{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2MIR4SYJU23XJIG7WOTEEWHOBQ","short_pith_number":"pith:2MIR4SYJ","canonical_record":{"source":{"id":"2412.13224","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T04:13:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b7ac49a9ac74b67796fe2025b2eeebf6bbca5fe05293cfa220c180036e5434f4","abstract_canon_sha256":"5c6716605d22b1e517311646ab063203d1021c36b2e21ee7ffd8be1672f54277"},"schema_version":"1.0"},"canonical_sha256":"d3111e4b09a6b774a0dfb3a64258ee0c12d8044b52e7920e78e1a4c04986b018","source":{"kind":"arxiv","id":"2412.13224","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2MIR4SYJU23XJIG7WOTEEWHOBQ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13224","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T04:13:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b7ac49a9ac74b67796fe2025b2eeebf6bbca5fe05293cfa220c180036e5434f4","abstract_canon_sha256":"5c6716605d22b1e517311646ab063203d1021c36b2e21ee7ffd8be1672f54277"},"schema_version":"1.0"},"canonical_sha256":"d3111e4b09a6b774a0dfb3a64258ee0c12d8044b52e7920e78e1a4c04986b018","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:58.266643Z","signature_b64":"39zfoIufXPNMu5GnuAACRLjxlzNVqJ0dKVhscSqlvH7s4lI2Viv63tDnhjdvakOylQXMbI2crRxCwi6pw0PdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3111e4b09a6b774a0dfb3a64258ee0c12d8044b52e7920e78e1a4c04986b018","last_reissued_at":"2026-07-05T09:50:58.266161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:58.266161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13224","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":"2026-07-05T09:50:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C+AlPlPKwml4sVog06KouWv5SZOqD4KJCs83QwCJeVDg8XCn6btNMLxSaLxSdAEyZuuuIrFqxTIvpz7ywFxCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:36:38.668462Z"},"content_sha256":"7e532a50480477cb8acd169ddfbd8fb08587e6c35bd5a62811a4814ec838248c","schema_version":"1.0","event_id":"sha256:7e532a50480477cb8acd169ddfbd8fb08587e6c35bd5a62811a4814ec838248c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2MIR4SYJU23XJIG7WOTEEWHOBQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hongpeng Cao, Lui Sha, Marco Caccamo, Yanbing Mao","submitted_at":"2024-12-17T04:13:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13224","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/2412.13224/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":"2026-07-05T09:50:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qHen8ysQSk2bChmN1AAUhvi9DpKZ3ellXAukTDn6ozsxx7SrRX4/dlfp0YhaJKmN2awiiZw03VAQ+SpkQMdWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T23:36:38.668981Z"},"content_sha256":"850c2f850e1f8f3e16ca8ae9ca6d390c227b4d28a84268613f6d966c035e6734","schema_version":"1.0","event_id":"sha256:850c2f850e1f8f3e16ca8ae9ca6d390c227b4d28a84268613f6d966c035e6734"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MIR4SYJU23XJIG7WOTEEWHOBQ/bundle.json","state_url":"https://pith.science/pith/2MIR4SYJU23XJIG7WOTEEWHOBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MIR4SYJU23XJIG7WOTEEWHOBQ/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":"2026-08-14T23:36:38Z","links":{"resolver":"https://pith.science/pith/2MIR4SYJU23XJIG7WOTEEWHOBQ","bundle":"https://pith.science/pith/2MIR4SYJU23XJIG7WOTEEWHOBQ/bundle.json","state":"https://pith.science/pith/2MIR4SYJU23XJIG7WOTEEWHOBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MIR4SYJU23XJIG7WOTEEWHOBQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qV4YbxidP25VrUVRDCFJkp7tst9g7UxQ4GvgyNa2RwpZgfVv2sN1DTgVkwC4fgCvxwGDjlE+2uhoMZ88HDjoBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T23:36:38.673098Z","bundle_sha256":"4d9a1dc9d52a9ced763ea947a6f6d9b955af336e35921cb518b067fdbea37fdd"}}