{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C4X45NUX265JW2YLBC2X4VDVW7","short_pith_number":"pith:C4X45NUX","schema_version":"1.0","canonical_sha256":"172fceb697d7ba9b6b0b08b57e5475b7f5c3c8e0218fe23c4c8f24bd518ca455","source":{"kind":"arxiv","id":"2602.13830","version":2},"attestation_state":"computed","paper":{"title":"A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dongge Han, Dongmei Zhang, Fangkai Yang, Jue Zhang, Ming Ma, Qingwei Lin, Saravan Rajmohan, Victor R\\\"uhle, Zekun Yao, Zhuofan Shi","submitted_at":"2026-02-14T15:54:38Z","abstract_excerpt":"Open-Ended Deep Research (OEDR) pushes LLM agents beyond short-form QA toward long-horizon workflows that iteratively search, connect, and synthesize evidence into structured reports. However, existing OEDR agents largely follow either linear ``search-then-generate'' accumulation or outline-centric planning. The former suffers from lost-in-the-middle failures as evidence grows, while the latter relies on the LLM to implicitly infer knowledge gaps from the outline alone, providing weak supervision for identifying missing relations and triggering targeted exploration. We present DualGraph memory"},"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":"2602.13830","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-02-14T15:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"26b6a996acc848a7641db1f642fa02770003a77a6481fc1b356faab326b528ba","abstract_canon_sha256":"fabed4df3104c8c9cb1b67c71745360e0db71e4ae0f4a2c2e58517e9e29bd731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:54.408515Z","signature_b64":"di8gwSk/HFMwFVdWuYZ3yuLm+8uIOFYmavS3bx81pEFAfzg0bzizenFSZrvDTJ+Py6zbpKpJMSdo2iQqkUMxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"172fceb697d7ba9b6b0b08b57e5475b7f5c3c8e0218fe23c4c8f24bd518ca455","last_reissued_at":"2026-06-23T03:13:54.408013Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:54.408013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dongge Han, Dongmei Zhang, Fangkai Yang, Jue Zhang, Ming Ma, Qingwei Lin, Saravan Rajmohan, Victor R\\\"uhle, Zekun Yao, Zhuofan Shi","submitted_at":"2026-02-14T15:54:38Z","abstract_excerpt":"Open-Ended Deep Research (OEDR) pushes LLM agents beyond short-form QA toward long-horizon workflows that iteratively search, connect, and synthesize evidence into structured reports. However, existing OEDR agents largely follow either linear ``search-then-generate'' accumulation or outline-centric planning. The former suffers from lost-in-the-middle failures as evidence grows, while the latter relies on the LLM to implicitly infer knowledge gaps from the outline alone, providing weak supervision for identifying missing relations and triggering targeted exploration. We present DualGraph memory"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.13830","kind":"arxiv","version":2},"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/2602.13830/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":"2602.13830","created_at":"2026-06-23T03:13:54.408071+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.13830v2","created_at":"2026-06-23T03:13:54.408071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.13830","created_at":"2026-06-23T03:13:54.408071+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4X45NUX265J","created_at":"2026-06-23T03:13:54.408071+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4X45NUX265JW2YL","created_at":"2026-06-23T03:13:54.408071+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4X45NUX","created_at":"2026-06-23T03:13:54.408071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13034","citing_title":"ViDR: Grounding Multimodal Deep Research Reports in Source Visual Evidence","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7","json":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7.json","graph_json":"https://pith.science/api/pith-number/C4X45NUX265JW2YLBC2X4VDVW7/graph.json","events_json":"https://pith.science/api/pith-number/C4X45NUX265JW2YLBC2X4VDVW7/events.json","paper":"https://pith.science/paper/C4X45NUX"},"agent_actions":{"view_html":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7","download_json":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7.json","view_paper":"https://pith.science/paper/C4X45NUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.13830&json=true","fetch_graph":"https://pith.science/api/pith-number/C4X45NUX265JW2YLBC2X4VDVW7/graph.json","fetch_events":"https://pith.science/api/pith-number/C4X45NUX265JW2YLBC2X4VDVW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7/action/storage_attestation","attest_author":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7/action/author_attestation","sign_citation":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7/action/citation_signature","submit_replication":"https://pith.science/pith/C4X45NUX265JW2YLBC2X4VDVW7/action/replication_record"}},"created_at":"2026-06-23T03:13:54.408071+00:00","updated_at":"2026-06-23T03:13:54.408071+00:00"}