{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HRLJC4LYK62YMH6PBBUEYDBPNR","short_pith_number":"pith:HRLJC4LY","schema_version":"1.0","canonical_sha256":"3c5691717857b5861fcf08684c0c2f6c65ac5e36b5804cc824975d646fb77e0c","source":{"kind":"arxiv","id":"2509.18736","version":5},"attestation_state":"computed","paper":{"title":"Denoising Neural Reranker for Recommender Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"An Zhang, Hailan Yang, Han Li, Kun Gai, Lantao Hu, Shuchang Liu, Wenyu Mao, Xiang Li, Xiang Wang, Xiaobei Wang, Xiaoyu Yang, Xu Gao","submitted_at":"2025-09-23T07:29:52Z","abstract_excerpt":"For multi-stage recommenders in industry, a user request would first trigger a simple and efficient retriever module that selects and ranks a list of relevant items, then the recommender calls a slower but more sophisticated reranking model that refines the item list exposure to the user. To consistently optimize the two-stage retrieval reranking framework, most efforts have focused on learning reranker-aware retrievers. In contrast, there has been limited work on how to achieve a retriever-aware reranker. In this work, we provide evidence that the retriever scores from the previous stage are "},"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":"2509.18736","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-09-23T07:29:52Z","cross_cats_sorted":[],"title_canon_sha256":"8e5e3d4327716e5dbd83ec2fb814910efd52d7f46bc996aca12977699390d382","abstract_canon_sha256":"15a659b34f748fe95cec76b8945370ef2f01369dec77ab76fb4cbe8bc8eefb2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:13.492300Z","signature_b64":"t9jEhPFK2OT3bA6nXMqH+apbwcH6BOdlx6n5C1ArrkprajoHmJfRZiHwC53nU/iI7PJISiyyN+UhHo/eW1m7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c5691717857b5861fcf08684c0c2f6c65ac5e36b5804cc824975d646fb77e0c","last_reissued_at":"2026-05-20T00:04:13.491494Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:13.491494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Denoising Neural Reranker for Recommender Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"An Zhang, Hailan Yang, Han Li, Kun Gai, Lantao Hu, Shuchang Liu, Wenyu Mao, Xiang Li, Xiang Wang, Xiaobei Wang, Xiaoyu Yang, Xu Gao","submitted_at":"2025-09-23T07:29:52Z","abstract_excerpt":"For multi-stage recommenders in industry, a user request would first trigger a simple and efficient retriever module that selects and ranks a list of relevant items, then the recommender calls a slower but more sophisticated reranking model that refines the item list exposure to the user. To consistently optimize the two-stage retrieval reranking framework, most efforts have focused on learning reranker-aware retrievers. In contrast, there has been limited work on how to achieve a retriever-aware reranker. In this work, we provide evidence that the retriever scores from the previous stage are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.18736","kind":"arxiv","version":5},"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/2509.18736/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":"2509.18736","created_at":"2026-05-20T00:04:13.491639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.18736v5","created_at":"2026-05-20T00:04:13.491639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.18736","created_at":"2026-05-20T00:04:13.491639+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRLJC4LYK62Y","created_at":"2026-05-20T00:04:13.491639+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRLJC4LYK62YMH6P","created_at":"2026-05-20T00:04:13.491639+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRLJC4LY","created_at":"2026-05-20T00:04:13.491639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.25291","citing_title":"From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR","json":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR.json","graph_json":"https://pith.science/api/pith-number/HRLJC4LYK62YMH6PBBUEYDBPNR/graph.json","events_json":"https://pith.science/api/pith-number/HRLJC4LYK62YMH6PBBUEYDBPNR/events.json","paper":"https://pith.science/paper/HRLJC4LY"},"agent_actions":{"view_html":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR","download_json":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR.json","view_paper":"https://pith.science/paper/HRLJC4LY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.18736&json=true","fetch_graph":"https://pith.science/api/pith-number/HRLJC4LYK62YMH6PBBUEYDBPNR/graph.json","fetch_events":"https://pith.science/api/pith-number/HRLJC4LYK62YMH6PBBUEYDBPNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR/action/storage_attestation","attest_author":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR/action/author_attestation","sign_citation":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR/action/citation_signature","submit_replication":"https://pith.science/pith/HRLJC4LYK62YMH6PBBUEYDBPNR/action/replication_record"}},"created_at":"2026-05-20T00:04:13.491639+00:00","updated_at":"2026-05-20T00:04:13.491639+00:00"}