{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:KBPKPAQ4QXFE4D5ZYY2UMXJOA6","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":"a56e91206ae2fbe8cef192eabc248eaf37cfd2de307ef745d14981fa016e87f3","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-19T15:06:23Z","title_canon_sha256":"530251d12c04c1cbb9bd82a370134a88012a8ccbe83e36fb215ebc70aa5bc5e3"},"schema_version":"1.0","source":{"id":"1212.2475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1212.2475","created_at":"2026-05-18T03:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"1212.2475v1","created_at":"2026-05-18T03:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1212.2475","created_at":"2026-05-18T03:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"KBPKPAQ4QXFE","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_16","alias_value":"KBPKPAQ4QXFE4D5Z","created_at":"2026-05-18T12:27:11Z"},{"alias_kind":"pith_short_8","alias_value":"KBPKPAQ4","created_at":"2026-05-18T12:27:11Z"}],"graph_snapshots":[{"event_id":"sha256:e3e389afd9d5db7dd3d9c97376294c88ffc1c11a2583d06bfea2a159322087ca","target":"graph","created_at":"2026-05-18T03:38:44Z","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":"The task of estimating the gradient of a function in the presence of noise is     central to several forms of reinforcement learning, including policy search     methods. We present two techniques for reducing gradient estimation errors in     the presence of observable input noise applied to the control signal. The first     method extends the idea of a reinforcement baseline by fitting a local linear     model to the function whose gradient is being estimated; we show how to find     the linear model that minimizes the variance of the gradient estimate, and how     to estimate the model from","authors_text":"Gregory Lawrence, Noah Cowan, Stuart Russell","cross_cats":["cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-19T15:06:23Z","title":"Efficient Gradient Estimation for Motor Control Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1212.2475","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":"sha256:897fab6d69d81c6a3f53210249e76d72d75b07d86282bd31e6503c20b53c671e","target":"record","created_at":"2026-05-18T03:38:44Z","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":"a56e91206ae2fbe8cef192eabc248eaf37cfd2de307ef745d14981fa016e87f3","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-10-19T15:06:23Z","title_canon_sha256":"530251d12c04c1cbb9bd82a370134a88012a8ccbe83e36fb215ebc70aa5bc5e3"},"schema_version":"1.0","source":{"id":"1212.2475","kind":"arxiv","version":1}},"canonical_sha256":"505ea7821c85ca4e0fb9c635465d2e07affd869eb6976318f7b8706589461dee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"505ea7821c85ca4e0fb9c635465d2e07affd869eb6976318f7b8706589461dee","first_computed_at":"2026-05-18T03:38:44.724012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:38:44.724012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ep6jJI4MGkipkJdvw7PNC0qdg6wQdHf4xO+73HNr5T8WRC1PGQ8wdko8G9xTK/XeiOAYLPbh7Cd/C7z28O4tCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:38:44.724577Z","signed_message":"canonical_sha256_bytes"},"source_id":"1212.2475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:897fab6d69d81c6a3f53210249e76d72d75b07d86282bd31e6503c20b53c671e","sha256:e3e389afd9d5db7dd3d9c97376294c88ffc1c11a2583d06bfea2a159322087ca"],"state_sha256":"e14ba54261d5322fb4da460dd83198b2fa9e9334458358dfaa02b62c586221ec"}