{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:2RFXWMUMZ3AFD3Y4DXEP7EQDIQ","short_pith_number":"pith:2RFXWMUM","canonical_record":{"source":{"id":"1301.3878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-16T15:51:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a7c9a9689f9773481e50548d8052fda090adc2e41c93a67ddab8cadb4698b4a","abstract_canon_sha256":"7b89fa6c2dfd0bf6ebba2c8307327f609dae4a2732e11e395fa9c89af64b06c7"},"schema_version":"1.0"},"canonical_sha256":"d44b7b328ccec051ef1c1dc8ff920344177f215107b45190c452d12f619df9d4","source":{"kind":"arxiv","id":"1301.3878","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.3878","created_at":"2026-05-18T03:36:15Z"},{"alias_kind":"arxiv_version","alias_value":"1301.3878v1","created_at":"2026-05-18T03:36:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3878","created_at":"2026-05-18T03:36:15Z"},{"alias_kind":"pith_short_12","alias_value":"2RFXWMUMZ3AF","created_at":"2026-05-18T12:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"2RFXWMUMZ3AFD3Y4","created_at":"2026-05-18T12:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"2RFXWMUM","created_at":"2026-05-18T12:27:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:2RFXWMUMZ3AFD3Y4DXEP7EQDIQ","target":"record","payload":{"canonical_record":{"source":{"id":"1301.3878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-16T15:51:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9a7c9a9689f9773481e50548d8052fda090adc2e41c93a67ddab8cadb4698b4a","abstract_canon_sha256":"7b89fa6c2dfd0bf6ebba2c8307327f609dae4a2732e11e395fa9c89af64b06c7"},"schema_version":"1.0"},"canonical_sha256":"d44b7b328ccec051ef1c1dc8ff920344177f215107b45190c452d12f619df9d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:15.125804Z","signature_b64":"AqL9+Sk6pMjQEEm47oRmy7lEGXJlXMKic5mgqjkjUXOBmYDdwIcp5dh38UiUsXA+KlkwJ2/d2gBn0Jonido6Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d44b7b328ccec051ef1c1dc8ff920344177f215107b45190c452d12f619df9d4","last_reissued_at":"2026-05-18T03:36:15.125323Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:15.125323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.3878","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":"2026-05-18T03:36:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oWRisceOD5uKd+t7iPKzQvlDXoGiPSCyJKV144GDL1lpDkxjpqjPD9X+OcHafWrg88lzajMFkJmlWhVOaU6BDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:25:13.903380Z"},"content_sha256":"82edb2c39434486d5fc1b09a1e16fd4f20a6bd4d80f9b41054f3bd3a6638186b","schema_version":"1.0","event_id":"sha256:82edb2c39434486d5fc1b09a1e16fd4f20a6bd4d80f9b41054f3bd3a6638186b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:2RFXWMUMZ3AFD3Y4DXEP7EQDIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PEGASUS: A Policy Search Method for Large MDPs and POMDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andrew Y. Ng, Michael I. Jordan","submitted_at":"2013-01-16T15:51:42Z","abstract_excerpt":"We propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a model.  Our approach is based on the following observation: Any (PO)MDP can be transformed into an \"equivalent\" POMDP in which all state transitions (given the current state and action) are deterministic.  This reduces the general problem of policy search to one in which we need only consider POMDPs with deterministic transitions.  We give a natural way of estimating the value of all policies in these transformed POMDPs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3878","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":"2026-05-18T03:36:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EFZmmjsJaA00G4Dthyu58UCBbL6/7JyMLSmki/6WnxIUWzo1PkOgz2hlYphTYpvIYvfIXAKxaWr4zzJ6Wu4lDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T09:25:13.903924Z"},"content_sha256":"4613ff239709082f77c93783136f94e7bb488934f66ff4d9cd9207c5be5e9682","schema_version":"1.0","event_id":"sha256:4613ff239709082f77c93783136f94e7bb488934f66ff4d9cd9207c5be5e9682"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2RFXWMUMZ3AFD3Y4DXEP7EQDIQ/bundle.json","state_url":"https://pith.science/pith/2RFXWMUMZ3AFD3Y4DXEP7EQDIