{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZZNVVVW2NKZT5TPHTJTXEVRQEB","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":"49ef337ce84c01cd616df3515f8b87c4a309f5a9e31d3e843217d2fc143a5e24","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-23T18:07:38Z","title_canon_sha256":"90285bcb436ae2d3732840a578756ed1925f6d08e9ddc564c33a26fa7e6118ce"},"schema_version":"1.0","source":{"id":"2405.14956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14956","created_at":"2026-07-05T08:22:43Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14956v1","created_at":"2026-07-05T08:22:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14956","created_at":"2026-07-05T08:22:43Z"},{"alias_kind":"pith_short_12","alias_value":"ZZNVVVW2NKZT","created_at":"2026-07-05T08:22:43Z"},{"alias_kind":"pith_short_16","alias_value":"ZZNVVVW2NKZT5TPH","created_at":"2026-07-05T08:22:43Z"},{"alias_kind":"pith_short_8","alias_value":"ZZNVVVW2","created_at":"2026-07-05T08:22:43Z"}],"graph_snapshots":[{"event_id":"sha256:1c627428816478f3f70b0efba6013fc0397336d171a789de3e6e73ecc12451a6","target":"graph","created_at":"2026-07-05T08:22:43Z","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/2405.14956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning agents are prone to goal misalignments. The black-box nature of their policies hinders the detection and correction of such misalignments, and the trust necessary for real-world deployment. So far, solutions learning interpretable policies are inefficient or require many human priors. We propose INTERPRETER, a fast distillation method producing INTerpretable Editable tRee Programs for ReinforcEmenT lEaRning. We empirically demonstrate that INTERPRETER compact tree programs match oracles across a diverse set of sequential decision tasks and evaluate the impact of our","authors_text":"Hector Kohler, Kristian Kersting, Philippe Preux, Quentin Delfosse, Riad Akrour","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-23T18:07:38Z","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14956","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":"sha256:08bb059fcfe47fef2c75a48c72ace2b6d91b07bfbe3ed3d4bfa6a3f8b81857ca","target":"record","created_at":"2026-07-05T08:22:43Z","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":"49ef337ce84c01cd616df3515f8b87c4a309f5a9e31d3e843217d2fc143a5e24","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-23T18:07:38Z","title_canon_sha256":"90285bcb436ae2d3732840a578756ed1925f6d08e9ddc564c33a26fa7e6118ce"},"schema_version":"1.0","source":{"id":"2405.14956","kind":"arxiv","version":1}},"canonical_sha256":"ce5b5ad6da6ab33ecde79a677256302054761fd78d4f1e88aa7332918bb742ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce5b5ad6da6ab33ecde79a677256302054761fd78d4f1e88aa7332918bb742ed","first_computed_at":"2026-07-05T08:22:43.189749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:43.189749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9X6zM4kwjxJy3TErExZ6Tz5WGd35JQ0M9hJFHJji1b5dZ7+99z63PyFf/5700haUF4rVkRgf9K8W7oFjjcHwAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:43.190145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08bb059fcfe47fef2c75a48c72ace2b6d91b07bfbe3ed3d4bfa6a3f8b81857ca","sha256:1c627428816478f3f70b0efba6013fc0397336d171a789de3e6e73ecc12451a6"],"state_sha256":"e861fa76c72c131a09da62661eb380af895412e8dde67e7bc38d55d29ba1858e"}