{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7K6RHFINCJS74RMQXOUXYLXOJP","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":"490a06086f0bb93d155a76e969879807f2f4fd453ece3af00b65537d27b72d19","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T13:52:38Z","title_canon_sha256":"c71b1f74224333cde8f4f81cc624abef639d8093bce8dadc1134854c30b259f5"},"schema_version":"1.0","source":{"id":"2506.05445","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05445","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05445v1","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05445","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"7K6RHFINCJS7","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"7K6RHFINCJS74RMQ","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"7K6RHFIN","created_at":"2026-07-05T11:17:02Z"}],"graph_snapshots":[{"event_id":"sha256:98965e835ea266c51a9ef3d7dfae51356af387086758ceca711931a49f111cea","target":"graph","created_at":"2026-07-05T11:17:02Z","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/2506.05445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hidden confounders that influence both states and actions can bias policy learning in reinforcement learning (RL), leading to suboptimal or non-generalizable behavior. Most RL algorithms ignore this issue, learning policies from observational trajectories based solely on statistical associations rather than causal effects. We propose DoSAC (Do-Calculus Soft Actor-Critic with Backdoor Adjustment), a principled extension of the SAC algorithm that corrects for hidden confounding via causal intervention estimation. DoSAC estimates the interventional policy $\\pi(a | \\mathrm{do}(s))$ using the backd","authors_text":"Chien Lu, Haozhe Ma, Thanh Vinh Vo, Tze-Yun Leong, Young Lee","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T13:52:38Z","title":"Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05445","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":"sha256:6d080c686e2170f2ab4d91931236d0a15afefb44e2d550f0cf7aa5fb75c6b8e6","target":"record","created_at":"2026-07-05T11:17:02Z","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":"490a06086f0bb93d155a76e969879807f2f4fd453ece3af00b65537d27b72d19","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T13:52:38Z","title_canon_sha256":"c71b1f74224333cde8f4f81cc624abef639d8093bce8dadc1134854c30b259f5"},"schema_version":"1.0","source":{"id":"2506.05445","kind":"arxiv","version":1}},"canonical_sha256":"fabd13950d1265fe4590bba97c2eee4bc595ec25a3984913c1c84bf9ae335063","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fabd13950d1265fe4590bba97c2eee4bc595ec25a3984913c1c84bf9ae335063","first_computed_at":"2026-07-05T11:17:02.846790Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:02.846790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pcZ0jlB1FEth3rWJt+nXD3RXLA9glg+9FLzPVUseJYS9U4deTUdDm9W5IMx2Uf/MLI6iroopootcwCsQZ5dXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:02.849107Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05445","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d080c686e2170f2ab4d91931236d0a15afefb44e2d550f0cf7aa5fb75c6b8e6","sha256:98965e835ea266c51a9ef3d7dfae51356af387086758ceca711931a49f111cea"],"state_sha256":"4400d02c431dd49a816688c2b730f2059fa0a299c979d3ab249713a97536f50d"}