{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:UWDJEP65MUAHX2U7OY7UBINANJ","short_pith_number":"pith:UWDJEP65","canonical_record":{"source":{"id":"1404.7073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-04-28T17:57:48Z","cross_cats_sorted":["cs.LG","cs.LO","cs.RO"],"title_canon_sha256":"8fa8708a4ed4f1d5f4248a9363ca87d1002071232fbefc6835ec051299b1eef5","abstract_canon_sha256":"bd74f17f18cd30f6ef391ae6ab21184a25012596d097e15372d5c4ed301047cf"},"schema_version":"1.0"},"canonical_sha256":"a586923fdd65007bea9f763f40a1a06a60bfcc3b906f72749f950ce89d7e0fcb","source":{"kind":"arxiv","id":"1404.7073","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.7073","created_at":"2026-05-18T02:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"1404.7073v2","created_at":"2026-05-18T02:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.7073","created_at":"2026-05-18T02:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"UWDJEP65MUAH","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"UWDJEP65MUAHX2U7","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"UWDJEP65","created_at":"2026-05-18T12:28:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:UWDJEP65MUAHX2U7OY7UBINANJ","target":"record","payload":{"canonical_record":{"source":{"id":"1404.7073","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-04-28T17:57:48Z","cross_cats_sorted":["cs.LG","cs.LO","cs.RO"],"title_canon_sha256":"8fa8708a4ed4f1d5f4248a9363ca87d1002071232fbefc6835ec051299b1eef5","abstract_canon_sha256":"bd74f17f18cd30f6ef391ae6ab21184a25012596d097e15372d5c4ed301047cf"},"schema_version":"1.0"},"canonical_sha256":"a586923fdd65007bea9f763f40a1a06a60bfcc3b906f72749f950ce89d7e0fcb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:52:55.553689Z","signature_b64":"+rqJTwtoo2EVKgVC8w5rfNneoiYQbYN+4/AiXUAWnb4V0vWME5PdNc0ckOKwxpjKCYZayUtMIeMStVBrXotOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a586923fdd65007bea9f763f40a1a06a60bfcc3b906f72749f950ce89d7e0fcb","last_reissued_at":"2026-05-18T02:52:55.553034Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:52:55.553034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1404.7073","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":"2026-05-18T02:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pfgA/0WPtERpqkVVNiTPRrqSqHSdKsxRMAqVipa7CvPcbQsUMPXy43VcEABabYY89HESivhn4R1NmxkVN1yFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:48:06.350540Z"},"content_sha256":"907308fdd01bfd76e7d96b45cd8a36c7e2a18e05774ee89df9cc0af9f594edb8","schema_version":"1.0","event_id":"sha256:907308fdd01bfd76e7d96b45cd8a36c7e2a18e05774ee89df9cc0af9f594edb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:UWDJEP65MUAHX2U7OY7UBINANJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.LO","cs.RO"],"primary_cat":"cs.SY","authors_text":"Jie Fu, Ufuk Topcu","submitted_at":"2014-04-28T17:57:48Z","abstract_excerpt":"We consider synthesis of control policies that maximize the probability of satisfying given temporal logic specifications in unknown, stochastic environments. We model the interaction between the system and its environment as a Markov decision process (MDP) with initially unknown transition probabilities. The solution we develop builds on the so-called model-based probably approximately correct Markov decision process (PAC-MDP) methodology. The algorithm attains an $\\varepsilon$-approximately optimal policy with probability $1-\\delta$ using samples (i.e. observations), time and space that grow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.7073","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":""},"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":"2026-05-18T02:52:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OE9h2R975gfRGTdGoO3N2V2K+TEcgCg40f5vht9GY0leWtSVlcR/NEvpLeA6FpU2JkCYOGVAtoArEJ1TElnQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:48:06.351243Z"},"content_sha256":"3e4dff4c11b273d92e276ce16e3b9903a7e025fce71033b53d1436dea62aa589","schema_version":"1.0","event_id":"sha256:3e4dff4c11b273d92e276ce16e3b9903a7e025fce71033b53d1436dea62aa589"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWDJEP65MUAHX2U7OY7UBINANJ/bundle.json","state_url":"https://pith.science/pith/UWDJEP65MUAHX2U7OY7UBINANJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWDJEP65MUAHX2U7OY7UBINANJ/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":"2026-05-25T15:48:06Z","links":{"resolver":"https://pith.science/pith/UWDJEP65MUAHX2U7OY7UBINANJ","bundle":"https://pith.science/pith/UWDJEP65MUAHX2U7OY7UBINANJ/bundle.json","state":"https://pith.science/pith/UWDJEP65MUAHX2U7OY7UBINANJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWDJEP65MUAHX2U7OY7UBINANJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:UWDJEP65MUAHX2U7OY7UBINANJ","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":"bd74f17f18cd30f6ef391ae6ab21184a25012596d097e15372d5c4ed301047cf","cross_cats_sorted":["cs.LG","cs.LO","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-04-28T17:57:48Z","title_canon_sha256":"8fa8708a4ed4f1d5f4248a9363ca87d1002071232fbefc6835ec051299b1eef5"},"schema_version":"1.0","source":{"id":"1404.7073","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1404.7073","created_at":"2026-05-18T02:52:55Z"},{"alias_kind":"arxiv_version","alias_value":"1404.7073v2","created_at":"2026-05-18T02:52:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.7073","created_at":"2026-05-18T02:52:55Z"},{"alias_kind":"pith_short_12","alias_value":"UWDJEP65MUAH","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"UWDJEP65MUAHX2U7","created_at":"2026-05-18T12:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"UWDJEP65","created_at":"2026-05-18T12:28:52Z"}],"graph_snapshots":[{"event_id":"sha256:3e4dff4c11b273d92e276ce16e3b9903a7e025fce71033b53d1436dea62aa589","target":"graph","created_at":"2026-05-18T02:52:55Z","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"},"paper":{"abstract_excerpt":"We consider synthesis of control policies that maximize the probability of satisfying given temporal logic specifications in unknown, stochastic environments. We model the interaction between the system and its environment as a Markov decision process (MDP) with initially unknown transition probabilities. The solution we develop builds on the so-called model-based probably approximately correct Markov decision process (PAC-MDP) methodology. The algorithm attains an $\\varepsilon$-approximately optimal policy with probability $1-\\delta$ using samples (i.e. observations), time and space that grow","authors_text":"Jie Fu, Ufuk Topcu","cross_cats":["cs.LG","cs.LO","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-04-28T17:57:48Z","title":"Probably Approximately Correct MDP Learning and Control With Temporal Logic Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.7073","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":"sha256:907308fdd01bfd76e7d96b45cd8a36c7e2a18e05774ee89df9cc0af9f594edb8","target":"record","created_at":"2026-05-18T02:52:55Z","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":"bd74f17f18cd30f6ef391ae6ab21184a25012596d097e15372d5c4ed301047cf","cross_cats_sorted":["cs.LG","cs.LO","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2014-04-28T17:57:48Z","title_canon_sha256":"8fa8708a4ed4f1d5f4248a9363ca87d1002071232fbefc6835ec051299b1eef5"},"schema_version":"1.0","source":{"id":"1404.7073","kind":"arxiv","version":2}},"canonical_sha256":"a586923fdd65007bea9f763f40a1a06a60bfcc3b906f72749f950ce89d7e0fcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a586923fdd65007bea9f763f40a1a06a60bfcc3b906f72749f950ce89d7e0fcb","first_computed_at":"2026-05-18T02:52:55.553034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:52:55.553034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+rqJTwtoo2EVKgVC8w5rfNneoiYQbYN+4/AiXUAWnb4V0vWME5PdNc0ckOKwxpjKCYZayUtMIeMStVBrXotOBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:52:55.553689Z","signed_message":"canonical_sha256_bytes"},"source_id":"1404.7073","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:907308fdd01bfd76e7d96b45cd8a36c7e2a18e05774ee89df9cc0af9f594edb8","sha256:3e4dff4c11b273d92e276ce16e3b9903a7e025fce71033b53d1436dea62aa589"],"state_sha256":"854ec81a58ce8d0d34774dc78734cc45119fc75f0b86aa08806ae0373c22c820"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mxmB9I3SmnQdGeH3H25YxbpMXDWWcSVdB9H/up2fwe3iMV7luT2D+bG5BM4WXreld1xk8fuikYjYW6YgXWqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:48:06.354822Z","bundle_sha256":"a4b31fc70aa33bd46b9c1693b8546a84e4b7eff95952ba24ccc6b7a5f21f614d"}}