{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FVK5WIGG7WMM55VWECOIFY3N2V","short_pith_number":"pith:FVK5WIGG","canonical_record":{"source":{"id":"2103.14606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2021-03-26T17:16:39Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"8b4e5a14d9a7835d3ab727c6dc37cdbdb84b5211a82ff3a8598b98c03e2d4315","abstract_canon_sha256":"6681949c70e06e44b66c6b3350fa25e41efb1e0a0d9aae9fceedc1eb25836964"},"schema_version":"1.0"},"canonical_sha256":"2d55db20c6fd98cef6b6209c82e36dd55bb06b3eb29062da4731cfd419765b17","source":{"kind":"arxiv","id":"2103.14606","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14606","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14606v1","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14606","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"FVK5WIGG7WMM","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"FVK5WIGG7WMM55VW","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"FVK5WIGG","created_at":"2026-07-05T02:26:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FVK5WIGG7WMM55VWECOIFY3N2V","target":"record","payload":{"canonical_record":{"source":{"id":"2103.14606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2021-03-26T17:16:39Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"8b4e5a14d9a7835d3ab727c6dc37cdbdb84b5211a82ff3a8598b98c03e2d4315","abstract_canon_sha256":"6681949c70e06e44b66c6b3350fa25e41efb1e0a0d9aae9fceedc1eb25836964"},"schema_version":"1.0"},"canonical_sha256":"2d55db20c6fd98cef6b6209c82e36dd55bb06b3eb29062da4731cfd419765b17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:42.909235Z","signature_b64":"//hH9txqvpXxvCdE/aPKYAqTTlyXuxrL3oqHzVh/cdW+KdfbEXPS50/Ri8/39AD5FxdS+rjHK32dGoTsPPGoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d55db20c6fd98cef6b6209c82e36dd55bb06b3eb29062da4731cfd419765b17","last_reissued_at":"2026-07-05T02:26:42.908865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:42.908865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.14606","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":"2026-07-05T02:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GUcTbhLPkHs3V7L7yE127ozgo92O5LXZqCSDcr9jCHauEDa5Xb1H6mPlYQbzInFsMdSe1bKTyO8vBVaiD+AYBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:30:30.655664Z"},"content_sha256":"8c2305294aaedfa006eff66b0358c41d284b39c1e3a71aa8bb053bbe7a151baf","schema_version":"1.0","event_id":"sha256:8c2305294aaedfa006eff66b0358c41d284b39c1e3a71aa8bb053bbe7a151baf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FVK5WIGG7WMM55VWECOIFY3N2V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Convex Programming Approach to Data-Driven Risk-Averse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Hamidreza Modares, Majid Mazouchi, Subramanya Nageshrao, Yuzhen Han","submitted_at":"2021-03-26T17:16:39Z","abstract_excerpt":"This paper presents a model-free reinforcement learning (RL) algorithm to solve the risk-averse optimal control (RAOC) problem for discrete-time nonlinear systems. While successful RL algorithms have been presented to learn optimal control solutions under epistemic uncertainties (i.e., lack of knowledge of system dynamics), they do so by optimizing the expected utility of outcomes, which ignores the variance of cost under aleatory uncertainties (i.e., randomness). Performance-critical systems, however, must not only optimize the expected performance, but also reduce its variance to avoid perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14606","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/2103.14606/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":"2026-07-05T02:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"acAEOCtzVb4CKf/drLCAFAp8eGSy+pVOpV77mIsFPx9hS+uSlTf/VwWO/vB7K7mCBO+OvZU8nsjx3Y44Y2wCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:30:30.656167Z"},"content_sha256":"a1df7f2ad36941b35f2031b26283046b3a453d684d8c63d9f775c6adf2f86aa9","schema_version":"1.0","event_id":"sha256:a1df7f2ad36941b35f2031b26283046b3a453d684d8c63d9f775c6adf2f86aa9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FVK5WIGG7WMM55VWECOIFY3N2V/bundle.json","state_url":"https://pith.science/pith/FVK5WIGG7WMM55VWECOIFY3N2V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FVK5WIGG7WMM55VWECOIFY3N2V/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":"2026-08-04T00:30:30Z","links":{"resolver":"https://pith.science/pith/FVK5WIGG7WMM55VWECOIFY3N2V","bundle":"https://pith.science/pith/FVK5WIGG7WMM55VWECOIFY3N2V/bundle.json","state":"https://pith.science/pith/FVK5WIGG7WMM55VWECOIFY3N2V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FVK5WIGG7WMM55VWECOIFY3N2V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FVK5WIGG7WMM55VWECOIFY3N2V","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":"6681949c70e06e44b66c6b3350fa25e41efb1e0a0d9aae9fceedc1eb25836964","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2021-03-26T17:16:39Z","title_canon_sha256":"8b4e5a14d9a7835d3ab727c6dc37cdbdb84b5211a82ff3a8598b98c03e2d4315"},"schema_version":"1.0","source":{"id":"2103.14606","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14606","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14606v1","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14606","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"FVK5WIGG7WMM","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"FVK5WIGG7WMM55VW","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"FVK5WIGG","created_at":"2026-07-05T02:26:42Z"}],"graph_snapshots":[{"event_id":"sha256:a1df7f2ad36941b35f2031b26283046b3a453d684d8c63d9f775c6adf2f86aa9","target":"graph","created_at":"2026-07-05T02:26:42Z","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/2103.14606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a model-free reinforcement learning (RL) algorithm to solve the risk-averse optimal control (RAOC) problem for discrete-time nonlinear systems. While successful RL algorithms have been presented to learn optimal control solutions under epistemic uncertainties (i.e., lack of knowledge of system dynamics), they do so by optimizing the expected utility of outcomes, which ignores the variance of cost under aleatory uncertainties (i.e., randomness). Performance-critical systems, however, must not only optimize the expected performance, but also reduce its variance to avoid perfo","authors_text":"Hamidreza Modares, Majid Mazouchi, Subramanya Nageshrao, Yuzhen Han","cross_cats":["cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2021-03-26T17:16:39Z","title":"A Convex Programming Approach to Data-Driven Risk-Averse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14606","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":"sha256:8c2305294aaedfa006eff66b0358c41d284b39c1e3a71aa8bb053bbe7a151baf","target":"record","created_at":"2026-07-05T02:26:42Z","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":"6681949c70e06e44b66c6b3350fa25e41efb1e0a0d9aae9fceedc1eb25836964","cross_cats_sorted":["cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2021-03-26T17:16:39Z","title_canon_sha256":"8b4e5a14d9a7835d3ab727c6dc37cdbdb84b5211a82ff3a8598b98c03e2d4315"},"schema_version":"1.0","source":{"id":"2103.14606","kind":"arxiv","version":1}},"canonical_sha256":"2d55db20c6fd98cef6b6209c82e36dd55bb06b3eb29062da4731cfd419765b17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d55db20c6fd98cef6b6209c82e36dd55bb06b3eb29062da4731cfd419765b17","first_computed_at":"2026-07-05T02:26:42.908865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:42.908865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"//hH9txqvpXxvCdE/aPKYAqTTlyXuxrL3oqHzVh/cdW+KdfbEXPS50/Ri8/39AD5FxdS+rjHK32dGoTsPPGoBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:42.909235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.14606","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c2305294aaedfa006eff66b0358c41d284b39c1e3a71aa8bb053bbe7a151baf","sha256:a1df7f2ad36941b35f2031b26283046b3a453d684d8c63d9f775c6adf2f86aa9"],"state_sha256":"ac14f6a2923e10e3cb0340202485e5577f49a2435a18f42c0f2d9adc7f8b9f24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XbdPiIOoBUQqfk3y+aK92gkt3kMNpgIrK5F8XkV2cJl0gKlFSsYZtFmFqy5aarZAHWeKW04Hj7ykZE0wT9f4DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:30:30.661432Z","bundle_sha256":"8f8431e049a970ac2905e9b34d341821feca73335e8d945c9d794a75793a069c"}}