{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QU5MBFUELJJXBOQWINQXZRPZMK","short_pith_number":"pith:QU5MBFUE","schema_version":"1.0","canonical_sha256":"853ac096845a5370ba1643617cc5f96297c60a156c36e650c3dffa3a03c99f96","source":{"kind":"arxiv","id":"2401.08961","version":4},"attestation_state":"computed","paper":{"title":"Cascading Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"R. Srikant, Wei Chen, Yihan Du","submitted_at":"2024-01-17T04:20:26Z","abstract_excerpt":"Cascading bandits have gained popularity in recent years due to their applicability to recommendation systems and online advertising. In the cascading bandit model, at each timestep, an agent recommends an ordered subset of items (called an item list) from a pool of items, each associated with an unknown attraction probability. Then, the user examines the list, and clicks the first attractive item (if any), and after that, the agent receives a reward. The goal of the agent is to maximize the expected cumulative reward. However, the prior literature on cascading bandits ignores the influences o"},"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":"2401.08961","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T04:20:26Z","cross_cats_sorted":[],"title_canon_sha256":"ff69d1213b325b45325666ef6634b8e6958d30093aac5f80435ccf46b558ec28","abstract_canon_sha256":"5383b4ccc83081205d1b710917f740e3c316bf6422bb6183cbe10db9ea62d8a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:09.330352Z","signature_b64":"pNq3IrY49P1NcJVrJDYSWlwycR070bDEEv59RISdQQuGnFoNxO0Ov9efgHTQDbRQej4nrnDBde5jz9izVOJDBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"853ac096845a5370ba1643617cc5f96297c60a156c36e650c3dffa3a03c99f96","last_reissued_at":"2026-07-05T08:05:09.329886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:09.329886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascading Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"R. Srikant, Wei Chen, Yihan Du","submitted_at":"2024-01-17T04:20:26Z","abstract_excerpt":"Cascading bandits have gained popularity in recent years due to their applicability to recommendation systems and online advertising. In the cascading bandit model, at each timestep, an agent recommends an ordered subset of items (called an item list) from a pool of items, each associated with an unknown attraction probability. Then, the user examines the list, and clicks the first attractive item (if any), and after that, the agent receives a reward. The goal of the agent is to maximize the expected cumulative reward. However, the prior literature on cascading bandits ignores the influences o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08961","kind":"arxiv","version":4},"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/2401.08961/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":"2401.08961","created_at":"2026-07-05T08:05:09.329945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.08961v4","created_at":"2026-07-05T08:05:09.329945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08961","created_at":"2026-07-05T08:05:09.329945+00:00"},{"alias_kind":"pith_short_12","alias_value":"QU5MBFUELJJX","created_at":"2026-07-05T08:05:09.329945+00:00"},{"alias_kind":"pith_short_16","alias_value":"QU5MBFUELJJXBOQW","created_at":"2026-07-05T08:05:09.329945+00:00"},{"alias_kind":"pith_short_8","alias_value":"QU5MBFUE","created_at":"2026-07-05T08:05:09.329945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10158","citing_title":"Combinatorial Reinforcement Learning with Preference Feedback","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK","json":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK.json","graph_json":"https://pith.science/api/pith-number/QU5MBFUELJJXBOQWINQXZRPZMK/graph.json","events_json":"https://pith.science/api/pith-number/QU5MBFUELJJXBOQWINQXZRPZMK/events.json","paper":"https://pith.science/paper/QU5MBFUE"},"agent_actions":{"view_html":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK","download_json":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK.json","view_paper":"https://pith.science/paper/QU5MBFUE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.08961&json=true","fetch_graph":"https://pith.science/api/pith-number/QU5MBFUELJJXBOQWINQXZRPZMK/graph.json","fetch_events":"https://pith.science/api/pith-number/QU5MBFUELJJXBOQWINQXZRPZMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/action/storage_attestation","attest_author":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/action/author_attestation","sign_citation":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/action/citation_signature","submit_replication":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/action/replication_record"}},"created_at":"2026-07-05T08:05:09.329945+00:00","updated_at":"2026-07-05T08:05:09.329945+00:00"}