{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:NE4L6CVDPCZSK7QB6HC546AUPD","short_pith_number":"pith:NE4L6CVD","canonical_record":{"source":{"id":"1211.5901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-11-26T09:55:27Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"ca5f0fb4b6c46ab9d077d8a0620896ea412c9e8f3137a35e9aabf0769abac22c","abstract_canon_sha256":"fdd73e53a71abf5d830e93edd9a55d58808253cdf123d507dfda394ea49c5c8f"},"schema_version":"1.0"},"canonical_sha256":"6938bf0aa378b3257e01f1c5de781478e5527c5863621d58d99f861649bd58ea","source":{"kind":"arxiv","id":"1211.5901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1211.5901","created_at":"2026-05-18T03:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"1211.5901v1","created_at":"2026-05-18T03:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.5901","created_at":"2026-05-18T03:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"NE4L6CVDPCZS","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"NE4L6CVDPCZSK7QB","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"NE4L6CVD","created_at":"2026-05-18T12:27:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:NE4L6CVDPCZSK7QB6HC546AUPD","target":"record","payload":{"canonical_record":{"source":{"id":"1211.5901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-11-26T09:55:27Z","cross_cats_sorted":["cs.LG","stat.CO"],"title_canon_sha256":"ca5f0fb4b6c46ab9d077d8a0620896ea412c9e8f3137a35e9aabf0769abac22c","abstract_canon_sha256":"fdd73e53a71abf5d830e93edd9a55d58808253cdf123d507dfda394ea49c5c8f"},"schema_version":"1.0"},"canonical_sha256":"6938bf0aa378b3257e01f1c5de781478e5527c5863621d58d99f861649bd58ea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:40:01.641632Z","signature_b64":"L0sZgmt2hHug3aID69pa/8IoqHMzX9CTtM8bRr8M0y0NTKvYRd/3jP2RBfRkFbT84cesizfKWuQG0e2QfhbHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6938bf0aa378b3257e01f1c5de781478e5527c5863621d58d99f861649bd58ea","last_reissued_at":"2026-05-18T03:40:01.641189Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:40:01.641189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1211.5901","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":"2026-05-18T03:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QmmI9LADd8HRSw+oU82d+C2oPp2PnUvpPsh5TkPXOw7PG7w9PNT8hplFmplislkritBTYVjjh1kWJ14Ut68CCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:11:37.523931Z"},"content_sha256":"c322879edb9f0a71da24d255addca4a1e1737f8c3c0e24d24fafe3a8c14ad5b7","schema_version":"1.0","event_id":"sha256:c322879edb9f0a71da24d255addca4a1e1737f8c3c0e24d24fafe3a8c14ad5b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:NE4L6CVDPCZSK7QB6HC546AUPD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian learning of noisy Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.CO"],"primary_cat":"stat.ML","authors_text":"Nick Whiteley, Nicolas Chopin, Sumeetpal S. Singh","submitted_at":"2012-11-26T09:55:27Z","abstract_excerpt":"We consider the inverse reinforcement learning problem, that is, the problem of learning from, and then predicting or mimicking a controller based on state/action data. We propose a statistical model for such data, derived from the structure of a Markov decision process. Adopting a Bayesian approach to inference, we show how latent variables of the model can be estimated, and how predictions about actions can be made, in a unified framework. A new Markov chain Monte Carlo (MCMC) sampler is devised for simulation from the posterior distribution. This step includes a parameter expansion step, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1211.5901","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":"2026-05-18T03:40:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06v5TxtEjgPYkuUtvToT7XSeaopTUbSyAUshOs07TKevdYleN/DKo82EydsDpfmVkSrRaHzSMgp5nbw7iAfqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:11:37.524306Z"},"content_sha256":"70b2343d94047f3ced986a879ede18277176e43b4bd1b447dd090d90fd000bca","schema_version":"1.0","event_id":"sha256:70b2343d94047f3ced986a879ede18277176e43b4bd1b447dd090d90fd000bca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NE4L6CVDPCZSK7QB6HC546AUPD/bundle.json","state_url":"https://pith.science/pith/