{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DKZ4M6RHAE7MNK4HRYLPQR65AS","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":"3258f71556f7f5487927b7a68c5d15e516da166a7ff67e0ab969bd7100d1e558","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-30T15:18:11Z","title_canon_sha256":"708ea2c28547b76f846d25b1defdb9faf2aea9c507d4aa223dcc10ba606af0dd"},"schema_version":"1.0","source":{"id":"2208.00250","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.00250","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"arxiv_version","alias_value":"2208.00250v1","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00250","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_12","alias_value":"DKZ4M6RHAE7M","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_16","alias_value":"DKZ4M6RHAE7MNK4H","created_at":"2026-07-05T04:44:49Z"},{"alias_kind":"pith_short_8","alias_value":"DKZ4M6RH","created_at":"2026-07-05T04:44:49Z"}],"graph_snapshots":[{"event_id":"sha256:4ba7d8f48b045fd989f6c7dc7af9d180ea09f397f3f7b2f85d08bdc00958f668","target":"graph","created_at":"2026-07-05T04:44:49Z","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/2208.00250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the reinforcement learning literature, there are many algorithms developed for either Contextual Bandit (CB) or Markov Decision Processes (MDP) environments. However, when deploying reinforcement learning algorithms in the real world, even with domain expertise, it is often difficult to know whether it is appropriate to treat a sequential decision making problem as a CB or an MDP. In other words, do actions affect future states, or only the immediate rewards? Making the wrong assumption regarding the nature of the environment can lead to inefficient learning, or even prevent the algorithm f","authors_text":"Finale Doshi-Velez, Kelly W. Zhang, Omer Gottesman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-30T15:18:11Z","title":"A Bayesian Approach to Learning Bandit Structure in Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00250","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":"sha256:0cbd87daf17b7aa7926d81828c4aafa533365962fb9383bbbec977bcc752b131","target":"record","created_at":"2026-07-05T04:44:49Z","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":"3258f71556f7f5487927b7a68c5d15e516da166a7ff67e0ab969bd7100d1e558","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-30T15:18:11Z","title_canon_sha256":"708ea2c28547b76f846d25b1defdb9faf2aea9c507d4aa223dcc10ba606af0dd"},"schema_version":"1.0","source":{"id":"2208.00250","kind":"arxiv","version":1}},"canonical_sha256":"1ab3c67a27013ec6ab878e16f847dd04a858f31ec4c70a637783b150dfe70304","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ab3c67a27013ec6ab878e16f847dd04a858f31ec4c70a637783b150dfe70304","first_computed_at":"2026-07-05T04:44:49.486778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:44:49.486778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UZ2gx/1nJp64waROok2XSs0qimldJTo89NaeXYGwlZzMiJFPkErBeFdBfkVAHGseRi2LY3XZ/6uJdsmlV0PMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:44:49.487167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.00250","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cbd87daf17b7aa7926d81828c4aafa533365962fb9383bbbec977bcc752b131","sha256:4ba7d8f48b045fd989f6c7dc7af9d180ea09f397f3f7b2f85d08bdc00958f668"],"state_sha256":"6bbb1f000af5e3cef0d52597fb46274867aca9971ac3710fa3dadec51b87f266"}