{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WL5MVQB6JS7EGZKP4OBPNZYLKP","short_pith_number":"pith:WL5MVQB6","canonical_record":{"source":{"id":"2103.08241","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-15T09:51:34Z","cross_cats_sorted":[],"title_canon_sha256":"d70891ea53824eb1f9a0386a8bc2d17ba542f6db91cf842a47c6ed1ac47b51bc","abstract_canon_sha256":"e8131adffac1fe508c60f4f3bcfa891989de24f9627b95cd8ebc8b5cf1221430"},"schema_version":"1.0"},"canonical_sha256":"b2facac03e4cbe43654fe382f6e70b53c48798c8cc84b94ed54fd7d2b48c66a2","source":{"kind":"arxiv","id":"2103.08241","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08241","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08241v2","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08241","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"pith_short_12","alias_value":"WL5MVQB6JS7E","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"pith_short_16","alias_value":"WL5MVQB6JS7EGZKP","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"pith_short_8","alias_value":"WL5MVQB6","created_at":"2026-07-05T04:28:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WL5MVQB6JS7EGZKP4OBPNZYLKP","target":"record","payload":{"canonical_record":{"source":{"id":"2103.08241","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-15T09:51:34Z","cross_cats_sorted":[],"title_canon_sha256":"d70891ea53824eb1f9a0386a8bc2d17ba542f6db91cf842a47c6ed1ac47b51bc","abstract_canon_sha256":"e8131adffac1fe508c60f4f3bcfa891989de24f9627b95cd8ebc8b5cf1221430"},"schema_version":"1.0"},"canonical_sha256":"b2facac03e4cbe43654fe382f6e70b53c48798c8cc84b94ed54fd7d2b48c66a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:06.566644Z","signature_b64":"WB885HZPPawvrMsqQWd0OyBlpnSptG+JTaNuD53Vi5bdBlpERwpv1IDI4BErHoDyQAOfoW0o8wi3oTqyJnY9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2facac03e4cbe43654fe382f6e70b53c48798c8cc84b94ed54fd7d2b48c66a2","last_reissued_at":"2026-07-05T04:28:06.566172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:06.566172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.08241","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:28:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4srEH1IIZ+1Yi+6hQm8JuEbxw5CEImXibx1P6fh9o/R1mIMDlWTUhk/oqbfxkTkQuLBjhpCFxK7lM0TjapPICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T18:49:44.444570Z"},"content_sha256":"14f557bf890f9b735cac4abbdb1617b17b1388b0d12c1cc5342ef5055cb15f51","schema_version":"1.0","event_id":"sha256:14f557bf890f9b735cac4abbdb1617b17b1388b0d12c1cc5342ef5055cb15f51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WL5MVQB6JS7EGZKP4OBPNZYLKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Algorithms from Probabilistic Structure Estimation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrew Cullen, Christopher King, Djallel Bouneffouf, Jonathan P. Epperlein, Robert Shorten, Roman Overko, Sergiy Zhuk","submitted_at":"2021-03-15T09:51:34Z","abstract_excerpt":"Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL agent, in which case the problem can be modeled as a contextual multi-armed bandit and lightweight myopic algorithms can be employed. On the other hand, when the RL agent's actions affect the environment, the problem must be modeled as a Markov decision process and more complex RL algorithms are required which take the future effects of actions into account. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08241","kind":"arxiv","version":2},"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/2103.08241/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":"2026-07-05T04:28:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"79KPFEdtK9Os+auj8eIcyPluo9Vs+bjnwhGMV8v2AAm9WkP/RE41NdqmIZGfogvoDa2BWIer94AkC9+6AgIjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T18:49:44.444953Z"},"content_sha256":"e7f0914a0d747b1247ccd5c6ad1bd1efb00fed7992b8973fa0b1ab1302c8146c","schema_version":"1.0","event_id":"sha256:e7f0914a0d747b1247ccd5c6ad1bd1efb00fed7992b8973fa0b1ab1302c8146c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WL5MVQB6JS7EGZKP4OBPNZYLKP/bundle.json","state_url":"https