{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7ENCCS2DNZGKQBRL6ONZEKUL3M","short_pith_number":"pith:7ENCCS2D","canonical_record":{"source":{"id":"1903.02993","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T15:29:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b49aa7f54a3ff42926d1d6b7eae65fa5c3e3fc5f3d62ac71698dd79d4af2e47b","abstract_canon_sha256":"6ba9fd45360bed155302581e57b8e87d9b3a76d1ce33534c652431dcfd51eda0"},"schema_version":"1.0"},"canonical_sha256":"f91a214b436e4ca8062bf39b922a8bdb36b7f1afc33d7669b30d02dfed220ba8","source":{"kind":"arxiv","id":"1903.02993","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02993","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02993v2","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02993","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"pith_short_12","alias_value":"7ENCCS2DNZGK","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7ENCCS2DNZGKQBRL","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7ENCCS2D","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7ENCCS2DNZGKQBRL6ONZEKUL3M","target":"record","payload":{"canonical_record":{"source":{"id":"1903.02993","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T15:29:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b49aa7f54a3ff42926d1d6b7eae65fa5c3e3fc5f3d62ac71698dd79d4af2e47b","abstract_canon_sha256":"6ba9fd45360bed155302581e57b8e87d9b3a76d1ce33534c652431dcfd51eda0"},"schema_version":"1.0"},"canonical_sha256":"f91a214b436e4ca8062bf39b922a8bdb36b7f1afc33d7669b30d02dfed220ba8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:17.466832Z","signature_b64":"tfdno/FFn8uv30NIlMueaeUAVc/Jb5gy5f8R4FbyGiOSIjQ/rZ9byvVWWqpVv0H3NxPkJHi38SF9EaesgB2FCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f91a214b436e4ca8062bf39b922a8bdb36b7f1afc33d7669b30d02dfed220ba8","last_reissued_at":"2026-05-17T23:41:17.466180Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:17.466180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.02993","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":"2026-05-17T23:41:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cQSrLoq+zunA0eyBc7iyEq/pY64uzHrDK6VusR3trrneysMni5SfCPRCLKvGvbEBP+zcaTdYcOSydG9RYP7KBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:34:36.983531Z"},"content_sha256":"0f8e5bcd5c71b15dacca83e43ecbc3cc9764b006dc7d255633498485dce003d4","schema_version":"1.0","event_id":"sha256:0f8e5bcd5c71b15dacca83e43ecbc3cc9764b006dc7d255633498485dce003d4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7ENCCS2DNZGKQBRL6ONZEKUL3M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Robust Blackbox Optimization for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Atil Iscen, Deepali Jain, Jack Parker-Holder, Jasmine Hsu, Krzysztof Choromanski, Vikas Sindhwani, Yunhao Tang, Yuxiang Yang","submitted_at":"2019-03-07T15:29:05Z","abstract_excerpt":"Interest in derivative-free optimization (DFO) and \"evolutionary strategies\" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization problems in Robotics. However, it is well known that DFO methods suffer from prohibitively high sampling complexity. They can also be very sensitive to noisy rewards and stochastic dynamics. In this paper, we propose a new class of algorithms, called Robust Blackbox Optimization (RBO). Remarkably, even if up to $23\\%$ of all the measurements are arbitrarily c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02993","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":"2026-05-17T23:41:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pey+ysRG4oOo/7YS0/rRkGh2DwvkOSYejyUUrG7FItmhFD5Z6CFYPWqMzDqzmkVou5kkCNdTWMAppTCE890xBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T11:34:36.983881Z"},"content_sha256":"129fcb900479dac7e8d22e76ed3b4e283a9cec2f5fb3a6486eceb16f40f00ef4","schema_version":"1.0","event_id":"sha256:129fcb900479dac7e8d22e76ed3b4e283a9cec2f5fb3a6486eceb16f40f00ef4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ENCCS2DNZGKQBRL6ONZEKUL3M/bundle.json","state_url":"https://pith.science/pith/7ENCCS2DNZGKQBRL6ONZEKUL3M