{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OR7RCH3W3WTATFSIBJKFY6Z4D5","short_pith_number":"pith:OR7RCH3W","schema_version":"1.0","canonical_sha256":"747f111f76dda60996480a545c7b3c1f47f4a8c67b629c0d084dab0906cd2621","source":{"kind":"arxiv","id":"2505.04180","version":2},"attestation_state":"computed","paper":{"title":"Towards Large-scale Generative Ranking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Lei Chen, Leilei Ma, Lei Zhang, Liujie Zhang, Mingliang Qi, Min Zhu, Qingchang Han, Ruiwen Xu, Rui Yang, Taoyu Zhu, Weihang Chen, Xiong Cao, Xuefeng Yao, Yanhua Huang, Yaowei Liu, Yinghao Zhu, Yinqi Zhang, Yuqi Chen, Yuting Jia, Zhaoyu Liu","submitted_at":"2025-05-07T07:25:46Z","abstract_excerpt":"Generative recommendation has recently emerged as a promising paradigm in information retrieval. However, generative ranking systems are still understudied, particularly with respect to their effectiveness and feasibility in large-scale industrial settings. This paper investigates this topic at the ranking stage of Xiaohongshu's Explore Feed, a recommender system that serves hundreds of millions of users. Specifically, we first examine how generative ranking outperforms current industrial recommenders. Through theoretical and empirical analyses, we find that the primary improvement in effectiv"},"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":"2505.04180","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-07T07:25:46Z","cross_cats_sorted":[],"title_canon_sha256":"5252016f4e7bd61364ee1e4481df207e8584aff7bef68a4b14bad188b5dc6242","abstract_canon_sha256":"12938123805a373e729b613e9820954d24bcbd92c81baa8ccb1f9cfc89c76f21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:09.428650Z","signature_b64":"JTU9yBFAAqptM2jwSek0Y8Q1zGLjtDhFZG9mzChijZfeHwTtKUozuyA8/9vjzzyAoxT2mGSoMJY2CoV2uJ0fDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"747f111f76dda60996480a545c7b3c1f47f4a8c67b629c0d084dab0906cd2621","last_reissued_at":"2026-07-05T11:00:09.428153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:09.428153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Large-scale Generative Ranking","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Lei Chen, Leilei Ma, Lei Zhang, Liujie Zhang, Mingliang Qi, Min Zhu, Qingchang Han, Ruiwen Xu, Rui Yang, Taoyu Zhu, Weihang Chen, Xiong Cao, Xuefeng Yao, Yanhua Huang, Yaowei Liu, Yinghao Zhu, Yinqi Zhang, Yuqi Chen, Yuting Jia, Zhaoyu Liu","submitted_at":"2025-05-07T07:25:46Z","abstract_excerpt":"Generative recommendation has recently emerged as a promising paradigm in information retrieval. However, generative ranking systems are still understudied, particularly with respect to their effectiveness and feasibility in large-scale industrial settings. This paper investigates this topic at the ranking stage of Xiaohongshu's Explore Feed, a recommender system that serves hundreds of millions of users. Specifically, we first examine how generative ranking outperforms current industrial recommenders. Through theoretical and empirical analyses, we find that the primary improvement in effectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04180","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/2505.04180/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":"2505.04180","created_at":"2026-07-05T11:00:09.428209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04180v2","created_at":"2026-07-05T11:00:09.428209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04180","created_at":"2026-07-05T11:00:09.428209+00:00"},{"alias_kind":"pith_short_12","alias_value":"OR7RCH3W3WTA","created_at":"2026-07-05T11:00:09.428209+00:00"},{"alias_kind":"pith_short_16","alias_value":"OR7RCH3W3WTATFSI","created_at":"2026-07-05T11:00:09.428209+00:00"},{"alias_kind":"pith_short_8","alias_value":"OR7RCH3W","created_at":"2026-07-05T11:00:09.428209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25147","citing_title":"TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19635","citing_title":"Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06970","citing_title":"SSRLive: Live Streaming Recommendation with Dynamic Semantic ID","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31031","citing_title":"GenPage: Towards End-to-End Generative Homepage Construction at Netflix","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25290","citing_title":"Limitations of LTI Koopman Modeling for Nonlinear Control Systems","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05249","citing_title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00422","citing_title":"UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10445","citing_title":"End-to-End Semantic ID Generation for Generative Advertisement Recommendation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05249","citing_title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20861","citing_title":"Deep Interest Mining for Intent-Enriched Semantic IDs in Multimodal Generative Recommendation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14512","citing_title":"Asymmetric Generative Recommendation via Kronecker Residual Bridge and Multi-Faceted Hierarchical Quantization","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02684","citing_title":"MBGR: Multi-Business Prediction for Generative Recommendation at Meituan","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04976","citing_title":"Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25291","citing_title":"From Local Indices to Global Identifiers: Generative Reranking for Recommender Systems via Global Action Space","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05803","citing_title":"UniVA: Unified Value Alignment for Generative Recommendation in Online Advertising at Tencent","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22881","citing_title":"MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05249","citing_title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04450","citing_title":"One Pool, Two Caches: Adaptive HBM Partitioning for Accelerating Generative Recommender Serving","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5","json":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5.json","graph_json":"https://pith.science/api/pith-number/OR7RCH3W3WTATFSIBJKFY6Z4D5/graph.json","events_json":"https://pith.science/api/pith-number/OR7RCH3W3WTATFSIBJKFY6Z4D5/events.json","paper":"https://pith.science/paper/OR7RCH3W"},"agent_actions":{"view_html":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5","download_json":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5.json","view_paper":"https://pith.science/paper/OR7RCH3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04180&json=true","fetch_graph":"https://pith.science/api/pith-number/OR7RCH3W3WTATFSIBJKFY6Z4D5/graph.json","fetch_events":"https://pith.science/api/pith-number/OR7RCH3W3WTATFSIBJKFY6Z4D5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5/action/storage_attestation","attest_author":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5/action/author_attestation","sign_citation":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5/action/citation_signature","submit_replication":"https://pith.science/pith/OR7RCH3W3WTATFSIBJKFY6Z4D5/action/replication_record"}},"created_at":"2026-07-05T11:00:09.428209+00:00","updated_at":"2026-07-05T11:00:09.428209+00:00"}