://pith.science/pith/WL5MVQB6JS7EGZKP4OBPNZYLKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WL5MVQB6JS7EGZKP4OBPNZYLKP/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":"2026-07-19T18:49:44Z","links":{"resolver":"https://pith.science/pith/WL5MVQB6JS7EGZKP4OBPNZYLKP","bundle":"https://pith.science/pith/WL5MVQB6JS7EGZKP4OBPNZYLKP/bundle.json","state":"https://pith.science/pith/WL5MVQB6JS7EGZKP4OBPNZYLKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WL5MVQB6JS7EGZKP4OBPNZYLKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WL5MVQB6JS7EGZKP4OBPNZYLKP","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":"e8131adffac1fe508c60f4f3bcfa891989de24f9627b95cd8ebc8b5cf1221430","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-15T09:51:34Z","title_canon_sha256":"d70891ea53824eb1f9a0386a8bc2d17ba542f6db91cf842a47c6ed1ac47b51bc"},"schema_version":"1.0","source":{"id":"2103.08241","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08241","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08241v2","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08241","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"pith_short_12","alias_value":"WL5MVQB6JS7E","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"pith_short_16","alias_value":"WL5MVQB6JS7EGZKP","created_at":"2026-07-05T04:28:06Z"},{"alias_kind":"pith_short_8","alias_value":"WL5MVQB6","created_at":"2026-07-05T04:28:06Z"}],"graph_snapshots":[{"event_id":"sha256:e7f0914a0d747b1247ccd5c6ad1bd1efb00fed7992b8973fa0b1ab1302c8146c","target":"graph","created_at":"2026-07-05T04:28:06Z","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/2103.08241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL agent, in which case the problem can be modeled as a contextual multi-armed bandit and lightweight myopic algorithms can be employed. On the other hand, when the RL agent's actions affect the environment, the problem must be modeled as a Markov decision process and more complex RL algorithms are required which take the future effects of actions into account. ","authors_text":"Andrew Cullen, Christopher King, Djallel Bouneffouf, Jonathan P. Epperlein, Robert Shorten, Roman Overko, Sergiy Zhuk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-15T09:51:34Z","title":"Reinforcement Learning with Algorithms from Probabilistic Structure Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08241","kind":"arxiv","version":2},"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":"sha256:14f557bf890f9b735cac4abbdb1617b17b1388b0d12c1cc5342ef5055cb15f51","target":"record","created_at":"2026-07-05T04:28:06Z","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":"e8131adffac1fe508c60f4f3bcfa891989de24f9627b95cd8ebc8b5cf1221430","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-15T09:51:34Z","title_canon_sha256":"d70891ea53824eb1f9a0386a8bc2d17ba542f6db91cf842a47c6ed1ac47b51bc"},"schema_version":"1.0","source":{"id":"2103.08241","kind":"arxiv","version":2}},"canonical_sha256":"b2facac03e4cbe43654fe382f6e70b53c48798c8cc84b94ed54fd7d2b48c66a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2facac03e4cbe43654fe382f6e70b53c48798c8cc84b94ed54fd7d2b48c66a2","first_computed_at":"2026-07-05T04:28:06.566172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:06.566172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WB885HZPPawvrMsqQWd0OyBlpnSptG+JTaNuD53Vi5bdBlpERwpv1IDI4BErHoDyQAOfoW0o8wi3oTqyJnY9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:06.566644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.08241","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14f557bf890f9b735cac4abbdb1617b17b1388b0d12c1cc5342ef5055cb15f51","sha256:e7f0914a0d747b1247ccd5c6ad1bd1efb00fed7992b8973fa0b1ab1302c8146c"],"state_sha256":"24a772957b58ac340e50985fb4c81bb0ec864598f4c8d0954f3775ea220a93ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"COLmu+zobeEuwWLXwF4kEOlghWohSaEmg+QFfvNtWxQmZ0PagrXdMwT0x+QGZzhc3A2orshf5kmFBAw/bYj5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T18:49:44.447095Z","bundle_sha256":"31e142a20859ebddeea3ad06a7bd5a8232f5121072a12b4d9efdcf4c4725940f"}}