{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:EGLF4B3OCURZBTQRVFE5WNVJXX","short_pith_number":"pith:EGLF4B3O","canonical_record":{"source":{"id":"1202.3890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-17T11:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"974e49cc698372b9ff0ca1d8c134cfed710c914f2d24c324ce1dea44a80b98ce","abstract_canon_sha256":"1d91efa1010b3c16807e1ee69e40fceba1321efa37464be8667d80ff46c6d3c2"},"schema_version":"1.0"},"canonical_sha256":"21965e076e152390ce11a949db36a9bdd66670ae3a86b72b4091b3eb251b2848","source":{"kind":"arxiv","id":"1202.3890","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.3890","created_at":"2026-05-18T03:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"1202.3890v1","created_at":"2026-05-18T03:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3890","created_at":"2026-05-18T03:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"EGLF4B3OCURZ","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"EGLF4B3OCURZBTQR","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"EGLF4B3O","created_at":"2026-05-18T12:27:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:EGLF4B3OCURZBTQRVFE5WNVJXX","target":"record","payload":{"canonical_record":{"source":{"id":"1202.3890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-17T11:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"974e49cc698372b9ff0ca1d8c134cfed710c914f2d24c324ce1dea44a80b98ce","abstract_canon_sha256":"1d91efa1010b3c16807e1ee69e40fceba1321efa37464be8667d80ff46c6d3c2"},"schema_version":"1.0"},"canonical_sha256":"21965e076e152390ce11a949db36a9bdd66670ae3a86b72b4091b3eb251b2848","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:25:35.225207Z","signature_b64":"2vNMkkbLFZQwfFU2U0/chbv+Zy4Pr36LV5wp2VMxxH+vTiBqHUQ+KJ+1fJTFNMxIWr46XmDYizT5N/LP45OMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21965e076e152390ce11a949db36a9bdd66670ae3a86b72b4091b3eb251b2848","last_reissued_at":"2026-05-18T03:25:35.224462Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:25:35.224462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1202.3890","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":"2026-05-18T03:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f/Hw2IF8FI4a8hF0ZWO+Fbv6vze0n6QXZrHQOZvSrQTUCYReEfG4D7lFSOdZ66YdCBrZtzQbjtmVDMZTh7ZyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:44:23.194706Z"},"content_sha256":"1e9b2e1507c01d0af477d9ac8e863fca4bb858c0cdbabcc0921cf3e3ba6a2863","schema_version":"1.0","event_id":"sha256:1e9b2e1507c01d0af477d9ac8e863fca4bb858c0cdbabcc0921cf3e3ba6a2863"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:EGLF4B3OCURZBTQRVFE5WNVJXX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAC Bounds for Discounted MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marcus Hutter, Tor Lattimore","submitted_at":"2012-02-17T11:59:55Z","abstract_excerpt":"We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (MDPs). For the upper bound we make the assumption that each action leads to at most two possible next-states and prove a new bound for a UCRL-style algorithm on the number of time-steps when it is not Probably Approximately Correct (PAC). The new lower bound strengthens previous work by being both more general (it applies to all policies) and tighter. The upper and lower bounds match up to logarithmic factors."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3890","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":""},"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":"2026-05-18T03:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"opRA+VOkABVzOBBfNB7WijqLy6PUVp8QQGMw3P/N8NBVrICWOc0Z2sYvgyg2clQMEFgH2V4ooccwxBxjOH9ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T20:44:23.195344Z"},"content_sha256":"889a2f2f72a9dd47b2e88e4ea97f99b4b0cdf733d3aad73894005075f05e1445","schema_version":"1.0","event_id":"sha256:889a2f2f72a9dd47b2e88e4ea97f99b4b0cdf733d3aad73894005075f05e1445"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EGLF4B3OCURZBTQRVFE5WNVJXX/bundle.json","state_url":"https://pith.science/pith/EGLF4B3OCURZBTQRVFE5WNVJXX