{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CT56DUHOUWBF6NCR5BKYMO3I57","short_pith_number":"pith:CT56DUHO","canonical_record":{"source":{"id":"1801.05039","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"20770361605e8bfe0845253a52422d78511ee1138a9aaed396413e6c7424d0ed","abstract_canon_sha256":"5862a4a9cf9d9686f29a70cdeee2a1c7f5a44547537612f4f1a23bdd94ef3f57"},"schema_version":"1.0"},"canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","source":{"kind":"arxiv","id":"1801.05039","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.05039","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"1801.05039v3","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05039","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"CT56DUHOUWBF","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CT56DUHOUWBF6NCR","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CT56DUHO","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CT56DUHOUWBF6NCR5BKYMO3I57","target":"record","payload":{"canonical_record":{"source":{"id":"1801.05039","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"20770361605e8bfe0845253a52422d78511ee1138a9aaed396413e6c7424d0ed","abstract_canon_sha256":"5862a4a9cf9d9686f29a70cdeee2a1c7f5a44547537612f4f1a23bdd94ef3f57"},"schema_version":"1.0"},"canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:38.793374Z","signature_b64":"wTLEvvCeGp08UvlbZxvR59+RBOIXExnC0E7e3uEKl6VYgQ+/mBPx6ps68mDll07I4IZjVvoeG5QqtGd0mFzUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","last_reissued_at":"2026-05-17T23:50:38.792792Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:38.792792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.05039","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w2JqdMqXdN9LrK3RWF7+aZkQeboPHZcMcrQl2HXjwKdN7uPcaJ5tfyFWIUYWTp7Ie6kIg6/7kTzr6+EtGT+ZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:12:35.797636Z"},"content_sha256":"8f10c9af0eb70ae76927484af9dcd92717c990d0373605725d3c385e98ecac45","schema_version":"1.0","event_id":"sha256:8f10c9af0eb70ae76927484af9dcd92717c990d0373605725d3c385e98ecac45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CT56DUHOUWBF6NCR5BKYMO3I57","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Maryam Fazel, Mehran Mesbahi, Rong Ge, Sham M. Kakade","submitted_at":"2018-01-15T21:40:50Z","abstract_excerpt":"Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an \"end-to-end\" approach, directly optimizing the performance metric of interest 3) they inherently allow for richly parameterized policies. A notable drawback is that even in the most basic continuous control problem (that of linear quadratic regulators), these methods must solve a non-convex optimization problem, where little is understood about their efficiency f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05039","kind":"arxiv","version":3},"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":"2026-05-17T23:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v83zJyfo9JdJstC44a4aw6+U8IOV3WCzHn8xM7763qlt+5NUz9h85xEitiNI6umjY4aTJ7O4P952OFbXsXLyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:12:35.797982Z"},"content_sha256":"9f1d16a16ee04066f9a58322d801d8cabdc5498907d6fa2afa4b439c65da20eb","schema_version":"1.0","event_id":"sha256:9f1d16a16ee04066f9a58322d801d8cabdc5498907d6fa2afa4b439c65da20eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/bundle.json","state_url":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CT56DUHOUWBF6NCR5BKYMO3I57/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":"2026-06-03T00:12:35Z","links":{"resolver":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57","bundle":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/bundle.json","state":"https://pith.science/pith/CT56DUHOUWBF6NCR5BKYMO3I57/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CT56DUHOUWBF6NCR5BKYMO3I57/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CT56DUHOUWBF6NCR5BKYMO3I57","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":"5862a4a9cf9d9686f29a70cdeee2a1c7f5a44547537612f4f1a23bdd94ef3f57","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","title_canon_sha256":"20770361605e8bfe0845253a52422d78511ee1138a9aaed396413e6c7424d0ed"},"schema_version":"1.0","source":{"id":"1801.05039","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.05039","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"1801.05039v3","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05039","created_at":"2026-05-17T23:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"CT56DUHOUWBF","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CT56DUHOUWBF6NCR","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CT56DUHO","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:9f1d16a16ee04066f9a58322d801d8cabdc5498907d6fa2afa4b439c65da20eb","target":"graph","created_at":"2026-05-17T23:50:38Z","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":"Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an \"end-to-end\" approach, directly optimizing the performance metric of interest 3) they inherently allow for richly parameterized policies. A notable drawback is that even in the most basic continuous control problem (that of linear quadratic regulators), these methods must solve a non-convex optimization problem, where little is understood about their efficiency f","authors_text":"Maryam Fazel, Mehran Mesbahi, Rong Ge, Sham M. Kakade","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05039","kind":"arxiv","version":3},"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":"sha256:8f10c9af0eb70ae76927484af9dcd92717c990d0373605725d3c385e98ecac45","target":"record","created_at":"2026-05-17T23:50:38Z","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":"5862a4a9cf9d9686f29a70cdeee2a1c7f5a44547537612f4f1a23bdd94ef3f57","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-15T21:40:50Z","title_canon_sha256":"20770361605e8bfe0845253a52422d78511ee1138a9aaed396413e6c7424d0ed"},"schema_version":"1.0","source":{"id":"1801.05039","kind":"arxiv","version":3}},"canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14fbe1d0eea5825f3451e855863b68efe9c924834861b95c86ceb96f13a2072c","first_computed_at":"2026-05-17T23:50:38.792792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:38.792792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wTLEvvCeGp08UvlbZxvR59+RBOIXExnC0E7e3uEKl6VYgQ+/mBPx6ps68mDll07I4IZjVvoeG5QqtGd0mFzUDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:38.793374Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.05039","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f10c9af0eb70ae76927484af9dcd92717c990d0373605725d3c385e98ecac45","sha256:9f1d16a16ee04066f9a58322d801d8cabdc5498907d6fa2afa4b439c65da20eb"],"state_sha256":"7ff67a7ac97b979562e5e9fa127df3fa92b51a04f42dae524e90287322314a4e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7OqEwtGBxjkMLtoS38Otj3pRJHHzJHfHt8MqGxCEVWEgbEgI2SBbwT5+H40M8rRbNCfmNCnk2UYXlvRnMVLvBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T00:12:35.799900Z","bundle_sha256":"6dc1c03b58525d1f181624883ff9a99a792dabb7811a0a57b5af107ce0d2e195"}}