{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:P2MBEKVBTDIL655IKNXQLGOOMK","short_pith_number":"pith:P2MBEKVB","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"},"canonical_sha256":"7e98122aa198d0bf77a8536f0599ce62b56bf88c72df5f25872d943dd23c4ead","source":{"kind":"arxiv","id":"2105.09297","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09297","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09297v1","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09297","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"P2MBEKVBTDIL","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"pith_short_16","alias_value":"P2MBEKVBTDIL655I","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"pith_short_8","alias_value":"P2MBEKVB","created_at":"2026-07-05T02:41:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:P2MBEKVBTDIL655IKNXQLGOOMK","target":"record","payload":{"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"},"canonical_sha256":"7e98122aa198d0bf77a8536f0599ce62b56bf88c72df5f25872d943dd23c4ead","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"},"source_kind":"arxiv","source_id":"2105.09297","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:41:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XR5ClxJIPkdyC9jjI3kmPdMOSP2ouKEJDfbgD3lqso9FhmslQuDGogJpb0Wftkb7adQIclHFrCvtb3wuUCcuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T23:01:27.330816Z"},"content_sha256":"028a58943da104d32de286f4717507cc59c054d423be12cb5c578ce77758ada7","schema_version":"1.0","event_id":"sha256:028a58943da104d32de286f4717507cc59c054d423be12cb5c578ce77758ada7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:P2MBEKVBTDIL655IKNXQLGOOMK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:41:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6WV3//nZqbzIdVij/wunjbX+mga5omCwsLyQhfoJJjkeHLU7aIRyV5jEOSAOphUd+WuheYTeh+DFR7O5hP3SAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T23:01:27.331178Z"},"content_sha256":"d96505591748a75cdc21d6dc3f23eeeb31321f0de9f17dd10a4384b3ee4e5130","schema_version":"1.0","event_id":"sha256:d96505591748a75cdc21d6dc3f23eeeb31321f0de9f17dd10a4384b3ee4e5130"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/bundle.json","state_url":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P2MBEKVBTDIL655IKNXQLGOOMK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-21T23:01:27Z","links":{"resolver":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK","bundle":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/bundle.json","state":"https://pith.science/pith/P2MBEKVBTDIL655IKNXQLGOOMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P2MBEKVBTDIL655IKNXQLGOOMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P2MBEKVBTDIL655IKNXQLGOOMK","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":"1952a347f729d478e806d08abb56378656ec53aa4ce2360df5e4e5f2b9936bd6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-05-14T06:26:22Z","title_canon_sha256":"910eae2f01e459d8c8e3bd7009b1330ba54c07c7876f6046f7f70c9e251e7888"},"schema_version":"1.0","source":{"id":"2105.09297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09297","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09297v1","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09297","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"pith_short_12","alias_value":"P2MBEKVBTDIL","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"pith_short_16","alias_value":"P2MBEKVBTDIL655I","created_at":"2026-07-05T02:41:51Z"},{"alias_kind":"pith_short_8","alias_value":"P2MBEKVB","created_at":"2026-07-05T02:41:51Z"}],"graph_snapshots":[{"event_id":"sha256:d96505591748a75cdc21d6dc3f23eeeb31321f0de9f17dd10a4384b3ee4e5130","target":"graph","created_at":"2026-07-05T02:41:51Z","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/2105.09297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ganbin Zhou, Ping Luo, Rongyu Cao, Yixuan Cao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-05-14T06:26:22Z","title":"Extracting Variable-Depth Logical Document Hierarchy from Long Documents: Method, Evaluation, and Application"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09297","kind":"arxiv","version":1},"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":"sha256:028a58943da104d32de286f4717507cc59c054d423be12cb5c578ce77758ada7","target":"record","created_at":"2026-07-05T02:41:51Z","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":"1952a347f729d478e806d08abb56378656ec53aa4ce2360df5e4e5f2b9936bd6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-05-14T06:26:22Z","title_canon_sha256":"910eae2f01e459d8c8e3bd7009b1330ba54c07c7876f6046f7f70c9e251e7888"},"schema_version":"1.0","source":{"id":"2105.09297","kind":"arxiv","version":1}},"canonical_sha256":"7e98122aa198d0bf77a8536f0599ce62b56bf88c72df5f25872d943dd23c4ead","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e98122aa198d0bf77a8536f0599ce62b56bf88c72df5f25872d943dd23c4ead","first_computed_at":"2026-07-05T02:41:51.660232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:41:51.660232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"78gVxnIDX8EO2uA2ot0LwfsBb1CTEj6OOBoyIrfMcnZLXpdcQixKbx3e13+OlKf2I90iGFEZud5AK7sM0UF2Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:41:51.660650Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.09297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:028a58943da104d32de286f4717507cc59c054d423be12cb5c578ce77758ada7","sha256:d96505591748a75cdc21d6dc3f23eeeb31321f0de9f17dd10a4384b3ee4e5130"],"state_sha256":"f5c63b5b809688fcb03b3badcb8fe4476fc5edbd6aeeec610e8513df5a797226"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7xR8o0BlHVKH1TBffIMwcFhoo7N7kRJthlwubr9AsL1Vu+JomCb4bASnP96ynxapDNL2K8UtpPAkzaIdRwDMBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T23:01:27.333696Z","bundle_sha256":"a2787898560c94dc6c7c1deabd48697e23a015f4b883afad9e9f033d75f82f35"}}