{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UC4VOU7MK7NGCBHFMYG4V4SJ25","short_pith_number":"pith:UC4VOU7M","canonical_record":{"source":{"id":"2008.07820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-08-18T09:27:26Z","cross_cats_sorted":["cs.LG","econ.EM"],"title_canon_sha256":"cfe1bbc24f2b64e95e3ca5c16ce1c98bec504db22c7100fd871cc5d71b238057","abstract_canon_sha256":"f3c0b00f3fc90e6914dccd8672304a61ef97e08da2a89bcb9af5fcfe959406da"},"schema_version":"1.0"},"canonical_sha256":"a0b95753ec57da6104e5660dcaf249d757e65f27904bf2702c0ee7886906905b","source":{"kind":"arxiv","id":"2008.07820","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.07820","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"arxiv_version","alias_value":"2008.07820v1","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07820","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"pith_short_12","alias_value":"UC4VOU7MK7NG","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"pith_short_16","alias_value":"UC4VOU7MK7NGCBHF","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"pith_short_8","alias_value":"UC4VOU7M","created_at":"2026-07-05T01:27:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UC4VOU7MK7NGCBHFMYG4V4SJ25","target":"record","payload":{"canonical_record":{"source":{"id":"2008.07820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-08-18T09:27:26Z","cross_cats_sorted":["cs.LG","econ.EM"],"title_canon_sha256":"cfe1bbc24f2b64e95e3ca5c16ce1c98bec504db22c7100fd871cc5d71b238057","abstract_canon_sha256":"f3c0b00f3fc90e6914dccd8672304a61ef97e08da2a89bcb9af5fcfe959406da"},"schema_version":"1.0"},"canonical_sha256":"a0b95753ec57da6104e5660dcaf249d757e65f27904bf2702c0ee7886906905b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:55.791192Z","signature_b64":"RElfWjz14joMSD/at/fUnjYAnyqF+upF2s2WOSanv0lLImD3yWG9fhgEpsjkkwaS0e1nrZnFP3mZ8qnoCRYVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0b95753ec57da6104e5660dcaf249d757e65f27904bf2702c0ee7886906905b","last_reissued_at":"2026-07-05T01:27:55.790729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:55.790729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.07820","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":"2026-07-05T01:27:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yed8gXEw3Xj+sL/BAnCLAxZPIitkjZSrHTqmCkKjc9HZCoUJxzArpVXsGRb7DuOK7tgHYcteBQrwn//6O7KxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:30:29.756023Z"},"content_sha256":"5d074e90afc84f0df42830657a77c7a0f28cddf0280b0566f3002c797ef542a7","schema_version":"1.0","event_id":"sha256:5d074e90afc84f0df42830657a77c7a0f28cddf0280b0566f3002c797ef542a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UC4VOU7MK7NGCBHFMYG4V4SJ25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Relation Analysis of Markov Decision Process Frameworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","econ.EM"],"primary_cat":"math.OC","authors_text":"Patrick Jaillet, Tien Mai","submitted_at":"2020-08-18T09:27:26Z","abstract_excerpt":"We study the relation between different Markov Decision Process (MDP) frameworks in the machine learning and econometrics literatures, including the standard MDP, the entropy and general regularized MDP, and stochastic MDP, where the latter is based on the assumption that the reward function is stochastic and follows a given distribution. We show that the entropy-regularized MDP is equivalent to a stochastic MDP model, and is strictly subsumed by the general regularized MDP. Moreover, we propose a distributional stochastic MDP framework by assuming that the distribution of the reward function "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07820","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.07820/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":"2026-07-05T01:27:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"McWC0pLaJbf7RCdfA49ttoWhJRPnIbPdmW+3asYpAvK+AOIx1Wps7dl6g902ngtCuoY4s4IZtJ2sc6E+Xh6kDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:30:29.756551Z"},"content_sha256":"81a96162d71b023d6f6433f4447dc1f8ef678633a00f2057addfc07ff3aba2ec","schema_version":"1.0","event_id":"sha256:81a96162d71b023d6f6433f4447dc1f8ef678633a00f2057addfc07ff3aba2ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UC4VOU7MK7NGCBHFMYG4V4SJ25/bundle.json","state_url":"https://pith.science/pith