{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VJU2NITEBIOPBPHRUT3WUE4A3Y","short_pith_number":"pith:VJU2NITE","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"},"canonical_sha256":"aa69a6a2640a1cf0bcf1a4f76a1380de247a29935b31f4fa9204d3c41d74b8f8","source":{"kind":"arxiv","id":"2607.08539","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VJU2NITEBIOPBPHRUT3WUE4A3Y","target":"record","payload":{"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"},"canonical_sha256":"aa69a6a2640a1cf0bcf1a4f76a1380de247a29935b31f4fa9204d3c41d74b8f8","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"},"source_kind":"arxiv","source_id":"2607.08539","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":"2026-07-10T01:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cHi+V+vpJTA4U8t7aZXnv6dzN1lGgOxx4w2z53zQrLX45Ret95lhZQT6dNoATZ++99U+6dDcPa2HpheG5LCfCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:02:05.871078Z"},"content_sha256":"b81c9b1b28b1cdb6659f9763715fa25def5d58fcff48b57bdcb3a7975d2c8a50","schema_version":"1.0","event_id":"sha256:b81c9b1b28b1cdb6659f9763715fa25def5d58fcff48b57bdcb3a7975d2c8a50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VJU2NITEBIOPBPHRUT3WUE4A3Y","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-10T01:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/u8lMmp6ML/DgrYyhnzdi8UrNi+u0/F4yoyKpUoBcs0gOb+uaBMKLOEokBfLOMwFipcwB62dfiuuXidd6YSXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:02:05.871993Z"},"content_sha256":"ca15d2198da47ea2796e7d8d1510f1622ccd96501f88de25946c8f50d21a91ae","schema_version":"1.0","event_id":"sha256:ca15d2198da47ea2796e7d8d1510f1622ccd96501f88de25946c8f50d21a91ae"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:VJU2NITEBIOPBPHRUT3WUE4A3Y","target":"integrity","payload":{"note":"Identifier '10.5281/zenodo.1234' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Jerry Liu. 2022.LlamaIndex. doi:10.5281/zenodo.1234","arxiv_id":"2607.08539","detector":"doi_compliance","evidence":{"doi":"10.5281/zenodo.1234","arxiv_id":null,"ref_index":9,"raw_excerpt":"Jerry Liu. 2022.LlamaIndex. doi:10.5281/zenodo.1234","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":9,"audited_at":"2026-07-10T05:52:01.662349Z","event_type":"pith.integrity.v1","detected_doi":"10.5281/zenodo.1234","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"fce6c99d2f333c02a144b48605484cb941a742344800aa22e97a9aedaee7aea4","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":11889,"payload_sha256":"a77d8b8288fe24eedf318edb2ab4f2534fb5f357f83e4904885bf28d8162354f","signature_b64":"+kieiapw1iXf/BDq/povL7Q92+/PLJS7s3vPh6HzxEcO/7CJ+jmGHuWHu5LEiWYp3eSUmJODHXUy8tz415o+CQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-10T05:53:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nZ3W8IhOgv7k6myHliUR784W/ynwzdeAQlumiaH1LqhfQSIy4/slOioWR8/aNIqCoG86x0RfAEo08ciZOs/6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:02:05.895657Z"},"content_sha256":"c0248c8315e649b4d243781f4cb09107abf3980b894080e15a524653638e9967","schema_version":"1.0","event_id":"sha256:c0248c8315e649b4d243781f4cb09107abf3980b894080e15a524653638e9967"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/bundle.json","state_url":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/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":"2026-08-05T18:02:05Z","links":{"resolver":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y","bundle":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/bundle.json","state":"https://pith.science/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJU2NITEBIOPBPHRUT3WUE4A3Y/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"14Rk6TlxpYZT3r0Do1wnrm+EqD+WQjwxCJ7Vx3tHsDOXkF8CBMcOyBXxQO+MfVkBa39/DQgUry2c2tuaP3qdAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:02:05.899411Z","bundle_sha256":"b5c3b2126c5c327dc68c0cb5c34b9e756b318c7a2a1dd8ceb6ff1630a58c1a9a"}}