{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZZXJHBWKOKR77ELELIMTIDXG4X","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":"6cf36c6e4aed384c28255f41d9ea11b9ddabeb825864980646fdb37da92ecb3d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-10T19:06:28Z","title_canon_sha256":"5307e2a9b408fd2cee87d0b8f4ee63f82b19f39eeb1f383899f76c7e72d20e23"},"schema_version":"1.0","source":{"id":"2106.06009","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.06009","created_at":"2026-07-05T02:48:24Z"},{"alias_kind":"arxiv_version","alias_value":"2106.06009v1","created_at":"2026-07-05T02:48:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06009","created_at":"2026-07-05T02:48:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZZXJHBWKOKR7","created_at":"2026-07-05T02:48:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZZXJHBWKOKR77ELE","created_at":"2026-07-05T02:48:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZZXJHBWK","created_at":"2026-07-05T02:48:24Z"}],"graph_snapshots":[{"event_id":"sha256:2456a18310c4da47847f8ef01fc0531da4e824154cf84d5de2d0ce04b38b86f0","target":"graph","created_at":"2026-07-05T02:48:24Z","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/2106.06009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Today's advanced Reinforcement Learning algorithms produce black-box policies, that are often difficult to interpret and trust for a person. We introduce a policy distilling algorithm, building on the CN2 rule mining algorithm, that distills the policy into a rule-based decision system. At the core of our approach is the fact that an RL process does not just learn a policy, a mapping from states to actions, but also produces extra meta-information, such as action values indicating the quality of alternative actions. This meta-information can indicate whether more than one action is near-optima","authors_text":"Ann Now\\'e, Catholijn M. Jonker, Denis Steckelmacher, Youri Coppens","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-10T19:06:28Z","title":"Synthesising Reinforcement Learning Policies through Set-Valued Inductive Rule Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06009","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":"sha256:28686681697d842fb5eea29fc22954530a4fe89a7ebb75b4b58c97ba01efbd3c","target":"record","created_at":"2026-07-05T02:48:24Z","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":"6cf36c6e4aed384c28255f41d9ea11b9ddabeb825864980646fdb37da92ecb3d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-10T19:06:28Z","title_canon_sha256":"5307e2a9b408fd2cee87d0b8f4ee63f82b19f39eeb1f383899f76c7e72d20e23"},"schema_version":"1.0","source":{"id":"2106.06009","kind":"arxiv","version":1}},"canonical_sha256":"ce6e9386ca72a3ff91645a19340ee6e5cfba8fd443211d7e791ac01a0838f155","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce6e9386ca72a3ff91645a19340ee6e5cfba8fd443211d7e791ac01a0838f155","first_computed_at":"2026-07-05T02:48:24.936156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:24.936156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+JnRk1qlyCp0zyll3Eb/awrEfHWrt4q+VmK230yUOKE8WK0QqiZEAmFGPDqeaYk5YhG2bNajt75Oi8CvFHQ2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:24.936707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.06009","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28686681697d842fb5eea29fc22954530a4fe89a7ebb75b4b58c97ba01efbd3c","sha256:2456a18310c4da47847f8ef01fc0531da4e824154cf84d5de2d0ce04b38b86f0"],"state_sha256":"6f5526d66b03f6eff86e62c1d149d9dd2a6de06b2436b09ff238cb00faf0596a"}