{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CXSMJ4SK6LRIP5AGNVFUP3QBHJ","short_pith_number":"pith:CXSMJ4SK","canonical_record":{"source":{"id":"2003.01303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-03T02:53:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fa89778939bde012bae94f750615c832f36d5e215c16e87827ce38601b15d6dc","abstract_canon_sha256":"a7a69511587a635f48a0dfdeb8f3ef3c6a3b35cc87dae257202430013ad80894"},"schema_version":"1.0"},"canonical_sha256":"15e4c4f24af2e287f4066d4b47ee013a46d67fd0025fbd33869587394d29b0f3","source":{"kind":"arxiv","id":"2003.01303","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.01303","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"2003.01303v1","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01303","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"CXSMJ4SK6LRI","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"pith_short_16","alias_value":"CXSMJ4SK6LRIP5AG","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"pith_short_8","alias_value":"CXSMJ4SK","created_at":"2026-07-05T00:45:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CXSMJ4SK6LRIP5AGNVFUP3QBHJ","target":"record","payload":{"canonical_record":{"source":{"id":"2003.01303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-03T02:53:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fa89778939bde012bae94f750615c832f36d5e215c16e87827ce38601b15d6dc","abstract_canon_sha256":"a7a69511587a635f48a0dfdeb8f3ef3c6a3b35cc87dae257202430013ad80894"},"schema_version":"1.0"},"canonical_sha256":"15e4c4f24af2e287f4066d4b47ee013a46d67fd0025fbd33869587394d29b0f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:27.268409Z","signature_b64":"XFpEn5LBFFKBTVRBxlPZAiVxdFJFOMKEkTGm/76A89BKYrJhcbRTMIeo3nCtE4n+TSawwkLogr6S6m85OXMsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15e4c4f24af2e287f4066d4b47ee013a46d67fd0025fbd33869587394d29b0f3","last_reissued_at":"2026-07-05T00:45:27.267974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:27.267974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.01303","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":"2026-07-05T00:45:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R7JXo5FF5Rh4+Ze7vbWOh+qdRxR3eEIc6YAHz6rYO69o4Z4XexUWjSdr/qQUvWbRqEX/NfRbTtNWaRNjyEPqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:35:00.804628Z"},"content_sha256":"9c34e4ef2edb3c0fc8a4a56a128e7488b12df46a88d763aa2f87b8c3b132e83d","schema_version":"1.0","event_id":"sha256:9c34e4ef2edb3c0fc8a4a56a128e7488b12df46a88d763aa2f87b8c3b132e83d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CXSMJ4SK6LRIP5AGNVFUP3QBHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Huei Peng, Jingliang Duan, Lu Wen, Shaobing Xu, Shengbo Eben Li","submitted_at":"2020-03-03T02:53:30Z","abstract_excerpt":"Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two predominant problems: behaviours are unexplainable, and they cannot guarantee safety under new scenarios. This paper presents a safe RL algorithm, called Parallel Constrained Policy Optimization (PCPO), for two autonomous driving tasks. PCPO extends today's common actor-critic architecture to a three-component learning framework, in which three neural networks a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01303","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/2003.01303/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":"2026-07-05T00:45:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rEwaYHro7hDPHxVn69Y63kDtyp5u5fF/mqfcN+2jNx8jaJOuXeDr8AddPM7IaIy3HgkN11HKIhc3qa+SiKMPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:35:00.805256Z"},"content_sha256":"d9acabf41a3ad430797327984b3fa04ccca647a2aec7b71762a48256b63ef2fd","schema_version":"1.0","event_id":"sha256:d9acabf41a3ad430797327984b3fa04ccca647a2aec7b71762a48256b63ef2fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXSMJ4SK6LRIP5AGNVFUP3QBHJ/bundle.json","state_url":"https://pith.science/pith/CXSMJ4SK6LRIP5AGNVFUP3QBHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXSMJ4SK6LRIP5AGNVFUP3QBHJ/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