{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TZ247IAZLYSTS5Z5KH6Q2BCIY6","short_pith_number":"pith:TZ247IAZ","schema_version":"1.0","canonical_sha256":"9e75cfa0195e2539773d51fd0d0448c791ac3db91fa37ffca6363a2af1e6d59f","source":{"kind":"arxiv","id":"2605.13433","version":1},"attestation_state":"computed","paper":{"title":"TurboGR: An Accelerated Training System for Large-Scale Generative Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"TurboGR enables training of up to 0.2 billion parameter generative recommendation models on Ascend NPUs at 54.71 percent MFU with 0.97 scalability.","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Hengfeng Wang, Huichao Chai, Lu Xu, Maojun Peng, Shiqing Fan, Wei Guo, Xuemiao Li, Yaoyuan Wang, Yibo Jin, Yongxiang Feng, Zhixin Wu","submitted_at":"2026-05-13T12:26:29Z","abstract_excerpt":"Generative recommendation (GR) has emerged as a promising paradigm that replaces fragmented, scenario-specific architectures with unified Transformer-based models, exhibiting scaling-law behavior where recommendation quality improves systematically with increased model capacity and training data. However, deploying GR at scale on Ascend NPUs faces fundamental system-level challenges. These challenges are further exacerbated on Ascend NPUs due to the absence of high-performance implementations for jagged operators and the architectural mismatch between irregular sparse primitives and NPU's dens"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T12:26:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa247671bf92b2d203769e19b019030dec67b2f9ac8541c99f45a487433ed684","abstract_canon_sha256":"9b843c1eb7b068d475825115698c86e176fc5f280e62609a6d8b7e9831c5ea37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:47.145932Z","signature_b64":"Cu5erN1b1gsKN5MKo5rizUULMr6zrgT96LYvBrv19E7bKibl7A76V3epqstR/bVkMZ0cWJ5oUYiDtaOnofqbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e75cfa0195e2539773d51fd0d0448c791ac3db91fa37ffca6363a2af1e6d59f","last_reissued_at":"2026-05-18T02:44:47.145484Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:47.145484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TurboGR: An Accelerated Training System for Large-Scale Generative Recommendation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"TurboGR enables training of up to 0.2 billion parameter generative recommendation models on Ascend NPUs at 54.71 percent MFU with 0.97 scalability.","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Hengfeng Wang, Huichao Chai, Lu Xu, Maojun Peng, Shiqing Fan, Wei Guo, Xuemiao Li, Yaoyuan Wang, Yibo Jin, Yongxiang Feng, Zhixin Wu","submitted_at":"2026-05-13T12:26:29Z","abstract_excerpt":"Generative recommendation (GR) has emerged as a promising paradigm that replaces fragmented, scenario-specific architectures with unified Transformer-based models, exhibiting scaling-law behavior where recommendation quality improves systematically with increased model capacity and training data. However, deploying GR at scale on Ascend NPUs faces fundamental system-level challenges. These challenges are further exacerbated on Ascend NPUs due to the absence of high-performance implementations for jagged operators and the architectural mismatch between irregular sparse primitives and NPU's dens"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluated on the KuaiRand-27K dataset, TurboGR supports training at up to 0.2B parameters and achieves 54.71% MFU with near-linear scalability (0.97).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The semi-asynchronous training and jagged optimizations preserve model quality and convergence while the reported MFU and scalability numbers generalize beyond the specific KuaiRand-27K setup and Ascend hardware configuration.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TurboGR trains up to 0.2B-parameter generative recommendation models on Ascend NPUs at 54.71% MFU with 0.97 near-linear scalability via jagged acceleration, hierarchical parallelism, and negative sampling optimizations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TurboGR enables training of up to 0.2 billion parameter generative recommendation models on Ascend NPUs at 54.71 percent MFU with 0.97 scalability.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"77d23e31e58850d03cbc97b7b3494c92fc08020f60f0aa48f6ef20e52de40dfc"},"source":{"id":"2605.13433","kind":"arxiv","version":1},"verdict":{"id":"cca99fea-3770-46ce-8585-3dc1c982a71b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:13:34.300120Z","strongest_claim":"Evaluated on the KuaiRand-27K dataset, TurboGR supports training at up to 0.2B parameters and achieves 54.71% MFU with near-linear scalability (0.97).","one_line_summary":"TurboGR trains up to 0.2B-parameter generative recommendation models on Ascend NPUs at 54.71% MFU with 0.97 near-linear scalability via jagged acceleration, hierarchical parallelism, and negative sampling optimizations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The semi-asynchronous training and jagged optimizations preserve model quality and convergence while the reported MFU and scalability numbers generalize beyond the specific KuaiRand-27K setup and Ascend hardware configuration.","pith_extraction_headline":"TurboGR enables training of up to 0.2 billion parameter generative recommendation models on Ascend NPUs at 54.71 percent MFU with 0.97 scalability."},"references":{"count":21,"sample":[{"doi":"","year":2023,"title":"Personalized news recommendation: Methods and challenges.ACM Transactions on Information Systems, 41(1):1–50, 2023","work_id":"b52b3f9e-d7ba-4223-b120-632261c0b3a8","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2000,"title":"Analysis of recommendation algorithms for e-commerce","work_id":"841957dc-6d8d-4f90-aa17-da83415dfb9e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Analyzing user engagement with tiktok’s short format video recommendations using data donations","work_id":"d1ad05e1-6b87-4031-bf5e-83cf6e2284e7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2001,"title":"Item-based collaborative filtering recommen- dation algorithms","work_id":"d013d10a-a65c-488d-8754-5652e1073e36","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Self-attentive sequential recommendation","work_id":"5c939252-a610-423e-8bb5-92e0ac0a59f6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"a27f0f8b341d20a24d8812d4174557be1c51c8a2f742cc18bd88f42b8313925b","internal_anchors":1},"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":"2605.13433","created_at":"2026-05-18T02:44:47.145564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13433v1","created_at":"2026-05-18T02:44:47.145564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13433","created_at":"2026-05-18T02:44:47.145564+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZ247IAZLYST","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZ247IAZLYSTS5Z5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZ247IAZ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6","json":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6.json","graph_json":"https://pith.science/api/pith-number/TZ247IAZLYSTS5Z5KH6Q2BCIY6/graph.json","events_json":"https://pith.science/api/pith-number/TZ247IAZLYSTS5Z5KH6Q2BCIY6/events.json","paper":"https://pith.science/paper/TZ247IAZ"},"agent_actions":{"view_html":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6","download_json":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6.json","view_paper":"https://pith.science/paper/TZ247IAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13433&json=true","fetch_graph":"https://pith.science/api/pith-number/TZ247IAZLYSTS5Z5KH6Q2BCIY6/graph.json","fetch_events":"https://pith.science/api/pith-number/TZ247IAZLYSTS5Z5KH6Q2BCIY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6/action/storage_attestation","attest_author":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6/action/author_attestation","sign_citation":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6/action/citation_signature","submit_replication":"https://pith.science/pith/TZ247IAZLYSTS5Z5KH6Q2BCIY6/action/replication_record"}},"created_at":"2026-05-18T02:44:47.145564+00:00","updated_at":"2026-05-18T02:44:47.145564+00:00"}