{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XBX65FJW4TD6C5FRTVAVQ63E5T","short_pith_number":"pith:XBX65FJW","schema_version":"1.0","canonical_sha256":"b86fee9536e4c7e174b19d41587b64ece079dfd87bb13596060a60b4095f2b8a","source":{"kind":"arxiv","id":"2402.07092","version":3},"attestation_state":"computed","paper":{"title":"Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Haonan Chen, Jiongnan Liu, Kelong Mao, Zhicheng Dou, Ziliang Zhao","submitted_at":"2024-02-11T03:27:22Z","abstract_excerpt":"Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses, overlooking the severe data sparsity problem -- that is, users can perform a conversation in various ways, and these alternate conversations are unrecorded. Consequently, they often struggle to generalize to diverse conversations in real-world scenarios. In this work, we propose a framework for generalizing Conversational dense retrieval via LLM-cognition data Augmentation (Con"},"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":"2402.07092","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-11T03:27:22Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"3f84798e37df57cd43e5d5f27797a6bee8b8fd4eb7e6d9e7698d2132c9e8c264","abstract_canon_sha256":"4d97369f73988519b5ae12c3fe0e0ffcb9563596fd024e067bb030c94b577def"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:03.474960Z","signature_b64":"RGZEz2l299lHu3XYn3iSB1IFyx1BW1cZoqLmxZTtb43JroMsJyxLt6kq5iQB8H7f578aVQoeO4ZZlxRXGSX3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b86fee9536e4c7e174b19d41587b64ece079dfd87bb13596060a60b4095f2b8a","last_reissued_at":"2026-07-05T08:27:03.474501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:03.474501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Haonan Chen, Jiongnan Liu, Kelong Mao, Zhicheng Dou, Ziliang Zhao","submitted_at":"2024-02-11T03:27:22Z","abstract_excerpt":"Conversational search utilizes muli-turn natural language contexts to retrieve relevant passages. Existing conversational dense retrieval models mostly view a conversation as a fixed sequence of questions and responses, overlooking the severe data sparsity problem -- that is, users can perform a conversation in various ways, and these alternate conversations are unrecorded. Consequently, they often struggle to generalize to diverse conversations in real-world scenarios. In this work, we propose a framework for generalizing Conversational dense retrieval via LLM-cognition data Augmentation (Con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07092","kind":"arxiv","version":3},"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/2402.07092/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":"2402.07092","created_at":"2026-07-05T08:27:03.474557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07092v3","created_at":"2026-07-05T08:27:03.474557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07092","created_at":"2026-07-05T08:27:03.474557+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBX65FJW4TD6","created_at":"2026-07-05T08:27:03.474557+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBX65FJW4TD6C5FR","created_at":"2026-07-05T08:27:03.474557+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBX65FJW","created_at":"2026-07-05T08:27:03.474557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.21015","citing_title":"Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17174","citing_title":"Modeling Multi-Dimensional Cognitive States in Large Language Models under Cognitive Crowding","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T","json":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T.json","graph_json":"https://pith.science/api/pith-number/XBX65FJW4TD6C5FRTVAVQ63E5T/graph.json","events_json":"https://pith.science/api/pith-number/XBX65FJW4TD6C5FRTVAVQ63E5T/events.json","paper":"https://pith.science/paper/XBX65FJW"},"agent_actions":{"view_html":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T","download_json":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T.json","view_paper":"https://pith.science/paper/XBX65FJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07092&json=true","fetch_graph":"https://pith.science/api/pith-number/XBX65FJW4TD6C5FRTVAVQ63E5T/graph.json","fetch_events":"https://pith.science/api/pith-number/XBX65FJW4TD6C5FRTVAVQ63E5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T/action/storage_attestation","attest_author":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T/action/author_attestation","sign_citation":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T/action/citation_signature","submit_replication":"https://pith.science/pith/XBX65FJW4TD6C5FRTVAVQ63E5T/action/replication_record"}},"created_at":"2026-07-05T08:27:03.474557+00:00","updated_at":"2026-07-05T08:27:03.474557+00:00"}