{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XGZGBC6277CQJ7IQX2TMVPE7GJ","short_pith_number":"pith:XGZGBC62","schema_version":"1.0","canonical_sha256":"b9b2608bdaffc504fd10bea6cabc9f327cffb5d71b85570a79b5d7155f48cedc","source":{"kind":"arxiv","id":"2505.12663","version":3},"attestation_state":"computed","paper":{"title":"MTGenRec: An Efficient Distributed Training System for Generative Recommendation Models in Meituan","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bin Yin, Bo Du, Chi Ma, Chuan Liu, Fei Jiang, Haowei Han, He Jiang, Jiawei Jiang, Lei Yu, Mincong Huang, Ruidong Han, Shangyu Chen, Wei Lin, Xiang Li, Xiaoguang Li, Xiaokai Zhou, Xiao Yan, Yuxiang Wang","submitted_at":"2025-05-19T03:26:18Z","abstract_excerpt":"Recommendation is crucial for both user experience and company revenue in Meituan as a leading lifestyle company, and generative recommendation models (GRMs) are shown to produce quality recommendations recently. However, existing systems are limited by insufficient functionality support and inefficient implementations for training GRMs in industrial scenarios. As such, we introduce MTGenRec as an efficient and scalable system for GRM training. Specifically, to handle real-time insertions/deletions of sparse embeddings, MTGenRec employs dynamic hash tables to replace static ones. To improve tr"},"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":"2505.12663","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-05-19T03:26:18Z","cross_cats_sorted":[],"title_canon_sha256":"eae52c994ae04a0620927469607958faf356ee3ede04ee4d524170ac25ef4028","abstract_canon_sha256":"98912a6cc1711652b2843476a58fb49b6774e954badc73d3c245a408a5f3e22d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:45.456402Z","signature_b64":"/aFrDUZc/qe3M2vw5v2ODwJBinFDpXVVCWBUoFbB1ZAK7LhNX5AiqXXfJXT0HU3dfoCgkCTdjD1BcvkG48/+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9b2608bdaffc504fd10bea6cabc9f327cffb5d71b85570a79b5d7155f48cedc","last_reissued_at":"2026-06-23T03:13:45.455795Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:45.455795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTGenRec: An Efficient Distributed Training System for Generative Recommendation Models in Meituan","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bin Yin, Bo Du, Chi Ma, Chuan Liu, Fei Jiang, Haowei Han, He Jiang, Jiawei Jiang, Lei Yu, Mincong Huang, Ruidong Han, Shangyu Chen, Wei Lin, Xiang Li, Xiaoguang Li, Xiaokai Zhou, Xiao Yan, Yuxiang Wang","submitted_at":"2025-05-19T03:26:18Z","abstract_excerpt":"Recommendation is crucial for both user experience and company revenue in Meituan as a leading lifestyle company, and generative recommendation models (GRMs) are shown to produce quality recommendations recently. However, existing systems are limited by insufficient functionality support and inefficient implementations for training GRMs in industrial scenarios. As such, we introduce MTGenRec as an efficient and scalable system for GRM training. Specifically, to handle real-time insertions/deletions of sparse embeddings, MTGenRec employs dynamic hash tables to replace static ones. To improve tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12663","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/2505.12663/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":"2505.12663","created_at":"2026-06-23T03:13:45.455870+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12663v3","created_at":"2026-06-23T03:13:45.455870+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12663","created_at":"2026-06-23T03:13:45.455870+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGZGBC6277CQ","created_at":"2026-06-23T03:13:45.455870+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGZGBC6277CQJ7IQ","created_at":"2026-06-23T03:13:45.455870+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGZGBC62","created_at":"2026-06-23T03:13:45.455870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.22881","citing_title":"MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ","json":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ.json","graph_json":"https://pith.science/api/pith-number/XGZGBC6277CQJ7IQX2TMVPE7GJ/graph.json","events_json":"https://pith.science/api/pith-number/XGZGBC6277CQJ7IQX2TMVPE7GJ/events.json","paper":"https://pith.science/paper/XGZGBC62"},"agent_actions":{"view_html":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ","download_json":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ.json","view_paper":"https://pith.science/paper/XGZGBC62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12663&json=true","fetch_graph":"https://pith.science/api/pith-number/XGZGBC6277CQJ7IQX2TMVPE7GJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XGZGBC6277CQJ7IQX2TMVPE7GJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ/action/storage_attestation","attest_author":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ/action/author_attestation","sign_citation":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ/action/citation_signature","submit_replication":"https://pith.science/pith/XGZGBC6277CQJ7IQX2TMVPE7GJ/action/replication_record"}},"created_at":"2026-06-23T03:13:45.455870+00:00","updated_at":"2026-06-23T03:13:45.455870+00:00"}