{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VB3W3AHLZU4A6HDH6S4QTIISUL","short_pith_number":"pith:VB3W3AHL","schema_version":"1.0","canonical_sha256":"a8776d80ebcd380f1c67f4b909a112a2cc5a1d4d4928a88d698074471b8e11a2","source":{"kind":"arxiv","id":"2402.17983","version":3},"attestation_state":"computed","paper":{"title":"3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Caren Han, Jean Lee, Josiah Poon, Lorenzo Vaiani, Luca Cagliero, Paolo Garza, Yihao Ding","submitted_at":"2024-02-28T01:56:00Z","abstract_excerpt":"This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and coarse-grained levels by facilitating a nuanced correlation between token and entity representations, addressing the complexities inherent in form documents. Additionally, we introduce new inter-grained and cross-grained loss functions to further refine diverse multi-teacher knowledge distillation transfer process, presenting distribution gaps and a harmonised un"},"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":"2402.17983","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T01:56:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"329f7bf3f1b8b2530a12b0079b554aa009edd2e69d1244bf535b72199d04a3c3","abstract_canon_sha256":"75ba536ebf8ef3d92bee4fc5839bfbe715ba84c70b1849c0d7070131258b80f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:41.617431Z","signature_b64":"X7pFk4HYrGFjFOCCjA1aN6ZKepGe7+L0cLPDb/XP/CaB7AcT0Umh+39TfN9AHWuMWcdTEQbrT+I2RKayfddYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8776d80ebcd380f1c67f4b909a112a2cc5a1d4d4928a88d698074471b8e11a2","last_reissued_at":"2026-07-05T08:48:41.616941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:41.616941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Caren Han, Jean Lee, Josiah Poon, Lorenzo Vaiani, Luca Cagliero, Paolo Garza, Yihao Ding","submitted_at":"2024-02-28T01:56:00Z","abstract_excerpt":"This paper presents a groundbreaking multimodal, multi-task, multi-teacher joint-grained knowledge distillation model for visually-rich form document understanding. The model is designed to leverage insights from both fine-grained and coarse-grained levels by facilitating a nuanced correlation between token and entity representations, addressing the complexities inherent in form documents. Additionally, we introduce new inter-grained and cross-grained loss functions to further refine diverse multi-teacher knowledge distillation transfer process, presenting distribution gaps and a harmonised un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17983","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/2402.17983/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":"2402.17983","created_at":"2026-07-05T08:48:41.617002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17983v3","created_at":"2026-07-05T08:48:41.617002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17983","created_at":"2026-07-05T08:48:41.617002+00:00"},{"alias_kind":"pith_short_12","alias_value":"VB3W3AHLZU4A","created_at":"2026-07-05T08:48:41.617002+00:00"},{"alias_kind":"pith_short_16","alias_value":"VB3W3AHLZU4A6HDH","created_at":"2026-07-05T08:48:41.617002+00:00"},{"alias_kind":"pith_short_8","alias_value":"VB3W3AHL","created_at":"2026-07-05T08:48:41.617002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01388","citing_title":"VRD-IU: Lessons from Visually Rich Document Intelligence and Understanding","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL","json":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL.json","graph_json":"https://pith.science/api/pith-number/VB3W3AHLZU4A6HDH6S4QTIISUL/graph.json","events_json":"https://pith.science/api/pith-number/VB3W3AHLZU4A6HDH6S4QTIISUL/events.json","paper":"https://pith.science/paper/VB3W3AHL"},"agent_actions":{"view_html":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL","download_json":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL.json","view_paper":"https://pith.science/paper/VB3W3AHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17983&json=true","fetch_graph":"https://pith.science/api/pith-number/VB3W3AHLZU4A6HDH6S4QTIISUL/graph.json","fetch_events":"https://pith.science/api/pith-number/VB3W3AHLZU4A6HDH6S4QTIISUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL/action/storage_attestation","attest_author":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL/action/author_attestation","sign_citation":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL/action/citation_signature","submit_replication":"https://pith.science/pith/VB3W3AHLZU4A6HDH6S4QTIISUL/action/replication_record"}},"created_at":"2026-07-05T08:48:41.617002+00:00","updated_at":"2026-07-05T08:48:41.617002+00:00"}