{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2MIR4SYJU23XJIG7WOTEEWHOBQ","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":"5c6716605d22b1e517311646ab063203d1021c36b2e21ee7ffd8be1672f54277","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T04:13:06Z","title_canon_sha256":"b7ac49a9ac74b67796fe2025b2eeebf6bbca5fe05293cfa220c180036e5434f4"},"schema_version":"1.0","source":{"id":"2412.13224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13224","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13224v1","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13224","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"pith_short_12","alias_value":"2MIR4SYJU23X","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"pith_short_16","alias_value":"2MIR4SYJU23XJIG7","created_at":"2026-07-05T09:50:58Z"},{"alias_kind":"pith_short_8","alias_value":"2MIR4SYJ","created_at":"2026-07-05T09:50:58Z"}],"graph_snapshots":[{"event_id":"sha256:850c2f850e1f8f3e16ca8ae9ca6d390c227b4d28a84268613f6d966c035e6734","target":"graph","created_at":"2026-07-05T09:50:58Z","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/2412.13224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world accidents in learning-enabled CPS frequently occur in challenging corner cases. During the training of deep reinforcement learning (DRL) policy, the standard setup for training conditions is either fixed at a single initial condition or uniformly sampled from the admissible state space. This setup often overlooks the challenging but safety-critical corner cases. To bridge this gap, this paper proposes a physics-model-guided worst-case sampling strategy for training safe policies that can handle safety-critical cases toward guaranteed safety. Furthermore, we integrate the proposed wo","authors_text":"Hongpeng Cao, Lui Sha, Marco Caccamo, Yanbing Mao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T04:13:06Z","title":"Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13224","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":"sha256:7e532a50480477cb8acd169ddfbd8fb08587e6c35bd5a62811a4814ec838248c","target":"record","created_at":"2026-07-05T09:50:58Z","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":"5c6716605d22b1e517311646ab063203d1021c36b2e21ee7ffd8be1672f54277","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T04:13:06Z","title_canon_sha256":"b7ac49a9ac74b67796fe2025b2eeebf6bbca5fe05293cfa220c180036e5434f4"},"schema_version":"1.0","source":{"id":"2412.13224","kind":"arxiv","version":1}},"canonical_sha256":"d3111e4b09a6b774a0dfb3a64258ee0c12d8044b52e7920e78e1a4c04986b018","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3111e4b09a6b774a0dfb3a64258ee0c12d8044b52e7920e78e1a4c04986b018","first_computed_at":"2026-07-05T09:50:58.266161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:58.266161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"39zfoIufXPNMu5GnuAACRLjxlzNVqJ0dKVhscSqlvH7s4lI2Viv63tDnhjdvakOylQXMbI2crRxCwi6pw0PdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:58.266643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e532a50480477cb8acd169ddfbd8fb08587e6c35bd5a62811a4814ec838248c","sha256:850c2f850e1f8f3e16ca8ae9ca6d390c227b4d28a84268613f6d966c035e6734"],"state_sha256":"2aebe7e93de29ef7eb26eebc72fa6d4ed1a0a81acb38708f2b84f364947471fc"}