{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VJU2NITEBIOPBPHRUT3WUE4A3Y","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4be48a51a5a7f9af10a811a102a20380a28bbad8c2819f258c9d7de21989ed37","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-07-09T14:33:47Z","title_canon_sha256":"704ab7733a92524c3f68cc44f51de4b52b6a4a32e0f00b2d347f87557735978c"},"schema_version":"1.0","source":{"id":"2607.08539","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08539","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08539v1","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08539","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"VJU2NITEBIOP","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_16","alias_value":"VJU2NITEBIOPBPHR","created_at":"2026-07-10T01:19:53Z"},{"alias_kind":"pith_short_8","alias_value":"VJU2NITE","created_at":"2026-07-10T01:19:53Z"}],"graph_snapshots":[{"event_id":"sha256:ca15d2198da47ea2796e7d8d1510f1622ccd96501f88de25946c8f50d21a91ae","target":"graph","created_at":"2026-07-10T01:19:53Z","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/2607.08539/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chuanhui Yang, Fangyuan Zhang, Quanqing Xu, Yingli Zhou, Yixiang Fang, Ziqi Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-07-09T14:33:47Z","title":"DocMaster: A Hierarchical Structure-Aware System for Document Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08539","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:b81c9b1b28b1cdb6659f9763715fa25def5d58fcff48b57bdcb3a7975d2c8a50","target":"record","created_at":"2026-07-10T01:19:53Z","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":"4be48a51a5a7f9af10a811a102a20380a28bbad8c2819f258c9d7de21989ed37","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-07-09T14:33:47Z","title_canon_sha256":"704ab7733a92524c3f68cc44f51de4b52b6a4a32e0f00b2d347f87557735978c"},"schema_version":"1.0","source":{"id":"2607.08539","kind":"arxiv","version":1}},"canonical_sha256":"aa69a6a2640a1cf0bcf1a4f76a1380de247a29935b31f4fa9204d3c41d74b8f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa69a6a2640a1cf0bcf1a4f76a1380de247a29935b31f4fa9204d3c41d74b8f8","first_computed_at":"2026-07-10T01:19:53.161684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:53.161684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AXox/wP1SI4IXoC/SNDxUu2O1GZ+Nf9iEceUzJPrlrWSPKHgCgs4awE1WW4NeM/7pEqk4nJn4l68KHDA3ZmGBw==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:53.162087Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08539","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b81c9b1b28b1cdb6659f9763715fa25def5d58fcff48b57bdcb3a7975d2c8a50","sha256:ca15d2198da47ea2796e7d8d1510f1622ccd96501f88de25946c8f50d21a91ae","sha256:c0248c8315e649b4d243781f4cb09107abf3980b894080e15a524653638e9967"],"state_sha256":"d71df04dbc7f506acb7f129e1e15ce769c13f810790512565cf6ae5b51fb075b"}