{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WKSWWIMEM3H3S5P73JPVF7IPRZ","short_pith_number":"pith:WKSWWIME","schema_version":"1.0","canonical_sha256":"b2a56b218466cfb975ffda5f52fd0f8e6ec656d5f3e68d269e7d00ceab4d74d2","source":{"kind":"arxiv","id":"1906.00091","version":1},"attestation_state":"computed","paper":{"title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Alisson G. Azzolini, Andrey Mallevich, Ansha Yu, Bill Jia, Carole-Jean Wu, Dheevatsa Mudigere, Dmytro Dzhulgakov, Hao-Jun Michael Shi, Ilia Cherniavskii, Jianyu Huang, Jongsoo Park, Liang Xiong, Maxim Naumov, Misha Smelyanskiy, Narayanan Sundaraman, Raghuraman Krishnamoorthi, Stephanie Pereira, Udit Gupta, Vijay Rao, Volodymyr Kondratenko, Wenlin Chen, Xianjie Chen, Xiaodong Wang, Yinghai Lu","submitted_at":"2019-05-31T21:51:16Z","abstract_excerpt":"With the advent of deep learning, neural network-based recommendation models have emerged as an important tool for tackling personalization and recommendation tasks. These networks differ significantly from other deep learning networks due to their need to handle categorical features and are not well studied or understood. In this paper, we develop a state-of-the-art deep learning recommendation model (DLRM) and provide its implementation in both PyTorch and Caffe2 frameworks. In addition, we design a specialized parallelization scheme utilizing model parallelism on the embedding tables to mit"},"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":"1906.00091","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-05-31T21:51:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"15e4adbdc34ff82df4f69d2339c7cd8fde4c42ff52c809a87de5c6d96f7d8b1e","abstract_canon_sha256":"6f5aea267de1216b890f35778efdc15134d5805463195f00acef99f8d3494109"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:28.200727Z","signature_b64":"bvnvhdeWmmq4ilN1CcawQbeTdzBEZqLRVxi/DzsUtyQj9IY7LyIsbfaZ1txtrCslNLOfD8GURBQwNBJWY/EBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2a56b218466cfb975ffda5f52fd0f8e6ec656d5f3e68d269e7d00ceab4d74d2","last_reissued_at":"2026-05-17T23:44:28.200096Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:28.200096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Alisson G. Azzolini, Andrey Mallevich, Ansha Yu, Bill Jia, Carole-Jean Wu, Dheevatsa Mudigere, Dmytro Dzhulgakov, Hao-Jun Michael Shi, Ilia Cherniavskii, Jianyu Huang, Jongsoo Park, Liang Xiong, Maxim Naumov, Misha Smelyanskiy, Narayanan Sundaraman, Raghuraman Krishnamoorthi, Stephanie Pereira, Udit Gupta, Vijay Rao, Volodymyr Kondratenko, Wenlin Chen, Xianjie Chen, Xiaodong Wang, Yinghai Lu","submitted_at":"2019-05-31T21:51:16Z","abstract_excerpt":"With the advent of deep learning, neural network-based recommendation models have emerged as an important tool for tackling personalization and recommendation tasks. These networks differ significantly from other deep learning networks due to their need to handle categorical features and are not well studied or understood. In this paper, we develop a state-of-the-art deep learning recommendation model (DLRM) and provide its implementation in both PyTorch and Caffe2 frameworks. In addition, we design a specialized parallelization scheme utilizing model parallelism on the embedding tables to mit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00091","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":""},"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":"1906.00091","created_at":"2026-05-17T23:44:28.200181+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.00091v1","created_at":"2026-05-17T23:44:28.200181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00091","created_at":"2026-05-17T23:44:28.200181+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKSWWIMEM3H3","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKSWWIMEM3H3S5P7","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKSWWIME","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":13,"sample":[{"citing_arxiv_id":"2603.24226","citing_title":"Joint Model Parameter Scaling and Universal-Domain Data Integration for E-commerce Search Ranking","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2412.12636","citing_title":"TrainMover: An Interruption-Resilient Runtime for ML Training","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21832","citing_title":"FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21969","citing_title":"LLM Retrieval for Stable and Predictable Ad Recommendations","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2511.06077","citing_title":"Make It Long, Keep It Fast: End-to-End 10K Long User Behavior Sequence Modeling for Billion-Scale Douyin Recommendation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11333","citing_title":"MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14401","citing_title":"Agentic Recommender System with Hierarchical Belief-State Memory","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2508.10695","citing_title":"Learning from Natural Language Feedback for Personalized Question Answering","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2511.06077","citing_title":"Make It Long, Keep It Fast: End-to-End 10K Long User Behavior Sequence Modeling for Billion-Scale Douyin Recommendation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2511.14881","citing_title":"SilverTorch: A Unified Model-based System to Democratize Large-Scale Recommendation on GPUs","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2512.08160","citing_title":"LayerPipe2: Multistage Pipelining and Weight Recompute via Improved Exponential Moving Average for Training Neural Networks","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10886","citing_title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14401","citing_title":"Agentic Recommender System with Hierarchical Belief-State Memory","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04976","citing_title":"Tencent Advertising Algorithm Challenge 2025: All-Modality Generative Recommendation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11333","citing_title":"MLCommons Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26587","citing_title":"Sparse-on-Dense: Area and Energy-Efficient Computing of Sparse Neural Networks on Dense Matrix Multiplication Accelerators","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10886","citing_title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09338","citing_title":"A General Framework for Multimodal LLM-Based Multimedia Understanding in Large-Scale Recommendation Systems","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09794","citing_title":"LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25338","citing_title":"RecFlash: Fast Recommendation System on In-Storage Computing with Frequency-Based Data Mapping","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01503","citing_title":"Recommender Systems as Control Systems","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01060","citing_title":"SURGE: SuperBatch Unified Resource-efficient GPU Encoding for Heterogeneous Partitioned Data","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00324","citing_title":"Intelligent Elastic Feature Fading: Enabling Model Retrain-Free Feature Efficiency Rollouts at Scale","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12110","citing_title":"SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08011","citing_title":"Beyond Dense Connectivity: Explicit Sparsity for Scalable Recommendation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ","json":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ.json","graph_json":"https://pith.science/api/pith-number/WKSWWIMEM3H3S5P73JPVF7IPRZ/graph.json","events_json":"https://pith.science/api/pith-number/WKSWWIMEM3H3S5P73JPVF7IPRZ/events.json","paper":"https://pith.science/paper/WKSWWIME"},"agent_actions":{"view_html":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ","download_json":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ.json","view_paper":"https://pith.science/paper/WKSWWIME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.00091&json=true","fetch_graph":"https://pith.science/api/pith-number/WKSWWIMEM3H3S5P73JPVF7IPRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WKSWWIMEM3H3S5P73JPVF7IPRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ/action/storage_attestation","attest_author":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ/action/author_attestation","sign_citation":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ/action/citation_signature","submit_replication":"https://pith.science/pith/WKSWWIMEM3H3S5P73JPVF7IPRZ/action/replication_record"}},"created_at":"2026-05-17T23:44:28.200181+00:00","updated_at":"2026-05-17T23:44:28.200181+00:00"}