{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OMSQJKM7VTQILPBLNDF2LJVIXM","short_pith_number":"pith:OMSQJKM7","canonical_record":{"source":{"id":"2507.00485","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T06:59:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7982092db1cdda69ecba36f740015294e90adce4e466b245b799ae2b2a74402c","abstract_canon_sha256":"37a4d2d012401253547c65f5cc7bc9d5acb177e6aab7bfa8191655165c91b7bf"},"schema_version":"1.0"},"canonical_sha256":"732504a99face085bc2b68cba5a6a8bb0a9b5a6721becf5097d58bdeb296c688","source":{"kind":"arxiv","id":"2507.00485","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00485","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00485v1","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00485","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"pith_short_12","alias_value":"OMSQJKM7VTQI","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"OMSQJKM7VTQILPBL","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"OMSQJKM7","created_at":"2026-07-05T11:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OMSQJKM7VTQILPBLNDF2LJVIXM","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00485","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T06:59:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7982092db1cdda69ecba36f740015294e90adce4e466b245b799ae2b2a74402c","abstract_canon_sha256":"37a4d2d012401253547c65f5cc7bc9d5acb177e6aab7bfa8191655165c91b7bf"},"schema_version":"1.0"},"canonical_sha256":"732504a99face085bc2b68cba5a6a8bb0a9b5a6721becf5097d58bdeb296c688","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:09.779626Z","signature_b64":"bZ6PWuZUMoUtv0SoAtssaHbl0QXDhnxBzLqLhseavtSgESVBMCX3oAXeaiDEK5/1BgtSr7xGqq5w40j4KWy5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"732504a99face085bc2b68cba5a6a8bb0a9b5a6721becf5097d58bdeb296c688","last_reissued_at":"2026-07-05T11:30:09.779152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:09.779152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00485","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":"2026-07-05T11:30:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j+PJBwPkUjG4Xo7z7OYVLPAuFt/JmbFA+pwskecmuL/VS190BfXVyhXfxRtpOCiy9hx9mXnn0JyjxNAxQQtjCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:27:39.911818Z"},"content_sha256":"91ca01e0026c0d08b06944406eacabb14e789580ec8af1a33d75f468e2781b2e","schema_version":"1.0","event_id":"sha256:91ca01e0026c0d08b06944406eacabb14e789580ec8af1a33d75f468e2781b2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OMSQJKM7VTQILPBLNDF2LJVIXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guanjun Liu, Ling Wang, Weiran Guo, Ziyuan Zhou","submitted_at":"2025-07-01T06:59:59Z","abstract_excerpt":"Reinforcement Learning (RL) is widely used in tasks where agents interact with an environment to maximize rewards. Building on this foundation, Safe Reinforcement Learning (Safe RL) incorporates a cost metric alongside the reward metric, ensuring that agents adhere to safety constraints during decision-making. In this paper, we identify that Safe RL is vulnerable to backdoor attacks, which can manipulate agents into performing unsafe actions. First, we introduce the relevant concepts and evaluation metrics for backdoor attacks in Safe RL. It is the first attack framework in the Safe RL field t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00485","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/2507.00485/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":"2026-07-05T11:30:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"suQkItVtNq9dzMwcaS4JLrMy8ZVnF9bTEu5CHMpRJ4dxdwRlgXE6h19vG2QF5/peF6bohvNpnulnzonUiaYqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:27:39.912884Z"},"content_sha256":"0098036a4aa8006adb5040eb9b5a024335a8c380bf03d3f8468bee6d43540e4c","schema_version":"1.0","event_id":"sha256:0098036a4aa8006adb5040eb9b5a024335a8c380bf03d3f8468bee6d43540e4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMSQJKM7VTQILPBLNDF2LJVIXM/bundle.json","state_url":"https://pith.science/pith/OMSQJKM7VTQILPBLNDF2LJVIXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMSQJKM7VTQILPBLNDF2LJVIXM/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":"2026-08-07T17:27:39Z","links":{"resolver":"https://pith.science/pith/OMSQJKM7VTQILPBLNDF2LJVIXM","bundle":"https://pith.science/pith/OMSQJKM7VTQILPBLNDF2LJVIXM/bundle.json","state":"https://pith.science/pith/OMSQJKM7VTQILPBLNDF2LJVIXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMSQJKM7VTQILPBLNDF2LJVIXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OMSQJKM7VTQILPBLNDF2LJVIXM","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":"37a4d2d012401253547c65f5cc7bc9d5acb177e6aab7bfa8191655165c91b7bf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T06:59:59Z","title_canon_sha256":"7982092db1cdda69ecba36f740015294e90adce4e466b245b799ae2b2a74402c"},"schema_version":"1.0","source":{"id":"2507.00485","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00485","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00485v1","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00485","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"pith_short_12","alias_value":"OMSQJKM7VTQI","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"OMSQJKM7VTQILPBL","created_at":"2026-07-05T11:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"OMSQJKM7","created_at":"2026-07-05T11:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:0098036a4aa8006adb5040eb9b5a024335a8c380bf03d3f8468bee6d43540e4c","target":"graph","created_at":"2026-07-05T11:30:09Z","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/2507.00485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) is widely used in tasks where agents interact with an environment to maximize rewards. Building on this foundation, Safe Reinforcement Learning (Safe RL) incorporates a cost metric alongside the reward metric, ensuring that agents adhere to safety constraints during decision-making. In this paper, we identify that Safe RL is vulnerable to backdoor attacks, which can manipulate agents into performing unsafe actions. First, we introduce the relevant concepts and evaluation metrics for backdoor attacks in Safe RL. It is the first attack framework in the Safe RL field t","authors_text":"Guanjun Liu, Ling Wang, Weiran Guo, Ziyuan Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T06:59:59Z","title":"PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00485","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":"sha256:91ca01e0026c0d08b06944406eacabb14e789580ec8af1a33d75f468e2781b2e","target":"record","created_at":"2026-07-05T11:30:09Z","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":"37a4d2d012401253547c65f5cc7bc9d5acb177e6aab7bfa8191655165c91b7bf","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-01T06:59:59Z","title_canon_sha256":"7982092db1cdda69ecba36f740015294e90adce4e466b245b799ae2b2a74402c"},"schema_version":"1.0","source":{"id":"2507.00485","kind":"arxiv","version":1}},"canonical_sha256":"732504a99face085bc2b68cba5a6a8bb0a9b5a6721becf5097d58bdeb296c688","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"732504a99face085bc2b68cba5a6a8bb0a9b5a6721becf5097d58bdeb296c688","first_computed_at":"2026-07-05T11:30:09.779152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:09.779152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bZ6PWuZUMoUtv0SoAtssaHbl0QXDhnxBzLqLhseavtSgESVBMCX3oAXeaiDEK5/1BgtSr7xGqq5w40j4KWy5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:09.779626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00485","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91ca01e0026c0d08b06944406eacabb14e789580ec8af1a33d75f468e2781b2e","sha256:0098036a4aa8006adb5040eb9b5a024335a8c380bf03d3f8468bee6d43540e4c"],"state_sha256":"58e081f8e4a9f65197fd8365365b8c7ee3081af9a541ede8d85d3faa9f95af45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bw7LvWGDu2VclFUgknPl+MY9WdkQZ843dCEi86hfYg8Q3b0HimdltE6fITPSl+5PJwXUY9YUpF5X7NCD1EhTBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:27:39.917099Z","bundle_sha256":"78876f84ce5deda1c420deff8a3bf934255e35810540a58e4a25fdbe11c91a1a"}}