{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DGYNP5F2YB2WJL3HY3QUMGB5RL","short_pith_number":"pith:DGYNP5F2","canonical_record":{"source":{"id":"2102.10643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T16:50:17Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"e64044915cd68ef11b2deaaa4185dd2577d6f9c859540994ab499290dafb66bf","abstract_canon_sha256":"2158d83047aff5c64e9d9151ef5ecf4462b36a1e710b7e8bfa160b532ce12d4c"},"schema_version":"1.0"},"canonical_sha256":"19b0d7f4bac07564af67c6e146183d8ad2e6afa245f896c36321ff41d200bc85","source":{"kind":"arxiv","id":"2102.10643","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10643","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10643v2","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10643","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"DGYNP5F2YB2W","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"DGYNP5F2YB2WJL3H","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"DGYNP5F2","created_at":"2026-07-05T02:36:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DGYNP5F2YB2WJL3HY3QUMGB5RL","target":"record","payload":{"canonical_record":{"source":{"id":"2102.10643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T16:50:17Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"e64044915cd68ef11b2deaaa4185dd2577d6f9c859540994ab499290dafb66bf","abstract_canon_sha256":"2158d83047aff5c64e9d9151ef5ecf4462b36a1e710b7e8bfa160b532ce12d4c"},"schema_version":"1.0"},"canonical_sha256":"19b0d7f4bac07564af67c6e146183d8ad2e6afa245f896c36321ff41d200bc85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:22.653083Z","signature_b64":"pgDf9ahgZujtvoL1aPrGLVwub/YseHObONQ+upkwNB5vGJ/3pWbnCnRTYd9xn9F/GLMwn3Se6A4ZGLxSAihhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19b0d7f4bac07564af67c6e146183d8ad2e6afa245f896c36321ff41d200bc85","last_reissued_at":"2026-07-05T02:36:22.652673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:22.652673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.10643","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":"2026-07-05T02:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kr3JYtDqL3cvT0dcSM1KuJdUpUZJOrzyxG7WawcESL/rLaQYW57Eav/eCuT90wVoLhr8XKPoEfooN3LpZHZmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:44:35.048469Z"},"content_sha256":"495e9eb7d9c367b7f32b7b8523a2676c254a0edb9ab7d7d8f8a0f34204e36d4f","schema_version":"1.0","event_id":"sha256:495e9eb7d9c367b7f32b7b8523a2676c254a0edb9ab7d7d8f8a0f34204e36d4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DGYNP5F2YB2WJL3HY3QUMGB5RL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning Using Robust Action Governor","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Anouck Girard, Dimitar Filev, H. Eric Tseng, Ilya Kolmanovsky, Nan Li, Yutong Li","submitted_at":"2021-02-21T16:50:17Z","abstract_excerpt":"Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially to those for safety-critical systems. In this paper, we introduce a framework for safe RL that is based on integration of a RL algorithm with an add-on safety supervision module, called the Robust Action Governor (RAG), which exploits set-theoretic techniques and online optimization to manage safety-related requirements during learning. We illustrate this pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10643","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.10643/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":"2026-07-05T02:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d6c2Tnv0VXODKwgkxnETco9IzGT+6z7xa+/wwaJLzYAOAeowY1cE5tCH1gxl7aDKSJCrILATVB40tulsk4VeDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T20:44:35.049381Z"},"content_sha256":"a8b0316063e86d97197a08e83d904bc1375591a7602d29f552a009262857b98e","schema_version":"1.0","event_id":"sha256:a8b0316063e86d97197a08e83d904bc1375591a7602d29f552a009262857b98e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DGYNP5F2YB2WJL3HY3QUMGB5RL/bundle.json","state_url":"https://pith.science/pith/DGYNP5F2YB2WJL3HY3QUMGB5RL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DGYNP5F2YB2WJL3HY3QUMGB5RL/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":"2026-08-13T20:44:35Z","links":{"resolver":"https://pith.science/pith/DGYNP5F2YB2WJL3HY3QUMGB5RL","bundle":"https://pith.science/pith/DGYNP5F2YB2WJL3HY3QUMGB5RL/bundle.json","state":"https://pith.science/pith/DGYNP5F2YB2WJL3HY3QUMGB5RL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DGYNP5F2YB2WJL3HY3QUMGB5RL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DGYNP5F2YB2WJL3HY3QUMGB5RL","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":"2158d83047aff5c64e9d9151ef5ecf4462b36a1e710b7e8bfa160b532ce12d4c","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T16:50:17Z","title_canon_sha256":"e64044915cd68ef11b2deaaa4185dd2577d6f9c859540994ab499290dafb66bf"},"schema_version":"1.0","source":{"id":"2102.10643","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.10643","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2102.10643v2","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.10643","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"DGYNP5F2YB2W","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"DGYNP5F2YB2WJL3H","created_at":"2026-07-05T02:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"DGYNP5F2","created_at":"2026-07-05T02:36:22Z"}],"graph_snapshots":[{"event_id":"sha256:a8b0316063e86d97197a08e83d904bc1375591a7602d29f552a009262857b98e","target":"graph","created_at":"2026-07-05T02:36:22Z","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/2102.10643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) is essentially a trial-and-error learning procedure which may cause unsafe behavior during the exploration-and-exploitation process. This hinders the application of RL to real-world control problems, especially to those for safety-critical systems. In this paper, we introduce a framework for safe RL that is based on integration of a RL algorithm with an add-on safety supervision module, called the Robust Action Governor (RAG), which exploits set-theoretic techniques and online optimization to manage safety-related requirements during learning. We illustrate this pro","authors_text":"Anouck Girard, Dimitar Filev, H. Eric Tseng, Ilya Kolmanovsky, Nan Li, Yutong Li","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T16:50:17Z","title":"Safe Reinforcement Learning Using Robust Action Governor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.10643","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":"sha256:495e9eb7d9c367b7f32b7b8523a2676c254a0edb9ab7d7d8f8a0f34204e36d4f","target":"record","created_at":"2026-07-05T02:36:22Z","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":"2158d83047aff5c64e9d9151ef5ecf4462b36a1e710b7e8bfa160b532ce12d4c","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-21T16:50:17Z","title_canon_sha256":"e64044915cd68ef11b2deaaa4185dd2577d6f9c859540994ab499290dafb66bf"},"schema_version":"1.0","source":{"id":"2102.10643","kind":"arxiv","version":2}},"canonical_sha256":"19b0d7f4bac07564af67c6e146183d8ad2e6afa245f896c36321ff41d200bc85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19b0d7f4bac07564af67c6e146183d8ad2e6afa245f896c36321ff41d200bc85","first_computed_at":"2026-07-05T02:36:22.652673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:22.652673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pgDf9ahgZujtvoL1aPrGLVwub/YseHObONQ+upkwNB5vGJ/3pWbnCnRTYd9xn9F/GLMwn3Se6A4ZGLxSAihhAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:22.653083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.10643","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:495e9eb7d9c367b7f32b7b8523a2676c254a0edb9ab7d7d8f8a0f34204e36d4f","sha256:a8b0316063e86d97197a08e83d904bc1375591a7602d29f552a009262857b98e"],"state_sha256":"bb530a3c7f5a29050fa857e2beec868dd078c7dfbe148a6587101acdb4b52ff9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MurEZZgxnzvsY50U6XCaZeYLhMQvpnQ+EV884PiHxbrDxNem8eFct8HLiX3n/qz75ywh7d/4kfcbhXyAMT2KAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T20:44:35.090851Z","bundle_sha256":"95d4e023b12ff7d3e3a2885ad4e6256dc5189aa6ec76753f1483b52be42dee7f"}}