{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LCHTXZLAB5BOXOH37JC6NBMAL5","short_pith_number":"pith:LCHTXZLA","schema_version":"1.0","canonical_sha256":"588f3be5600f42ebb8fbfa45e685805f65c8f1843e54662bfdac46db18e5a2ee","source":{"kind":"arxiv","id":"2502.10158","version":3},"attestation_state":"computed","paper":{"title":"Combinatorial Reinforcement Learning with Preference Feedback","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Joongkyu Lee, Min-hwan Oh","submitted_at":"2025-02-14T13:37:02Z","abstract_excerpt":"In this paper, we consider combinatorial reinforcement learning with preference feedback, where a learning agent sequentially offers an action--an assortment of multiple items to--a user, whose preference feedback follows a multinomial logistic (MNL) model. This framework allows us to model real-world scenarios, particularly those involving long-term user engagement, such as in recommender systems and online advertising. However, this framework faces two main challenges: (1) the unknown value of each item, unlike traditional MNL bandits that only address single-step preference feedback, and (2"},"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":"2502.10158","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-14T13:37:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"332ad7da6e680625a062aa879bdebd222a04890ddee2fddab98cbac74f727793","abstract_canon_sha256":"2ee6bafc48175217943c948c7d410c2ef19e3ee53fcfa1cd9abc24803d4fc845"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:06.217709Z","signature_b64":"1IGbwFkYAfSbECfSKMPgxRTyoXrJFVZCUswLrlFRGDgo7JF6BSzOIJhhu02bbh5ulhBrh2NEuYRH7HsmlHmuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"588f3be5600f42ebb8fbfa45e685805f65c8f1843e54662bfdac46db18e5a2ee","last_reissued_at":"2026-07-05T11:16:06.217209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:06.217209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combinatorial Reinforcement Learning with Preference Feedback","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Joongkyu Lee, Min-hwan Oh","submitted_at":"2025-02-14T13:37:02Z","abstract_excerpt":"In this paper, we consider combinatorial reinforcement learning with preference feedback, where a learning agent sequentially offers an action--an assortment of multiple items to--a user, whose preference feedback follows a multinomial logistic (MNL) model. This framework allows us to model real-world scenarios, particularly those involving long-term user engagement, such as in recommender systems and online advertising. However, this framework faces two main challenges: (1) the unknown value of each item, unlike traditional MNL bandits that only address single-step preference feedback, and (2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10158","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/2502.10158/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":"2502.10158","created_at":"2026-07-05T11:16:06.217269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10158v3","created_at":"2026-07-05T11:16:06.217269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10158","created_at":"2026-07-05T11:16:06.217269+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCHTXZLAB5BO","created_at":"2026-07-05T11:16:06.217269+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCHTXZLAB5BOXOH3","created_at":"2026-07-05T11:16:06.217269+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCHTXZLA","created_at":"2026-07-05T11:16:06.217269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10020","citing_title":"Improved Online Confidence Bounds for Multinomial Logistic Bandits","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5","json":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5.json","graph_json":"https://pith.science/api/pith-number/LCHTXZLAB5BOXOH37JC6NBMAL5/graph.json","events_json":"https://pith.science/api/pith-number/LCHTXZLAB5BOXOH37JC6NBMAL5/events.json","paper":"https://pith.science/paper/LCHTXZLA"},"agent_actions":{"view_html":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5","download_json":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5.json","view_paper":"https://pith.science/paper/LCHTXZLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10158&json=true","fetch_graph":"https://pith.science/api/pith-number/LCHTXZLAB5BOXOH37JC6NBMAL5/graph.json","fetch_events":"https://pith.science/api/pith-number/LCHTXZLAB5BOXOH37JC6NBMAL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5/action/storage_attestation","attest_author":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5/action/author_attestation","sign_citation":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5/action/citation_signature","submit_replication":"https://pith.science/pith/LCHTXZLAB5BOXOH37JC6NBMAL5/action/replication_record"}},"created_at":"2026-07-05T11:16:06.217269+00:00","updated_at":"2026-07-05T11:16:06.217269+00:00"}