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EGLF4B3OCURZBTQRVFE5WNVJXX/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":"2026-05-29T20:44:23Z","links":{"resolver":"https://pith.science/pith/EGLF4B3OCURZBTQRVFE5WNVJXX","bundle":"https://pith.science/pith/EGLF4B3OCURZBTQRVFE5WNVJXX/bundle.json","state":"https://pith.science/pith/EGLF4B3OCURZBTQRVFE5WNVJXX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EGLF4B3OCURZBTQRVFE5WNVJXX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:EGLF4B3OCURZBTQRVFE5WNVJXX","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":"1d91efa1010b3c16807e1ee69e40fceba1321efa37464be8667d80ff46c6d3c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-17T11:59:55Z","title_canon_sha256":"974e49cc698372b9ff0ca1d8c134cfed710c914f2d24c324ce1dea44a80b98ce"},"schema_version":"1.0","source":{"id":"1202.3890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1202.3890","created_at":"2026-05-18T03:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"1202.3890v1","created_at":"2026-05-18T03:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3890","created_at":"2026-05-18T03:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"EGLF4B3OCURZ","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"EGLF4B3OCURZBTQR","created_at":"2026-05-18T12:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"EGLF4B3O","created_at":"2026-05-18T12:27:04Z"}],"graph_snapshots":[{"event_id":"sha256:889a2f2f72a9dd47b2e88e4ea97f99b4b0cdf733d3aad73894005075f05e1445","target":"graph","created_at":"2026-05-18T03:25:35Z","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"},"paper":{"abstract_excerpt":"We study upper and lower bounds on the sample-complexity of learning near-optimal behaviour in finite-state discounted Markov Decision Processes (MDPs). For the upper bound we make the assumption that each action leads to at most two possible next-states and prove a new bound for a UCRL-style algorithm on the number of time-steps when it is not Probably Approximately Correct (PAC). The new lower bound strengthens previous work by being both more general (it applies to all policies) and tighter. The upper and lower bounds match up to logarithmic factors.","authors_text":"Marcus Hutter, Tor Lattimore","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-17T11:59:55Z","title":"PAC Bounds for Discounted MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3890","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":"sha256:1e9b2e1507c01d0af477d9ac8e863fca4bb858c0cdbabcc0921cf3e3ba6a2863","target":"record","created_at":"2026-05-18T03:25:35Z","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":"1d91efa1010b3c16807e1ee69e40fceba1321efa37464be8667d80ff46c6d3c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-17T11:59:55Z","title_canon_sha256":"974e49cc698372b9ff0ca1d8c134cfed710c914f2d24c324ce1dea44a80b98ce"},"schema_version":"1.0","source":{"id":"1202.3890","kind":"arxiv","version":1}},"canonical_sha256":"21965e076e152390ce11a949db36a9bdd66670ae3a86b72b4091b3eb251b2848","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21965e076e152390ce11a949db36a9bdd66670ae3a86b72b4091b3eb251b2848","first_computed_at":"2026-05-18T03:25:35.224462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:25:35.224462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2vNMkkbLFZQwfFU2U0/chbv+Zy4Pr36LV5wp2VMxxH+vTiBqHUQ+KJ+1fJTFNMxIWr46XmDYizT5N/LP45OMCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:25:35.225207Z","signed_message":"canonical_sha256_bytes"},"source_id":"1202.3890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e9b2e1507c01d0af477d9ac8e863fca4bb858c0cdbabcc0921cf3e3ba6a2863","sha256:889a2f2f72a9dd47b2e88e4ea97f99b4b0cdf733d3aad73894005075f05e1445"],"state_sha256":"7012b21e4e6974a29cf8e68099e6188054cd0cca6ddb4b869622845d5965c116"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwphSwf8t3sy9W2vXdASVjARyflSizpieurI5k6fFod+A1E685H3kwALJ9T6EHl5Ak54Cg0ltaXb8LE4p73KCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T20:44:23.198239Z","bundle_sha256":"c994093beb10352b2d7c9308524f49740c3b255c6ae92bac08d2228f285bbf0d"}}