/UC4VOU7MK7NGCBHFMYG4V4SJ25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UC4VOU7MK7NGCBHFMYG4V4SJ25/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":"2026-08-11T19:30:29Z","links":{"resolver":"https://pith.science/pith/UC4VOU7MK7NGCBHFMYG4V4SJ25","bundle":"https://pith.science/pith/UC4VOU7MK7NGCBHFMYG4V4SJ25/bundle.json","state":"https://pith.science/pith/UC4VOU7MK7NGCBHFMYG4V4SJ25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UC4VOU7MK7NGCBHFMYG4V4SJ25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UC4VOU7MK7NGCBHFMYG4V4SJ25","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":"f3c0b00f3fc90e6914dccd8672304a61ef97e08da2a89bcb9af5fcfe959406da","cross_cats_sorted":["cs.LG","econ.EM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-08-18T09:27:26Z","title_canon_sha256":"cfe1bbc24f2b64e95e3ca5c16ce1c98bec504db22c7100fd871cc5d71b238057"},"schema_version":"1.0","source":{"id":"2008.07820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.07820","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"arxiv_version","alias_value":"2008.07820v1","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07820","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"pith_short_12","alias_value":"UC4VOU7MK7NG","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"pith_short_16","alias_value":"UC4VOU7MK7NGCBHF","created_at":"2026-07-05T01:27:55Z"},{"alias_kind":"pith_short_8","alias_value":"UC4VOU7M","created_at":"2026-07-05T01:27:55Z"}],"graph_snapshots":[{"event_id":"sha256:81a96162d71b023d6f6433f4447dc1f8ef678633a00f2057addfc07ff3aba2ec","target":"graph","created_at":"2026-07-05T01:27:55Z","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/2008.07820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the relation between different Markov Decision Process (MDP) frameworks in the machine learning and econometrics literatures, including the standard MDP, the entropy and general regularized MDP, and stochastic MDP, where the latter is based on the assumption that the reward function is stochastic and follows a given distribution. We show that the entropy-regularized MDP is equivalent to a stochastic MDP model, and is strictly subsumed by the general regularized MDP. Moreover, we propose a distributional stochastic MDP framework by assuming that the distribution of the reward function ","authors_text":"Patrick Jaillet, Tien Mai","cross_cats":["cs.LG","econ.EM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-08-18T09:27:26Z","title":"A Relation Analysis of Markov Decision Process Frameworks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07820","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":"sha256:5d074e90afc84f0df42830657a77c7a0f28cddf0280b0566f3002c797ef542a7","target":"record","created_at":"2026-07-05T01:27:55Z","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":"f3c0b00f3fc90e6914dccd8672304a61ef97e08da2a89bcb9af5fcfe959406da","cross_cats_sorted":["cs.LG","econ.EM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-08-18T09:27:26Z","title_canon_sha256":"cfe1bbc24f2b64e95e3ca5c16ce1c98bec504db22c7100fd871cc5d71b238057"},"schema_version":"1.0","source":{"id":"2008.07820","kind":"arxiv","version":1}},"canonical_sha256":"a0b95753ec57da6104e5660dcaf249d757e65f27904bf2702c0ee7886906905b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0b95753ec57da6104e5660dcaf249d757e65f27904bf2702c0ee7886906905b","first_computed_at":"2026-07-05T01:27:55.790729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:55.790729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RElfWjz14joMSD/at/fUnjYAnyqF+upF2s2WOSanv0lLImD3yWG9fhgEpsjkkwaS0e1nrZnFP3mZ8qnoCRYVDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:55.791192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.07820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d074e90afc84f0df42830657a77c7a0f28cddf0280b0566f3002c797ef542a7","sha256:81a96162d71b023d6f6433f4447dc1f8ef678633a00f2057addfc07ff3aba2ec"],"state_sha256":"796c26efd331471880f3564034bea3623e867bd6691194e07d7eba3c52b303f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5SvrTB0V+YMI9+wMntdcHSBdTBzWQkoO++tQWJxyXOMMmQywc0edxvpwtHpKLcCdLeMiiBtQ3Xu7tPp2QELDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:30:29.760357Z","bundle_sha256":"2a5e7216e547abe8e6b481de263f3339290692a2584b47f0f6a0b1efb486bed4"}}