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ENCCS2DNZGKQBRL6ONZEKUL3M/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":"2026-06-01T11:34:36Z","links":{"resolver":"https://pith.science/pith/7ENCCS2DNZGKQBRL6ONZEKUL3M","bundle":"https://pith.science/pith/7ENCCS2DNZGKQBRL6ONZEKUL3M/bundle.json","state":"https://pith.science/pith/7ENCCS2DNZGKQBRL6ONZEKUL3M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ENCCS2DNZGKQBRL6ONZEKUL3M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7ENCCS2DNZGKQBRL6ONZEKUL3M","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":"6ba9fd45360bed155302581e57b8e87d9b3a76d1ce33534c652431dcfd51eda0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T15:29:05Z","title_canon_sha256":"b49aa7f54a3ff42926d1d6b7eae65fa5c3e3fc5f3d62ac71698dd79d4af2e47b"},"schema_version":"1.0","source":{"id":"1903.02993","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02993","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02993v2","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02993","created_at":"2026-05-17T23:41:17Z"},{"alias_kind":"pith_short_12","alias_value":"7ENCCS2DNZGK","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7ENCCS2DNZGKQBRL","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7ENCCS2D","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:129fcb900479dac7e8d22e76ed3b4e283a9cec2f5fb3a6486eceb16f40f00ef4","target":"graph","created_at":"2026-05-17T23:41:17Z","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":"Interest in derivative-free optimization (DFO) and \"evolutionary strategies\" (ES) has recently surged in the Reinforcement Learning (RL) community, with growing evidence that they can match state of the art methods for policy optimization problems in Robotics. However, it is well known that DFO methods suffer from prohibitively high sampling complexity. They can also be very sensitive to noisy rewards and stochastic dynamics. In this paper, we propose a new class of algorithms, called Robust Blackbox Optimization (RBO). Remarkably, even if up to $23\\%$ of all the measurements are arbitrarily c","authors_text":"Aldo Pacchiano, Atil Iscen, Deepali Jain, Jack Parker-Holder, Jasmine Hsu, Krzysztof Choromanski, Vikas Sindhwani, Yunhao Tang, Yuxiang Yang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T15:29:05Z","title":"Provably Robust Blackbox Optimization for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02993","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":"sha256:0f8e5bcd5c71b15dacca83e43ecbc3cc9764b006dc7d255633498485dce003d4","target":"record","created_at":"2026-05-17T23:41:17Z","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":"6ba9fd45360bed155302581e57b8e87d9b3a76d1ce33534c652431dcfd51eda0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T15:29:05Z","title_canon_sha256":"b49aa7f54a3ff42926d1d6b7eae65fa5c3e3fc5f3d62ac71698dd79d4af2e47b"},"schema_version":"1.0","source":{"id":"1903.02993","kind":"arxiv","version":2}},"canonical_sha256":"f91a214b436e4ca8062bf39b922a8bdb36b7f1afc33d7669b30d02dfed220ba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f91a214b436e4ca8062bf39b922a8bdb36b7f1afc33d7669b30d02dfed220ba8","first_computed_at":"2026-05-17T23:41:17.466180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:17.466180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tfdno/FFn8uv30NIlMueaeUAVc/Jb5gy5f8R4FbyGiOSIjQ/rZ9byvVWWqpVv0H3NxPkJHi38SF9EaesgB2FCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:17.466832Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.02993","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f8e5bcd5c71b15dacca83e43ecbc3cc9764b006dc7d255633498485dce003d4","sha256:129fcb900479dac7e8d22e76ed3b4e283a9cec2f5fb3a6486eceb16f40f00ef4"],"state_sha256":"49b1031af33e1e2e31b3b3660604012a11d48d39bc84ccc865ba01f786008c5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YZEK0rUZLMwjK8uHeOwvFDkCiXwJDM0yNTcMd6w3K4odfms57VesgOpUywqsLL75iSlRumRFEoKLPKsN6yMADw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T11:34:36.985913Z","bundle_sha256":"8b1f7987b9ef15a5ad0d26d8335fecba411716cad500e8282adb7576a3da5b86"}}