{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WNSUZFI5C7DEEBVIYJFV6PCNXF","short_pith_number":"pith:WNSUZFI5","schema_version":"1.0","canonical_sha256":"b3654c951d17c64206a8c24b5f3c4db96c580b1222fadbafb389d0319af9b555","source":{"kind":"arxiv","id":"2304.14662","version":1},"attestation_state":"computed","paper":{"title":"CED: Catalog Extraction from Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoxing Huai, Guoliang Zhang, Junfei Ren, Mengsong Wu, Pingfu Chao, Tong Zhu, Wenliang Chen, Zechang Li, Zhefeng Wang, Zijian Yu","submitted_at":"2023-04-28T07:32:00Z","abstract_excerpt":"Sentence-by-sentence information extraction from long documents is an exhausting and error-prone task. As the indicator of document skeleton, catalogs naturally chunk documents into segments and provide informative cascade semantics, which can help to reduce the search space. Despite their usefulness, catalogs are hard to be extracted without the assist from external knowledge. For documents that adhere to a specific template, regular expressions are practical to extract catalogs. However, handcrafted heuristics are not applicable when processing documents from different sources with diverse f"},"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":"2304.14662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-28T07:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"8f7e5d792a6b949c450f75d65b297d06aae3e3af56409f4023ee7de0918f9136","abstract_canon_sha256":"72683ac653ac6127a34c1eb6551d2b0b2e56784ef010b6c53df073f7122e6304"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:19.705616Z","signature_b64":"tX+QBED2FIKVE9xRcCZhwM85KXqOS0gcD8ycEoV22ZsjOXcE2Gfapvh9d+aMWV79JoXCKS+bN8FIedO4qMsCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3654c951d17c64206a8c24b5f3c4db96c580b1222fadbafb389d0319af9b555","last_reissued_at":"2026-07-05T06:05:19.705181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:19.705181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CED: Catalog Extraction from Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoxing Huai, Guoliang Zhang, Junfei Ren, Mengsong Wu, Pingfu Chao, Tong Zhu, Wenliang Chen, Zechang Li, Zhefeng Wang, Zijian Yu","submitted_at":"2023-04-28T07:32:00Z","abstract_excerpt":"Sentence-by-sentence information extraction from long documents is an exhausting and error-prone task. As the indicator of document skeleton, catalogs naturally chunk documents into segments and provide informative cascade semantics, which can help to reduce the search space. Despite their usefulness, catalogs are hard to be extracted without the assist from external knowledge. For documents that adhere to a specific template, regular expressions are practical to extract catalogs. However, handcrafted heuristics are not applicable when processing documents from different sources with diverse f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14662","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/2304.14662/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":"2304.14662","created_at":"2026-07-05T06:05:19.705246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14662v1","created_at":"2026-07-05T06:05:19.705246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14662","created_at":"2026-07-05T06:05:19.705246+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNSUZFI5C7DE","created_at":"2026-07-05T06:05:19.705246+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNSUZFI5C7DEEBVI","created_at":"2026-07-05T06:05:19.705246+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNSUZFI5","created_at":"2026-07-05T06:05:19.705246+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/WNSUZFI5C7DEEBVIYJFV6PCNXF","json":"https://pith.science/pith/WNSUZFI5C7DEEBVIYJFV6PCNXF.json","graph_json":"https://pith.science/api/pith-number/WNSUZFI5C7DEEBVIYJFV6PCNXF/graph.json","events_json":"https://pith.science/api/pith-number/WNSUZFI5C7DEEBVIYJFV6PCNXF/events.json","paper":"https://pith.science/paper/WNSUZFI5"},"agent_actions":{"view_html":"https://pith.science/pith/WNSUZFI5C7DEEBVIYJFV6PCNXF","download_json":"https://pith.science/pith/WNSUZFI5C7DEEBVIYJFV6PCNXF.json","view_paper":"https://pith.science/paper/WNSUZFI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14662&json=true","fetch_graph":"https://pith.science/api/pith-number/WNSUZFI5C7DEEBVIYJFV6PCNXF/graph.json","fetch_events":"https://pith.science/api/pith-number/WNSUZFI5C7DEEBVIYJFV6PCNXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNSUZFI5C7DEEBVIYJFV6PCNXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNSUZFI5C7DEEBVIYJFV6PCNXF/action/storage_attestation","attest_author":"https://pith.science/pith/WNSUZFI5C7DEEBVIYJFV6PCNXF/action/author_attestation","sign_citation":"https://pith.science/pith/WNSUZFI5C7DEEBVIYJFV6PCNXF/action/citation_signature","submit_replication":"https://pith.science/pith/WNSUZFI5C7DEEBVIYJFV6PCNXF/action/replication_record"}},"created_at":"2026-07-05T06:05:19.705246+00:00","updated_at":"2026-07-05T06:05:19.705246+00:00"}