR 3.0 presents three major solutions: (1) PP-OCRv5 for multilingual text recognition, (2) PP-StructureV3 for hierarchical document parsing, and (3) PP-ChatOCRv4 for key information extraction. Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs. In a","authors_text":"Changda Zhou, Cheng Cui, Dianhai Yu, Hongen Liu, Jiaxuan Liu, Jing Zhang, Jun Zhang, Kui Huang, Manhui Lin, Tingquan Gao, Ting Sun, Wenyu Lv, Xueqing Wang, Yanjun Ma, Yichao Zhang, Yi Liu, Yubo Zhang, Yue Zhang, Zelun Zhang","cross_cats":[],"headline":"PaddleOCR 3.0 shows models under 100 million parameters match billion-parameter vision-language models on OCR and document tasks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T02:14:10Z","title":"PaddleOCR 3.0 Technical Report"},"references":{"count":73,"internal_anchors":9,"resolved_work":73,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"R. AI. Rolmocr: A faster, lighter open source ocr model, 2025","work_id":"f184e001-9327-4f9d-a66b-b2d302b6e3f3","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Ernie 4.5 technical report, 2025","work_id":"8c68a0de-e7a8-4c44-acb9-a8b0156da515","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"L. Blecher, G. Cucurull, T. Scialom, and R. Stojnic. Nougat: Neural optical understanding for academic documents, 2023","work_id":"9acde2c6-2d5d-4706-8e69-874a806f4d42","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"breezedeus. Pix2text. https://github.com/breezedeus/Pix2Text, 2022. Accessed: 2025-06-23","work_id":"48b3d827-09f0-4252-896e-5ce92c16b5c1","year":2022},{"cited_arxiv_id":"","doi":"10.1109/34.506792","is_internal_anchor":false,"ref_index":6,"title":"R. Casey and E. Lecolinet. A survey of methods and strategies in character segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18 0 (7): 0 690--706, 1996. doi:10.1109/34.5067","work_id":"006b9910-bab8-4a4b-abc9-cd6e4623d194","year":1996}],"snapshot_sha256":"9021d854fd446c78bcde8a0bd206c6bf1dc2c2c35af99748be2956ab534624a8"},"source":{"id":"2507.05595","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T23:20:15.585633Z","id":"24f8aeb1-2dce-4bc2-993f-6d6dcdee9a3f","model_set":{"reader":"grok-4.3"},"one_line_summary":"PaddleOCR 3.0 releases compact open-source models for OCR, document structure parsing, and information extraction that rival billion-parameter VLMs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"PaddleOCR 3.0 shows models under 100 million parameters match billion-parameter vision-language models on OCR and document tasks.","strongest_claim":"Compared to mainstream vision-language models (VLMs), these models with fewer than 100 million parameters achieve competitive accuracy and efficiency, rivaling billion-parameter VLMs.","weakest_assumption":"The benchmarks used to claim competitiveness are representative of real-world use and do not contain undisclosed advantages in data selection or evaluation protocol."}},"verdict_id":"24f8aeb1-2dce-4bc2-993f-6d6dcdee9a3f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:92587d399a7f35cc3737fb0a94a09c3180ed0ab3ee83d1d1792b4f57c45aecc5","target":"record","created_at":"2026-05-17T23:39:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3f3e53475258f1b87f64798338c41e36fa6fcf35184ce7b6b8681d3116db5f47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-08T02:14:10Z","title_canon_sha256":"82285a5b2ad48f34d92c2129da2d5f2f609456792d462a63c6650508507b1e8e"},"schema_version":"1.0","source":{"id":"2507.05595","kind":"arxiv","version":1}},"canonical_sha256":"dac4744fe5c1eecf0e80955f411c1bbb9075f922086dba3861300c2853576ee0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dac4744fe5c1eecf0e80955f411c1bbb9075f922086dba3861300c2853576ee0","first_computed_at":"2026-05-17T23:39:19.863640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:19.863640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8rC0n8pt64EZ4KoaL9A8Bid1dl/KUG15E8XndPDRNtIHuy3MobM5jhfOENsFyVd1bljudbpXGsBW0nGjCX4FBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:19.864266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05595","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92587d399a7f35cc3737fb0a94a09c3180ed0ab3ee83d1d1792b4f57c45aecc5","sha256:281b164b4f0a07f493c87a5b86c031a12ed1643fbe35b716e3c149d99238591e"],"state_sha256":"f4120fb1b505eec1d4fb2e532296b93cc51a7f6bc3c34a8e6aafd28c23d9ada9"}