{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GNV4VCE5GSBFE3ZAVXWOV522WM","short_pith_number":"pith:GNV4VCE5","canonical_record":{"source":{"id":"1906.01127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T23:43:16Z","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"0dc3d2030484b83c27dae8e3313f0efd2321e57985a5c19fe3195b7db0dbaf6b","abstract_canon_sha256":"213bb3dd9d1f39d173ebf97d255c64e8e3176ccf353f21d99694a3fa31ce34be"},"schema_version":"1.0"},"canonical_sha256":"336bca889d3482526f20adeceaf75ab30a37acafe4136e6fcb6ad5067483c254","source":{"kind":"arxiv","id":"1906.01127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01127","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01127v1","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01127","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"GNV4VCE5GSBF","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"GNV4VCE5GSBFE3ZA","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"GNV4VCE5","created_at":"2026-07-05T09:09:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GNV4VCE5GSBFE3ZAVXWOV522WM","target":"record","payload":{"canonical_record":{"source":{"id":"1906.01127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T23:43:16Z","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"0dc3d2030484b83c27dae8e3313f0efd2321e57985a5c19fe3195b7db0dbaf6b","abstract_canon_sha256":"213bb3dd9d1f39d173ebf97d255c64e8e3176ccf353f21d99694a3fa31ce34be"},"schema_version":"1.0"},"canonical_sha256":"336bca889d3482526f20adeceaf75ab30a37acafe4136e6fcb6ad5067483c254","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:44.116305Z","signature_b64":"ouH5nmxg6w07KyIWNkrhQri3MxgG+ZswslP9B3HWAD35irkT5gsGOdkwA67hsYeelWNk1ooLddg7J0FBw4HLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"336bca889d3482526f20adeceaf75ab30a37acafe4136e6fcb6ad5067483c254","last_reissued_at":"2026-07-05T09:09:44.115788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:44.115788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.01127","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":"2026-07-05T09:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGjjdo3LBoLFrY9hZg+VPK2Pn3g8o7nX8r2amJTpFkCRs2L0wBi0gAETdud7JtJqkFMKpJvE/n9+xKwqgEiPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:20:44.050861Z"},"content_sha256":"cc53232737e1db53787f98769f747d014eebe3749a185a005d901ea371e80fef","schema_version":"1.0","event_id":"sha256:cc53232737e1db53787f98769f747d014eebe3749a185a005d901ea371e80fef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GNV4VCE5GSBFE3ZAVXWOV522WM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Proximal Reliability Optimization for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Narendra Patwardhan, Zequn Wang","submitted_at":"2019-06-03T23:43:16Z","abstract_excerpt":"Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on absolute or deterministic reward as a metric for optimization process renders reinforcement learning highly susceptible to changes in problem dynamics. We introduce a novel framework that effectively quantizes the uncertainty of the design space and induces robustness in controllers by switching to a reliability-based optimization routine. The data efficiency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01127","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.01127/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":"2026-07-05T09:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKHa12scYKfVoW+0RrLBnT8hf+LduBBVkFf+Z3alI8ArG1NbCGVvWpOoblAJ6nGyJIQ/q4Uwcq6DRjajtT/oDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:20:44.051242Z"},"content_sha256":"8a262eed12f076c7a88be87b7b11252cb848b077a40c8305851181c3daf61360","schema_version":"1.0","event_id":"sha256:8a262eed12f076c7a88be87b7b11252cb848b077a40c8305851181c3daf61360"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GNV4VCE5GSBFE3ZAVXWOV522WM/bundle.json","state_url":"https://pith.science/pith/GNV4VCE5GSBFE3ZAVXWOV522WM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GNV4VCE5GSBFE3ZAVXWOV522WM/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":"2026-07-06T19:20:44Z","links":{"resolver":"https://pith.science/pith/GNV4VCE5GSBFE3ZAVXWOV522WM","bundle":"https://pith.science/pith/GNV4VCE5GSBFE3ZAVXWOV522WM/bundle.json","state":"https://pith.science/pith/GNV4VCE5GSBFE3ZAVXWOV522WM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GNV4VCE5GSBFE3ZAVXWOV522WM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GNV4VCE5GSBFE3ZAVXWOV522WM","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":"213bb3dd9d1f39d173ebf97d255c64e8e3176ccf353f21d99694a3fa31ce34be","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T23:43:16Z","title_canon_sha256":"0dc3d2030484b83c27dae8e3313f0efd2321e57985a5c19fe3195b7db0dbaf6b"},"schema_version":"1.0","source":{"id":"1906.01127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.01127","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.01127v1","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01127","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"GNV4VCE5GSBF","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"GNV4VCE5GSBFE3ZA","created_at":"2026-07-05T09:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"GNV4VCE5","created_at":"2026-07-05T09:09:44Z"}],"graph_snapshots":[{"event_id":"sha256:8a262eed12f076c7a88be87b7b11252cb848b077a40c8305851181c3daf61360","target":"graph","created_at":"2026-07-05T09:09:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1906.01127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the numerous advances, reinforcement learning remains away from widespread acceptance for autonomous controller design as compared to classical methods due to lack of ability to effectively tackle the reality gap. The reliance on absolute or deterministic reward as a metric for optimization process renders reinforcement learning highly susceptible to changes in problem dynamics. We introduce a novel framework that effectively quantizes the uncertainty of the design space and induces robustness in controllers by switching to a reliability-based optimization routine. The data efficiency ","authors_text":"Narendra Patwardhan, Zequn Wang","cross_cats":["cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T23:43:16Z","title":"Proximal Reliability Optimization for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01127","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:cc53232737e1db53787f98769f747d014eebe3749a185a005d901ea371e80fef","target":"record","created_at":"2026-07-05T09:09:44Z","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":"213bb3dd9d1f39d173ebf97d255c64e8e3176ccf353f21d99694a3fa31ce34be","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T23:43:16Z","title_canon_sha256":"0dc3d2030484b83c27dae8e3313f0efd2321e57985a5c19fe3195b7db0dbaf6b"},"schema_version":"1.0","source":{"id":"1906.01127","kind":"arxiv","version":1}},"canonical_sha256":"336bca889d3482526f20adeceaf75ab30a37acafe4136e6fcb6ad5067483c254","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"336bca889d3482526f20adeceaf75ab30a37acafe4136e6fcb6ad5067483c254","first_computed_at":"2026-07-05T09:09:44.115788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:44.115788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ouH5nmxg6w07KyIWNkrhQri3MxgG+ZswslP9B3HWAD35irkT5gsGOdkwA67hsYeelWNk1ooLddg7J0FBw4HLBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:44.116305Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.01127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc53232737e1db53787f98769f747d014eebe3749a185a005d901ea371e80fef","sha256:8a262eed12f076c7a88be87b7b11252cb848b077a40c8305851181c3daf61360"],"state_sha256":"8cfe1b3c290c645cb84e17604895117053a0abafbd0443573c64103a406fd021"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UKiOL4K37EjW8B4KvQBMEj41PFg5g+ya/2ccHukkvLGdWv/GHD99EI0LKf0QV6So/n9SD1A59iO0aRiZNKc9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:20:44.053260Z","bundle_sha256":"72f92c47cd072f3baf13c0d374cea89ddfac594050d49829238636fcd82ce9e2"}}