{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:M3YUDMNLWO52XQRC646IYTXS2L","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":"f026e6a6021051614aeef562eec638b0e7c1a981e274e16a3a6cabc09712c83d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T22:34:35Z","title_canon_sha256":"87f726ebe26a27efc545046e5db1a82be59c8ad92045efa5268f7f99a897b3d6"},"schema_version":"1.0","source":{"id":"2507.17056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17056","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17056v1","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17056","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_12","alias_value":"M3YUDMNLWO52","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_16","alias_value":"M3YUDMNLWO52XQRC","created_at":"2026-07-05T11:42:00Z"},{"alias_kind":"pith_short_8","alias_value":"M3YUDMNL","created_at":"2026-07-05T11:42:00Z"}],"graph_snapshots":[{"event_id":"sha256:951c70b638803f15bf236793ec188c9683ac037dc40192c8d2355e909aa83c30","target":"graph","created_at":"2026-07-05T11:42:00Z","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/2507.17056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) holds great promise for deriving optimal policies from observational data, but challenges related to interpretability and evaluation limit its practical use in safety-critical domains. Interpretability is hindered by the black-box nature of unconstrained RL policies, while evaluation -- typically performed off-policy -- is sensitive to large deviations from the data-collecting behavior policy, especially when using methods based on importance sampling. To address these challenges, we propose a simple yet practical alternative: deriving treatment policies fro","authors_text":"Anton Matsson, Fredrik D. Johansson, Heather J. Litman, Yaochen Rao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T22:34:35Z","title":"Pragmatic Policy Development via Interpretable Behavior Cloning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17056","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":"sha256:4a57304ef2e1da65ef55ee720b6a393f0cb1d62e1504c5335acee7fdd071577e","target":"record","created_at":"2026-07-05T11:42:00Z","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":"f026e6a6021051614aeef562eec638b0e7c1a981e274e16a3a6cabc09712c83d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T22:34:35Z","title_canon_sha256":"87f726ebe26a27efc545046e5db1a82be59c8ad92045efa5268f7f99a897b3d6"},"schema_version":"1.0","source":{"id":"2507.17056","kind":"arxiv","version":1}},"canonical_sha256":"66f141b1abb3bbabc222f73c8c4ef2d2e9aee2f795663d6fde13221bcbcfad01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66f141b1abb3bbabc222f73c8c4ef2d2e9aee2f795663d6fde13221bcbcfad01","first_computed_at":"2026-07-05T11:42:00.806247Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:00.806247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qve5Xv3IqsF98IPZ5cV75P2yYYmVLIP+KFl+3I5NoZjSj7ui86BaKrRRA9Bk73xrLPXat8cmORA5Yzx1tPoRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:00.806667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a57304ef2e1da65ef55ee720b6a393f0cb1d62e1504c5335acee7fdd071577e","sha256:951c70b638803f15bf236793ec188c9683ac037dc40192c8d2355e909aa83c30"],"state_sha256":"3c0a46f2dbb050d00336a786a28a3578e0c5ffc32bf55c2528f70a1a90685420"}