{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QU5MBFUELJJXBOQWINQXZRPZMK","short_pith_number":"pith:QU5MBFUE","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"},"canonical_sha256":"853ac096845a5370ba1643617cc5f96297c60a156c36e650c3dffa3a03c99f96","source":{"kind":"arxiv","id":"2401.08961","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08961","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08961v4","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08961","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"QU5MBFUELJJX","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"QU5MBFUELJJXBOQW","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"QU5MBFUE","created_at":"2026-07-05T08:05:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QU5MBFUELJJXBOQWINQXZRPZMK","target":"record","payload":{"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"},"canonical_sha256":"853ac096845a5370ba1643617cc5f96297c60a156c36e650c3dffa3a03c99f96","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"},"source_kind":"arxiv","source_id":"2401.08961","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"weToF3Ub6lVoolnUeoCvjdOMB27FtOBKQ4qNsxJawBXGo0TEVC73n5FNVrNmqBqQqwJNZ9U/k2T3L6cx72+OAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:06:49.071166Z"},"content_sha256":"ccbbe3b1566db00625da00edeffd84558f4947ee9672777366dafd38f29e5a25","schema_version":"1.0","event_id":"sha256:ccbbe3b1566db00625da00edeffd84558f4947ee9672777366dafd38f29e5a25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QU5MBFUELJJXBOQWINQXZRPZMK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnVuAksJF6QW6eYo0HTFvWEtoo7hSYpNf5oo71xFXPI0RfLfsiTLgPgZuT/s0V26jqmpgmnPFZtNPmrQTJlmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:06:49.071692Z"},"content_sha256":"e5b9358d3dde9a9f42c705f001a475f37df2606c6f3df02c275785dd4b938e0f","schema_version":"1.0","event_id":"sha256:e5b9358d3dde9a9f42c705f001a475f37df2606c6f3df02c275785dd4b938e0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/bundle.json","state_url":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QU5MBFUELJJXBOQWINQXZRPZMK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T13:06:49Z","links":{"resolver":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK","bundle":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/bundle.json","state":"https://pith.science/pith/QU5MBFUELJJXBOQWINQXZRPZMK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QU5MBFUELJJXBOQWINQXZRPZMK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QU5MBFUELJJXBOQWINQXZRPZMK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5383b4ccc83081205d1b710917f740e3c316bf6422bb6183cbe10db9ea62d8a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T04:20:26Z","title_canon_sha256":"ff69d1213b325b45325666ef6634b8e6958d30093aac5f80435ccf46b558ec28"},"schema_version":"1.0","source":{"id":"2401.08961","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08961","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08961v4","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08961","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"QU5MBFUELJJX","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"QU5MBFUELJJXBOQW","created_at":"2026-07-05T08:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"QU5MBFUE","created_at":"2026-07-05T08:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:e5b9358d3dde9a9f42c705f001a475f37df2606c6f3df02c275785dd4b938e0f","target":"graph","created_at":"2026-07-05T08:05:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.08961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"R. Srikant, Wei Chen, Yihan Du","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T04:20:26Z","title":"Cascading Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08961","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ccbbe3b1566db00625da00edeffd84558f4947ee9672777366dafd38f29e5a25","target":"record","created_at":"2026-07-05T08:05:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5383b4ccc83081205d1b710917f740e3c316bf6422bb6183cbe10db9ea62d8a6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-17T04:20:26Z","title_canon_sha256":"ff69d1213b325b45325666ef6634b8e6958d30093aac5f80435ccf46b558ec28"},"schema_version":"1.0","source":{"id":"2401.08961","kind":"arxiv","version":4}},"canonical_sha256":"853ac096845a5370ba1643617cc5f96297c60a156c36e650c3dffa3a03c99f96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"853ac096845a5370ba1643617cc5f96297c60a156c36e650c3dffa3a03c99f96","first_computed_at":"2026-07-05T08:05:09.329886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:09.329886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pNq3IrY49P1NcJVrJDYSWlwycR070bDEEv59RISdQQuGnFoNxO0Ov9efgHTQDbRQej4nrnDBde5jz9izVOJDBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:09.330352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08961","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccbbe3b1566db00625da00edeffd84558f4947ee9672777366dafd38f29e5a25","sha256:e5b9358d3dde9a9f42c705f001a475f37df2606c6f3df02c275785dd4b938e0f"],"state_sha256":"7e9c8a25864a280c6c2ad312b153bf1f9ff9a26fc69174c35b69f1f4202f9b93"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1BTrJ6zy+8xeLQruwPO+L1RW1bVxjKZNXpukWgVKcQ3F3U6eHNfwf2p0P5AWfCDIuvcNmBVEVaIFazoOlnGACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:06:49.077500Z","bundle_sha256":"516e55e19caf67df05d5a6a6022ceb256c00821b95f463d9664f49bcee021724"}}