{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5A7I65I7KMU46HDFTAEZM54BLR","short_pith_number":"pith:5A7I65I7","canonical_record":{"source":{"id":"1803.07055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-19T17:35:14Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"02a3ea84709b16cb22fae6309ddfcaeb124d0208ec8c1461d1772ce84c7a5951","abstract_canon_sha256":"ab98760cbc14a827c4c5c3f41ead6a02dba73aec6a039c81915fdddcccae94e7"},"schema_version":"1.0"},"canonical_sha256":"e83e8f751f5329cf1c6598099677815c6491064be3f40cb871af59fa8a9811b9","source":{"kind":"arxiv","id":"1803.07055","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07055","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07055v1","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07055","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"5A7I65I7KMU4","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5A7I65I7KMU46HDF","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5A7I65I7","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5A7I65I7KMU46HDFTAEZM54BLR","target":"record","payload":{"canonical_record":{"source":{"id":"1803.07055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-19T17:35:14Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"02a3ea84709b16cb22fae6309ddfcaeb124d0208ec8c1461d1772ce84c7a5951","abstract_canon_sha256":"ab98760cbc14a827c4c5c3f41ead6a02dba73aec6a039c81915fdddcccae94e7"},"schema_version":"1.0"},"canonical_sha256":"e83e8f751f5329cf1c6598099677815c6491064be3f40cb871af59fa8a9811b9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:40.456884Z","signature_b64":"xunw+VvX4XNTpR41sx7RZiQitbCv6EWsJbj4sHtzoBOO7M+1GDfI4O5huVlk7PTYmQ4XwbtZc+n8HDhsEmpbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e83e8f751f5329cf1c6598099677815c6491064be3f40cb871af59fa8a9811b9","last_reissued_at":"2026-05-18T00:20:40.456065Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:40.456065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.07055","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":"2026-05-18T00:20:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwB5iAY0aGcDL0+9hfkmPuUSkJUMPJ8VcD9wZ88m3K84MkGE/rbWDYfO+TY0fyAqk1GHsFZ9zurjx5DnqerSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T06:32:42.846660Z"},"content_sha256":"ea46e8d94fa4316ee072191bf5fe5e1f693830c291e0f627922a5a09322059eb","schema_version":"1.0","event_id":"sha256:ea46e8d94fa4316ee072191bf5fe5e1f693830c291e0f627922a5a09322059eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5A7I65I7KMU46HDFTAEZM54BLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simple random search provides a competitive approach to reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelia Guy, Benjamin Recht, Horia Mania","submitted_at":"2018-03-19T17:35:14Z","abstract_excerpt":"A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions. We dispel such beliefs by introducing a random search method for training static, linear policies for continuous control problems, matching state-of-the-art sample efficiency on the benchmark MuJoCo locomotion tasks. Our method also finds a nearly optimal controller for a challenging instance of the Linear Quadratic Regulator, a classical problem in control theory, when the dyna"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07055","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":"2026-05-18T00:20:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UkiUnvYJVeEfV2Vhv4OAnExWkK8n6m3visGPoKNdTZupzdkcnPN2aG1WKem8bc1GakBY/hFBnwPO8jydE2GrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T06:32:42.847000Z"},"content_sha256":"36c7828bedc24b952eb0b070ba80a1e6f0e0c1dca3423bff454ca08059b9e8de","schema_version":"1.0","event_id":"sha256:36c7828bedc24b952eb0b070ba80a1e6f0e0c1dca3423bff454ca08059b9e8de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5A7I65I7KMU46HDFTAEZM54BLR/bundle.json","state_url":"https://pith.science/pith/5A7I65I7KMU46HDFTAEZM54BLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5A7I65I7KMU46HDFTAEZM54BLR/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":"2026-06-20T06:32:42Z","links":{"resolver":"https://pith.science/pith/5A7I65I7KMU46HDFTAEZM54BLR","bundle":"https://pith.science/pith/5A7I65I7KMU46HDFTAEZM54BLR/bundle.json","state":"https://pith.science/pith/5A7I65I7KMU46HDFTAEZM54BLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5A7I65I7KMU46HDFTAEZM54BLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5A7I65I7KMU46HDFTAEZM54BLR","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":"ab98760cbc14a827c4c5c3f41ead6a02dba73aec6a039c81915fdddcccae94e7","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-19T17:35:14Z","title_canon_sha256":"02a3ea84709b16cb22fae6309ddfcaeb124d0208ec8c1461d1772ce84c7a5951"},"schema_version":"1.0","source":{"id":"1803.07055","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07055","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07055v1","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07055","created_at":"2026-05-18T00:20:40Z"},{"alias_kind":"pith_short_12","alias_value":"5A7I65I7KMU4","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5A7I65I7KMU46HDF","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5A7I65I7","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:36c7828bedc24b952eb0b070ba80a1e6f0e0c1dca3423bff454ca08059b9e8de","target":"graph","created_at":"2026-05-18T00:20:40Z","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":"A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions. We dispel such beliefs by introducing a random search method for training static, linear policies for continuous control problems, matching state-of-the-art sample efficiency on the benchmark MuJoCo locomotion tasks. Our method also finds a nearly optimal controller for a challenging instance of the Linear Quadratic Regulator, a classical problem in control theory, when the dyna","authors_text":"Aurelia Guy, Benjamin Recht, Horia Mania","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-19T17:35:14Z","title":"Simple random search provides a competitive approach to reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07055","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:ea46e8d94fa4316ee072191bf5fe5e1f693830c291e0f627922a5a09322059eb","target":"record","created_at":"2026-05-18T00:20:40Z","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":"ab98760cbc14a827c4c5c3f41ead6a02dba73aec6a039c81915fdddcccae94e7","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-19T17:35:14Z","title_canon_sha256":"02a3ea84709b16cb22fae6309ddfcaeb124d0208ec8c1461d1772ce84c7a5951"},"schema_version":"1.0","source":{"id":"1803.07055","kind":"arxiv","version":1}},"canonical_sha256":"e83e8f751f5329cf1c6598099677815c6491064be3f40cb871af59fa8a9811b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e83e8f751f5329cf1c6598099677815c6491064be3f40cb871af59fa8a9811b9","first_computed_at":"2026-05-18T00:20:40.456065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:40.456065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xunw+VvX4XNTpR41sx7RZiQitbCv6EWsJbj4sHtzoBOO7M+1GDfI4O5huVlk7PTYmQ4XwbtZc+n8HDhsEmpbBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:40.456884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.07055","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea46e8d94fa4316ee072191bf5fe5e1f693830c291e0f627922a5a09322059eb","sha256:36c7828bedc24b952eb0b070ba80a1e6f0e0c1dca3423bff454ca08059b9e8de"],"state_sha256":"7bb6efb93c172ca6e1dbe7c6eca625f8fab7005b81a79fb9dcee9e3696ff67cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ICxhjZU3lbh1BosJHueT/IuErHMbXQ7+DMkS1ChJu8+pSSqbgqxKb211YIYOsuZfZ9FovjZfZBVsOrd1Z0p9Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T06:32:42.848947Z","bundle_sha256":"9f84ab036d102d884cfb85457a42548b71dd15b39e0111ef0d70cf7f7602a0b3"}}