{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C6HWFCY6XD7UCK4KGOYT34ZD66","short_pith_number":"pith:C6HWFCY6","canonical_record":{"source":{"id":"2408.11632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T14:04:00Z","cross_cats_sorted":[],"title_canon_sha256":"1174198ce9d581ff7dcf6e73a8b864dc98bd8971a673fb034238d55f804f4826","abstract_canon_sha256":"b85de24867bb93898bf718d72b81b2eab837aeb60ae384ff0501ae0dd1b14551"},"schema_version":"1.0"},"canonical_sha256":"178f628b1eb8ff412b8a33b13df323f7900b19c643f2619f43fae475c32cff86","source":{"kind":"arxiv","id":"2408.11632","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11632","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11632v1","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11632","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_12","alias_value":"C6HWFCY6XD7U","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_16","alias_value":"C6HWFCY6XD7UCK4K","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_8","alias_value":"C6HWFCY6","created_at":"2026-07-05T08:57:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C6HWFCY6XD7UCK4KGOYT34ZD66","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T14:04:00Z","cross_cats_sorted":[],"title_canon_sha256":"1174198ce9d581ff7dcf6e73a8b864dc98bd8971a673fb034238d55f804f4826","abstract_canon_sha256":"b85de24867bb93898bf718d72b81b2eab837aeb60ae384ff0501ae0dd1b14551"},"schema_version":"1.0"},"canonical_sha256":"178f628b1eb8ff412b8a33b13df323f7900b19c643f2619f43fae475c32cff86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:46.377406Z","signature_b64":"iLZ19lmhrt6IZbXsMYyogulkXSOEsi2qT2ZCDm8GNYLe1bmQlQaZ6UYaqlrT+9hAd++VrW0dn7abeZKkCYjDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"178f628b1eb8ff412b8a33b13df323f7900b19c643f2619f43fae475c32cff86","last_reissued_at":"2026-07-05T08:57:46.376905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:46.376905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11632","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pIurGbCXkQsVLt+TyIbFnoAdO4CnqpMdlkICQf3x2WQKCdIJJ5MTxzkM/iCdOdtUJ16Zk5VgRp5Mj9O7jpZSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:47:21.044807Z"},"content_sha256":"6a3a95c414e908b37089fc35628d9bb9bd570807aab42ef2fe7695ad3204120d","schema_version":"1.0","event_id":"sha256:6a3a95c414e908b37089fc35628d9bb9bd570807aab42ef2fe7695ad3204120d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C6HWFCY6XD7UCK4KGOYT34ZD66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Interpretable Decision Tree Policies for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dani\\\"el Vos, Sicco Verwer","submitted_at":"2024-08-21T14:04:00Z","abstract_excerpt":"Reinforcement learning techniques leveraging deep learning have made tremendous progress in recent years. However, the complexity of neural networks prevents practitioners from understanding their behavior. Decision trees have gained increased attention in supervised learning for their inherent interpretability, enabling modelers to understand the exact prediction process after learning. This paper considers the problem of optimizing interpretable decision tree policies to replace neural networks in reinforcement learning settings. Previous works have relaxed the tree structure, restricted to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11632","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.11632/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pumX6D627p1szIFC9GdCi9y56Ty8eH4hY87xzoj43yQGErzfnVbbAiETQM7Nh3JLeTJc8bxapcA4dJZPJnVhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:47:21.045318Z"},"content_sha256":"c2af8527bf6ff47f665194d0ca577e00fa4c1ebc5b905bbe32e79cd773073a32","schema_version":"1.0","event_id":"sha256:c2af8527bf6ff47f665194d0ca577e00fa4c1ebc5b905bbe32e79cd773073a32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C6HWFCY6XD7UCK4KGOYT34ZD66/bundle.json","state_url":"https://pith.science/pith/C6HWFCY6XD7UCK4KGOYT34ZD66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C6HWFCY6XD7UCK4KGOYT34ZD66/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T19:47:21Z","links":{"resolver":"https://pith.science/pith/C6HWFCY6XD7UCK4KGOYT34ZD66","bundle":"https://pith.science/pith/C6HWFCY6XD7UCK4KGOYT34ZD66/bundle.json","state":"https://pith.science/pith/C6HWFCY6XD7UCK4KGOYT34ZD66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C6HWFCY6XD7UCK4KGOYT34ZD66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C6HWFCY6XD7UCK4KGOYT34ZD66","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":"b85de24867bb93898bf718d72b81b2eab837aeb60ae384ff0501ae0dd1b14551","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T14:04:00Z","title_canon_sha256":"1174198ce9d581ff7dcf6e73a8b864dc98bd8971a673fb034238d55f804f4826"},"schema_version":"1.0","source":{"id":"2408.11632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11632","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11632v1","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11632","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_12","alias_value":"C6HWFCY6XD7U","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_16","alias_value":"C6HWFCY6XD7UCK4K","created_at":"2026-07-05T08:57:46Z"},{"alias_kind":"pith_short_8","alias_value":"C6HWFCY6","created_at":"2026-07-05T08:57:46Z"}],"graph_snapshots":[{"event_id":"sha256:c2af8527bf6ff47f665194d0ca577e00fa4c1ebc5b905bbe32e79cd773073a32","target":"graph","created_at":"2026-07-05T08:57:46Z","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/2408.11632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning techniques leveraging deep learning have made tremendous progress in recent years. However, the complexity of neural networks prevents practitioners from understanding their behavior. Decision trees have gained increased attention in supervised learning for their inherent interpretability, enabling modelers to understand the exact prediction process after learning. This paper considers the problem of optimizing interpretable decision tree policies to replace neural networks in reinforcement learning settings. Previous works have relaxed the tree structure, restricted to ","authors_text":"Dani\\\"el Vos, Sicco Verwer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T14:04:00Z","title":"Optimizing Interpretable Decision Tree Policies for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11632","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":"sha256:6a3a95c414e908b37089fc35628d9bb9bd570807aab42ef2fe7695ad3204120d","target":"record","created_at":"2026-07-05T08:57:46Z","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":"b85de24867bb93898bf718d72b81b2eab837aeb60ae384ff0501ae0dd1b14551","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-21T14:04:00Z","title_canon_sha256":"1174198ce9d581ff7dcf6e73a8b864dc98bd8971a673fb034238d55f804f4826"},"schema_version":"1.0","source":{"id":"2408.11632","kind":"arxiv","version":1}},"canonical_sha256":"178f628b1eb8ff412b8a33b13df323f7900b19c643f2619f43fae475c32cff86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"178f628b1eb8ff412b8a33b13df323f7900b19c643f2619f43fae475c32cff86","first_computed_at":"2026-07-05T08:57:46.376905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:46.376905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iLZ19lmhrt6IZbXsMYyogulkXSOEsi2qT2ZCDm8GNYLe1bmQlQaZ6UYaqlrT+9hAd++VrW0dn7abeZKkCYjDAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:46.377406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a3a95c414e908b37089fc35628d9bb9bd570807aab42ef2fe7695ad3204120d","sha256:c2af8527bf6ff47f665194d0ca577e00fa4c1ebc5b905bbe32e79cd773073a32"],"state_sha256":"7bf93e2384b4a8618498fa6c2363555a736582eaf90a619ede1a03522be8b146"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3vVXxkrINxsHvaCgm4Ip/+reQcOOcSIMl8jRkqmqwDUfzOXoDfKSrFOcvLnpf+WjsOL/HmNzlWOpHfMRQ9NyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:47:21.050716Z","bundle_sha256":"3376ac37269591dc21ba59349f9ed74111bd3cc0de20e757c9f6a4d24c541057"}}