{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DN5Y4IFP5KXWJU4UQYDB3NPA6Y","short_pith_number":"pith:DN5Y4IFP","canonical_record":{"source":{"id":"1805.09365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:16:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0092bc50a765a451fc40b2812db460dcc1592fe0a63a56991ad6109e6752070c","abstract_canon_sha256":"13f4a57c04c3fa11b5a65c1cc970f79022a9cd5480da1d185852c7b7c81bc3c6"},"schema_version":"1.0"},"canonical_sha256":"1b7b8e20afeaaf64d39486061db5e0f62ddb6a05e1b39117626a9f9713599e6b","source":{"kind":"arxiv","id":"1805.09365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09365","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09365v1","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09365","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"DN5Y4IFP5KXW","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DN5Y4IFP5KXWJU4U","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DN5Y4IFP","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DN5Y4IFP5KXWJU4UQYDB3NPA6Y","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:16:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0092bc50a765a451fc40b2812db460dcc1592fe0a63a56991ad6109e6752070c","abstract_canon_sha256":"13f4a57c04c3fa11b5a65c1cc970f79022a9cd5480da1d185852c7b7c81bc3c6"},"schema_version":"1.0"},"canonical_sha256":"1b7b8e20afeaaf64d39486061db5e0f62ddb6a05e1b39117626a9f9713599e6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:04.270383Z","signature_b64":"oK1PxhndpSnI5WRBTo+b4R3GtAP6UREAGADlwsbfRa7APiEZHclddIylHXsa8j0YBhIUgiyu4bQGJwPDiIGmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b7b8e20afeaaf64d39486061db5e0f62ddb6a05e1b39117626a9f9713599e6b","last_reissued_at":"2026-05-18T00:15:04.269567Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:04.269567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09365","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A8K+LlFpVML7vCqLSFSw6R/LRrGMqNnYDBWbyJB64JB62e22N39BsNXL6x5p1jldnDVpdb9es4r4672fH5vzBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T16:31:55.658852Z"},"content_sha256":"93fb64ea0dc6a140173b0a956b102b3f3659d4dc3878c781c89fd915e1d9fddc","schema_version":"1.0","event_id":"sha256:93fb64ea0dc6a140173b0a956b102b3f3659d4dc3878c781c89fd915e1d9fddc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DN5Y4IFP5KXWJU4UQYDB3NPA6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Contextual Bandits in a Non-stationary Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongning Wang, Naveen Iyer, Qingyun Wu","submitted_at":"2018-05-23T18:16:39Z","abstract_excerpt":"Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually assume a stationary reward distribution, which hardly holds in practice as users' preferences are dynamic. This inevitably costs a recommender system consistent suboptimal performance. In this paper, we consider the situation where the underlying distribution of reward remains unchanged over (possibly short) epochs and shifts at unknown time instants. In accor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09365","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":""},"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":"2026-05-18T00:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N0I2lV7kGOb+EteJAuFbmiAfTuUS/jDbTPGm182CgKJYPk0nacnLp6IJwMl6U5i1MAzJbFoBqFsZBmfe/q/pDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T16:31:55.659188Z"},"content_sha256":"16c398100834064312af1121cd0d49c312fe11017f574ed6ae1b5c2a171fb56c","schema_version":"1.0","event_id":"sha256:16c398100834064312af1121cd0d49c312fe11017f574ed6ae1b5c2a171fb56c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DN5Y4IFP5KXWJU4UQYDB3NPA6Y/bundle.json","state_url":"https://pith.science/pith/DN5Y4IFP5KXWJU4UQYDB3NPA6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DN5Y4IFP5KXWJU4UQYDB3NPA6Y/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":"2026-06-27T16:31:55Z","links":{"resolver":"https://pith.science/pith/DN5Y4IFP5KXWJU4UQYDB3NPA6Y","bundle":"https://pith.science/pith/DN5Y4IFP5KXWJU4UQYDB3NPA6Y/bundle.json","state":"https://pith.science/pith/DN5Y4IFP5KXWJU4UQYDB3NPA6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DN5Y4IFP5KXWJU4UQYDB3NPA6Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DN5Y4IFP5KXWJU4UQYDB3NPA6Y","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":"13f4a57c04c3fa11b5a65c1cc970f79022a9cd5480da1d185852c7b7c81bc3c6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:16:39Z","title_canon_sha256":"0092bc50a765a451fc40b2812db460dcc1592fe0a63a56991ad6109e6752070c"},"schema_version":"1.0","source":{"id":"1805.09365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09365","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09365v1","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09365","created_at":"2026-05-18T00:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"DN5Y4IFP5KXW","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DN5Y4IFP5KXWJU4U","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DN5Y4IFP","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:16c398100834064312af1121cd0d49c312fe11017f574ed6ae1b5c2a171fb56c","target":"graph","created_at":"2026-05-18T00:15:04Z","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"},"paper":{"abstract_excerpt":"Multi-armed bandit algorithms have become a reference solution for handling the explore/exploit dilemma in recommender systems, and many other important real-world problems, such as display advertisement. However, such algorithms usually assume a stationary reward distribution, which hardly holds in practice as users' preferences are dynamic. This inevitably costs a recommender system consistent suboptimal performance. In this paper, we consider the situation where the underlying distribution of reward remains unchanged over (possibly short) epochs and shifts at unknown time instants. In accor","authors_text":"Hongning Wang, Naveen Iyer, Qingyun Wu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:16:39Z","title":"Learning Contextual Bandits in a Non-stationary Environment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09365","kind":"arxiv","version":1},"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":"sha256:93fb64ea0dc6a140173b0a956b102b3f3659d4dc3878c781c89fd915e1d9fddc","target":"record","created_at":"2026-05-18T00:15:04Z","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":"13f4a57c04c3fa11b5a65c1cc970f79022a9cd5480da1d185852c7b7c81bc3c6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T18:16:39Z","title_canon_sha256":"0092bc50a765a451fc40b2812db460dcc1592fe0a63a56991ad6109e6752070c"},"schema_version":"1.0","source":{"id":"1805.09365","kind":"arxiv","version":1}},"canonical_sha256":"1b7b8e20afeaaf64d39486061db5e0f62ddb6a05e1b39117626a9f9713599e6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b7b8e20afeaaf64d39486061db5e0f62ddb6a05e1b39117626a9f9713599e6b","first_computed_at":"2026-05-18T00:15:04.269567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:04.269567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oK1PxhndpSnI5WRBTo+b4R3GtAP6UREAGADlwsbfRa7APiEZHclddIylHXsa8j0YBhIUgiyu4bQGJwPDiIGmBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:04.270383Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93fb64ea0dc6a140173b0a956b102b3f3659d4dc3878c781c89fd915e1d9fddc","sha256:16c398100834064312af1121cd0d49c312fe11017f574ed6ae1b5c2a171fb56c"],"state_sha256":"2ea811d5b6609a00c2757681a7985d2fc14cab414cd99497a94791fa6231c453"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"12zlFw0pwe8onzm3gibzxA7b1HB3PGCkptSxApXJGZutaw/eJCSoNnJVcfzFBIa29mZG0WvsphNIQtGvWOg5CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T16:31:55.661172Z","bundle_sha256":"add90d9f14295c1cf2010d91340553d83fc169504b5fdf2b03387c8485061f0c"}}