{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F6OZ7UILPGHPC6HGBEMQP4MSQR","short_pith_number":"pith:F6OZ7UIL","schema_version":"1.0","canonical_sha256":"2f9d9fd10b798ef178e6091907f1928445fecad6b184143ea267bb824fe26847","source":{"kind":"arxiv","id":"2605.04254","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Linear support vector machine splits distill black-box reinforcement learning policies into fewer interpretable subpolicies with higher returns.","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Mehrdad Asadi, Senne Deproost","submitted_at":"2026-05-05T19:40:05Z","abstract_excerpt":"We introduce State Vector Space Partitioning (SVSP), a novel method to mimic a black box reinforcement learning policy using a set of human-interpretable subpolicies. By partitioning a distillation dataset of state action pairs with linear support vector machine splits, SVSP constructs a compact and structured representation of the original policy. Our method improves mean return by +7.4% over previous critic driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8% over the original TD3 policy, while reducing the number of required subpolicies against VSP by 82.1%."},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.04254","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-05T19:40:05Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"90b3f301a6e07a8ad0a702478aa2b34dd15ddaecbcc30e97482a58d252860d2e","abstract_canon_sha256":"c820fbc7ba95f475bed269d17cafa20ca108aebaba1cf2172a4f9f77307f28aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:40.656835Z","signature_b64":"QP2AjBgDwyZ8vZb/aykYWGXqnQTsSMuiWGzngO5AiSocei1pTDteQfdrm0fVBpPtUc8bHCK0FetGHSyF3TlKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f9d9fd10b798ef178e6091907f1928445fecad6b184143ea267bb824fe26847","last_reissued_at":"2026-05-20T00:00:40.656177Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:40.656177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Support Vector State Partitioning for Distilling Black Box Reinforcement Learning Policies","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Linear support vector machine splits distill black-box reinforcement learning policies into fewer interpretable subpolicies with higher returns.","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Mehrdad Asadi, Senne Deproost","submitted_at":"2026-05-05T19:40:05Z","abstract_excerpt":"We introduce State Vector Space Partitioning (SVSP), a novel method to mimic a black box reinforcement learning policy using a set of human-interpretable subpolicies. By partitioning a distillation dataset of state action pairs with linear support vector machine splits, SVSP constructs a compact and structured representation of the original policy. Our method improves mean return by +7.4% over previous critic driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8% over the original TD3 policy, while reducing the number of required subpolicies against VSP by 82.1%."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our method improves mean return by +7.4% over previous critic driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8% over the original TD3 policy, while reducing the number of required subpolicies against VSP by 82.1%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That linear SVM splits on a distillation dataset of state-action pairs will reliably produce a compact hierarchical set of human-interpretable subpolicies that accurately mimic the original black-box policy behavior.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SVSP partitions distillation datasets with linear SVMs to create compact interpretable subpolicies, reporting +7.4% better mean return than VSP and +2.8% over TD3 while using 82.1% fewer subpolicies.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Linear support vector machine splits distill black-box reinforcement learning policies into fewer interpretable subpolicies with higher returns.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"70524e805331e949039010867d6f5c1df893ae0e5e454b60f61b66ebae80dded"},"source":{"id":"2605.04254","kind":"arxiv","version":2},"verdict":{"id":"77b359a9-51b5-40f3-bf61-4e7d9a6f4ca4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:35:48.801042Z","strongest_claim":"Our method improves mean return by +7.4% over previous critic driven state partitioning attempts such as Voronoi State Partitioning (VSP) and +2.8% over the original TD3 policy, while reducing the number of required subpolicies against VSP by 82.1%.","one_line_summary":"SVSP partitions distillation datasets with linear SVMs to create compact interpretable subpolicies, reporting +7.4% better mean return than VSP and +2.8% over TD3 while using 82.1% fewer subpolicies.