{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PL75D4CXWZPIMIGNEEHMXYRZCE","short_pith_number":"pith:PL75D4CX","schema_version":"1.0","canonical_sha256":"7affd1f057b65e8620cd210ecbe239111e1956f6e24fe50f4dadcb283a8a69e3","source":{"kind":"arxiv","id":"2303.07678","version":2},"attestation_state":"computed","paper":{"title":"Query2doc: Query Expansion with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Furu Wei, Liang Wang, Nan Yang","submitted_at":"2023-03-14T07:27:30Z","abstract_excerpt":"This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first generates pseudo-documents by few-shot prompting large language models (LLMs), and then expands the query with generated pseudo-documents. LLMs are trained on web-scale text corpora and are adept at knowledge memorization. The pseudo-documents from LLMs often contain highly relevant information that can aid in query disambiguation and guide the retrievers. Experimental results demonstrate that query2doc boosts the performance"},"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":"2303.07678","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-03-14T07:27:30Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"00b1b4b0ec849edf4dd5ae857edb432e0b8ea26751734e48651142e25a68bfd9","abstract_canon_sha256":"d749fa2f1435eea53d076f83dff9f0b22a21a63ab3c8031c62a7ae3b7ccb7665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:30.381311Z","signature_b64":"0/tfbgYuvs/vlQJTu83SYUw2udw1SsdV5Hr7LbOv0I8vTgCndDdT+DctBz13i0qsoN8ySMQCf+NZGRzCmeenBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7affd1f057b65e8620cd210ecbe239111e1956f6e24fe50f4dadcb283a8a69e3","last_reissued_at":"2026-07-05T06:59:30.380949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:30.380949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query2doc: Query Expansion with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Furu Wei, Liang Wang, Nan Yang","submitted_at":"2023-03-14T07:27:30Z","abstract_excerpt":"This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems. The proposed method first generates pseudo-documents by few-shot prompting large language models (LLMs), and then expands the query with generated pseudo-documents. LLMs are trained on web-scale text corpora and are adept at knowledge memorization. The pseudo-documents from LLMs often contain highly relevant information that can aid in query disambiguation and guide the retrievers. Experimental results demonstrate that query2doc boosts the performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.07678","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/2303.07678/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":"2303.07678","created_at":"2026-07-05T06:59:30.381005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.07678v2","created_at":"2026-07-05T06:59:30.381005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.07678","created_at":"2026-07-05T06:59:30.381005+00:00"},{"alias_kind":"pith_short_12","alias_value":"PL75D4CXWZPI","created_at":"2026-07-05T06:59:30.381005+00:00"},{"alias_kind":"pith_short_16","alias_value":"PL75D4CXWZPIMIGN","created_at":"2026-07-05T06:59:30.381005+00:00"},{"alias_kind":"pith_short_8","alias_value":"PL75D4CX","created_at":"2026-07-05T06:59:30.381005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27291","citing_title":"Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28566","citing_title":"R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26352","citing_title":"RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14751","citing_title":"Query pipeline optimization for cancer patient question answering systems","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16479","citing_title":"Policy-Grounded Dynamic Facet Suggestions for Job Search","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07794","citing_title":"Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17667","citing_title":"When & How to Write for Personalized Demand-aware Query Rewriting in Video Search","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27421","citing_title":"A Reproducibility Study of LLM-Based Query Reformulation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22661","citing_title":"Can QPP Choose the Right Query Variant? Evaluating Query Variant Selection for RAG Pipelines","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05538","citing_title":"AgenticRAG: Agentic Retrieval for Enterprise Knowledge Bases","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07201","citing_title":"BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07079","citing_title":"MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17543","citing_title":"PoliLegalLM: A Technical Report on a Large Language Model for Political and Legal Affairs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02411","citing_title":"FitText: Evolving Agent Tool Ecologies via Memetic Retrieval","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE","json":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE.json","graph_json":"https://pith.science/api/pith-number/PL75D4CXWZPIMIGNEEHMXYRZCE/graph.json","events_json":"https://pith.science/api/pith-number/PL75D4CXWZPIMIGNEEHMXYRZCE/events.json","paper":"https://pith.science/paper/PL75D4CX"},"agent_actions":{"view_html":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE","download_json":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE.json","view_paper":"https://pith.science/paper/PL75D4CX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.07678&json=true","fetch_graph":"https://pith.science/api/pith-number/PL75D4CXWZPIMIGNEEHMXYRZCE/graph.json","fetch_events":"https://pith.science/api/pith-number/PL75D4CXWZPIMIGNEEHMXYRZCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE/action/storage_attestation","attest_author":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE/action/author_attestation","sign_citation":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE/action/citation_signature","submit_replication":"https://pith.science/pith/PL75D4CXWZPIMIGNEEHMXYRZCE/action/replication_record"}},"created_at":"2026-07-05T06:59:30.381005+00:00","updated_at":"2026-07-05T06:59:30.381005+00:00"}