{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5SOADSOGZQR7ZQAADPGR5CVUVX","short_pith_number":"pith:5SOADSOG","schema_version":"1.0","canonical_sha256":"ec9c01c9c6cc23fcc0001bcd1e8ab4ade47cc386fff315a9a1443a63765022a2","source":{"kind":"arxiv","id":"2512.24787","version":3},"attestation_state":"computed","paper":{"title":"HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bin Wang, Chengxiang Zhuo, Chenyun Yu, Cong Xu, Kai Jiang, Shaojie Zhu, Shichen Shen, Sikai Wu, Yudong Li, Yunsheng Pang, Zang Li, Zijian Liu, Zijian Luo","submitted_at":"2025-12-31T11:16:24Z","abstract_excerpt":"Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. While recent generative recommendation methods have shown strong potential in modeling item sequences with semantic IDs, directly applying them to industrial-scale slate recommendation faces a fundamental disconnect: entangled SID spaces confound high-level list planning, fine-grained autoregressive decoding over long sequences limits semantic planning efficiency, and token-level objectives misalign with holistic slate quality. In this paper, we propose HiGR"},"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":"2512.24787","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-12-31T11:16:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a06d046707c0383b23aa0fe89844cd19e8888f5b0d14788e238ac6ce4660d2b","abstract_canon_sha256":"75abc516e0f4b0f8b2e015c13722fec61679d1bbb81e44b7e71e3425fdaa7695"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:51.433053Z","signature_b64":"SjxHV4+mgG2VXHRNTJntHoESmU9oExrhAtHW1jhxYLBEICjP163c9YtkpbqUcPGG07hGJoKna2yS6PBkGUoZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec9c01c9c6cc23fcc0001bcd1e8ab4ade47cc386fff315a9a1443a63765022a2","last_reissued_at":"2026-06-10T01:09:51.431942Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:51.431942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Bin Wang, Chengxiang Zhuo, Chenyun Yu, Cong Xu, Kai Jiang, Shaojie Zhu, Shichen Shen, Sikai Wu, Yudong Li, Yunsheng Pang, Zang Li, Zijian Liu, Zijian Luo","submitted_at":"2025-12-31T11:16:24Z","abstract_excerpt":"Slate recommendation, which presents users with a ranked item list in a single display, is ubiquitous across mainstream online platforms. While recent generative recommendation methods have shown strong potential in modeling item sequences with semantic IDs, directly applying them to industrial-scale slate recommendation faces a fundamental disconnect: entangled SID spaces confound high-level list planning, fine-grained autoregressive decoding over long sequences limits semantic planning efficiency, and token-level objectives misalign with holistic slate quality. In this paper, we propose HiGR"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.24787","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/2512.24787/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":"2512.24787","created_at":"2026-06-10T01:09:51.432101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.24787v3","created_at":"2026-06-10T01:09:51.432101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.24787","created_at":"2026-06-10T01:09:51.432101+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SOADSOGZQR7","created_at":"2026-06-10T01:09:51.432101+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SOADSOGZQR7ZQAA","created_at":"2026-06-10T01:09:51.432101+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SOADSOG","created_at":"2026-06-10T01:09:51.432101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.05249","citing_title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05249","citing_title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12995","citing_title":"F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Ranking","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05249","citing_title":"TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX","json":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX.json","graph_json":"https://pith.science/api/pith-number/5SOADSOGZQR7ZQAADPGR5CVUVX/graph.json","events_json":"https://pith.science/api/pith-number/5SOADSOGZQR7ZQAADPGR5CVUVX/events.json","paper":"https://pith.science/paper/5SOADSOG"},"agent_actions":{"view_html":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX","download_json":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX.json","view_paper":"https://pith.science/paper/5SOADSOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.24787&json=true","fetch_graph":"https://pith.science/api/pith-number/5SOADSOGZQR7ZQAADPGR5CVUVX/graph.json","fetch_events":"https://pith.science/api/pith-number/5SOADSOGZQR7ZQAADPGR5CVUVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX/action/storage_attestation","attest_author":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX/action/author_attestation","sign_citation":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX/action/citation_signature","submit_replication":"https://pith.science/pith/5SOADSOGZQR7ZQAADPGR5CVUVX/action/replication_record"}},"created_at":"2026-06-10T01:09:51.432101+00:00","updated_at":"2026-06-10T01:09:51.432101+00:00"}