{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EDPRKAKADITWNCHWZSO6RTBNQQ","short_pith_number":"pith:EDPRKAKA","schema_version":"1.0","canonical_sha256":"20df1501401a276688f6cc9de8cc2d841bda8a58f17903090a54038ef3f35353","source":{"kind":"arxiv","id":"2504.10208","version":3},"attestation_state":"computed","paper":{"title":"From Prompting to Alignment: A Generative Framework for Query Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Dawei Yin, Erxue Min, Hengyi Cai, Hsiu-Yuan Huang, Junfeng Wang, Min Yang, Shuaiqiang Wang, Xihong Yang, Xin Jia, Yunfang Wu","submitted_at":"2025-04-14T13:21:29Z","abstract_excerpt":"In modern search systems, search engines often suggest relevant queries to users through various panels or components, helping refine their information needs. Traditionally, these recommendations heavily rely on historical search logs to build models, which suffer from cold-start or long-tail issues. Furthermore, tasks such as query suggestion, completion or clarification are studied separately by specific design, which lacks generalizability and hinders adaptation to novel applications. Despite recent attempts to explore the use of LLMs for query recommendation, these methods mainly rely on t"},"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":"2504.10208","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-14T13:21:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"108e54c5a8a76b7bd8710d3fe43dda72eca11efb5b4f09ab7a1a4ba5e00d9614","abstract_canon_sha256":"96125afe9642597f60b4cb94e6ce3ae6f6bd1c976556904d07cafabf5fce59d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:28.078223Z","signature_b64":"9CXcMnHMJUiHdRBfRONPQqeXd4T8yQ8M2JoKo5seJQYxcDNMjfBXWNYsOlO0d8Y0MXpHEqpSJq5XRIN9DZJ3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20df1501401a276688f6cc9de8cc2d841bda8a58f17903090a54038ef3f35353","last_reissued_at":"2026-07-05T11:32:28.077726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:28.077726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Prompting to Alignment: A Generative Framework for Query Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Dawei Yin, Erxue Min, Hengyi Cai, Hsiu-Yuan Huang, Junfeng Wang, Min Yang, Shuaiqiang Wang, Xihong Yang, Xin Jia, Yunfang Wu","submitted_at":"2025-04-14T13:21:29Z","abstract_excerpt":"In modern search systems, search engines often suggest relevant queries to users through various panels or components, helping refine their information needs. Traditionally, these recommendations heavily rely on historical search logs to build models, which suffer from cold-start or long-tail issues. Furthermore, tasks such as query suggestion, completion or clarification are studied separately by specific design, which lacks generalizability and hinders adaptation to novel applications. Despite recent attempts to explore the use of LLMs for query recommendation, these methods mainly rely on t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10208","kind":"arxiv","version":3},"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/2504.10208/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":"2504.10208","created_at":"2026-07-05T11:32:28.077786+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10208v3","created_at":"2026-07-05T11:32:28.077786+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10208","created_at":"2026-07-05T11:32:28.077786+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDPRKAKADITW","created_at":"2026-07-05T11:32:28.077786+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDPRKAKADITWNCHW","created_at":"2026-07-05T11:32:28.077786+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDPRKAKA","created_at":"2026-07-05T11:32:28.077786+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20408","citing_title":"Spectral Souping: A Unified Framework for Online Preference Alignment","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05855","citing_title":"Bridging Passive and Active: Enhancing Conversation Starter Recommendation via Active Expression Modeling","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ","json":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ.json","graph_json":"https://pith.science/api/pith-number/EDPRKAKADITWNCHWZSO6RTBNQQ/graph.json","events_json":"https://pith.science/api/pith-number/EDPRKAKADITWNCHWZSO6RTBNQQ/events.json","paper":"https://pith.science/paper/EDPRKAKA"},"agent_actions":{"view_html":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ","download_json":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ.json","view_paper":"https://pith.science/paper/EDPRKAKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10208&json=true","fetch_graph":"https://pith.science/api/pith-number/EDPRKAKADITWNCHWZSO6RTBNQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/EDPRKAKADITWNCHWZSO6RTBNQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ/action/storage_attestation","attest_author":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ/action/author_attestation","sign_citation":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ/action/citation_signature","submit_replication":"https://pith.science/pith/EDPRKAKADITWNCHWZSO6RTBNQQ/action/replication_record"}},"created_at":"2026-07-05T11:32:28.077786+00:00","updated_at":"2026-07-05T11:32:28.077786+00:00"}