{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:335CVRWBMV3QW54IXP5RD6PQJI","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":"0ab4ae1c6a13dc41d067bec6282d4b288697b6607433b9ee547c34bcd4cc49f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T06:05:33Z","title_canon_sha256":"3de66b3f9d62aa3b79abde15dee4fe3a30d6cbc1484dd7a43abbb8b39defb896"},"schema_version":"1.0","source":{"id":"2503.02304","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.02304","created_at":"2026-07-05T10:31:55Z"},{"alias_kind":"arxiv_version","alias_value":"2503.02304v2","created_at":"2026-07-05T10:31:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02304","created_at":"2026-07-05T10:31:55Z"},{"alias_kind":"pith_short_12","alias_value":"335CVRWBMV3Q","created_at":"2026-07-05T10:31:55Z"},{"alias_kind":"pith_short_16","alias_value":"335CVRWBMV3QW54I","created_at":"2026-07-05T10:31:55Z"},{"alias_kind":"pith_short_8","alias_value":"335CVRWB","created_at":"2026-07-05T10:31:55Z"}],"graph_snapshots":[{"event_id":"sha256:6869cbfb4c7cb86b8774a3aec8a146b2207fe4ecc94525ba7be8951850b5219d","target":"graph","created_at":"2026-07-05T10:31:55Z","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/2503.02304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, general visual foundation models (VFMs) have witnessed increasing adoption, particularly as image encoders for popular multi-modal large language models (MLLMs). However, without semantically fine-grained supervision, these models still encounter fundamental prediction errors in the context of downstream text-image-related tasks, i.e., perception, understanding and reasoning with images containing small and dense texts. To bridge this gap, we develop TokenOCR, the first token-level visual foundation model specifically tailored for text-image-related tasks, designed to support ","authors_text":"Chen Duan, Hao Sun, Junfeng Luo, Kai Zhou, Pei Fu, Qianyi Jiang, Tiezhu Yue, Tongkun Guan, Wei Shen, Xiaokang Yang, Zhengtao Guo, Zining Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T06:05:33Z","title":"A Token-level Text Image Foundation Model for Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02304","kind":"arxiv","version":2},"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":"sha256:3ae9f9d8a917b89aed7257781b0e52a7511ae502809cc6d93fc0185cbeb72a31","target":"record","created_at":"2026-07-05T10:31:55Z","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":"0ab4ae1c6a13dc41d067bec6282d4b288697b6607433b9ee547c34bcd4cc49f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-04T06:05:33Z","title_canon_sha256":"3de66b3f9d62aa3b79abde15dee4fe3a30d6cbc1484dd7a43abbb8b39defb896"},"schema_version":"1.0","source":{"id":"2503.02304","kind":"arxiv","version":2}},"canonical_sha256":"defa2ac6c165770b7788bbfb11f9f04a27249cb4bfa543be3a1a60f4901e2416","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"defa2ac6c165770b7788bbfb11f9f04a27249cb4bfa543be3a1a60f4901e2416","first_computed_at":"2026-07-05T10:31:55.282051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:55.282051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MfZlzBWpwqFfToWNmAzbg5ZX6EARkZgYiKNKyqmg8Ahe0CQUj+GmfOhtyXofC/Rv4EVA9Ws+bXn9PFvqr9QtAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:55.282668Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.02304","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ae9f9d8a917b89aed7257781b0e52a7511ae502809cc6d93fc0185cbeb72a31","sha256:6869cbfb4c7cb86b8774a3aec8a146b2207fe4ecc94525ba7be8951850b5219d"],"state_sha256":"63ee4d299c29f559591c2c3cb8473c5d7dafa21ad8c499682f690f304ec6804e"}