{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7ZPIEZFZK6ZBEMQI3XV3LWVNTZ","short_pith_number":"pith:7ZPIEZFZ","schema_version":"1.0","canonical_sha256":"fe5e8264b957b2123208ddebb5daad9e5c9304446a9ceaf26d995db068a7f164","source":{"kind":"arxiv","id":"2506.19783","version":2},"attestation_state":"computed","paper":{"title":"SAGE: Strategy-Adaptive Generation Engine for Query Rewriting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changwang Zhang, Hailei Gong, Jun Wang, Teng Wang","submitted_at":"2025-06-24T16:50:51Z","abstract_excerpt":"Query rewriting is pivotal for enhancing dense retrieval, yet current methods demand large-scale supervised data or suffer from inefficient reinforcement learning (RL) exploration. In this work, we first establish that guiding Large Language Models (LLMs) with a concise set of expert-crafted strategies, such as semantic expansion and entity disambiguation, substantially improves retrieval effectiveness on challenging benchmarks, including HotpotQA, FEVER, NFCorpus, and SciFact. Building on this insight, we introduce the Strategy-Adaptive Generation Engine (SAGE), which operationalizes these st"},"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":"2506.19783","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-24T16:50:51Z","cross_cats_sorted":[],"title_canon_sha256":"99faead3d48a22c49cb77206cc710b987b73e9c498213729fca94c333ea92a18","abstract_canon_sha256":"1e3fef3a5e83dee40ac7993d1f0369d3d95d244cc42032c3f0220aca6bf9a857"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:32.997536Z","signature_b64":"5Hqd5X/1AXSUi5jA9x6owo94bGOyKcSiHvUy6PDRp2Jtd+loscSl4JWvbWrCljDQ7VEVkNAjwFX6XGEQ2ZLxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe5e8264b957b2123208ddebb5daad9e5c9304446a9ceaf26d995db068a7f164","last_reissued_at":"2026-07-05T11:43:32.997068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:32.997068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAGE: Strategy-Adaptive Generation Engine for Query Rewriting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Changwang Zhang, Hailei Gong, Jun Wang, Teng Wang","submitted_at":"2025-06-24T16:50:51Z","abstract_excerpt":"Query rewriting is pivotal for enhancing dense retrieval, yet current methods demand large-scale supervised data or suffer from inefficient reinforcement learning (RL) exploration. In this work, we first establish that guiding Large Language Models (LLMs) with a concise set of expert-crafted strategies, such as semantic expansion and entity disambiguation, substantially improves retrieval effectiveness on challenging benchmarks, including HotpotQA, FEVER, NFCorpus, and SciFact. Building on this insight, we introduce the Strategy-Adaptive Generation Engine (SAGE), which operationalizes these st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19783","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/2506.19783/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":"2506.19783","created_at":"2026-07-05T11:43:32.997123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19783v2","created_at":"2026-07-05T11:43:32.997123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19783","created_at":"2026-07-05T11:43:32.997123+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZPIEZFZK6ZB","created_at":"2026-07-05T11:43:32.997123+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZPIEZFZK6ZBEMQI","created_at":"2026-07-05T11:43:32.997123+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZPIEZFZ","created_at":"2026-07-05T11:43:32.997123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ","json":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ.json","graph_json":"https://pith.science/api/pith-number/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/graph.json","events_json":"https://pith.science/api/pith-number/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/events.json","paper":"https://pith.science/paper/7ZPIEZFZ"},"agent_actions":{"view_html":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ","download_json":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ.json","view_paper":"https://pith.science/paper/7ZPIEZFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19783&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/action/storage_attestation","attest_author":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/action/author_attestation","sign_citation":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/action/citation_signature","submit_replication":"https://pith.science/pith/7ZPIEZFZK6ZBEMQI3XV3LWVNTZ/action/replication_record"}},"created_at":"2026-07-05T11:43:32.997123+00:00","updated_at":"2026-07-05T11:43:32.997123+00:00"}