{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MTETA5FT7IOP44QVV4CULBIYLU","short_pith_number":"pith:MTETA5FT","canonical_record":{"source":{"id":"2412.02251","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-03T08:28:47Z","cross_cats_sorted":["cs.AI","cs.LG","econ.EM","math.PR"],"title_canon_sha256":"217c3cc5c2fdd8763f7e9ac933a1bc14bff7d14da6fdb823c91bb2cdee0f39f2","abstract_canon_sha256":"0e76f72d7f2fd796a4e96a235bb457ce5f11ef019a2851f762c897ab2e17eb7c"},"schema_version":"1.0"},"canonical_sha256":"64c93074b3fa1cfe7215af054585185d21da8ae08d7b50ca49fac5f73d776e7e","source":{"kind":"arxiv","id":"2412.02251","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02251","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02251v3","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02251","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"MTETA5FT7IOP","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"MTETA5FT7IOP44QV","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"MTETA5FT","created_at":"2026-07-05T10:16:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MTETA5FT7IOP44QVV4CULBIYLU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.02251","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-03T08:28:47Z","cross_cats_sorted":["cs.AI","cs.LG","econ.EM","math.PR"],"title_canon_sha256":"217c3cc5c2fdd8763f7e9ac933a1bc14bff7d14da6fdb823c91bb2cdee0f39f2","abstract_canon_sha256":"0e76f72d7f2fd796a4e96a235bb457ce5f11ef019a2851f762c897ab2e17eb7c"},"schema_version":"1.0"},"canonical_sha256":"64c93074b3fa1cfe7215af054585185d21da8ae08d7b50ca49fac5f73d776e7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:59.409444Z","signature_b64":"RB76oOo7YY00zAuskHwDgRT+4OHVyyXbNM9E++W81GASej9KE34XdpncjFQiesQJQzXZuM2ZcVRz0xc57E5DDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64c93074b3fa1cfe7215af054585185d21da8ae08d7b50ca49fac5f73d776e7e","last_reissued_at":"2026-07-05T10:16:59.408955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:59.408955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.02251","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JG+4/Ej477zW7G5jArH/Z26gddhVMYO32HZuUTYpKCQmSEJ7Ux0wxv6k8icgoN2oJZqCedZN6VlKyj32Q5CEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:24:53.021644Z"},"content_sha256":"6a85a7c0be9d6c0c1b2fb6221feb41f79b47b42fcbd727e8ae5ebaa35c1f6262","schema_version":"1.0","event_id":"sha256:6a85a7c0be9d6c0c1b2fb6221feb41f79b47b42fcbd727e8ae5ebaa35c1f6262"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MTETA5FT7IOP44QVV4CULBIYLU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selective Reviews of Bandit Problems in AI via a Statistical View","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","econ.EM","math.PR"],"primary_cat":"stat.ML","authors_text":"Haoyu Wei, Huiming Zhang, Pengjie Zhou","submitted_at":"2024-12-03T08:28:47Z","abstract_excerpt":"Reinforcement Learning (RL) is a widely researched area in artificial intelligence that focuses on teaching agents decision-making through interactions with their environment. A key subset includes stochastic multi-armed bandit (MAB) and continuum-armed bandit (SCAB) problems, which model sequential decision-making under uncertainty. This review outlines the foundational models and assumptions of bandit problems, explores non-asymptotic theoretical tools like concentration inequalities and minimax regret bounds, and compares frequentist and Bayesian algorithms for managing exploration-exploita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02251","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/2412.02251/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":"2026-07-05T10:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q2VbYt/u48i9pscHJrHk28/+G4oXJy9nVRj0DFQ48o8eT5z3/c8rKhztpnVwFbNPTsjypeyM1ET8XfqDbvRDBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:24:53.022206Z"},"content_sha256":"5df460924e0fb7bff598e4c691ce2219db4dc760e7a6cdf88f31492436bb9eb2","schema_version":"1.0","event_id":"sha256:5df460924e0fb7bff598e4c691ce2219db4dc760e7a6cdf88f31492436bb9eb2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/bundle.json","state_url":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MTETA5FT7IOP44QVV4CULBIYLU/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":"2026-08-15T18:24:53Z","links":{"resolver":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU","bundle":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/bundle.json","state":"https://pith.science/pith/MTETA5FT7IOP44QVV4CULBIYLU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MTETA5FT7IOP44QVV4CULBIYLU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MTETA5FT7IOP44QVV4CULBIYLU","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":"0e76f72d7f2fd796a4e96a235bb457ce5f11ef019a2851f762c897ab2e17eb7c","cross_cats_sorted":["cs.AI","cs.LG","econ.EM","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-03T08:28:47Z","title_canon_sha256":"217c3cc5c2fdd8763f7e9ac933a1bc14bff7d14da6fdb823c91bb2cdee0f39f2"},"schema_version":"1.0","source":{"id":"2412.02251","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02251","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02251v3","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02251","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"MTETA5FT7IOP","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"MTETA5FT7IOP44QV","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"MTETA5FT","created_at":"2026-07-05T10:16:59Z"}],"graph_snapshots":[{"event_id":"sha256:5df460924e0fb7bff598e4c691ce2219db4dc760e7a6cdf88f31492436bb9eb2","target":"graph","created_at":"2026-07-05T10:16:59Z","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/2412.02251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) is a widely researched area in artificial intelligence that focuses on teaching agents decision-making through interactions with their environment. A key subset includes stochastic multi-armed bandit (MAB) and continuum-armed bandit (SCAB) problems, which model sequential decision-making under uncertainty. This review outlines the foundational models and assumptions of bandit problems, explores non-asymptotic theoretical tools like concentration inequalities and minimax regret bounds, and compares frequentist and Bayesian algorithms for managing exploration-exploita","authors_text":"Haoyu Wei, Huiming Zhang, Pengjie Zhou","cross_cats":["cs.AI","cs.LG","econ.EM","math.PR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-03T08:28:47Z","title":"Selective Reviews of Bandit Problems in AI via a Statistical View"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02251","kind":"arxiv","version":3},"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":"sha256:6a85a7c0be9d6c0c1b2fb6221feb41f79b47b42fcbd727e8ae5ebaa35c1f6262","target":"record","created_at":"2026-07-05T10:16:59Z","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":"0e76f72d7f2fd796a4e96a235bb457ce5f11ef019a2851f762c897ab2e17eb7c","cross_cats_sorted":["cs.AI","cs.LG","econ.EM","math.PR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-12-03T08:28:47Z","title_canon_sha256":"217c3cc5c2fdd8763f7e9ac933a1bc14bff7d14da6fdb823c91bb2cdee0f39f2"},"schema_version":"1.0","source":{"id":"2412.02251","kind":"arxiv","version":3}},"canonical_sha256":"64c93074b3fa1cfe7215af054585185d21da8ae08d7b50ca49fac5f73d776e7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64c93074b3fa1cfe7215af054585185d21da8ae08d7b50ca49fac5f73d776e7e","first_computed_at":"2026-07-05T10:16:59.408955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:59.408955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RB76oOo7YY00zAuskHwDgRT+4OHVyyXbNM9E++W81GASej9KE34XdpncjFQiesQJQzXZuM2ZcVRz0xc57E5DDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:59.409444Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02251","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a85a7c0be9d6c0c1b2fb6221feb41f79b47b42fcbd727e8ae5ebaa35c1f6262","sha256:5df460924e0fb7bff598e4c691ce2219db4dc760e7a6cdf88f31492436bb9eb2"],"state_sha256":"91659f2af169f70ccc944a22fed85f1e694e6a3703a22c17aa83ed8733935cf0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WftycQNQCeIzn+PGLRwcMotVORdUxEMG0XCoTBaOdCH5zNkCI8MMKxwCZRRUctaMnoSuDfzS3BE97UFF6aBrDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:24:53.028042Z","bundle_sha256":"8e789283fae4c3466fe1e10c6a5da3f21a1bf493f22f1a478145ed2b8f3e1acd"}}