{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VB3W3AHLZU4A6HDH6S4QTIISUL","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":"75ba536ebf8ef3d92bee4fc5839bfbe715ba84c70b1849c0d7070131258b80f4","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T01:56:00Z","title_canon_sha256":"329f7bf3f1b8b2530a12b0079b554aa009edd2e69d1244bf535b72199d04a3c3"},"schema_version":"1.0","source":{"id":"2402.17983","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17983","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17983v3","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17983","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"VB3W3AHLZU4A","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"VB3W3AHLZU4A6HDH","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"VB3W3AHL","created_at":"2026-07-05T08:48:41Z"}],"graph_snapshots":[{"event_id":"sha256:a7e9689ec2d579dd4a1abb136670059fac891986df915555ac4e6ec5d8724382","target":"graph","created_at":"2026-07-05T08:48:41Z","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/2402.17983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Caren Han, Jean Lee, Josiah Poon, Lorenzo Vaiani, Luca Cagliero, Paolo Garza, Yihao Ding","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T01:56:00Z","title":"3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17983","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":"sha256:7e860f7509220d9646ab3263d935723144fe39e98051ed56934e34b8cdf8389d","target":"record","created_at":"2026-07-05T08:48:41Z","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":"75ba536ebf8ef3d92bee4fc5839bfbe715ba84c70b1849c0d7070131258b80f4","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T01:56:00Z","title_canon_sha256":"329f7bf3f1b8b2530a12b0079b554aa009edd2e69d1244bf535b72199d04a3c3"},"schema_version":"1.0","source":{"id":"2402.17983","kind":"arxiv","version":3}},"canonical_sha256":"a8776d80ebcd380f1c67f4b909a112a2cc5a1d4d4928a88d698074471b8e11a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8776d80ebcd380f1c67f4b909a112a2cc5a1d4d4928a88d698074471b8e11a2","first_computed_at":"2026-07-05T08:48:41.616941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:41.616941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X7pFk4HYrGFjFOCCjA1aN6ZKepGe7+L0cLPDb/XP/CaB7AcT0Umh+39TfN9AHWuMWcdTEQbrT+I2RKayfddYAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:41.617431Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17983","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e860f7509220d9646ab3263d935723144fe39e98051ed56934e34b8cdf8389d","sha256:a7e9689ec2d579dd4a1abb136670059fac891986df915555ac4e6ec5d8724382"],"state_sha256":"dba9584b8744b3ad15b2b1d03833043c027c88935b4e097c0f5bff14f9623804"}