{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4RY7ODAKQIS6SMEGAJBDRPLKQF","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":"403ce1a50b6f4cb37da5734eb404a88cadfd9797ec763ac0636eeadbd2cfabb6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T00:47:24Z","title_canon_sha256":"cb77fb6f9c24958e11429d135090da85fcdb391f1c88f4c70b271bbd593c9755"},"schema_version":"1.0","source":{"id":"2506.00328","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00328","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00328v3","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00328","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"4RY7ODAKQIS6","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"4RY7ODAKQIS6SMEG","created_at":"2026-07-05T11:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"4RY7ODAK","created_at":"2026-07-05T11:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:2479748be1c2a73ec963814652a7cfc0a1fce17747317317ff93bd84b05a2ed0","target":"graph","created_at":"2026-07-05T11:19:27Z","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/2506.00328/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The quest for interpretable reinforcement learning is a grand challenge for the deployment of autonomous decision-making systems in safety-critical applications. Modern deep reinforcement learning approaches, while powerful, tend to produce opaque policies that compromise verification, reduce transparency, and impede human oversight. To address this, we introduce BASIL (Best-Action Symbolic Interpretable Learning), a systematic approach for generating symbolic, rule-based policies via online evolutionary search with quality-diversity (QD) optimization. BASIL represents policies as ordered list","authors_text":"Kourosh Shahnazari, Mohammadali Keshtparvar, Seyed Moein Ayyoubzadeh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T00:47:24Z","title":"BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00328","kind":"arxiv","version":3},"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":"sha256:226c093fcdbd44b3dcf3436fd229ae991504b1710635d8c058e683f2ebf86e27","target":"record","created_at":"2026-07-05T11:19:27Z","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":"403ce1a50b6f4cb37da5734eb404a88cadfd9797ec763ac0636eeadbd2cfabb6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-31T00:47:24Z","title_canon_sha256":"cb77fb6f9c24958e11429d135090da85fcdb391f1c88f4c70b271bbd593c9755"},"schema_version":"1.0","source":{"id":"2506.00328","kind":"arxiv","version":3}},"canonical_sha256":"e471f70c0a8225e93086024238bd6a814308ab39c03e2c742f66c34aec05c01a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e471f70c0a8225e93086024238bd6a814308ab39c03e2c742f66c34aec05c01a","first_computed_at":"2026-07-05T11:19:27.715029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:27.715029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MIu00SB4lQb6GPTXXv7jXQEhjUnhNqWGv2pp+CD4L20tQewtP6UJcee1/yJxLIMt9WSoZDqnfLbEjmktFK0eAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:27.715541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00328","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:226c093fcdbd44b3dcf3436fd229ae991504b1710635d8c058e683f2ebf86e27","sha256:2479748be1c2a73ec963814652a7cfc0a1fce17747317317ff93bd84b05a2ed0"],"state_sha256":"f150a462f94115124fc73d7aaef4029cb84a07e05c0fadbb14aed877eac322b7"}