{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FBNCLQI57LZZAX6MJACJALQVLS","short_pith_number":"pith:FBNCLQI5","schema_version":"1.0","canonical_sha256":"285a25c11dfaf3905fcc4804902e155c94a8c4cdf5f517f9499bd0243c42ec5a","source":{"kind":"arxiv","id":"2311.04528","version":1},"attestation_state":"computed","paper":{"title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Chaosheng Dong, Jia Liu, Tianchen Zhou, Yan Gao, Yang Jiao, Yetian Chen, Yi Sun","submitted_at":"2023-11-08T08:33:03Z","abstract_excerpt":"Online learning to rank (ONL2R) is a foundational problem for recommender systems and has received increasing attention in recent years. Among the existing approaches for ONL2R, a natural modeling architecture is the multi-armed bandit framework coupled with the position-based click model. However, developing efficient online learning policies for MAB-based ONL2R with position-based click models is highly challenging due to the combinatorial nature of the problem, and partial observability in the position-based click model. To date, results in MAB-based ONL2R with position-based click models r"},"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":"2311.04528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-08T08:33:03Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7aad6918f9dcdd6fd2695cb2afc29080f334c51748afac3608a5b2e9c97bbacc","abstract_canon_sha256":"3e5c1a8b690bb9c03bca337b5fab878b58bc1946787255a8c3124e0e6969562d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:37.379607Z","signature_b64":"IACSHuGG9ZNXpdkvD+LWj3d8EzOJRzosQhPyuaHki/rrsM/cOA/Bdv6HrXKFY0CZMSz+hI0pPbDnUnxl0jsEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"285a25c11dfaf3905fcc4804902e155c94a8c4cdf5f517f9499bd0243c42ec5a","last_reissued_at":"2026-07-05T07:10:37.379111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:37.379111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Chaosheng Dong, Jia Liu, Tianchen Zhou, Yan Gao, Yang Jiao, Yetian Chen, Yi Sun","submitted_at":"2023-11-08T08:33:03Z","abstract_excerpt":"Online learning to rank (ONL2R) is a foundational problem for recommender systems and has received increasing attention in recent years. Among the existing approaches for ONL2R, a natural modeling architecture is the multi-armed bandit framework coupled with the position-based click model. However, developing efficient online learning policies for MAB-based ONL2R with position-based click models is highly challenging due to the combinatorial nature of the problem, and partial observability in the position-based click model. To date, results in MAB-based ONL2R with position-based click models r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04528","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/2311.04528/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":"2311.04528","created_at":"2026-07-05T07:10:37.379171+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04528v1","created_at":"2026-07-05T07:10:37.379171+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04528","created_at":"2026-07-05T07:10:37.379171+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBNCLQI57LZZ","created_at":"2026-07-05T07:10:37.379171+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBNCLQI57LZZAX6M","created_at":"2026-07-05T07:10:37.379171+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBNCLQI5","created_at":"2026-07-05T07:10:37.379171+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/FBNCLQI57LZZAX6MJACJALQVLS","json":"https://pith.science/pith/FBNCLQI57LZZAX6MJACJALQVLS.json","graph_json":"https://pith.science/api/pith-number/FBNCLQI57LZZAX6MJACJALQVLS/graph.json","events_json":"https://pith.science/api/pith-number/FBNCLQI57LZZAX6MJACJALQVLS/events.json","paper":"https://pith.science/paper/FBNCLQI5"},"agent_actions":{"view_html":"https://pith.science/pith/FBNCLQI57LZZAX6MJACJALQVLS","download_json":"https://pith.science/pith/FBNCLQI57LZZAX6MJACJALQVLS.json","view_paper":"https://pith.science/paper/FBNCLQI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04528&json=true","fetch_graph":"https://pith.science/api/pith-number/FBNCLQI57LZZAX6MJACJALQVLS/graph.json","fetch_events":"https://pith.science/api/pith-number/FBNCLQI57LZZAX6MJACJALQVLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBNCLQI57LZZAX6MJACJALQVLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBNCLQI57LZZAX6MJACJALQVLS/action/storage_attestation","attest_author":"https://pith.science/pith/FBNCLQI57LZZAX6MJACJALQVLS/action/author_attestation","sign_citation":"https://pith.science/pith/FBNCLQI57LZZAX6MJACJALQVLS/action/citation_signature","submit_replication":"https://pith.science/pith/FBNCLQI57LZZAX6MJACJALQVLS/action/replication_record"}},"created_at":"2026-07-05T07:10:37.379171+00:00","updated_at":"2026-07-05T07:10:37.379171+00:00"}