{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MGEBWEYWR4S3PTYNVE5R5LD5NZ","short_pith_number":"pith:MGEBWEYW","canonical_record":{"source":{"id":"2405.17108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:24:14Z","cross_cats_sorted":[],"title_canon_sha256":"740b87900539dd6a45ccda315eaa00bd69d9f99a9e46d8611610e64d5d33a318","abstract_canon_sha256":"a3f203ff76852a21ef1028fb9e0c8d3e080aa8886021f5243ff279edc3c85b3f"},"schema_version":"1.0"},"canonical_sha256":"61881b13168f25b7cf0da93b1eac7d6e5cb656b9bca7f6a64ca23e48ed22ba17","source":{"kind":"arxiv","id":"2405.17108","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17108","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17108v1","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17108","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"MGEBWEYWR4S3","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"MGEBWEYWR4S3PTYN","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"MGEBWEYW","created_at":"2026-07-05T08:23:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MGEBWEYWR4S3PTYNVE5R5LD5NZ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17108","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:24:14Z","cross_cats_sorted":[],"title_canon_sha256":"740b87900539dd6a45ccda315eaa00bd69d9f99a9e46d8611610e64d5d33a318","abstract_canon_sha256":"a3f203ff76852a21ef1028fb9e0c8d3e080aa8886021f5243ff279edc3c85b3f"},"schema_version":"1.0"},"canonical_sha256":"61881b13168f25b7cf0da93b1eac7d6e5cb656b9bca7f6a64ca23e48ed22ba17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:40.077764Z","signature_b64":"WvSzKpvpZBe1GqzKfRmUb/ZIzA7Wa9EkHj/OrwJnnaI8sCd042ykek95VBke981dj8aPhi+cfh1MU6nZkUnJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61881b13168f25b7cf0da93b1eac7d6e5cb656b9bca7f6a64ca23e48ed22ba17","last_reissued_at":"2026-07-05T08:23:40.077216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:40.077216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17108","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":"2026-07-05T08:23:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vwLwtYsu3Klju0LcDHDJcT6JuODH9hQnyG/a0SFmqJAxQR2f8BufSBBrp1j/N6dOC1ajUn8iwncOwVx5xiRUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T07:21:56.930864Z"},"content_sha256":"a67fc3355e118f9600cbf50065d4a95ec9cceaeef26be9613cf6f4298c54e13a","schema_version":"1.0","event_id":"sha256:a67fc3355e118f9600cbf50065d4a95ec9cceaeef26be9613cf6f4298c54e13a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MGEBWEYWR4S3PTYNVE5R5LD5NZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finding good policies in average-reward Markov Decision Processes without prior knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adrienne Tuynman, Emilie Kaufmann, R\\'emy Degenne","submitted_at":"2024-05-27T12:24:14Z","abstract_excerpt":"We revisit the identification of an $\\varepsilon$-optimal policy in average-reward Markov Decision Processes (MDP). In such MDPs, two measures of complexity have appeared in the literature: the diameter, $D$, and the optimal bias span, $H$, which satisfy $H\\leq D$. Prior work have studied the complexity of $\\varepsilon$-optimal policy identification only when a generative model is available. In this case, it is known that there exists an MDP with $D \\simeq H$ for which the sample complexity to output an $\\varepsilon$-optimal policy is $\\Omega(SAD/\\varepsilon^2)$ where $S$ and $A$ are the sizes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17108","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/2405.17108/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":"2026-07-05T08:23:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRCv6tqMw6WynluBNppO6rActPd9taL9c8HhWRpQXEo6pUHKe0jmasRkqHOuuVdIfYmez0WVi/nyHIra5aDZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T07:21:56.931383Z"},"content_sha256":"da966b593c078d50590126bdbed6a5ed067952b0b75af446ba6c0335cd3ee6ac","schema_version":"1.0","event_id":"sha256:da966b593c078d50590126bdbed6a5ed067952b0b75af446ba6c0335cd3ee6ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGEBWEYWR4S3PTYNVE5R5LD5NZ/bundle.json","state_url":"https://pith.science/pith/MGEBWEYWR4S3PTYNVE5R5LD5NZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGEBWEYWR4S3PTYNVE5R5LD5NZ/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":"2026-08-18T07:21:56Z","links":{"resolver":"https://pith.science/pith/MGEBWEYWR4S3PTYNVE5R5LD5NZ","bundle":"https://pith.science/pith/MGEBWEYWR4S3PTYNVE5R5LD5NZ/bundle.json","state":"https://pith.science/pith/MGEBWEYWR4S3PTYNVE5R5LD5NZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGEBWEYWR4S3PTYNVE5R5LD5NZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MGEBWEYWR4S3PTYNVE5R5LD5NZ","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":"a3f203ff76852a21ef1028fb9e0c8d3e080aa8886021f5243ff279edc3c85b3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:24:14Z","title_canon_sha256":"740b87900539dd6a45ccda315eaa00bd69d9f99a9e46d8611610e64d5d33a318"},"schema_version":"1.0","source":{"id":"2405.17108","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17108","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17108v1","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17108","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_12","alias_value":"MGEBWEYWR4S3","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_16","alias_value":"MGEBWEYWR4S3PTYN","created_at":"2026-07-05T08:23:40Z"},{"alias_kind":"pith_short_8","alias_value":"MGEBWEYW","created_at":"2026-07-05T08:23:40Z"}],"graph_snapshots":[{"event_id":"sha256:da966b593c078d50590126bdbed6a5ed067952b0b75af446ba6c0335cd3ee6ac","target":"graph","created_at":"2026-07-05T08:23:40Z","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/2405.17108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit the identification of an $\\varepsilon$-optimal policy in average-reward Markov Decision Processes (MDP). In such MDPs, two measures of complexity have appeared in the literature: the diameter, $D$, and the optimal bias span, $H$, which satisfy $H\\leq D$. Prior work have studied the complexity of $\\varepsilon$-optimal policy identification only when a generative model is available. In this case, it is known that there exists an MDP with $D \\simeq H$ for which the sample complexity to output an $\\varepsilon$-optimal policy is $\\Omega(SAD/\\varepsilon^2)$ where $S$ and $A$ are the sizes","authors_text":"Adrienne Tuynman, Emilie Kaufmann, R\\'emy Degenne","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:24:14Z","title":"Finding good policies in average-reward Markov Decision Processes without prior knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17108","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:a67fc3355e118f9600cbf50065d4a95ec9cceaeef26be9613cf6f4298c54e13a","target":"record","created_at":"2026-07-05T08:23:40Z","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":"a3f203ff76852a21ef1028fb9e0c8d3e080aa8886021f5243ff279edc3c85b3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T12:24:14Z","title_canon_sha256":"740b87900539dd6a45ccda315eaa00bd69d9f99a9e46d8611610e64d5d33a318"},"schema_version":"1.0","source":{"id":"2405.17108","kind":"arxiv","version":1}},"canonical_sha256":"61881b13168f25b7cf0da93b1eac7d6e5cb656b9bca7f6a64ca23e48ed22ba17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61881b13168f25b7cf0da93b1eac7d6e5cb656b9bca7f6a64ca23e48ed22ba17","first_computed_at":"2026-07-05T08:23:40.077216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:40.077216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WvSzKpvpZBe1GqzKfRmUb/ZIzA7Wa9EkHj/OrwJnnaI8sCd042ykek95VBke981dj8aPhi+cfh1MU6nZkUnJAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:40.077764Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17108","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a67fc3355e118f9600cbf50065d4a95ec9cceaeef26be9613cf6f4298c54e13a","sha256:da966b593c078d50590126bdbed6a5ed067952b0b75af446ba6c0335cd3ee6ac"],"state_sha256":"0c771255a8b202ae6a27d477d75e9636a37fe827a59f61e4db5d4da313439175"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJuBVj6So/VgHyTMprKJOThcpQricz+LeTgZjyJ3fusyfSVLTeZcBRbQpq03JLeIysw6T5DA5SsXSqJ594ayCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T07:21:56.935433Z","bundle_sha256":"c2b2458db35579b0829852783daa54e2008b32bbd104231b3a642f07fa05548c"}}