{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VJU2NITEBIOPBPHRUT3WUE4A3Y","short_pith_number":"pith:VJU2NITE","schema_version":"1.0","canonical_sha256":"aa69a6a2640a1cf0bcf1a4f76a1380de247a29935b31f4fa9204d3c41d74b8f8","source":{"kind":"arxiv","id":"2607.08539","version":1},"attestation_state":"computed","paper":{"title":"DocMaster: A Hierarchical Structure-Aware System for Document Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Chuanhui Yang, Fangyuan Zhang, Quanqing Xu, Yingli Zhou, Yixiang Fang, Ziqi Chen","submitted_at":"2026-07-09T14:33:47Z","abstract_excerpt":"Leveraging large language models (LLMs) to analyze complex documents -- such as academic papers, technical manuals, and financial reports -- has emerged as a mainstream and critical task in both research and industry. In practice, users must first filter relevant documents from large collections and then conduct in-depth analysis (e.g. question answering) over the selected subset, yet existing systems flatten documents into plain-text chunks, discarding the rich hierarchical structures (sections, tables, figures, equations) and degrading downstream performance. We present DocMaster, a hierarch"},"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":"2607.08539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-07-09T14:33:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"704ab7733a92524c3f68cc44f51de4b52b6a4a32e0f00b2d347f87557735978c","abstract_canon_sha256":"4be48a51a5a7f9af10a811a102a20380a28bbad8c2819f258c9d7de21989ed37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:53.162087Z","signature_b64":"AXox/wP1SI4IXoC/SNDxUu2O1GZ+Nf9iEceUzJPrlrWSPKHgCgs4awE1WW4NeM/7pEqk4nJn4l68KHDA3ZmGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa69a6a2640a1cf0bcf1a4f76a1380de247a29935b31f4fa9204d3c41d74b8f8","last_reissued_at":"2026-07-10T01:19:53.161684Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:53.161684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocMaster: A Hierarchical Structure-Aware System for Document Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Chuanhui Yang, Fangyuan Zhang, Quanqing Xu, Yingli Zhou, Yixiang Fang, Ziqi Chen","submitted_at":"2026-07-09T14:33:47Z","abstract_excerpt":"Leveraging large language models (LLMs) to analyze complex documents -- such as academic papers, technical manuals, and financial reports -- has emerged as a mainstream and critical task in both research and industry. In practice, users must first filter relevant documents from large collections and then conduct in-depth analysis (e.g. question answering) over the selected subset, yet existing systems flatten documents into plain-text chunks, discarding the rich hierarchical structures (sections, tables, figures, equations) and degrading downstream performance. We present DocMaster, a hierarch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08539","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/2607.08539/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":"2607.08539","created_at":"2026-07-10T01:19:53.161746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08539v1","created_at":"2026-07-10T01:19:53.161746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08539","created_at":"2026-07-10T01:19:53.161746+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJU2NITEBIOP","created_at":"2026-07-10T01:19:53.161746+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJU2NITEBIOPBPHR","created_at":"2026-07-10T01:19:53.161746+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJU2NITE","created_at":"2026-07-10T01:19:53.161746+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/VJU2NITEBIOPBPHRUT3WUE4A3Y","json":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y.json","graph_json":"https://pith.science/api/pith-number/VJU2NITEBIOPBPHRUT3WUE4A3Y/graph.json","events_json":"https://pith.science/api/pith-number/VJU2NITEBIOPBPHRUT3WUE4A3Y/events.json","paper":"https://pith.science/paper/VJU2NITE"},"agent_actions":{"view_html":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y","download_json":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y.json","view_paper":"https://pith.science/paper/VJU2NITE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08539&json=true","fetch_graph":"https://pith.science/api/pith-number/VJU2NITEBIOPBPHRUT3WUE4A3Y/graph.json","fetch_events":"https://pith.science/api/pith-number/VJU2NITEBIOPBPHRUT3WUE4A3Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/action/storage_attestation","attest_author":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/action/author_attestation","sign_citation":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/action/citation_signature","submit_replication":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/action/replication_record"}},"created_at":"2026-07-10T01:19:53.161746+00:00","updated_at":"2026-07-10T01:19:53.161746+00:00"}