{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HG2JUZ7NGXHFE2Y5WZAFQMHBZK","short_pith_number":"pith:HG2JUZ7N","schema_version":"1.0","canonical_sha256":"39b49a67ed35ce526b1db6405830e1ca9b43f9374b97646ac8f758a9e7d8426a","source":{"kind":"arxiv","id":"2606.10921","version":1},"attestation_state":"computed","paper":{"title":"Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Chen, Wenjie Zhang, Xiangjun Zai, Xiaoyang Wang, Xingyu Tan","submitted_at":"2026-06-09T14:29:06Z","abstract_excerpt":"Long-document question answering (QA) requires large language models (LLMs) to reason over evidence scattered across lengthy documents, where answers often depend on event order, section-level context, and cross-part evidence connections. Although retrieval-augmented generation (RAG) reduces the input context by retrieving relevant evidence, existing structured RAG methods still face three limitations: costly query-agnostic knowledge organization, insufficient use of original document structure, and no reuse of historical reasoning experience. To address these limitations, we propose DocTrace,"},"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":"2606.10921","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-09T14:29:06Z","cross_cats_sorted":[],"title_canon_sha256":"03e4933bd2b011fb97cf3b1e581a6aef161c30ac34b149ac5dacfa55a5de7f0e","abstract_canon_sha256":"543d6732f173f21e42f69d0375b6ceb28aa2a4b5bc465b9595e564c671714001"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:48.238520Z","signature_b64":"IfSGrJV1tWTBgPYnfD+obZ9WDfYvyX1EYVUcWklt82JRcApWmDBPLlsRu8ty9qGBdyKjwe0UmK+4iadWSli3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39b49a67ed35ce526b1db6405830e1ca9b43f9374b97646ac8f758a9e7d8426a","last_reissued_at":"2026-06-10T01:10:48.237656Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:48.237656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Chen, Wenjie Zhang, Xiangjun Zai, Xiaoyang Wang, Xingyu Tan","submitted_at":"2026-06-09T14:29:06Z","abstract_excerpt":"Long-document question answering (QA) requires large language models (LLMs) to reason over evidence scattered across lengthy documents, where answers often depend on event order, section-level context, and cross-part evidence connections. Although retrieval-augmented generation (RAG) reduces the input context by retrieving relevant evidence, existing structured RAG methods still face three limitations: costly query-agnostic knowledge organization, insufficient use of original document structure, and no reuse of historical reasoning experience. To address these limitations, we propose DocTrace,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10921","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/2606.10921/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":"2606.10921","created_at":"2026-06-10T01:10:48.237793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10921v1","created_at":"2026-06-10T01:10:48.237793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10921","created_at":"2026-06-10T01:10:48.237793+00:00"},{"alias_kind":"pith_short_12","alias_value":"HG2JUZ7NGXHF","created_at":"2026-06-10T01:10:48.237793+00:00"},{"alias_kind":"pith_short_16","alias_value":"HG2JUZ7NGXHFE2Y5","created_at":"2026-06-10T01:10:48.237793+00:00"},{"alias_kind":"pith_short_8","alias_value":"HG2JUZ7N","created_at":"2026-06-10T01:10:48.237793+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/HG2JUZ7NGXHFE2Y5WZAFQMHBZK","json":"https://pith.science/pith/HG2JUZ7NGXHFE2Y5WZAFQMHBZK.json","graph_json":"https://pith.science/api/pith-number/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/graph.json","events_json":"https://pith.science/api/pith-number/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/events.json","paper":"https://pith.science/paper/HG2JUZ7N"},"agent_actions":{"view_html":"https://pith.science/pith/HG2JUZ7NGXHFE2Y5WZAFQMHBZK","download_json":"https://pith.science/pith/HG2JUZ7NGXHFE2Y5WZAFQMHBZK.json","view_paper":"https://pith.science/paper/HG2JUZ7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10921&json=true","fetch_graph":"https://pith.science/api/pith-number/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/graph.json","fetch_events":"https://pith.science/api/pith-number/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/action/storage_attestation","attest_author":"https://pith.science/pith/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/action/author_attestation","sign_citation":"https://pith.science/pith/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/action/citation_signature","submit_replication":"https://pith.science/pith/HG2JUZ7NGXHFE2Y5WZAFQMHBZK/action/replication_record"}},"created_at":"2026-06-10T01:10:48.237793+00:00","updated_at":"2026-06-10T01:10:48.237793+00:00"}