{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LD4XZDQWDPVA5OUNKYDUOH6RON","short_pith_number":"pith:LD4XZDQW","schema_version":"1.0","canonical_sha256":"58f97c8e161bea0eba8d5607471fd17346b3ec2ea6f98eaf40b42c80d24c57fc","source":{"kind":"arxiv","id":"2308.08285","version":1},"attestation_state":"computed","paper":{"title":"Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Guangyuan Ma, Peng Wang, Songlin Hu, Xing Wu, Zijia Lin","submitted_at":"2023-08-16T11:10:43Z","abstract_excerpt":"In this paper, we systematically study the potential of pre-training with Large Language Model(LLM)-based document expansion for dense passage retrieval. Concretely, we leverage the capabilities of LLMs for document expansion, i.e. query generation, and effectively transfer expanded knowledge to retrievers using pre-training strategies tailored for passage retrieval. These strategies include contrastive learning and bottlenecked query generation. Furthermore, we incorporate a curriculum learning strategy to reduce the reliance on LLM inferences. Experimental results demonstrate that pre-traini"},"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":"2308.08285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-08-16T11:10:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d13815c489fcc4ddcb217ddf8712ea470b9527ecd30ba6ab8e8b584632bcaf16","abstract_canon_sha256":"7b2e73203147776b9567701f7d17cbb7521fa74faccfafb6baba2f5172c85e35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:57.356661Z","signature_b64":"z0HKGQ61S8OdwUQL58ciLb9UfSG/4MY8vkMKLHCfennCdIVNvuplXYFncRBuPeLm5rqLLc1Y2txJtdnCJi06DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58f97c8e161bea0eba8d5607471fd17346b3ec2ea6f98eaf40b42c80d24c57fc","last_reissued_at":"2026-07-05T06:41:57.356142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:57.356142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Guangyuan Ma, Peng Wang, Songlin Hu, Xing Wu, Zijia Lin","submitted_at":"2023-08-16T11:10:43Z","abstract_excerpt":"In this paper, we systematically study the potential of pre-training with Large Language Model(LLM)-based document expansion for dense passage retrieval. Concretely, we leverage the capabilities of LLMs for document expansion, i.e. query generation, and effectively transfer expanded knowledge to retrievers using pre-training strategies tailored for passage retrieval. These strategies include contrastive learning and bottlenecked query generation. Furthermore, we incorporate a curriculum learning strategy to reduce the reliance on LLM inferences. Experimental results demonstrate that pre-traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08285","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/2308.08285/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":"2308.08285","created_at":"2026-07-05T06:41:57.356208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.08285v1","created_at":"2026-07-05T06:41:57.356208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08285","created_at":"2026-07-05T06:41:57.356208+00:00"},{"alias_kind":"pith_short_12","alias_value":"LD4XZDQWDPVA","created_at":"2026-07-05T06:41:57.356208+00:00"},{"alias_kind":"pith_short_16","alias_value":"LD4XZDQWDPVA5OUN","created_at":"2026-07-05T06:41:57.356208+00:00"},{"alias_kind":"pith_short_8","alias_value":"LD4XZDQW","created_at":"2026-07-05T06:41:57.356208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17250","citing_title":"SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON","json":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON.json","graph_json":"https://pith.science/api/pith-number/LD4XZDQWDPVA5OUNKYDUOH6RON/graph.json","events_json":"https://pith.science/api/pith-number/LD4XZDQWDPVA5OUNKYDUOH6RON/events.json","paper":"https://pith.science/paper/LD4XZDQW"},"agent_actions":{"view_html":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON","download_json":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON.json","view_paper":"https://pith.science/paper/LD4XZDQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.08285&json=true","fetch_graph":"https://pith.science/api/pith-number/LD4XZDQWDPVA5OUNKYDUOH6RON/graph.json","fetch_events":"https://pith.science/api/pith-number/LD4XZDQWDPVA5OUNKYDUOH6RON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON/action/storage_attestation","attest_author":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON/action/author_attestation","sign_citation":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON/action/citation_signature","submit_replication":"https://pith.science/pith/LD4XZDQWDPVA5OUNKYDUOH6RON/action/replication_record"}},"created_at":"2026-07-05T06:41:57.356208+00:00","updated_at":"2026-07-05T06:41:57.356208+00:00"}