{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y66ZIUSITJDWAJ5CCNJNRKC5CQ","short_pith_number":"pith:Y66ZIUSI","schema_version":"1.0","canonical_sha256":"c7bd9452489a476027a21352d8a85d141fe42b7ab0cd7362d6a228493a0e6dec","source":{"kind":"arxiv","id":"2308.00415","version":1},"attestation_state":"computed","paper":{"title":"Generative Query Reformulation for Effective Adhoc Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Craig Macdonald, Iadh Ounis, Sean MacAvaney, Xiao Wang","submitted_at":"2023-08-01T09:51:35Z","abstract_excerpt":"Performing automatic reformulations of a user's query is a popular paradigm used in information retrieval (IR) for improving effectiveness -- as exemplified by the pseudo-relevance feedback approaches, which expand the query in order to alleviate the vocabulary mismatch problem. Recent advancements in generative language models have demonstrated their ability in generating responses that are relevant to a given prompt. In light of this success, we seek to study the capacity of such models to perform query reformulation and how they compare with long-standing query reformulation methods that us"},"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":"2308.00415","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2023-08-01T09:51:35Z","cross_cats_sorted":[],"title_canon_sha256":"dcb834fdf32ef0dd4b1b4130114f17d9f516f9ca1ff1a469427ac60cf42588f2","abstract_canon_sha256":"8bd77f44b554869f1db57a571fb2fb84076a04e47fb5945c9c66526c46f4fc99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:47.237430Z","signature_b64":"oF60jSY3IUN8tSTfCz1/CUwSRyAzSxUFQN/Kj56O98j9niA4+VeBc+gJxVz/R0pG2GMgRhTAHdK6axofcaTWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7bd9452489a476027a21352d8a85d141fe42b7ab0cd7362d6a228493a0e6dec","last_reissued_at":"2026-07-05T06:36:47.237018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:47.237018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Query Reformulation for Effective Adhoc Search","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Craig Macdonald, Iadh Ounis, Sean MacAvaney, Xiao Wang","submitted_at":"2023-08-01T09:51:35Z","abstract_excerpt":"Performing automatic reformulations of a user's query is a popular paradigm used in information retrieval (IR) for improving effectiveness -- as exemplified by the pseudo-relevance feedback approaches, which expand the query in order to alleviate the vocabulary mismatch problem. Recent advancements in generative language models have demonstrated their ability in generating responses that are relevant to a given prompt. In light of this success, we seek to study the capacity of such models to perform query reformulation and how they compare with long-standing query reformulation methods that us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00415","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/2308.00415/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":"2308.00415","created_at":"2026-07-05T06:36:47.237068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.00415v1","created_at":"2026-07-05T06:36:47.237068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00415","created_at":"2026-07-05T06:36:47.237068+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y66ZIUSITJDW","created_at":"2026-07-05T06:36:47.237068+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y66ZIUSITJDWAJ5C","created_at":"2026-07-05T06:36:47.237068+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y66ZIUSI","created_at":"2026-07-05T06:36:47.237068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22501","citing_title":"BeLink: Biomedical Entity Linking Meets Generative Re-Ranking","ref_index":26,"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":108,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27421","citing_title":"A Reproducibility Study of LLM-Based Query Reformulation","ref_index":36,"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":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00560","citing_title":"When More Reformulations Hurt: Avoiding Drift using Ranker Feedback","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ","json":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ.json","graph_json":"https://pith.science/api/pith-number/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/graph.json","events_json":"https://pith.science/api/pith-number/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/events.json","paper":"https://pith.science/paper/Y66ZIUSI"},"agent_actions":{"view_html":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ","download_json":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ.json","view_paper":"https://pith.science/paper/Y66ZIUSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.00415&json=true","fetch_graph":"https://pith.science/api/pith-number/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/action/storage_attestation","attest_author":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/action/author_attestation","sign_citation":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/action/citation_signature","submit_replication":"https://pith.science/pith/Y66ZIUSITJDWAJ5CCNJNRKC5CQ/action/replication_record"}},"created_at":"2026-07-05T06:36:47.237068+00:00","updated_at":"2026-07-05T06:36:47.237068+00:00"}