{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P2Q2DAFJAQOYMQHK2AOV4FPLTG","short_pith_number":"pith:P2Q2DAFJ","schema_version":"1.0","canonical_sha256":"7ea1a180a9041d8640ead01d5e15eb99827d3980fd924684c173d37cc201d8cd","source":{"kind":"arxiv","id":"2305.15645","version":3},"attestation_state":"computed","paper":{"title":"ConvGQR: Generative Query Reformulation for Conversational Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Fengran Mo, Jian-Yun Nie, Kaiyu Huang, Kelong Mao, Yihong Wu, Yutao Zhu","submitted_at":"2023-05-25T01:45:06Z","abstract_excerpt":"In conversational search, the user's real search intent for the current turn is dependent on the previous conversation history. It is challenging to determine a good search query from the whole conversation context. To avoid the expensive re-training of the query encoder, most existing methods try to learn a rewriting model to de-contextualize the current query by mimicking the manual query rewriting. However, manually rewritten queries are not always the best search queries. Training a rewriting model on them would limit the model's ability to produce good search queries. Another useful hint "},"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":"2305.15645","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2023-05-25T01:45:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b02e05c28d846ddc5faa477d7158e44d9f53821f227c9381e224c633d2ed940e","abstract_canon_sha256":"52bf76a9093148efccc52ece3a496b0fd1c3e2ef6a37173f5d782c05ba254de4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:08.855262Z","signature_b64":"H5+5pFubatFhtMznMQbJ7IDrUDvuceQm+3bXYAcTEooM5NWG96VmxSq5+TvDPaDWKjBSFRDMKW/581hu17CVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ea1a180a9041d8640ead01d5e15eb99827d3980fd924684c173d37cc201d8cd","last_reissued_at":"2026-07-05T07:38:08.854817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:08.854817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConvGQR: Generative Query Reformulation for Conversational Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Fengran Mo, Jian-Yun Nie, Kaiyu Huang, Kelong Mao, Yihong Wu, Yutao Zhu","submitted_at":"2023-05-25T01:45:06Z","abstract_excerpt":"In conversational search, the user's real search intent for the current turn is dependent on the previous conversation history. It is challenging to determine a good search query from the whole conversation context. To avoid the expensive re-training of the query encoder, most existing methods try to learn a rewriting model to de-contextualize the current query by mimicking the manual query rewriting. However, manually rewritten queries are not always the best search queries. Training a rewriting model on them would limit the model's ability to produce good search queries. Another useful hint "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15645","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/2305.15645/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":"2305.15645","created_at":"2026-07-05T07:38:08.854875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15645v3","created_at":"2026-07-05T07:38:08.854875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15645","created_at":"2026-07-05T07:38:08.854875+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2Q2DAFJAQOY","created_at":"2026-07-05T07:38:08.854875+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2Q2DAFJAQOYMQHK","created_at":"2026-07-05T07:38:08.854875+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2Q2DAFJ","created_at":"2026-07-05T07:38:08.854875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26352","citing_title":"RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27421","citing_title":"A Reproducibility Study of LLM-Based Query Reformulation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07201","citing_title":"BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignment","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG","json":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG.json","graph_json":"https://pith.science/api/pith-number/P2Q2DAFJAQOYMQHK2AOV4FPLTG/graph.json","events_json":"https://pith.science/api/pith-number/P2Q2DAFJAQOYMQHK2AOV4FPLTG/events.json","paper":"https://pith.science/paper/P2Q2DAFJ"},"agent_actions":{"view_html":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG","download_json":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG.json","view_paper":"https://pith.science/paper/P2Q2DAFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15645&json=true","fetch_graph":"https://pith.science/api/pith-number/P2Q2DAFJAQOYMQHK2AOV4FPLTG/graph.json","fetch_events":"https://pith.science/api/pith-number/P2Q2DAFJAQOYMQHK2AOV4FPLTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG/action/storage_attestation","attest_author":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG/action/author_attestation","sign_citation":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG/action/citation_signature","submit_replication":"https://pith.science/pith/P2Q2DAFJAQOYMQHK2AOV4FPLTG/action/replication_record"}},"created_at":"2026-07-05T07:38:08.854875+00:00","updated_at":"2026-07-05T07:38:08.854875+00:00"}