{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BKEZ74ZR7KO7IL74OIJHQPH7MT","short_pith_number":"pith:BKEZ74ZR","schema_version":"1.0","canonical_sha256":"0a899ff331fa9df42ffc7212783cff64dc7cfec92aa8bdeb886fc36432142741","source":{"kind":"arxiv","id":"2110.07367","version":2},"attestation_state":"computed","paper":{"title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hua Wu, Jing Liu, Ji-Rong Wen, Qiaoqiao She, Ruiyang Ren, Wayne Xin Zhao, Yingqi Qu","submitted_at":"2021-10-14T13:52:55Z","abstract_excerpt":"In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to jointly optimize them in order to achieve mutual improvement. In this paper, we propose a novel joint training approach for dense passage retrieval and passage re-ranking. A major contribution is that we introduce the dynamic listwise distillation, where we design a unified listwise training approach for both the retriever and the re-ranker. During the dyna"},"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":"2110.07367","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T13:52:55Z","cross_cats_sorted":[],"title_canon_sha256":"20f3cd3e391ed1216e63f65267a2cfb70a4e72bcc4ed8b4a6e15d9b40fb435de","abstract_canon_sha256":"55decbf1cb8b966beadb34e5fc3d6be8a383233e45d8f4279f2678fc34285ff5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:22.105891Z","signature_b64":"J9m1WtPwZEfIZJdgRirBEzTlM6VSOo/1/yxHgOIi2OzPqOtXyQUGvihOQZt+EotL0zKpnFiStnd26RJNKsspAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a899ff331fa9df42ffc7212783cff64dc7cfec92aa8bdeb886fc36432142741","last_reissued_at":"2026-07-05T06:03:22.105425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:22.105425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hua Wu, Jing Liu, Ji-Rong Wen, Qiaoqiao She, Ruiyang Ren, Wayne Xin Zhao, Yingqi Qu","submitted_at":"2021-10-14T13:52:55Z","abstract_excerpt":"In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to jointly optimize them in order to achieve mutual improvement. In this paper, we propose a novel joint training approach for dense passage retrieval and passage re-ranking. A major contribution is that we introduce the dynamic listwise distillation, where we design a unified listwise training approach for both the retriever and the re-ranker. During the dyna"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07367","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/2110.07367/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":"2110.07367","created_at":"2026-07-05T06:03:22.105482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07367v2","created_at":"2026-07-05T06:03:22.105482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07367","created_at":"2026-07-05T06:03:22.105482+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKEZ74ZR7KO7","created_at":"2026-07-05T06:03:22.105482+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKEZ74ZR7KO7IL74","created_at":"2026-07-05T06:03:22.105482+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKEZ74ZR","created_at":"2026-07-05T06:03:22.105482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.03216","citing_title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22180","citing_title":"ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07930","citing_title":"Unified Supervision for Walmart's Sponsored Search Retrieval via Joint Semantic Relevance and Behavioral Engagement Modeling","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04734","citing_title":"Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT","json":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT.json","graph_json":"https://pith.science/api/pith-number/BKEZ74ZR7KO7IL74OIJHQPH7MT/graph.json","events_json":"https://pith.science/api/pith-number/BKEZ74ZR7KO7IL74OIJHQPH7MT/events.json","paper":"https://pith.science/paper/BKEZ74ZR"},"agent_actions":{"view_html":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT","download_json":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT.json","view_paper":"https://pith.science/paper/BKEZ74ZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07367&json=true","fetch_graph":"https://pith.science/api/pith-number/BKEZ74ZR7KO7IL74OIJHQPH7MT/graph.json","fetch_events":"https://pith.science/api/pith-number/BKEZ74ZR7KO7IL74OIJHQPH7MT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT/action/storage_attestation","attest_author":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT/action/author_attestation","sign_citation":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT/action/citation_signature","submit_replication":"https://pith.science/pith/BKEZ74ZR7KO7IL74OIJHQPH7MT/action/replication_record"}},"created_at":"2026-07-05T06:03:22.105482+00:00","updated_at":"2026-07-05T06:03:22.105482+00:00"}