{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WWWHRLQXO25W2TFREQIHHEVVOA","short_pith_number":"pith:WWWHRLQX","canonical_record":{"source":{"id":"1903.09328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-22T02:48:21Z","cross_cats_sorted":[],"title_canon_sha256":"0f769f23764c2e9f04e23b9bed05ad73ff3621ad228d9b404ecbfca56ec88d37","abstract_canon_sha256":"8039e7ad95ef9d397a459c13213d3c5ebb6dd4d64723689b154cc2a1ddd1f269"},"schema_version":"1.0"},"canonical_sha256":"b5ac78ae1776bb6d4cb124107392b5700c513e0bda4e584c1b6272739072b475","source":{"kind":"arxiv","id":"1903.09328","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09328","created_at":"2026-05-17T23:50:39Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09328v1","created_at":"2026-05-17T23:50:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09328","created_at":"2026-05-17T23:50:39Z"},{"alias_kind":"pith_short_12","alias_value":"WWWHRLQXO25W","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WWWHRLQXO25W2TFR","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WWWHRLQX","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WWWHRLQXO25W2TFREQIHHEVVOA","target":"record","payload":{"canonical_record":{"source":{"id":"1903.09328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-22T02:48:21Z","cross_cats_sorted":[],"title_canon_sha256":"0f769f23764c2e9f04e23b9bed05ad73ff3621ad228d9b404ecbfca56ec88d37","abstract_canon_sha256":"8039e7ad95ef9d397a459c13213d3c5ebb6dd4d64723689b154cc2a1ddd1f269"},"schema_version":"1.0"},"canonical_sha256":"b5ac78ae1776bb6d4cb124107392b5700c513e0bda4e584c1b6272739072b475","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:39.931895Z","signature_b64":"gi8J5/4IVHB4aDmF1rVXUygUHsfi+WWDHLKXE2ZkeJHX2RL/D6mGan7N60+dIDH2bx1subn2uaa2cv68EsnnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5ac78ae1776bb6d4cb124107392b5700c513e0bda4e584c1b6272739072b475","last_reissued_at":"2026-05-17T23:50:39.931367Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:39.931367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.09328","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":"2026-05-17T23:50:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tdfeiDgJ2ce/1B185UmPdfk5+r6CXmVvtiE/kVIzpakjkg6N2hmfGHjKnZ2VSdpy/A922Cc+endZDRb6k+7zCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T20:28:12.811692Z"},"content_sha256":"e76c3ab76d09e8df05d87e3c841e11f6c4b6de2ba04b53e19ceb0b05aa1e197b","schema_version":"1.0","event_id":"sha256:e76c3ab76d09e8df05d87e3c841e11f6c4b6de2ba04b53e19ceb0b05aa1e197b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WWWHRLQXO25W2TFREQIHHEVVOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Intervention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bharat Prakash, Mohit Khatwani, Nicholas Waytowich, Tinoosh Mohsenin","submitted_at":"2019-03-22T02:48:21Z","abstract_excerpt":"Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of little or no consequence. Most real-world applications, however, require training solutions that are safe to operate as catastrophic failures are inadmissible especially when there is human interaction involved. Currently, Safe RL systems use human oversight during training and exploration in order to make sure the RL agent does not go into a catastrophic state."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09328","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":""},"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":"2026-05-17T23:50:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rg+wspBRDpftMpv6yBlFhHnh8doG0uQx2HHp9fFzoDb7BGCrHrXajmwBwawpWCmZZ9U7lJj5eTzKh9FnBi9EDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T20:28:12.812418Z"},"content_sha256":"ec3d7a05cc7b6c4550be4759992c8e49440c836905f765c7310492fa85ac8684","schema_version":"1.0","event_id":"sha256:ec3d7a05cc7b6c4550be4759992c8e49440c836905f765c7310492fa85ac8684"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WWWHRLQXO25W2TFREQIHHEVVOA/bundle.json","state_url":"https://pith.science/pith/WWWHRLQXO25W2TFREQIHHEVVOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WWWHRLQXO25W2TFREQIHHEVVOA/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":"2026-05-30T20:28:12Z","links":{"resolver":"https://pith.science/pith/WWWHRLQXO25W2TFREQIHHEVVOA","bundle":"https://pith.science/pith/WWWHRLQXO25W2TFREQIHHEVVOA/bundle.json","state":"https://pith.science/pith/WWWHRLQXO25W2TFREQIHHEVVOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WWWHRLQXO25W2TFREQIHHEVVOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WWWHRLQXO25W2TFREQIHHEVVOA","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":"8039e7ad95ef9d397a459c13213d3c5ebb6dd4d64723689b154cc2a1ddd1f269","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-22T02:48:21Z","title_canon_sha256":"0f769f23764c2e9f04e23b9bed05ad73ff3621ad228d9b404ecbfca56ec88d37"},"schema_version":"1.0","source":{"id":"1903.09328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09328","created_at":"2026-05-17T23:50:39Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09328v1","created_at":"2026-05-17T23:50:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09328","created_at":"2026-05-17T23:50:39Z"},{"alias_kind":"pith_short_12","alias_value":"WWWHRLQXO25W","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"WWWHRLQXO25W2TFR","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"WWWHRLQX","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:ec3d7a05cc7b6c4550be4759992c8e49440c836905f765c7310492fa85ac8684","target":"graph","created_at":"2026-05-17T23:50:39Z","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":"Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of little or no consequence. Most real-world applications, however, require training solutions that are safe to operate as catastrophic failures are inadmissible especially when there is human interaction involved. Currently, Safe RL systems use human oversight during training and exploration in order to make sure the RL agent does not go into a catastrophic state.","authors_text":"Bharat Prakash, Mohit Khatwani, Nicholas Waytowich, Tinoosh Mohsenin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-22T02:48:21Z","title":"Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Intervention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09328","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:e76c3ab76d09e8df05d87e3c841e11f6c4b6de2ba04b53e19ceb0b05aa1e197b","target":"record","created_at":"2026-05-17T23:50:39Z","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":"8039e7ad95ef9d397a459c13213d3c5ebb6dd4d64723689b154cc2a1ddd1f269","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-22T02:48:21Z","title_canon_sha256":"0f769f23764c2e9f04e23b9bed05ad73ff3621ad228d9b404ecbfca56ec88d37"},"schema_version":"1.0","source":{"id":"1903.09328","kind":"arxiv","version":1}},"canonical_sha256":"b5ac78ae1776bb6d4cb124107392b5700c513e0bda4e584c1b6272739072b475","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5ac78ae1776bb6d4cb124107392b5700c513e0bda4e584c1b6272739072b475","first_computed_at":"2026-05-17T23:50:39.931367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:39.931367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gi8J5/4IVHB4aDmF1rVXUygUHsfi+WWDHLKXE2ZkeJHX2RL/D6mGan7N60+dIDH2bx1subn2uaa2cv68EsnnDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:39.931895Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.09328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e76c3ab76d09e8df05d87e3c841e11f6c4b6de2ba04b53e19ceb0b05aa1e197b","sha256:ec3d7a05cc7b6c4550be4759992c8e49440c836905f765c7310492fa85ac8684"],"state_sha256":"1a2baff565142124813ab3bd7e767c5d570e41309fd78123757abc02f7da04f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFh99TafgCGbcWV6z5jVIvjwwIq1s9U7HB+gM949H23s9+9W9/vZA+8Zy5rd+yf2+We99YiMoQMZMCCJDuNpBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T20:28:12.816020Z","bundle_sha256":"d1091b096d1b7e940a16c70e4de98a90a60c62d0891f8a0ef2e8a6784e81c5c2"}}