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That linear SVM splits on a distillation dataset of state-action pairs will reliably produce a compact hierarchical set of human-interpretable subpolicies that accurately mimic the original black-box policy behavior.","pith_extraction_headline":"Linear support vector machine splits distill black-box reinforcement learning policies into fewer interpretable subpolicies with higher returns."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.04254/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T23:31:20.927215Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T14:40:39.029023Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"2e2e6e65576b471ba085e1a27885c9a510439f9f4665ed6b65a73c11ef9d28aa"},"references":{"count":8,"sample":[{"doi":"","year":2016,"title":"Ribeiro, M., Singh, S. & Guestrin, C. ” Why should i trust you?” Explaining the predictions of any classifier.Proceedings Of The 22nd ACM SIGKDD International Conference On Knowledge Discovery And Dat","work_id":"2f79d143-ed08-47ef-837c-658925c65f38","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Deproost, S., Steckelmacher, D. & Now ´e, A. Explainable RL Policies by Distilling to Locally- Specialized Linear Policies with V oronoi State Partitioning.ArXiv Preprint ArXiv:2511.13322. (2025)","work_id":"3abb18b5-9486-4b0e-872a-d3e6d5e3aff5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Kohler, H., Delfosse, Q., Akrour, R., Kersting, K. & Preux, P. Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning. (2024,10,28)","work_id":"32539da4-9262-42d2-8026-c48785d2dc4f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Coppens, Y ., Efthymiadis, K., Lenaerts, T., Now ´e, A., Miller, T., Weber, R. & Magazzeni, D. Distilling deep reinforcement learning policies in soft decision trees.Proceedings Of The IJCAI 2019 Work","work_id":"30e9efa7-b445-41d6-9733-ed28e7b60373","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Blanco, V ., Jap ´on, A. & Puerto, J. Multiclass optimal classification trees with svm-splits.Machine Learning.112, 4905-4928 (2023)","work_id":"181576ba-35aa-443c-9821-01e10132aad0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":8,"snapshot_sha256":"8cc31c485a3a1014f5a4decd887449b386bb05bfe8deee7f6cc127234da57e74","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":"2605.04254","created_at":"2026-05-20T00:00:40.656304+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.04254v2","created_at":"2026-05-20T00:00:40.656304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04254","created_at":"2026-05-20T00:00:40.656304+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6OZ7UILPGHP","created_at":"2026-05-20T00:00:40.656304+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6OZ7UILPGHPC6HG","created_at":"2026-05-20T00:00:40.656304+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6OZ7UIL","created_at":"2026-05-20T00:00:40.656304+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/F6OZ7UILPGHPC6HGBEMQP4MSQR","json":"https://pith.science/pith/F6OZ7UILPGHPC6HGBEMQP4MSQR.json","graph_json":"https://pith.science/api/pith-number/F6OZ7UILPGHPC6HGBEMQP4MSQR/graph.json","events_json":"https://pith.science/api/pith-number/F6OZ7UILPGHPC6HGBEMQP4MSQR/events.json","paper":"https://pith.science/paper/F6OZ7UIL"},"agent_actions":{"view_html":"https://pith.science/pith/F6OZ7UILPGHPC6HGBEMQP4MSQR","download_json":"https://pith.science/pith/F6OZ7UILPGHPC6HGBEMQP4MSQR.json","view_paper":"https://pith.science/paper/F6OZ7UIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.04254&json=true","fetch_graph":"https://pith.science/api/pith-number/F6OZ7UILPGHPC6HGBEMQP4MSQR/graph.json","fetch_events":"https://pith.science/api/pith-number/F6OZ7UILPGHPC6HGBEMQP4MSQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6OZ7UILPGHPC6HGBEMQP4MSQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6OZ7UILPGHPC6HGBEMQP4MSQR/action/storage_attestation","attest_author":"https://pith.science/pith/F6OZ7UILPGHPC6HGBEMQP4MSQR/action/author_attestation","sign_citation":"https://pith.science/pith/F6OZ7UILPGHPC6HGBEMQP4MSQR/action/citation_signature","submit_replication":"https://pith.science/pith/F6OZ7UILPGHPC6HGBEMQP4MSQR/action/replication_record"}},"created_at":"2026-05-20T00:00:40.656304+00:00","updated_at":"2026-05-20T00:00:40.656304+00:00"}