{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:G2KG34CJQVMPDL2YQMDVODADMP","short_pith_number":"pith:G2KG34CJ","canonical_record":{"source":{"id":"2309.05756","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T18:35:14Z","cross_cats_sorted":[],"title_canon_sha256":"87701c9f1118ffd498841270a581e708e5171e4802a368bfc281d66915e02d79","abstract_canon_sha256":"ce21801fbe77a22bbf6395c14e9561c720ae18f076d7afb94ee0230a53882d0b"},"schema_version":"1.0"},"canonical_sha256":"36946df0498558f1af588307570c0363f5f2050ea43f34a01f67397cecabdab0","source":{"kind":"arxiv","id":"2309.05756","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05756","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05756v3","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05756","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_12","alias_value":"G2KG34CJQVMP","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_16","alias_value":"G2KG34CJQVMPDL2Y","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_8","alias_value":"G2KG34CJ","created_at":"2026-07-05T09:30:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:G2KG34CJQVMPDL2YQMDVODADMP","target":"record","payload":{"canonical_record":{"source":{"id":"2309.05756","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T18:35:14Z","cross_cats_sorted":[],"title_canon_sha256":"87701c9f1118ffd498841270a581e708e5171e4802a368bfc281d66915e02d79","abstract_canon_sha256":"ce21801fbe77a22bbf6395c14e9561c720ae18f076d7afb94ee0230a53882d0b"},"schema_version":"1.0"},"canonical_sha256":"36946df0498558f1af588307570c0363f5f2050ea43f34a01f67397cecabdab0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:56.757803Z","signature_b64":"cxFG9JyCYhDIp5qSVsCQBHCyIlWkXRBWgAyDi+YnMvRqyVFuYRuKlNVzCE+JKBDYNM9kJx33Qi+/30JFWQKGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36946df0498558f1af588307570c0363f5f2050ea43f34a01f67397cecabdab0","last_reissued_at":"2026-07-05T09:30:56.757293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:56.757293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.05756","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXDlgEBVlagsc0JSuVEn6rwZxLdc8rGbGbvROB1+mEXD6J0gS4fTcUBLV/LbNSqE5fBi4s4xfzX6beDesdaQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:00:24.364442Z"},"content_sha256":"ee4f21c395e014a5a1ff1d20cb8878a23f0cf2b6a6afd1e3b22701337e1cb123","schema_version":"1.0","event_id":"sha256:ee4f21c395e014a5a1ff1d20cb8878a23f0cf2b6a6afd1e3b22701337e1cb123"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:G2KG34CJQVMPDL2YQMDVODADMP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Josep Llad\\'os, Mar\\c{c}al Rusi\\~nol, Micka\\\"el Coustaty, Oriol Ramos Terrades, Sanket Biswas, Souhail Bakkali, Zuheng Ming","submitted_at":"2023-09-11T18:35:14Z","abstract_excerpt":"Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pre-training data to learn intermediate representations and often suffer a significant performance drop in real-world online industrial settings. A primary issue is their heavy reliance on OCR engines to extract local positional information within document pages, which limits the models' ability to capture global information and hinders their generalizability, flexibility, and robustness. In this paper, we introduce Gl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05756","kind":"arxiv","version":3},"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/2309.05756/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:30:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oIR5Wi4sM9E7BoaE0mQ5aBNH+42IGL58AJsS0/WNCDxbcyMMNis7OjULfHOf2lkrYZYPROD9L8jqNYKtNyZ0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:00:24.364813Z"},"content_sha256":"27d71459b086ecb5a128cdf72c5f815352c2cd9d98cbfbe3b8e09e8d24454765","schema_version":"1.0","event_id":"sha256:27d71459b086ecb5a128cdf72c5f815352c2cd9d98cbfbe3b8e09e8d24454765"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G2KG34CJQVMPDL2YQMDVODADMP/bundle.json","state_url":"https://pith.science/pith/G2KG34CJQVMPDL2YQMDVODADMP