{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GMGHCZ64EN7EDDOVOZNQLMVFBX","short_pith_number":"pith:GMGHCZ64","schema_version":"1.0","canonical_sha256":"330c7167dc237e418dd5765b05b2a50de6c3f87331b854f1d921c80b98c7af7c","source":{"kind":"arxiv","id":"2508.05640","version":3},"attestation_state":"computed","paper":{"title":"Request-Only Optimization for Recommendation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bin Wen, Fu Li, Huihui Cheng, Jiaqi Zhai, Keke Zhai, Leon Gao, Liang Guo, Lucy Liao, Lu Fang, Omkar Vichare, Pengchao Wang, Renqin Cai, Rui Jian, Rui Li, Rui Zhang, Shengzhi Wang, Shiyan Deng, Timothy Shi, Wei Li, Wenlei Xie, Xing Liu, Xingyu Liu, Xiong Zhang, Xuan Cao, Yanzun Huang, Yueming Wang, Yu Shi, Zhaojie Gong","submitted_at":"2025-07-24T05:56:55Z","abstract_excerpt":"Deep Learning Recommendation Models (DLRMs) represent one of the largest machine learning applications on the planet. Industry-scale DLRMs are trained with petabytes of recommendation data to serve billions of users every day. To utilize the rich user signals in the long user history, DLRMs have been scaled up to unprecedented complexity, up to trillions of floating-point operations (TFLOPs) per example. This scale, coupled with the huge amount of training data, necessitates new storage and training algorithms to efficiently improve the quality of these complex recommendation systems. In this "},"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":"2508.05640","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-24T05:56:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e18d2a5340cda977b7ad14dbab77e1b79aac1a471cc4127c35436cd14e4ac5ba","abstract_canon_sha256":"3d153e16bd99b9b93f27091305e55ca54f35e109f9e57239be52bb7ce8c6fbe7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:13.282857Z","signature_b64":"kUQ/1ZGjH05LeBp3rDX0YH4MDt5fv0hAYjwETHKXR6gtRN5gE4ZegOXBTiOOKEys/YCz+MuIkH9ucgYIc0zzDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"330c7167dc237e418dd5765b05b2a50de6c3f87331b854f1d921c80b98c7af7c","last_reissued_at":"2026-07-05T11:54:13.282368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:13.282368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Request-Only Optimization for Recommendation Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bin Wen, Fu Li, Huihui Cheng, Jiaqi Zhai, Keke Zhai, Leon Gao, Liang Guo, Lucy Liao, Lu Fang, Omkar Vichare, Pengchao Wang, Renqin Cai, Rui Jian, Rui Li, Rui Zhang, Shengzhi Wang, Shiyan Deng, Timothy Shi, Wei Li, Wenlei Xie, Xing Liu, Xingyu Liu, Xiong Zhang, Xuan Cao, Yanzun Huang, Yueming Wang, Yu Shi, Zhaojie Gong","submitted_at":"2025-07-24T05:56:55Z","abstract_excerpt":"Deep Learning Recommendation Models (DLRMs) represent one of the largest machine learning applications on the planet. Industry-scale DLRMs are trained with petabytes of recommendation data to serve billions of users every day. To utilize the rich user signals in the long user history, DLRMs have been scaled up to unprecedented complexity, up to trillions of floating-point operations (TFLOPs) per example. This scale, coupled with the huge amount of training data, necessitates new storage and training algorithms to efficiently improve the quality of these complex recommendation systems. In this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05640","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/2508.05640/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":"2508.05640","created_at":"2026-07-05T11:54:13.282429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05640v3","created_at":"2026-07-05T11:54:13.282429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05640","created_at":"2026-07-05T11:54:13.282429+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMGHCZ64EN7E","created_at":"2026-07-05T11:54:13.282429+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMGHCZ64EN7EDDOV","created_at":"2026-07-05T11:54:13.282429+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMGHCZ64","created_at":"2026-07-05T11:54:13.282429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27450","citing_title":"Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.27157","citing_title":"A Survey on Generative Recommendation: Data, Model, and Tasks","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24806","citing_title":"Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23810","citing_title":"Similar Users-Augmented Interest Network","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX","json":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX.json","graph_json":"https://pith.science/api/pith-number/GMGHCZ64EN7EDDOVOZNQLMVFBX/graph.json","events_json":"https://pith.science/api/pith-number/GMGHCZ64EN7EDDOVOZNQLMVFBX/events.json","paper":"https://pith.science/paper/GMGHCZ64"},"agent_actions":{"view_html":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX","download_json":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX.json","view_paper":"https://pith.science/paper/GMGHCZ64","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05640&json=true","fetch_graph":"https://pith.science/api/pith-number/GMGHCZ64EN7EDDOVOZNQLMVFBX/graph.json","fetch_events":"https://pith.science/api/pith-number/GMGHCZ64EN7EDDOVOZNQLMVFBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX/action/storage_attestation","attest_author":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX/action/author_attestation","sign_citation":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX/action/citation_signature","submit_replication":"https://pith.science/pith/GMGHCZ64EN7EDDOVOZNQLMVFBX/action/replication_record"}},"created_at":"2026-07-05T11:54:13.282429+00:00","updated_at":"2026-07-05T11:54:13.282429+00:00"}