{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MIGVCYVCWOO3VQMYLJRLBS2F7W","short_pith_number":"pith:MIGVCYVC","schema_version":"1.0","canonical_sha256":"620d5162a2b39dbac1985a62b0cb45fdaa1d37b1005328f6f70a9545d5d49f08","source":{"kind":"arxiv","id":"2605.14897","version":1},"attestation_state":"computed","paper":{"title":"Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Denis Steckelmacher, Senne Deproost","submitted_at":"2026-05-14T14:38:56Z","abstract_excerpt":"Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performance-interpretability trade-off and select a fitting surrogate model. In addition to this, traditional distillation only minimizes the distance between the behavior of the original and the surrogate policy while other RL-specific components such as action value are disregarded. To solve this, we introduce a new model-agnostic method called Critic-Driven Voronoi State Partitioning, which partitions a black box control policy into regions where a simp"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14897","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T14:38:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ebbf053d3f9c0ac9858202b8d9eaa5930370f1e7805aa778271a1bdc5692f386","abstract_canon_sha256":"4bdd7338a7c164fa9402f1ba4e75e3a03bc56d8ec5b2fa003c5914777a3a22d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:55.887354Z","signature_b64":"WBstZidgK0CAYsW0l8p/j+SiFUKbFpQyF3YgOpsRsM+KiOiemd8Rw2TH783OZIuzPHqFXQoUdhaM3hPOCMPPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"620d5162a2b39dbac1985a62b0cb45fdaa1d37b1005328f6f70a9545d5d49f08","last_reissued_at":"2026-05-17T23:38:55.886704Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:55.886704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Denis Steckelmacher, Senne Deproost","submitted_at":"2026-05-14T14:38:56Z","abstract_excerpt":"Despite many successful attempts at explaining Deep Reinforcement Learning policies using distillation, it remains difficult to balance the performance-interpretability trade-off and select a fitting surrogate model. In addition to this, traditional distillation only minimizes the distance between the behavior of the original and the surrogate policy while other RL-specific components such as action value are disregarded. To solve this, we introduce a new model-agnostic method called Critic-Driven Voronoi State Partitioning, which partitions a black box control policy into regions where a simp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14897","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.14897","created_at":"2026-05-17T23:38:55.886815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14897v1","created_at":"2026-05-17T23:38:55.886815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14897","created_at":"2026-05-17T23:38:55.886815+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIGVCYVCWOO3","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIGVCYVCWOO3VQMY","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIGVCYVC","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W","json":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W.json","graph_json":"https://pith.science/api/pith-number/MIGVCYVCWOO3VQMYLJRLBS2F7W/graph.json","events_json":"https://pith.science/api/pith-number/MIGVCYVCWOO3VQMYLJRLBS2F7W/events.json","paper":"https://pith.science/paper/MIGVCYVC"},"agent_actions":{"view_html":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W","download_json":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W.json","view_paper":"https://pith.science/paper/MIGVCYVC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14897&json=true","fetch_graph":"https://pith.science/api/pith-number/MIGVCYVCWOO3VQMYLJRLBS2F7W/graph.json","fetch_events":"https://pith.science/api/pith-number/MIGVCYVCWOO3VQMYLJRLBS2F7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W/action/storage_attestation","attest_author":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W/action/author_attestation","sign_citation":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W/action/citation_signature","submit_replication":"https://pith.science/pith/MIGVCYVCWOO3VQMYLJRLBS2F7W/action/replication_record"}},"created_at":"2026-05-17T23:38:55.886815+00:00","updated_at":"2026-05-17T23:38:55.886815+00:00"}