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G2KG34CJQVMPDL2YQMDVODADMP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T05:00:24Z","links":{"resolver":"https://pith.science/pith/G2KG34CJQVMPDL2YQMDVODADMP","bundle":"https://pith.science/pith/G2KG34CJQVMPDL2YQMDVODADMP/bundle.json","state":"https://pith.science/pith/G2KG34CJQVMPDL2YQMDVODADMP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G2KG34CJQVMPDL2YQMDVODADMP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G2KG34CJQVMPDL2YQMDVODADMP","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":"ce21801fbe77a22bbf6395c14e9561c720ae18f076d7afb94ee0230a53882d0b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T18:35:14Z","title_canon_sha256":"87701c9f1118ffd498841270a581e708e5171e4802a368bfc281d66915e02d79"},"schema_version":"1.0","source":{"id":"2309.05756","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.05756","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"arxiv_version","alias_value":"2309.05756v3","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05756","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_12","alias_value":"G2KG34CJQVMP","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_16","alias_value":"G2KG34CJQVMPDL2Y","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_8","alias_value":"G2KG34CJ","created_at":"2026-07-05T09:30:56Z"}],"graph_snapshots":[{"event_id":"sha256:27d71459b086ecb5a128cdf72c5f815352c2cd9d98cbfbe3b8e09e8d24454765","target":"graph","created_at":"2026-07-05T09:30:56Z","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/2309.05756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pre-training data to learn intermediate representations and often suffer a significant performance drop in real-world online industrial settings. A primary issue is their heavy reliance on OCR engines to extract local positional information within document pages, which limits the models' ability to capture global information and hinders their generalizability, flexibility, and robustness. In this paper, we introduce Gl","authors_text":"Josep Llad\\'os, Mar\\c{c}al Rusi\\~nol, Micka\\\"el Coustaty, Oriol Ramos Terrades, Sanket Biswas, Souhail Bakkali, Zuheng Ming","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T18:35:14Z","title":"GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05756","kind":"arxiv","version":3},"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:ee4f21c395e014a5a1ff1d20cb8878a23f0cf2b6a6afd1e3b22701337e1cb123","target":"record","created_at":"2026-07-05T09:30:56Z","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":"ce21801fbe77a22bbf6395c14e9561c720ae18f076d7afb94ee0230a53882d0b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-11T18:35:14Z","title_canon_sha256":"87701c9f1118ffd498841270a581e708e5171e4802a368bfc281d66915e02d79"},"schema_version":"1.0","source":{"id":"2309.05756","kind":"arxiv","version":3}},"canonical_sha256":"36946df0498558f1af588307570c0363f5f2050ea43f34a01f67397cecabdab0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36946df0498558f1af588307570c0363f5f2050ea43f34a01f67397cecabdab0","first_computed_at":"2026-07-05T09:30:56.757293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:56.757293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cxFG9JyCYhDIp5qSVsCQBHCyIlWkXRBWgAyDi+YnMvRqyVFuYRuKlNVzCE+JKBDYNM9kJx33Qi+/30JFWQKGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:56.757803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.05756","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee4f21c395e014a5a1ff1d20cb8878a23f0cf2b6a6afd1e3b22701337e1cb123","sha256:27d71459b086ecb5a128cdf72c5f815352c2cd9d98cbfbe3b8e09e8d24454765"],"state_sha256":"f79d9db84197cb710ed19ff17107611afbc81360ab3834d5d61c0775cf18bf9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NkZbBq9xPba0lLpYf2LfTR8NeOBMohTiDNa4QvQazarsWtXjBjU3whSQtSAGNXTt+n8bgsWqJq/5zP0NJZ0wCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:00:24.366856Z","bundle_sha256":"fc6a1b7d55ef1497055097f2002b4fb61e552aa9f918062b181d7fe02e1d1c80"}}