{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IYEUQ4IDKVAEUZ6VHA5J62PCDB","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":"25f141f3c68c4a9537a6163ba273d0b8a78f5109363f6ebd829fc888e8b8692a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T15:20:39Z","title_canon_sha256":"a6a0b5f562386a78622ceeaad0d82a56fa7b6d1a308baf93b8e8ea52088ebcdc"},"schema_version":"1.0","source":{"id":"2501.15558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15558","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15558v1","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15558","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_12","alias_value":"IYEUQ4IDKVAE","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_16","alias_value":"IYEUQ4IDKVAEUZ6V","created_at":"2026-07-05T10:05:31Z"},{"alias_kind":"pith_short_8","alias_value":"IYEUQ4ID","created_at":"2026-07-05T10:05:31Z"}],"graph_snapshots":[{"event_id":"sha256:3803ea70f84c4d5dfbd945b5e775b7a16b3f8a89fb1f0cfa7c8ceab54eb86316","target":"graph","created_at":"2026-07-05T10:05:31Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.15558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have shown impressive capabilities across various domains, excelling in processing and understanding information from multiple modalities. Despite the rapid progress made previously, insufficient OCR ability hinders MLLMs from excelling in text-related tasks. In this paper, we present \\textbf{Ocean-OCR}, a 3B MLLM with state-of-the-art performance on various OCR scenarios and comparable understanding ability on general tasks. We employ Native Resolution ViT to enable variable resolution input and utilize a substantial collection of high-quality OCR data","authors_text":"Dongdong Kuang, Fengyu Zhang, Jianhua Xu, Lingfeng Ming, MingAn Lin, Song Chen, Tao Zhang, Weipeng Chen, Xinyu Guo, Yadong Li, Youwei Zhang, Yuran Wang, Zenan Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T15:20:39Z","title":"Ocean-OCR: Towards General OCR Application via a Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15558","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1159c0788678721d7aa6981375cc59e9b4d2acff9e30640aa42625f79753f67c","target":"record","created_at":"2026-07-05T10:05:31Z","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":"25f141f3c68c4a9537a6163ba273d0b8a78f5109363f6ebd829fc888e8b8692a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-26T15:20:39Z","title_canon_sha256":"a6a0b5f562386a78622ceeaad0d82a56fa7b6d1a308baf93b8e8ea52088ebcdc"},"schema_version":"1.0","source":{"id":"2501.15558","kind":"arxiv","version":1}},"canonical_sha256":"460948710355404a67d5383a9f69e21863846cf079e3c455156c6b74afda0448","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"460948710355404a67d5383a9f69e21863846cf079e3c455156c6b74afda0448","first_computed_at":"2026-07-05T10:05:31.120999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:31.120999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DC5R15omJDM4PLqtMlMo33reOUZpo613YwQ5b8IfI4W5FNk5yEl7EFxE+I4jz2USVdZlxlnLKCm8apgjYK+oCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:31.121493Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1159c0788678721d7aa6981375cc59e9b4d2acff9e30640aa42625f79753f67c","sha256:3803ea70f84c4d5dfbd945b5e775b7a16b3f8a89fb1f0cfa7c8ceab54eb86316"],"state_sha256":"a577756b04d2abd7ed67420914d86e6e70b3c4f4a833181b019af1664838be98"}