{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UGCEAZV2WYPQUPKU4M3BHX2C55","short_pith_number":"pith:UGCEAZV2","schema_version":"1.0","canonical_sha256":"a1844066bab61f0a3d54e33613df42ef61fa555f372fc6a67f5244facd630d42","source":{"kind":"arxiv","id":"2608.09440","version":1},"attestation_state":"computed","paper":{"title":"MetaStrategy: Generative Ranking with Executable LLM Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bin Zhang, Chengyu Lai, Chuxin Chen, Dimin Wang, Han Zhu, Jialin Zhu, Jiuning Lin, Lingqing Zhang, Ruiquan Lan, Shuai Zhong, Wendong Zhang, Xiaodong Zhu, Yinjiang Cai, Zhibo Xiao, Zihong Huang","submitted_at":"2026-08-10T11:16:09Z","abstract_excerpt":"Industrial recommender systems rank heterogeneous content under coupled user, business, commercial, and experience objectives. Existing generative ranking methods typically construct item sequences directly, making them difficult to integrate with mature predictive models, operational rules, and field-level guardrails. We present MetaStrategy, a framework that instead generates a structured, executable ranking strategy. Conditioned on request context, a large language model (LLM) policy emits a typed JSON bundle controlling objective weights, content and category preferences, experience constr"},"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":"2608.09440","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-08-10T11:16:09Z","cross_cats_sorted":[],"title_canon_sha256":"6799c3975e483237721978b235fb441ef074df135fdf60999e404515fc243dd8","abstract_canon_sha256":"f0f107655fb495c70cca7c22db75b354bec29a02ec601731e7df404c76b473ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T02:24:13.760010Z","signature_b64":"6tg0d3lmaEp3+N9l9kA7jXO0V8u3ePl5NZv1yvYpKrjLMgSdePJg9gdzdeys1NHGjgCQwkzxzij7TGLCRH9SAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1844066bab61f0a3d54e33613df42ef61fa555f372fc6a67f5244facd630d42","last_reissued_at":"2026-08-11T02:24:13.758400Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T02:24:13.758400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaStrategy: Generative Ranking with Executable LLM Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Bin Zhang, Chengyu Lai, Chuxin Chen, Dimin Wang, Han Zhu, Jialin Zhu, Jiuning Lin, Lingqing Zhang, Ruiquan Lan, Shuai Zhong, Wendong Zhang, Xiaodong Zhu, Yinjiang Cai, Zhibo Xiao, Zihong Huang","submitted_at":"2026-08-10T11:16:09Z","abstract_excerpt":"Industrial recommender systems rank heterogeneous content under coupled user, business, commercial, and experience objectives. Existing generative ranking methods typically construct item sequences directly, making them difficult to integrate with mature predictive models, operational rules, and field-level guardrails. We present MetaStrategy, a framework that instead generates a structured, executable ranking strategy. Conditioned on request context, a large language model (LLM) policy emits a typed JSON bundle controlling objective weights, content and category preferences, experience constr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09440","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.09440/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":"2608.09440","created_at":"2026-08-11T02:24:13.759031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.09440v1","created_at":"2026-08-11T02:24:13.759031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09440","created_at":"2026-08-11T02:24:13.759031+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGCEAZV2WYPQ","created_at":"2026-08-11T02:24:13.759031+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGCEAZV2WYPQUPKU","created_at":"2026-08-11T02:24:13.759031+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGCEAZV2","created_at":"2026-08-11T02:24:13.759031+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/UGCEAZV2WYPQUPKU4M3BHX2C55","json":"https://pith.science/pith/UGCEAZV2WYPQUPKU4M3BHX2C55.json","graph_json":"https://pith.science/api/pith-number/UGCEAZV2WYPQUPKU4M3BHX2C55/graph.json","events_json":"https://pith.science/api/pith-number/UGCEAZV2WYPQUPKU4M3BHX2C55/events.json","paper":"https://pith.science/paper/UGCEAZV2"},"agent_actions":{"view_html":"https://pith.science/pith/UGCEAZV2WYPQUPKU4M3BHX2C55","download_json":"https://pith.science/pith/UGCEAZV2WYPQUPKU4M3BHX2C55.json","view_paper":"https://pith.science/paper/UGCEAZV2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.09440&json=true","fetch_graph":"https://pith.science/api/pith-number/UGCEAZV2WYPQUPKU4M3BHX2C55/graph.json","fetch_events":"https://pith.science/api/pith-number/UGCEAZV2WYPQUPKU4M3BHX2C55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGCEAZV2WYPQUPKU4M3BHX2C55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGCEAZV2WYPQUPKU4M3BHX2C55/action/storage_attestation","attest_author":"https://pith.science/pith/UGCEAZV2WYPQUPKU4M3BHX2C55/action/author_attestation","sign_citation":"https://pith.science/pith/UGCEAZV2WYPQUPKU4M3BHX2C55/action/citation_signature","submit_replication":"https://pith.science/pith/UGCEAZV2WYPQUPKU4M3BHX2C55/action/replication_record"}},"created_at":"2026-08-11T02:24:13.759031+00:00","updated_at":"2026-08-11T02:24:13.759031+00:00"}