{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D4476L54SXSKWF3OM5D5XHOL2Z","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":"b794ae78d32ef12a0889ba1e9a589c912b5e2b3e573b53a57166abe8bb443a96","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T10:57:33Z","title_canon_sha256":"a27af972fecc94c076b6a1a4feac9ad49f3d0a4eb480e8ed88558490688faa23"},"schema_version":"1.0","source":{"id":"2410.21940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21940","created_at":"2026-07-05T09:28:01Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21940v1","created_at":"2026-07-05T09:28:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21940","created_at":"2026-07-05T09:28:01Z"},{"alias_kind":"pith_short_12","alias_value":"D4476L54SXSK","created_at":"2026-07-05T09:28:01Z"},{"alias_kind":"pith_short_16","alias_value":"D4476L54SXSKWF3O","created_at":"2026-07-05T09:28:01Z"},{"alias_kind":"pith_short_8","alias_value":"D4476L54","created_at":"2026-07-05T09:28:01Z"}],"graph_snapshots":[{"event_id":"sha256:19e5bb0ff6024c670867ab7ee7eb0089d802e7a4c80ea00c628199de28c135db","target":"graph","created_at":"2026-07-05T09:28:01Z","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/2410.21940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With Deep Reinforcement Learning (DRL) being increasingly considered for the control of real-world systems, the lack of transparency of the neural network at the core of RL becomes a concern. Programmatic Reinforcement Learning (PRL) is able to to create representations of this black-box in the form of source code, not only increasing the explainability of the controller but also allowing for user adaptations. However, these methods focus on distilling a black-box policy into a program and do so after learning using the Mean Squared Error between produced and wanted behaviour, discarding other","authors_text":"Ann Now\\'e, Denis Steckelmacher, Senne Deproost","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T10:57:33Z","title":"Human-Readable Programs as Actors of Reinforcement Learning Agents Using Critic-Moderated Evolution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21940","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":"sha256:7786d4895b45e54ae9188e25617099a8c0575dad751cb2cc96e01ef0b7b147f9","target":"record","created_at":"2026-07-05T09:28:01Z","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":"b794ae78d32ef12a0889ba1e9a589c912b5e2b3e573b53a57166abe8bb443a96","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T10:57:33Z","title_canon_sha256":"a27af972fecc94c076b6a1a4feac9ad49f3d0a4eb480e8ed88558490688faa23"},"schema_version":"1.0","source":{"id":"2410.21940","kind":"arxiv","version":1}},"canonical_sha256":"1f39ff2fbc95e4ab176e6747db9dcbd655e571f59b83bd631fdcc891d18cdcd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f39ff2fbc95e4ab176e6747db9dcbd655e571f59b83bd631fdcc891d18cdcd0","first_computed_at":"2026-07-05T09:28:01.999486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:01.999486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hmhg+scVTzjeIZ9LaNq0ZCIL+CE8hJ4ge/wVHEG1Kie4a/6+qloZmeOq2FRON/TxU2XZUsMvUGceUffI+tBGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:01.999893Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7786d4895b45e54ae9188e25617099a8c0575dad751cb2cc96e01ef0b7b147f9","sha256:19e5bb0ff6024c670867ab7ee7eb0089d802e7a4c80ea00c628199de28c135db"],"state_sha256":"1fb110a9b391b8d1a3980d9775d2951e7af1404a13035f0449bc2c5068737cb7"}