{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RYXQ4Q32SXJQEAFSJV6G2MQ7IG","short_pith_number":"pith:RYXQ4Q32","schema_version":"1.0","canonical_sha256":"8e2f0e437a95d30200b24d7c6d321f419ef58b1e61979ea6ba9a957ad48da6cc","source":{"kind":"arxiv","id":"2506.04760","version":1},"attestation_state":"computed","paper":{"title":"Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Lingyuan Liu, Mengxiang Zhang","submitted_at":"2025-06-05T08:44:34Z","abstract_excerpt":"Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion, thereby enhancing information retrieval performance. However, the efficacy of this method is highly dependent on the quality of the generated documents, which often requires complex prompt strategies and the integration of advanced dense retrieval techniques. This can be both costly and computationally intensive. To mitigate these limitations, we explore the use of zero-shot LLM-based query expansion to improve sparse retrieval, particularly for learned sparse retrievers. We introduce a "},"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":"2506.04760","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-05T08:44:34Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"14816396d164c8a28cddc293132a3d73ad949468629189146b68a070a43a6bec","abstract_canon_sha256":"5e86fdd1920eb54c985bd9505d818054c597632e57a8b17d1e088fb51a85f11d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:43.456391Z","signature_b64":"Ee+rucOumAug8kYWy8wGKt3xz6UFL6CPdM/4fnBofaUcyHH+AdUC1Ni/urOI/YKnmJjiZDB48UKVi1aPJmOdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e2f0e437a95d30200b24d7c6d321f419ef58b1e61979ea6ba9a957ad48da6cc","last_reissued_at":"2026-07-05T11:18:43.455966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:43.455966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Lingyuan Liu, Mengxiang Zhang","submitted_at":"2025-06-05T08:44:34Z","abstract_excerpt":"Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion, thereby enhancing information retrieval performance. However, the efficacy of this method is highly dependent on the quality of the generated documents, which often requires complex prompt strategies and the integration of advanced dense retrieval techniques. This can be both costly and computationally intensive. To mitigate these limitations, we explore the use of zero-shot LLM-based query expansion to improve sparse retrieval, particularly for learned sparse retrievers. We introduce a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04760","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/2506.04760/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":"2506.04760","created_at":"2026-07-05T11:18:43.456015+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04760v1","created_at":"2026-07-05T11:18:43.456015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04760","created_at":"2026-07-05T11:18:43.456015+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYXQ4Q32SXJQ","created_at":"2026-07-05T11:18:43.456015+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYXQ4Q32SXJQEAFS","created_at":"2026-07-05T11:18:43.456015+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYXQ4Q32","created_at":"2026-07-05T11:18:43.456015+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.07794","citing_title":"Query Expansion in the Age of Pre-trained and Large Language Models: A Comprehensive Survey","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG","json":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG.json","graph_json":"https://pith.science/api/pith-number/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/graph.json","events_json":"https://pith.science/api/pith-number/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/events.json","paper":"https://pith.science/paper/RYXQ4Q32"},"agent_actions":{"view_html":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG","download_json":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG.json","view_paper":"https://pith.science/paper/RYXQ4Q32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04760&json=true","fetch_graph":"https://pith.science/api/pith-number/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/graph.json","fetch_events":"https://pith.science/api/pith-number/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/action/storage_attestation","attest_author":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/action/author_attestation","sign_citation":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/action/citation_signature","submit_replication":"https://pith.science/pith/RYXQ4Q32SXJQEAFSJV6G2MQ7IG/action/replication_record"}},"created_at":"2026-07-05T11:18:43.456015+00:00","updated_at":"2026-07-05T11:18:43.456015+00:00"}