{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FG25HU54QB3IZ6YAJEZ46JB45L","short_pith_number":"pith:FG25HU54","schema_version":"1.0","canonical_sha256":"29b5d3d3bc80768cfb004933cf243ceae48bd932c81016fc9947e6539aa061e3","source":{"kind":"arxiv","id":"2402.18262","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Da Ma, Hongshen Xu, Kai Yu, Lu Chen, Ruisheng Cao, Zichen Zhu, Zihan Zhao","submitted_at":"2024-02-28T11:50:36Z","abstract_excerpt":"The growing prevalence of visually rich documents, such as webpages and scanned/digital-born documents (images, PDFs, etc.), has led to increased interest in automatic document understanding and information extraction across academia and industry. Although various document modalities, including image, text, layout, and structure, facilitate human information retrieval, the interconnected nature of these modalities presents challenges for neural networks. In this paper, we introduce WebLM, a multimodal pre-training network designed to address the limitations of solely modeling text and structur"},"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":"2402.18262","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T11:50:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"092adbce95a258b7632e85cd651019a0f3328ffc341fdd6f2ec4052bd6687538","abstract_canon_sha256":"ceaac765a8c6d7e3829f7f944de98e9493878748b0f9093d8152c027b50a0a85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:14.459173Z","signature_b64":"a1yjF1LzF+amP/usHEAglVWgpUNuYtrTrW1TwqaaonV3IPuGMbwh25HJWLrUW9o1g68GBWp/FNYm9aX0bz+zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29b5d3d3bc80768cfb004933cf243ceae48bd932c81016fc9947e6539aa061e3","last_reissued_at":"2026-07-05T07:50:14.458799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:14.458799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Da Ma, Hongshen Xu, Kai Yu, Lu Chen, Ruisheng Cao, Zichen Zhu, Zihan Zhao","submitted_at":"2024-02-28T11:50:36Z","abstract_excerpt":"The growing prevalence of visually rich documents, such as webpages and scanned/digital-born documents (images, PDFs, etc.), has led to increased interest in automatic document understanding and information extraction across academia and industry. Although various document modalities, including image, text, layout, and structure, facilitate human information retrieval, the interconnected nature of these modalities presents challenges for neural networks. In this paper, we introduce WebLM, a multimodal pre-training network designed to address the limitations of solely modeling text and structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18262","kind":"arxiv","version":1},"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/2402.18262/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":"2402.18262","created_at":"2026-07-05T07:50:14.458855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18262v1","created_at":"2026-07-05T07:50:14.458855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18262","created_at":"2026-07-05T07:50:14.458855+00:00"},{"alias_kind":"pith_short_12","alias_value":"FG25HU54QB3I","created_at":"2026-07-05T07:50:14.458855+00:00"},{"alias_kind":"pith_short_16","alias_value":"FG25HU54QB3IZ6YA","created_at":"2026-07-05T07:50:14.458855+00:00"},{"alias_kind":"pith_short_8","alias_value":"FG25HU54","created_at":"2026-07-05T07:50:14.458855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L","json":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L.json","graph_json":"https://pith.science/api/pith-number/FG25HU54QB3IZ6YAJEZ46JB45L/graph.json","events_json":"https://pith.science/api/pith-number/FG25HU54QB3IZ6YAJEZ46JB45L/events.json","paper":"https://pith.science/paper/FG25HU54"},"agent_actions":{"view_html":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L","download_json":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L.json","view_paper":"https://pith.science/paper/FG25HU54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18262&json=true","fetch_graph":"https://pith.science/api/pith-number/FG25HU54QB3IZ6YAJEZ46JB45L/graph.json","fetch_events":"https://pith.science/api/pith-number/FG25HU54QB3IZ6YAJEZ46JB45L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L/action/storage_attestation","attest_author":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L/action/author_attestation","sign_citation":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L/action/citation_signature","submit_replication":"https://pith.science/pith/FG25HU54QB3IZ6YAJEZ46JB45L/action/replication_record"}},"created_at":"2026-07-05T07:50:14.458855+00:00","updated_at":"2026-07-05T07:50:14.458855+00:00"}