{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HDBOGZMGOBXLUFKVUGMJE3GJWH","short_pith_number":"pith:HDBOGZMG","schema_version":"1.0","canonical_sha256":"38c2e36586706eba1555a198926cc9b1c321de7ee98c49356a4d7067918f78e7","source":{"kind":"arxiv","id":"2208.08489","version":1},"attestation_state":"computed","paper":{"title":"Understanding Scaling Laws for Recommendation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Adnan Aziz, Bhargav Bhushanam, Carole-Jean Wu, Newsha Ardalani, Zeliang Chen","submitted_at":"2022-08-17T19:13:17Z","abstract_excerpt":"Scale has been a major driving force in improving machine learning performance, and understanding scaling laws is essential for strategic planning for a sustainable model quality performance growth, long-term resource planning and developing efficient system infrastructures to support large-scale models. In this paper, we study empirical scaling laws for DLRM style recommendation models, in particular Click-Through Rate (CTR). We observe that model quality scales with power law plus constant in model size, data size and amount of compute used for training. We characterize scaling efficiency al"},"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":"2208.08489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-08-17T19:13:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"49ed49b60e80135641393743c93dac57579aebcb8b7cc945f7f721d0bbcf94b0","abstract_canon_sha256":"765465b3bfd259267dd4961e29b770daf4fe94f5ab077d16e0bcc553ec18d735"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:49:34.546188Z","signature_b64":"9RVwszohWlU7gzRuxpPr/vRtyc/xgjFZCFsQSse2Ck6e38bz1+2h9ZLoftVMpfAvFMEu0ZwMDPfqobTvxE8KDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38c2e36586706eba1555a198926cc9b1c321de7ee98c49356a4d7067918f78e7","last_reissued_at":"2026-07-05T04:49:34.545843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:49:34.545843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Scaling Laws for Recommendation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Adnan Aziz, Bhargav Bhushanam, Carole-Jean Wu, Newsha Ardalani, Zeliang Chen","submitted_at":"2022-08-17T19:13:17Z","abstract_excerpt":"Scale has been a major driving force in improving machine learning performance, and understanding scaling laws is essential for strategic planning for a sustainable model quality performance growth, long-term resource planning and developing efficient system infrastructures to support large-scale models. In this paper, we study empirical scaling laws for DLRM style recommendation models, in particular Click-Through Rate (CTR). We observe that model quality scales with power law plus constant in model size, data size and amount of compute used for training. We characterize scaling efficiency al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.08489","kind":"arxiv","version":1},"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/2208.08489/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":"2208.08489","created_at":"2026-07-05T04:49:34.545901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.08489v1","created_at":"2026-07-05T04:49:34.545901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.08489","created_at":"2026-07-05T04:49:34.545901+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDBOGZMGOBXL","created_at":"2026-07-05T04:49:34.545901+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDBOGZMGOBXLUFKV","created_at":"2026-07-05T04:49:34.545901+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDBOGZMG","created_at":"2026-07-05T04:49:34.545901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05257","citing_title":"Scaling Laws for Behavioral Foundation Models over User Event Sequences","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2403.03952","citing_title":"Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24244","citing_title":"Model Merging Scaling Laws in Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14881","citing_title":"SilverTorch: A Unified Model-based System to Democratize Large-Scale Recommendation on GPUs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10886","citing_title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17878","citing_title":"RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10886","citing_title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17878","citing_title":"RankUp: Towards High-rank Representations for Large Scale Advertising Recommender Systems","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12965","citing_title":"Efficient Retrieval Scaling with Hierarchical Indexing for Large Scale Recommendation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH","json":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH.json","graph_json":"https://pith.science/api/pith-number/HDBOGZMGOBXLUFKVUGMJE3GJWH/graph.json","events_json":"https://pith.science/api/pith-number/HDBOGZMGOBXLUFKVUGMJE3GJWH/events.json","paper":"https://pith.science/paper/HDBOGZMG"},"agent_actions":{"view_html":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH","download_json":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH.json","view_paper":"https://pith.science/paper/HDBOGZMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.08489&json=true","fetch_graph":"https://pith.science/api/pith-number/HDBOGZMGOBXLUFKVUGMJE3GJWH/graph.json","fetch_events":"https://pith.science/api/pith-number/HDBOGZMGOBXLUFKVUGMJE3GJWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH/action/storage_attestation","attest_author":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH/action/author_attestation","sign_citation":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH/action/citation_signature","submit_replication":"https://pith.science/pith/HDBOGZMGOBXLUFKVUGMJE3GJWH/action/replication_record"}},"created_at":"2026-07-05T04:49:34.545901+00:00","updated_at":"2026-07-05T04:49:34.545901+00:00"}