":"2026-08-14T10:35:00Z","links":{"resolver":"https://pith.science/pith/CXSMJ4SK6LRIP5AGNVFUP3QBHJ","bundle":"https://pith.science/pith/CXSMJ4SK6LRIP5AGNVFUP3QBHJ/bundle.json","state":"https://pith.science/pith/CXSMJ4SK6LRIP5AGNVFUP3QBHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXSMJ4SK6LRIP5AGNVFUP3QBHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CXSMJ4SK6LRIP5AGNVFUP3QBHJ","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":"a7a69511587a635f48a0dfdeb8f3ef3c6a3b35cc87dae257202430013ad80894","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-03T02:53:30Z","title_canon_sha256":"fa89778939bde012bae94f750615c832f36d5e215c16e87827ce38601b15d6dc"},"schema_version":"1.0","source":{"id":"2003.01303","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.01303","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"2003.01303v1","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01303","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"CXSMJ4SK6LRI","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"pith_short_16","alias_value":"CXSMJ4SK6LRIP5AG","created_at":"2026-07-05T00:45:27Z"},{"alias_kind":"pith_short_8","alias_value":"CXSMJ4SK","created_at":"2026-07-05T00:45:27Z"}],"graph_snapshots":[{"event_id":"sha256:d9acabf41a3ad430797327984b3fa04ccca647a2aec7b71762a48256b63ef2fd","target":"graph","created_at":"2026-07-05T00:45:27Z","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/2003.01303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) is attracting increasing interests in autonomous driving due to its potential to solve complex classification and control problems. However, existing RL algorithms are rarely applied to real vehicles for two predominant problems: behaviours are unexplainable, and they cannot guarantee safety under new scenarios. This paper presents a safe RL algorithm, called Parallel Constrained Policy Optimization (PCPO), for two autonomous driving tasks. PCPO extends today's common actor-critic architecture to a three-component learning framework, in which three neural networks a","authors_text":"Huei Peng, Jingliang Duan, Lu Wen, Shaobing Xu, Shengbo Eben Li","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-03T02:53:30Z","title":"Safe Reinforcement Learning for Autonomous Vehicles through Parallel Constrained Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01303","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":"sha256:9c34e4ef2edb3c0fc8a4a56a128e7488b12df46a88d763aa2f87b8c3b132e83d","target":"record","created_at":"2026-07-05T00:45:27Z","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":"a7a69511587a635f48a0dfdeb8f3ef3c6a3b35cc87dae257202430013ad80894","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-03T02:53:30Z","title_canon_sha256":"fa89778939bde012bae94f750615c832f36d5e215c16e87827ce38601b15d6dc"},"schema_version":"1.0","source":{"id":"2003.01303","kind":"arxiv","version":1}},"canonical_sha256":"15e4c4f24af2e287f4066d4b47ee013a46d67fd0025fbd33869587394d29b0f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15e4c4f24af2e287f4066d4b47ee013a46d67fd0025fbd33869587394d29b0f3","first_computed_at":"2026-07-05T00:45:27.267974Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:45:27.267974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XFpEn5LBFFKBTVRBxlPZAiVxdFJFOMKEkTGm/76A89BKYrJhcbRTMIeo3nCtE4n+TSawwkLogr6S6m85OXMsAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:45:27.268409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.01303","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c34e4ef2edb3c0fc8a4a56a128e7488b12df46a88d763aa2f87b8c3b132e83d","sha256:d9acabf41a3ad430797327984b3fa04ccca647a2aec7b71762a48256b63ef2fd"],"state_sha256":"bed9fe1f2e6493df7775e3454aa26c729da8a8d38c9af1e38d8dc7f05af42f88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m50sTRT1y8Ojf4iLhaLZ738Fud7GX0Vy+/dzvf9bJglY8urPBiH0204pTAW5L9m+XfMPJ+OvCcCEqFiiY04RDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:35:00.811789Z","bundle_sha256":"489732c5bd0c24c6d6641f0b04333fd384486910f7f272ea6134318f61074453"}}