{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PIDPZGHNUUGANWDFIXLJQON77B","short_pith_number":"pith:PIDPZGHN","schema_version":"1.0","canonical_sha256":"7a06fc98eda50c06d86545d69839bff8696ed3fafe1bae4cac5986105ff06fb6","source":{"kind":"arxiv","id":"2409.11887","version":2},"attestation_state":"computed","paper":{"title":"DocMamba: Efficient Document Pre-training with State Space Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianshu Zhang, Jiefeng Ma, Jun Du, Pengfei Hu, Shuhang Liu, Zhenrong Zhang","submitted_at":"2024-09-18T11:34:28Z","abstract_excerpt":"In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the self-attention mechanism's quadratic computational complexity hinders their efficiency and ability to process long documents. In this paper, we present DocMamba, a novel framework based on the state space model. It is designed to reduce computational complexity to linear while preserving global modeling capabilities. To further enhance its effectiveness in document p"},"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":"2409.11887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T11:34:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"459a5e786de404c96ea7378ad0cdc769d9823f3ed89aeea1adf72c4fd8241996","abstract_canon_sha256":"235897d02a49ad736e82f128478afc8954d029a1a70463e5e7f406cf7e353f0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:24.314306Z","signature_b64":"KGXcfrxaf3yWLnwI35zMNEepzA7lYMSsxGBCbZy20HnBNgPVgfsULr0L6DnLIyYdN8OruZMLarUjEJTXl1veCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a06fc98eda50c06d86545d69839bff8696ed3fafe1bae4cac5986105ff06fb6","last_reissued_at":"2026-07-05T10:11:24.313785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:24.313785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocMamba: Efficient Document Pre-training with State Space Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jianshu Zhang, Jiefeng Ma, Jun Du, Pengfei Hu, Shuhang Liu, Zhenrong Zhang","submitted_at":"2024-09-18T11:34:28Z","abstract_excerpt":"In recent years, visually-rich document understanding has attracted increasing attention. Transformer-based pre-trained models have become the mainstream approach, yielding significant performance gains in this field. However, the self-attention mechanism's quadratic computational complexity hinders their efficiency and ability to process long documents. In this paper, we present DocMamba, a novel framework based on the state space model. It is designed to reduce computational complexity to linear while preserving global modeling capabilities. To further enhance its effectiveness in document p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11887","kind":"arxiv","version":2},"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/2409.11887/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":"2409.11887","created_at":"2026-07-05T10:11:24.313850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11887v2","created_at":"2026-07-05T10:11:24.313850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11887","created_at":"2026-07-05T10:11:24.313850+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIDPZGHNUUGA","created_at":"2026-07-05T10:11:24.313850+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIDPZGHNUUGANWDF","created_at":"2026-07-05T10:11:24.313850+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIDPZGHN","created_at":"2026-07-05T10:11:24.313850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.02235","citing_title":"Survey on Question Answering over Visually Rich Documents: Methods, Challenges, and Trends","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B","json":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B.json","graph_json":"https://pith.science/api/pith-number/PIDPZGHNUUGANWDFIXLJQON77B/graph.json","events_json":"https://pith.science/api/pith-number/PIDPZGHNUUGANWDFIXLJQON77B/events.json","paper":"https://pith.science/paper/PIDPZGHN"},"agent_actions":{"view_html":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B","download_json":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B.json","view_paper":"https://pith.science/paper/PIDPZGHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11887&json=true","fetch_graph":"https://pith.science/api/pith-number/PIDPZGHNUUGANWDFIXLJQON77B/graph.json","fetch_events":"https://pith.science/api/pith-number/PIDPZGHNUUGANWDFIXLJQON77B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B/action/storage_attestation","attest_author":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B/action/author_attestation","sign_citation":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B/action/citation_signature","submit_replication":"https://pith.science/pith/PIDPZGHNUUGANWDFIXLJQON77B/action/replication_record"}},"created_at":"2026-07-05T10:11:24.313850+00:00","updated_at":"2026-07-05T10:11:24.313850+00:00"}