{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:P2MBEKVBTDIL655IKNXQLGOOMK","short_pith_number":"pith:P2MBEKVB","schema_version":"1.0","canonical_sha256":"7e98122aa198d0bf77a8536f0599ce62b56bf88c72df5f25872d943dd23c4ead","source":{"kind":"arxiv","id":"2105.09297","version":1},"attestation_state":"computed","paper":{"title":"Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Ganbin Zhou, Ping Luo, Rongyu Cao, Yixuan Cao","submitted_at":"2021-05-14T06:26:22Z","abstract_excerpt":"In this paper, we study the problem of extracting variable-depth \"logical document hierarchy\" from long documents, namely organizing the recognized \"physical document objects\" into hierarchical structures. The discovery of logical document hierarchy is the vital step to support many downstream applications. However, long documents, containing hundreds or even thousands of pages and variable-depth hierarchy, challenge the existing methods. To address these challenges, we develop a framework, namely Hierarchy Extraction from Long Document (HELD), where we \"sequentially\" insert each physical obje"},"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":"2105.09297","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-05-14T06:26:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"910eae2f01e459d8c8e3bd7009b1330ba54c07c7876f6046f7f70c9e251e7888","abstract_canon_sha256":"1952a347f729d478e806d08abb56378656ec53aa4ce2360df5e4e5f2b9936bd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:51.660650Z","signature_b64":"78gVxnIDX8EO2uA2ot0LwfsBb1CTEj6OOBoyIrfMcnZLXpdcQixKbx3e13+OlKf2I90iGFEZud5AK7sM0UF2Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e98122aa198d0bf77a8536f0599ce62b56bf88c72df5f25872d943dd23c4ead","last_reissued_at":"2026-07-05T02:41:51.660232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:51.660232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Ganbin Zhou, Ping Luo, Rongyu Cao, Yixuan Cao","submitted_at":"2021-05-14T06:26:22Z","abstract_excerpt":"In this paper, we study the problem of extracting variable-depth \"logical document hierarchy\" from long documents, namely organizing the recognized \"physical document objects\" into hierarchical structures. The discovery of logical document hierarchy is the vital step to support many downstream applications. However, long documents, containing hundreds or even thousands of pages and variable-depth hierarchy, challenge the existing methods. To address these challenges, we develop a framework, namely Hierarchy Extraction from Long Document (HELD), where we \"sequentially\" insert each physical obje"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09297","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/2105.09297/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":"2105.09297","created_at":"2026-07-05T02:41:51.660289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.09297v1","created_at":"2026-07-05T02:41:51.660289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09297","created_at":"2026-07-05T02:41:51.660289+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2MBEKVBTDIL","created_at":"2026-07-05T02:41:51.660289+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2MBEKVBTDIL655I","created_at":"2026-07-05T02:41:51.660289+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2MBEKVB","created_at":"2026-07-05T02:41:51.660289+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/P2MBEKVBTDIL655IKNXQLGOOMK","json":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK.json","graph_json":"https://pith.science/api/pith-number/P2MBEKVBTDIL655IKNXQLGOOMK/graph.json","events_json":"https://pith.science/api/pith-number/P2MBEKVBTDIL655IKNXQLGOOMK/events.json","paper":"https://pith.science/paper/P2MBEKVB"},"agent_actions":{"view_html":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK","download_json":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK.json","view_paper":"https://pith.science/paper/P2MBEKVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.09297&json=true","fetch_graph":"https://pith.science/api/pith-number/P2MBEKVBTDIL655IKNXQLGOOMK/graph.json","fetch_events":"https://pith.science/api/pith-number/P2MBEKVBTDIL655IKNXQLGOOMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/action/storage_attestation","attest_author":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/action/author_attestation","sign_citation":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/action/citation_signature","submit_replication":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/action/replication_record"}},"created_at":"2026-07-05T02:41:51.660289+00:00","updated_at":"2026-07-05T02:41:51.660289+00:00"}