{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OSNS4FT6RYE6DY6T26575XRUHV","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":"4e9611e7446200c06052aac59eda63a892a08ec21319c1c9d0a458b234ccb0f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T20:33:21Z","title_canon_sha256":"84bec21ce7d0c4d46f918c96ac3f928e2415de690ae70f7e078db4fc9ee7486a"},"schema_version":"1.0","source":{"id":"2405.11669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.11669","created_at":"2026-07-05T08:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"2405.11669v1","created_at":"2026-07-05T08:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11669","created_at":"2026-07-05T08:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"OSNS4FT6RYE6","created_at":"2026-07-05T08:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"OSNS4FT6RYE6DY6T","created_at":"2026-07-05T08:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"OSNS4FT6","created_at":"2026-07-05T08:20:42Z"}],"graph_snapshots":[{"event_id":"sha256:c6bbd96542cd3d59a55e122472a1ce08607e16da5685ebc8e70bcfe5f7f78b7c","target":"graph","created_at":"2026-07-05T08:20:42Z","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/2405.11669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) for control has become increasingly popular due to its ability to learn rich feedback policies that take into account uncertainty and complex representations of the environment. When considering safety constraints, constrained optimization approaches, where agents are penalized for constraint violations, are commonly used. In such methods, if agents are initialized in, or must visit, states where constraint violation might be inevitable, it is unclear how much they should be penalized. We address this challenge by formulating a constraint on the counterfactual harm ","authors_text":"Chris L. Baker, Sean Vaskov, Wilko Schwarting","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T20:33:21Z","title":"Do No Harm: A Counterfactual Approach to Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11669","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:e182c8daad10cc35a7e8ee531e901eeb1ea892f610c905ed17cbf2a1c9bf434f","target":"record","created_at":"2026-07-05T08:20:42Z","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":"4e9611e7446200c06052aac59eda63a892a08ec21319c1c9d0a458b234ccb0f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-19T20:33:21Z","title_canon_sha256":"84bec21ce7d0c4d46f918c96ac3f928e2415de690ae70f7e078db4fc9ee7486a"},"schema_version":"1.0","source":{"id":"2405.11669","kind":"arxiv","version":1}},"canonical_sha256":"749b2e167e8e09e1e3d3d7bbfede343d49ef097ac2baee173f8dc9092ebb4ef2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"749b2e167e8e09e1e3d3d7bbfede343d49ef097ac2baee173f8dc9092ebb4ef2","first_computed_at":"2026-07-05T08:20:42.799051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:42.799051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/C22NyiT78QCq7yqqNPQjsLU8fxGv9S0qGhwmTIxMWDHs4ldWbsh/MSjibeSLxEXFnOtWAn5ZSVR4Dg+s0KBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:42.799595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.11669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e182c8daad10cc35a7e8ee531e901eeb1ea892f610c905ed17cbf2a1c9bf434f","sha256:c6bbd96542cd3d59a55e122472a1ce08607e16da5685ebc8e70bcfe5f7f78b7c"],"state_sha256":"58ec5e568d7d7080b3891bd3c2639645bad74ebf92c284eb8a1c6450a82ed515"}