{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2GQUXVKBFGA4RCBT7K6YXPZEUK","short_pith_number":"pith:2GQUXVKB","schema_version":"1.0","canonical_sha256":"d1a14bd5412981c88833fabd8bbf24a2b53216a8e5bd0d5baa6433fcf817327f","source":{"kind":"arxiv","id":"2508.04711","version":2},"attestation_state":"computed","paper":{"title":"Scaling Generative Recommendations with Context Parallelism on Hierarchical Sequential Transducers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Chuanhao Zhuge, Han Li, Nikhil Patel, Shen Li, Xiaodong Wang, Xing Liu, Yue Dong","submitted_at":"2025-07-23T07:28:05Z","abstract_excerpt":"Large-scale recommendation systems are pivotal to process an immense volume of daily user interactions, requiring the effective modeling of high cardinality and heterogeneous features to ensure accurate predictions. In prior work, we introduced Hierarchical Sequential Transducers (HSTU), an attention-based architecture for modeling high cardinality, non-stationary streaming recommendation data, providing good scaling law in the generative recommender framework (GR). Recent studies and experiments demonstrate that attending to longer user history sequences yields significant metric improvements"},"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":"2508.04711","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-23T07:28:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fc3d38ad9270775c7af2f638ed825b6f9b9827e9d2c6c7150ed90c592113241c","abstract_canon_sha256":"bc52cc01cc720bf374575a121a6a62580c48fa5b36ffeedb8b71832ce74fc2ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:50.326141Z","signature_b64":"N/Na96MXOKHR+qDGaX8NQi3NHc9Qd4ivT5eE9/wvJlJ9u86il7jz7mrpTIAxmhe5qhhQtC+YdBvIy6HhALXCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1a14bd5412981c88833fabd8bbf24a2b53216a8e5bd0d5baa6433fcf817327f","last_reissued_at":"2026-07-05T11:54:50.325641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:50.325641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Generative Recommendations with Context Parallelism on Hierarchical Sequential Transducers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Chuanhao Zhuge, Han Li, Nikhil Patel, Shen Li, Xiaodong Wang, Xing Liu, Yue Dong","submitted_at":"2025-07-23T07:28:05Z","abstract_excerpt":"Large-scale recommendation systems are pivotal to process an immense volume of daily user interactions, requiring the effective modeling of high cardinality and heterogeneous features to ensure accurate predictions. In prior work, we introduced Hierarchical Sequential Transducers (HSTU), an attention-based architecture for modeling high cardinality, non-stationary streaming recommendation data, providing good scaling law in the generative recommender framework (GR). Recent studies and experiments demonstrate that attending to longer user history sequences yields significant metric improvements"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04711","kind":"arxiv","version":2},"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/2508.04711/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":"2508.04711","created_at":"2026-07-05T11:54:50.325726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04711v2","created_at":"2026-07-05T11:54:50.325726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04711","created_at":"2026-07-05T11:54:50.325726+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GQUXVKBFGA4","created_at":"2026-07-05T11:54:50.325726+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GQUXVKBFGA4RCBT","created_at":"2026-07-05T11:54:50.325726+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GQUXVKB","created_at":"2026-07-05T11:54:50.325726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07317","citing_title":"Gated Bidirectional Linear Attention for Generative Retrieval","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK","json":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK.json","graph_json":"https://pith.science/api/pith-number/2GQUXVKBFGA4RCBT7K6YXPZEUK/graph.json","events_json":"https://pith.science/api/pith-number/2GQUXVKBFGA4RCBT7K6YXPZEUK/events.json","paper":"https://pith.science/paper/2GQUXVKB"},"agent_actions":{"view_html":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK","download_json":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK.json","view_paper":"https://pith.science/paper/2GQUXVKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04711&json=true","fetch_graph":"https://pith.science/api/pith-number/2GQUXVKBFGA4RCBT7K6YXPZEUK/graph.json","fetch_events":"https://pith.science/api/pith-number/2GQUXVKBFGA4RCBT7K6YXPZEUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK/action/storage_attestation","attest_author":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK/action/author_attestation","sign_citation":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK/action/citation_signature","submit_replication":"https://pith.science/pith/2GQUXVKBFGA4RCBT7K6YXPZEUK/action/replication_record"}},"created_at":"2026-07-05T11:54:50.325726+00:00","updated_at":"2026-07-05T11:54:50.325726+00:00"}