{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:55KPY2FT7JJYXFNT7XZL6RINL6","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":"fe6186ca616e8285e7487486527237817db4d6102ed6601f518de9ad062c7298","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-20T01:57:52Z","title_canon_sha256":"db01a5fe4017442b1c2c66d1a0fc6ddf1f2f517449b02dd1357bbbd48aa815c1"},"schema_version":"1.0","source":{"id":"2105.09452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09452","created_at":"2026-07-05T02:41:52Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09452v1","created_at":"2026-07-05T02:41:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09452","created_at":"2026-07-05T02:41:52Z"},{"alias_kind":"pith_short_12","alias_value":"55KPY2FT7JJY","created_at":"2026-07-05T02:41:52Z"},{"alias_kind":"pith_short_16","alias_value":"55KPY2FT7JJYXFNT","created_at":"2026-07-05T02:41:52Z"},{"alias_kind":"pith_short_8","alias_value":"55KPY2FT","created_at":"2026-07-05T02:41:52Z"}],"graph_snapshots":[{"event_id":"sha256:08790ebe7b0eb77258efdb4e414615e55106be87841dabe7f9193f4d5b8c05bc","target":"graph","created_at":"2026-07-05T02:41:52Z","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/2105.09452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes performance over a possibly infinite random sequence of Markov Decision Processes (MDPs), each of which drawn from some unknown distribution. We call each such MDP a context. Most related works make strong assumptions such as knowledge about the distribution over contexts, the existence of pre-training phases, or a priori knowledge about the number, sequence, o","authors_text":"Ana L. C. Bazzan, Bruno C. da Silva, Lucas N. Alegre","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-20T01:57:52Z","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09452","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:c6d9ab3977cbebebed038c425d89e587d316f401e4ce94f0de0eb8811ce63b63","target":"record","created_at":"2026-07-05T02:41:52Z","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":"fe6186ca616e8285e7487486527237817db4d6102ed6601f518de9ad062c7298","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-20T01:57:52Z","title_canon_sha256":"db01a5fe4017442b1c2c66d1a0fc6ddf1f2f517449b02dd1357bbbd48aa815c1"},"schema_version":"1.0","source":{"id":"2105.09452","kind":"arxiv","version":1}},"canonical_sha256":"ef54fc68b3fa538b95b3fdf2bf450d5fadf18ff93860dd60027ee4c4302e5367","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef54fc68b3fa538b95b3fdf2bf450d5fadf18ff93860dd60027ee4c4302e5367","first_computed_at":"2026-07-05T02:41:52.813772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:41:52.813772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RIxRcMIZqug2GOeRyqrzVTlc53Y2+LQRt2PFi4ENiE+ZT+TCM787fhJ7DRKF/KoaZvaSSNIYv+gazmz03CjkAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:41:52.814239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.09452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6d9ab3977cbebebed038c425d89e587d316f401e4ce94f0de0eb8811ce63b63","sha256:08790ebe7b0eb77258efdb4e414615e55106be87841dabe7f9193f4d5b8c05bc"],"state_sha256":"2584620018c6a3ddf1b4b4c095a6b01839b9e49dbae66b89406a97b9b62b1cd3"}