{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K4T666ZAY56S6645ACDMHR6JP7","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":"7f6563f7f2b2a044430d4f2a30c2b35ebb36ee43e62cbdd8f916ff1cbb31337a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T02:41:52Z","title_canon_sha256":"6d1aabe9b73ffeb075532c438c3b50e5abe2df59653dec81dd29153493d03901"},"schema_version":"1.0","source":{"id":"2403.18209","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.18209","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"arxiv_version","alias_value":"2403.18209v2","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18209","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"pith_short_12","alias_value":"K4T666ZAY56S","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"pith_short_16","alias_value":"K4T666ZAY56S6645","created_at":"2026-07-05T09:06:03Z"},{"alias_kind":"pith_short_8","alias_value":"K4T666ZA","created_at":"2026-07-05T09:06:03Z"}],"graph_snapshots":[{"event_id":"sha256:6dcaa53272f4e7a9b17abd9b50ea50d0e3013ac7bb5b198cf7fc13ff0fab76c3","target":"graph","created_at":"2026-07-05T09:06:03Z","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/2403.18209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its industrial applications such as autonomous driving systems. Safe RL methods are developed to handle this issue by constraining the expected safety violation costs as a training objective, but the occurring probability of an unsafe state is still high, which is unacceptable in autonomous driving tasks. Moreover, these methods are difficult to achieve a balance","authors_text":"Bo Tang, Long Chen, Pan Chen, Xuemin Hu, Yijun Wen","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T02:41:52Z","title":"Long and Short-Term Constraints Driven Safe Reinforcement Learning for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18209","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":"sha256:59c35393dc184b7a689067cacf055e464c313c8a2a27117547df11f66d06ed18","target":"record","created_at":"2026-07-05T09:06:03Z","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":"7f6563f7f2b2a044430d4f2a30c2b35ebb36ee43e62cbdd8f916ff1cbb31337a","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T02:41:52Z","title_canon_sha256":"6d1aabe9b73ffeb075532c438c3b50e5abe2df59653dec81dd29153493d03901"},"schema_version":"1.0","source":{"id":"2403.18209","kind":"arxiv","version":2}},"canonical_sha256":"5727ef7b20c77d2f7b9d0086c3c7c97fc9f9b4e60c6b1e36e7cefc1a98719896","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5727ef7b20c77d2f7b9d0086c3c7c97fc9f9b4e60c6b1e36e7cefc1a98719896","first_computed_at":"2026-07-05T09:06:03.762509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:03.762509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wqpnI4rGQszoqzjSGW0Hp2U84ix3z2P+8t/L6hpY62M7Lp01c0TfT818/QA+cCj/PSJI8jiLYuVnp6dE+h5xCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:03.762994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.18209","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59c35393dc184b7a689067cacf055e464c313c8a2a27117547df11f66d06ed18","sha256:6dcaa53272f4e7a9b17abd9b50ea50d0e3013ac7bb5b198cf7fc13ff0fab76c3"],"state_sha256":"4f293d30d69b9120fec4afdd6b75d78199c6d646b965c70bc2be4bf9c5b65a67"}