{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RNGRIJL4HVGRUWOZ365I3MB65T","short_pith_number":"pith:RNGRIJL4","canonical_record":{"source":{"id":"1703.03864","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-10T23:02:19Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"621fdf04f6a7ecce24860b6a43cb7392371960e54a33f9a5668de90859aed9fc","abstract_canon_sha256":"b51868ea0ae6c040f9d4afc1ad404a73f9acf582cfbd0d4203eccf6a3ce75237"},"schema_version":"1.0"},"canonical_sha256":"8b4d14257c3d4d1a59d9dfba8db03eecc1e91f8e40ddef472d0df1c9dbdccb25","source":{"kind":"arxiv","id":"1703.03864","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.03864","created_at":"2026-05-18T00:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"1703.03864v2","created_at":"2026-05-18T00:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03864","created_at":"2026-05-18T00:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"RNGRIJL4HVGR","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RNGRIJL4HVGRUWOZ","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RNGRIJL4","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RNGRIJL4HVGRUWOZ365I3MB65T","target":"record","payload":{"canonical_record":{"source":{"id":"1703.03864","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-10T23:02:19Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"621fdf04f6a7ecce24860b6a43cb7392371960e54a33f9a5668de90859aed9fc","abstract_canon_sha256":"b51868ea0ae6c040f9d4afc1ad404a73f9acf582cfbd0d4203eccf6a3ce75237"},"schema_version":"1.0"},"canonical_sha256":"8b4d14257c3d4d1a59d9dfba8db03eecc1e91f8e40ddef472d0df1c9dbdccb25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:46.479990Z","signature_b64":"BBpTkO9IN82H2t1dSVWA3BrwIUO3gq3mZzz8CgzB7wGQlwJ7tBLHj6YBSVI6Q1LXJ/5A1yxdWetJ+XMcHqUxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b4d14257c3d4d1a59d9dfba8db03eecc1e91f8e40ddef472d0df1c9dbdccb25","last_reissued_at":"2026-05-18T00:35:46.479381Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:46.479381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.03864","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:35:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GlnVjxHxLK7So7+zrgLn4s6XJ0kXhA6wqQjByNumpUbwX2mtf95hu2xhEUud0tyrQ1tByPwslotG2kuCjmjkBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:18:25.896486Z"},"content_sha256":"2505a71ff366f171044c49aa7d829d4eecbf378b1d45ca70bb37bf9d6419163e","schema_version":"1.0","event_id":"sha256:2505a71ff366f171044c49aa7d829d4eecbf378b1d45ca70bb37bf9d6419163e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RNGRIJL4HVGRUWOZ365I3MB65T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Ilya Sutskever, Jonathan Ho, Szymon Sidor, Tim Salimans, Xi Chen","submitted_at":"2017-03-10T23:02:19Z","abstract_excerpt":"We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients. Experiments on MuJoCo and Atari show that ES is a viable solution strategy that scales extremely well with the number of CPUs available: By using a novel communication strategy based on common random numbers, our ES implementation only needs to communicate scalars, making it possible to scale to over a thousand parallel workers. This allows us to solve 3D humanoid walking in 10 minutes and obtain competitive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03864","kind":"arxiv","version":2},"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":"2026-05-18T00:35:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OC/cRqSmOd4guJQp3FVKg0GIsdiuhpQawm/g7mo17kR5nsJ9PhQHeKN0wXvA1w0NRyIQ50+45mEEHi97NPoJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T16:18:25.896857Z"},"content_sha256":"2c1d1bffa424e77e86f5141ccb7c5ff45ae41eca44669b41d9304b2f767e4c32","schema_version":"1.0","event_id":"sha256:2c1d1bffa424e77e86f5141ccb7c5ff45ae41eca44669b41d9304b2f767e4c32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RNGRIJL4HVGRUWOZ365I3MB65T/bundle.json","state_url":"https://pith.science/pith/RNGRIJL4HVGRUWOZ365I3MB65T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RNGRIJL4HVGRUWOZ365I3MB65T/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":"2026-05-27T16:18:25Z","links":{"resolver":"https://pith.science/pith/RNGRIJL4HVGRUWOZ365I3MB65T","bundle":"https://pith.science/pith/RNGRIJL4HVGRUWOZ365I3MB65T/bundle.json","state":"https://pith.science/pith/RNGRIJL4HVGRUWOZ365I3MB65T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RNGRIJL4HVGRUWOZ365I3MB65T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RNGRIJL4HVGRUWOZ365I3MB65T","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":"b51868ea0ae6c040f9d4afc1ad404a73f9acf582cfbd0d4203eccf6a3ce75237","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-10T23:02:19Z","title_canon_sha256":"621fdf04f6a7ecce24860b6a43cb7392371960e54a33f9a5668de90859aed9fc"},"schema_version":"1.0","source":{"id":"1703.03864","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.03864","created_at":"2026-05-18T00:35:46Z"},{"alias_kind":"arxiv_version","alias_value":"1703.03864v2","created_at":"2026-05-18T00:35:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.03864","created_at":"2026-05-18T00:35:46Z"},{"alias_kind":"pith_short_12","alias_value":"RNGRIJL4HVGR","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RNGRIJL4HVGRUWOZ","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RNGRIJL4","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:2c1d1bffa424e77e86f5141ccb7c5ff45ae41eca44669b41d9304b2f767e4c32","target":"graph","created_at":"2026-05-18T00:35:46Z","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"},"paper":{"abstract_excerpt":"We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients. Experiments on MuJoCo and Atari show that ES is a viable solution strategy that scales extremely well with the number of CPUs available: By using a novel communication strategy based on common random numbers, our ES implementation only needs to communicate scalars, making it possible to scale to over a thousand parallel workers. This allows us to solve 3D humanoid walking in 10 minutes and obtain competitive","authors_text":"Ilya Sutskever, Jonathan Ho, Szymon Sidor, Tim Salimans, Xi Chen","cross_cats":["cs.AI","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-10T23:02:19Z","title":"Evolution Strategies as a Scalable Alternative to Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.03864","kind":"arxiv","version":2},"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":"sha256:2505a71ff366f171044c49aa7d829d4eecbf378b1d45ca70bb37bf9d6419163e","target":"record","created_at":"2026-05-18T00:35:46Z","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":"b51868ea0ae6c040f9d4afc1ad404a73f9acf582cfbd0d4203eccf6a3ce75237","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-03-10T23:02:19Z","title_canon_sha256":"621fdf04f6a7ecce24860b6a43cb7392371960e54a33f9a5668de90859aed9fc"},"schema_version":"1.0","source":{"id":"1703.03864","kind":"arxiv","version":2}},"canonical_sha256":"8b4d14257c3d4d1a59d9dfba8db03eecc1e91f8e40ddef472d0df1c9dbdccb25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b4d14257c3d4d1a59d9dfba8db03eecc1e91f8e40ddef472d0df1c9dbdccb25","first_computed_at":"2026-05-18T00:35:46.479381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:46.479381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBpTkO9IN82H2t1dSVWA3BrwIUO3gq3mZzz8CgzB7wGQlwJ7tBLHj6YBSVI6Q1LXJ/5A1yxdWetJ+XMcHqUxAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:46.479990Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.03864","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2505a71ff366f171044c49aa7d829d4eecbf378b1d45ca70bb37bf9d6419163e","sha256:2c1d1bffa424e77e86f5141ccb7c5ff45ae41eca44669b41d9304b2f767e4c32"],"state_sha256":"345ff4a33dad2ba497335c5af39bf6bd1b2f977d18d43214103fa6c9e488617a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bH1i3Rbr4Wl96VKZJ6qvzq0OS9iriiHr0K25kxdf6QxVRILEUW98DCq7FUUKbAedU3w57p1BtKKuarY8N43RDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T16:18:25.899944Z","bundle_sha256":"65583b3ce263b1bc42015564f867329be9c4cf6a5b06f0c65363df8a96ea3e29"}}