NE4L6CVDPCZSK7QB6HC546AUPD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NE4L6CVDPCZSK7QB6HC546AUPD/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":"2026-06-03T20:11:37Z","links":{"resolver":"https://pith.science/pith/NE4L6CVDPCZSK7QB6HC546AUPD","bundle":"https://pith.science/pith/NE4L6CVDPCZSK7QB6HC546AUPD/bundle.json","state":"https://pith.science/pith/NE4L6CVDPCZSK7QB6HC546AUPD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NE4L6CVDPCZSK7QB6HC546AUPD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:NE4L6CVDPCZSK7QB6HC546AUPD","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":"fdd73e53a71abf5d830e93edd9a55d58808253cdf123d507dfda394ea49c5c8f","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-11-26T09:55:27Z","title_canon_sha256":"ca5f0fb4b6c46ab9d077d8a0620896ea412c9e8f3137a35e9aabf0769abac22c"},"schema_version":"1.0","source":{"id":"1211.5901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1211.5901","created_at":"2026-05-18T03:40:01Z"},{"alias_kind":"arxiv_version","alias_value":"1211.5901v1","created_at":"2026-05-18T03:40:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.5901","created_at":"2026-05-18T03:40:01Z"},{"alias_kind":"pith_short_12","alias_value":"NE4L6CVDPCZS","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"NE4L6CVDPCZSK7QB","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"NE4L6CVD","created_at":"2026-05-18T12:27:16Z"}],"graph_snapshots":[{"event_id":"sha256:70b2343d94047f3ced986a879ede18277176e43b4bd1b447dd090d90fd000bca","target":"graph","created_at":"2026-05-18T03:40:01Z","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 the inverse reinforcement learning problem, that is, the problem of learning from, and then predicting or mimicking a controller based on state/action data. We propose a statistical model for such data, derived from the structure of a Markov decision process. Adopting a Bayesian approach to inference, we show how latent variables of the model can be estimated, and how predictions about actions can be made, in a unified framework. A new Markov chain Monte Carlo (MCMC) sampler is devised for simulation from the posterior distribution. This step includes a parameter expansion step, wh","authors_text":"Nick Whiteley, Nicolas Chopin, Sumeetpal S. Singh","cross_cats":["cs.LG","stat.CO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-11-26T09:55:27Z","title":"Bayesian learning of noisy Markov decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1211.5901","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:c322879edb9f0a71da24d255addca4a1e1737f8c3c0e24d24fafe3a8c14ad5b7","target":"record","created_at":"2026-05-18T03:40:01Z","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":"fdd73e53a71abf5d830e93edd9a55d58808253cdf123d507dfda394ea49c5c8f","cross_cats_sorted":["cs.LG","stat.CO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-11-26T09:55:27Z","title_canon_sha256":"ca5f0fb4b6c46ab9d077d8a0620896ea412c9e8f3137a35e9aabf0769abac22c"},"schema_version":"1.0","source":{"id":"1211.5901","kind":"arxiv","version":1}},"canonical_sha256":"6938bf0aa378b3257e01f1c5de781478e5527c5863621d58d99f861649bd58ea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6938bf0aa378b3257e01f1c5de781478e5527c5863621d58d99f861649bd58ea","first_computed_at":"2026-05-18T03:40:01.641189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:40:01.641189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L0sZgmt2hHug3aID69pa/8IoqHMzX9CTtM8bRr8M0y0NTKvYRd/3jP2RBfRkFbT84cesizfKWuQG0e2QfhbHDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:40:01.641632Z","signed_message":"canonical_sha256_bytes"},"source_id":"1211.5901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c322879edb9f0a71da24d255addca4a1e1737f8c3c0e24d24fafe3a8c14ad5b7","sha256:70b2343d94047f3ced986a879ede18277176e43b4bd1b447dd090d90fd000bca"],"state_sha256":"2b2a4b899d014481dc94e22b918e55a9a794297318b24b1dc207c7430d05612a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vI5/hjkSu2uWxgk0dmB9fjIh1olPdA+nP2wir+O1cHkUcDX83rjuIHKQ5Mw3n35C0JniZC/gwlVpoB2nbyIdCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:11:37.526301Z","bundle_sha256":"697e17ac8a944825139cf716cc0316e0b0943ca1c2c845abdc044b5131df4f1b"}}