{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QVDILQT5ZN22Y7YOP4P2LSYSGU","short_pith_number":"pith:QVDILQT5","schema_version":"1.0","canonical_sha256":"854685c27dcb75ac7f0e7f1fa5cb123510deaef9534bee33830af1dd91d36941","source":{"kind":"arxiv","id":"2606.03264","version":1},"attestation_state":"computed","paper":{"title":"PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changda Zhou, Cheng Cui, Dianhai Yu, Hongen Liu, Jiaxuan Liu, Manhui Lin, Suyin Liang, Tingquan Gao, Ting Sun, Yanjun Ma, Yi Liu, Yiqing Xiang, Yubo Zhang, Yue Zhang, Zelun Zhang","submitted_at":"2026-06-02T07:27:03Z","abstract_excerpt":"We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.9B baseline, its remaining errors concentrate in under-optimized regions where model behavior is unstable, data coverage is sparse, or supervision is unreliable. Rather than expanding the training corpus indiscriminately, PaddleOCR-VL-1.6 introduces a region-aware data optimization framework that identifies weak regions from the previous model, applies targeted enhancement to these regions, and improves the reliability of supervision signals. I"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.03264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T07:27:03Z","cross_cats_sorted":[],"title_canon_sha256":"c43e31a3275725def652379e0568eab62d454ae3c111dcf2320a2d9e542fb75f","abstract_canon_sha256":"ebe10f1e94957014b3c083da9ac746b0ce9a79d51ba1704194b16412d8e7d560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:37.082229Z","signature_b64":"/uWP4pDQO9czMUAvUPRXE7Ud6Idn4cQCRMBdqwYVEGtUbQAlhnMqK6/9Of5ZACT4VZ7mr8oUg9+MH6iBQx4jAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"854685c27dcb75ac7f0e7f1fa5cb123510deaef9534bee33830af1dd91d36941","last_reissued_at":"2026-06-03T01:05:37.081798Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:37.081798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changda Zhou, Cheng Cui, Dianhai Yu, Hongen Liu, Jiaxuan Liu, Manhui Lin, Suyin Liang, Tingquan Gao, Ting Sun, Yanjun Ma, Yi Liu, Yiqing Xiang, Yubo Zhang, Yue Zhang, Zelun Zhang","submitted_at":"2026-06-02T07:27:03Z","abstract_excerpt":"We introduce PaddleOCR-VL-1.6, an upgraded compact document parsing model built upon PaddleOCR-VL-1.5. Although PaddleOCR-VL-1.5 establishes a strong 0.9B baseline, its remaining errors concentrate in under-optimized regions where model behavior is unstable, data coverage is sparse, or supervision is unreliable. Rather than expanding the training corpus indiscriminately, PaddleOCR-VL-1.6 introduces a region-aware data optimization framework that identifies weak regions from the previous model, applies targeted enhancement to these regions, and improves the reliability of supervision signals. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03264","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.03264/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.03264","created_at":"2026-06-03T01:05:37.081858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03264v1","created_at":"2026-06-03T01:05:37.081858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03264","created_at":"2026-06-03T01:05:37.081858+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVDILQT5ZN22","created_at":"2026-06-03T01:05:37.081858+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVDILQT5ZN22Y7YO","created_at":"2026-06-03T01:05:37.081858+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVDILQT5","created_at":"2026-06-03T01:05:37.081858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU","json":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU.json","graph_json":"https://pith.science/api/pith-number/QVDILQT5ZN22Y7YOP4P2LSYSGU/graph.json","events_json":"https://pith.science/api/pith-number/QVDILQT5ZN22Y7YOP4P2LSYSGU/events.json","paper":"https://pith.science/paper/QVDILQT5"},"agent_actions":{"view_html":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU","download_json":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU.json","view_paper":"https://pith.science/paper/QVDILQT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03264&json=true","fetch_graph":"https://pith.science/api/pith-number/QVDILQT5ZN22Y7YOP4P2LSYSGU/graph.json","fetch_events":"https://pith.science/api/pith-number/QVDILQT5ZN22Y7YOP4P2LSYSGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU/action/storage_attestation","attest_author":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU/action/author_attestation","sign_citation":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU/action/citation_signature","submit_replication":"https://pith.science/pith/QVDILQT5ZN22Y7YOP4P2LSYSGU/action/replication_record"}},"created_at":"2026-06-03T01:05:37.081858+00:00","updated_at":"2026-06-03T01:05:37.081858+00:00"}