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2RFXWMUMZ3AFD3Y4DXEP7EQDIQ/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":"2026-05-21T09:25:13Z","links":{"resolver":"https://pith.science/pith/2RFXWMUMZ3AFD3Y4DXEP7EQDIQ","bundle":"https://pith.science/pith/2RFXWMUMZ3AFD3Y4DXEP7EQDIQ/bundle.json","state":"https://pith.science/pith/2RFXWMUMZ3AFD3Y4DXEP7EQDIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2RFXWMUMZ3AFD3Y4DXEP7EQDIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:2RFXWMUMZ3AFD3Y4DXEP7EQDIQ","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":"7b89fa6c2dfd0bf6ebba2c8307327f609dae4a2732e11e395fa9c89af64b06c7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-16T15:51:42Z","title_canon_sha256":"9a7c9a9689f9773481e50548d8052fda090adc2e41c93a67ddab8cadb4698b4a"},"schema_version":"1.0","source":{"id":"1301.3878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.3878","created_at":"2026-05-18T03:36:15Z"},{"alias_kind":"arxiv_version","alias_value":"1301.3878v1","created_at":"2026-05-18T03:36:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3878","created_at":"2026-05-18T03:36:15Z"},{"alias_kind":"pith_short_12","alias_value":"2RFXWMUMZ3AF","created_at":"2026-05-18T12:27:32Z"},{"alias_kind":"pith_short_16","alias_value":"2RFXWMUMZ3AFD3Y4","created_at":"2026-05-18T12:27:32Z"},{"alias_kind":"pith_short_8","alias_value":"2RFXWMUM","created_at":"2026-05-18T12:27:32Z"}],"graph_snapshots":[{"event_id":"sha256:4613ff239709082f77c93783136f94e7bb488934f66ff4d9cd9207c5be5e9682","target":"graph","created_at":"2026-05-18T03:36:15Z","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 propose a new approach to the problem of searching a space of policies for a Markov decision process (MDP) or a partially observable Markov decision process (POMDP), given a model.  Our approach is based on the following observation: Any (PO)MDP can be transformed into an \"equivalent\" POMDP in which all state transitions (given the current state and action) are deterministic.  This reduces the general problem of policy search to one in which we need only consider POMDPs with deterministic transitions.  We give a natural way of estimating the value of all policies in these transformed POMDPs","authors_text":"Andrew Y. Ng, Michael I. Jordan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-16T15:51:42Z","title":"PEGASUS: A Policy Search Method for Large MDPs and POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3878","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":"sha256:82edb2c39434486d5fc1b09a1e16fd4f20a6bd4d80f9b41054f3bd3a6638186b","target":"record","created_at":"2026-05-18T03:36:15Z","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":"7b89fa6c2dfd0bf6ebba2c8307327f609dae4a2732e11e395fa9c89af64b06c7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-01-16T15:51:42Z","title_canon_sha256":"9a7c9a9689f9773481e50548d8052fda090adc2e41c93a67ddab8cadb4698b4a"},"schema_version":"1.0","source":{"id":"1301.3878","kind":"arxiv","version":1}},"canonical_sha256":"d44b7b328ccec051ef1c1dc8ff920344177f215107b45190c452d12f619df9d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d44b7b328ccec051ef1c1dc8ff920344177f215107b45190c452d12f619df9d4","first_computed_at":"2026-05-18T03:36:15.125323Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:36:15.125323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AqL9+Sk6pMjQEEm47oRmy7lEGXJlXMKic5mgqjkjUXOBmYDdwIcp5dh38UiUsXA+KlkwJ2/d2gBn0Jonido6Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:36:15.125804Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.3878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82edb2c39434486d5fc1b09a1e16fd4f20a6bd4d80f9b41054f3bd3a6638186b","sha256:4613ff239709082f77c93783136f94e7bb488934f66ff4d9cd9207c5be5e9682"],"state_sha256":"38353a18671d6fab7d732d13ec741345498545de52121d844ba9ee9d90be5f27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hnxO9OsMsPeYMkLW0aWyDbmZ+J4zfG6TZKTSdyB00KrBK5YlqP1BVjshZTUHzPG+O6RQlQOsupzAL7raKqHSDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T09:25:13.906579Z","bundle_sha256":"4722b155cf9c95d14fc57ac8baadb58c3ede7056abae781cc0299c3dde1ec437"}}