{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZB52IGINCHDGUWRJEKG5IGPYMI","short_pith_number":"pith:ZB52IGIN","schema_version":"1.0","canonical_sha256":"c87ba4190d11c66a5a29228dd419f8623bd31f63f90d1f090655a7c693bf07fe","source":{"kind":"arxiv","id":"2506.09084","version":2},"attestation_state":"computed","paper":{"title":"PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongjie Wang, Liang Wu, Xinyuan Wang, Yanjie Fu","submitted_at":"2025-06-10T08:05:42Z","abstract_excerpt":"Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new route to it by treating page generation as sequence generation. Adapting LLMs to web-scale WPO, however, remains bottlenecked by the need for costly human annotations and by the mismatched granularity between page-level coherence and item-level placement. In this work we show that these two challenges are coupled: implicit user feedback alone suffices for alignment, provided the reward signal is decoupled into two complementary granularities. We propose"},"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":"2506.09084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T08:05:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04ef404d648497aae067f3928babb78c28cdc46d00aecaa27dbd524117a279e9","abstract_canon_sha256":"7e9f99772b0a073118b8811f002e2cfdb9b9368d516766b9ba515a64b0c6b824"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:26.887637Z","signature_b64":"Tm4ekJ08Ke1ecFPQZT90bAjxpmZ5ZnD95AJWCe8TTyTBbT9Y0413uNUn5Jp79kXynqOYNCKFdtROb1ooGufcDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c87ba4190d11c66a5a29228dd419f8623bd31f63f90d1f090655a7c693bf07fe","last_reissued_at":"2026-05-26T01:02:26.886857Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:26.886857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongjie Wang, Liang Wu, Xinyuan Wang, Yanjie Fu","submitted_at":"2025-06-10T08:05:42Z","abstract_excerpt":"Whole-page optimization (WPO) decides how search and recommendation results are surfaced to users, and large language models (LLMs) open a new route to it by treating page generation as sequence generation. Adapting LLMs to web-scale WPO, however, remains bottlenecked by the need for costly human annotations and by the mismatched granularity between page-level coherence and item-level placement. In this work we show that these two challenges are coupled: implicit user feedback alone suffices for alignment, provided the reward signal is decoupled into two complementary granularities. We propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09084","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/2506.09084/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":"2506.09084","created_at":"2026-05-26T01:02:26.886954+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09084v2","created_at":"2026-05-26T01:02:26.886954+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09084","created_at":"2026-05-26T01:02:26.886954+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZB52IGINCHDG","created_at":"2026-05-26T01:02:26.886954+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZB52IGINCHDGUWRJ","created_at":"2026-05-26T01:02:26.886954+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZB52IGIN","created_at":"2026-05-26T01:02:26.886954+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/ZB52IGINCHDGUWRJEKG5IGPYMI","json":"https://pith.science/pith/ZB52IGINCHDGUWRJEKG5IGPYMI.json","graph_json":"https://pith.science/api/pith-number/ZB52IGINCHDGUWRJEKG5IGPYMI/graph.json","events_json":"https://pith.science/api/pith-number/ZB52IGINCHDGUWRJEKG5IGPYMI/events.json","paper":"https://pith.science/paper/ZB52IGIN"},"agent_actions":{"view_html":"https://pith.science/pith/ZB52IGINCHDGUWRJEKG5IGPYMI","download_json":"https://pith.science/pith/ZB52IGINCHDGUWRJEKG5IGPYMI.json","view_paper":"https://pith.science/paper/ZB52IGIN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09084&json=true","fetch_graph":"https://pith.science/api/pith-number/ZB52IGINCHDGUWRJEKG5IGPYMI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZB52IGINCHDGUWRJEKG5IGPYMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZB52IGINCHDGUWRJEKG5IGPYMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZB52IGINCHDGUWRJEKG5IGPYMI/action/storage_attestation","attest_author":"https://pith.science/pith/ZB52IGINCHDGUWRJEKG5IGPYMI/action/author_attestation","sign_citation":"https://pith.science/pith/ZB52IGINCHDGUWRJEKG5IGPYMI/action/citation_signature","submit_replication":"https://pith.science/pith/ZB52IGINCHDGUWRJEKG5IGPYMI/action/replication_record"}},"created_at":"2026-05-26T01:02:26.886954+00:00","updated_at":"2026-05-26T01:02:26.886954+00:00"}