{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GY3C3VXZTFWEPM24EXRUTGEU3I","short_pith_number":"pith:GY3C3VXZ","canonical_record":{"source":{"id":"1906.01786","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T02:12:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a42133fc66844df75eeb86a1371eb5b166ab080f8ab7c8f6fe61dd1bc342450c","abstract_canon_sha256":"fc9b650615e16e91c40b2ac22201e6ffb9b1519cec7b51c954507ffcc52a12d6"},"schema_version":"1.0"},"canonical_sha256":"36362dd6f9996c47b35c25e3499894da08e749a1170ca2341d94595241519522","source":{"kind":"arxiv","id":"1906.01786","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01786","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01786v3","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01786","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"pith_short_12","alias_value":"GY3C3VXZTFWE","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"GY3C3VXZTFWEPM24","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"GY3C3VXZ","created_at":"2026-07-05T04:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GY3C3VXZTFWEPM24EXRUTGEU3I","target":"record","payload":{"canonical_record":{"source":{"id":"1906.01786","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T02:12:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a42133fc66844df75eeb86a1371eb5b166ab080f8ab7c8f6fe61dd1bc342450c","abstract_canon_sha256":"fc9b650615e16e91c40b2ac22201e6ffb9b1519cec7b51c954507ffcc52a12d6"},"schema_version":"1.0"},"canonical_sha256":"36362dd6f9996c47b35c25e3499894da08e749a1170ca2341d94595241519522","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:46.235421Z","signature_b64":"dFc8CZusKyXKTWUSryHuzn3pv6aLvLLI70I3iBUDutG4sjVU9a1GvfNzKanQt8kGTf4qi3TG40W0w6gzwr77Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36362dd6f9996c47b35c25e3499894da08e749a1170ca2341d94595241519522","last_reissued_at":"2026-07-05T04:32:46.234925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:46.234925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.01786","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":"2026-07-05T04:32:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWmxANEPS8FVujxXM0LFkMAG1u1W0FlSn8QsHtqmrBBYbBvFx6a7OSVRsycDVb6lT5BcRWTjAJ8g4UHtq/tpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:02:29.151829Z"},"content_sha256":"addd9abc358c541363fc7cd443e63c224cdb744287e9328d7b836d9a3ef49560","schema_version":"1.0","event_id":"sha256:addd9abc358c541363fc7cd443e63c224cdb744287e9328d7b836d9a3ef49560"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GY3C3VXZTFWEPM24EXRUTGEU3I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Global Optimality Guarantees For Policy Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Russo, Jalaj Bhandari","submitted_at":"2019-06-05T02:12:22Z","abstract_excerpt":"Policy gradients methods apply to complex, poorly understood, control problems by performing stochastic gradient descent over a parameterized class of polices. Unfortunately, even for simple control problems solvable by standard dynamic programming techniques, policy gradient algorithms face non-convex optimization problems and are widely understood to converge only to a stationary point. This work identifies structural properties -- shared by several classic control problems -- that ensure the policy gradient objective function has no suboptimal stationary points despite being non-convex. Whe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01786","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.01786/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:32:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WiworxlT78w0agC0JFIdfbLePKr8B1UwFUxxezuwysKWdrt0fx+MjbOaRXQ0fddmjsk+3BJ1fVn2pCbbuxzwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:02:29.152338Z"},"content_sha256":"251be4a7bb6cbcb81a956dfb833012aab8abf3515260b9308774fc5d3dfcc666","schema_version":"1.0","event_id":"sha256:251be4a7bb6cbcb81a956dfb833012aab8abf3515260b9308774fc5d3dfcc666"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GY3C3VXZTFWEPM24EXRUTGEU3I/bundle.json","state_url":"https://pith.science/pith/GY3C3VXZTFWEPM24EXRUTGEU3I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GY3C3VXZTFWEPM24EXRUTGEU3I/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":"2026-08-07T18:02:29Z","links":{"resolver":"https://pith.science/pith/GY3C3VXZTFWEPM24EXRUTGEU3I","bundle":"https://pith.science/pith/GY3C3VXZTFWEPM24EXRUTGEU3I/bundle.json","state":"https://pith.science/pith/GY3C3VXZTFWEPM24EXRUTGEU3I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GY3C3VXZTFWEPM24EXRUTGEU3I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GY3C3VXZTFWEPM24EXRUTGEU3I","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":"fc9b650615e16e91c40b2ac22201e6ffb9b1519cec7b51c954507ffcc52a12d6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T02:12:22Z","title_canon_sha256":"a42133fc66844df75eeb86a1371eb5b166ab080f8ab7c8f6fe61dd1bc342450c"},"schema_version":"1.0","source":{"id":"1906.01786","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01786","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01786v3","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01786","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"pith_short_12","alias_value":"GY3C3VXZTFWE","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"GY3C3VXZTFWEPM24","created_at":"2026-07-05T04:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"GY3C3VXZ","created_at":"2026-07-05T04:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:251be4a7bb6cbcb81a956dfb833012aab8abf3515260b9308774fc5d3dfcc666","target":"graph","created_at":"2026-07-05T04:32:46Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1906.01786/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradients methods apply to complex, poorly understood, control problems by performing stochastic gradient descent over a parameterized class of polices. Unfortunately, even for simple control problems solvable by standard dynamic programming techniques, policy gradient algorithms face non-convex optimization problems and are widely understood to converge only to a stationary point. This work identifies structural properties -- shared by several classic control problems -- that ensure the policy gradient objective function has no suboptimal stationary points despite being non-convex. Whe","authors_text":"Daniel Russo, Jalaj Bhandari","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T02:12:22Z","title":"Global Optimality Guarantees For Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01786","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:addd9abc358c541363fc7cd443e63c224cdb744287e9328d7b836d9a3ef49560","target":"record","created_at":"2026-07-05T04:32:46Z","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":"fc9b650615e16e91c40b2ac22201e6ffb9b1519cec7b51c954507ffcc52a12d6","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T02:12:22Z","title_canon_sha256":"a42133fc66844df75eeb86a1371eb5b166ab080f8ab7c8f6fe61dd1bc342450c"},"schema_version":"1.0","source":{"id":"1906.01786","kind":"arxiv","version":3}},"canonical_sha256":"36362dd6f9996c47b35c25e3499894da08e749a1170ca2341d94595241519522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36362dd6f9996c47b35c25e3499894da08e749a1170ca2341d94595241519522","first_computed_at":"2026-07-05T04:32:46.234925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:46.234925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dFc8CZusKyXKTWUSryHuzn3pv6aLvLLI70I3iBUDutG4sjVU9a1GvfNzKanQt8kGTf4qi3TG40W0w6gzwr77Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:46.235421Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.01786","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:addd9abc358c541363fc7cd443e63c224cdb744287e9328d7b836d9a3ef49560","sha256:251be4a7bb6cbcb81a956dfb833012aab8abf3515260b9308774fc5d3dfcc666"],"state_sha256":"01f148a5c5b5b198398a65b49fa74007912fa0d78e2a693d0b47861d17941258"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nu9gHgORQt6XTcRpEdg1XwZ4gxZvMg4BxLzSOnr9urV9/wlV64V22156V9vyVgKN1vMJ+QZzrWivorJjR3lLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:02:29.156655Z","bundle_sha256":"32729779b1b690c8ab662e3db2135af727b20393970085ed4f51e6da5df197af"}}