{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T6SV3C37U6XCAUQIIPEZBADHT6","short_pith_number":"pith:T6SV3C37","schema_version":"1.0","canonical_sha256":"9fa55d8b7fa7ae20520843c99080679fa87feea8d739a197a78efdcfb74c274b","source":{"kind":"arxiv","id":"2606.13169","version":1},"attestation_state":"computed","paper":{"title":"Redesigning Regularization for Effective Policy Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Naoto Yamanaka, Taisuke Kobayashi","submitted_at":"2026-06-11T10:40:43Z","abstract_excerpt":"This paper proposes a novel regularization design to effectively smooth policy functions in reinforcement learning. While regularization that enhances ``global'' Lipschitz continuity was initially considered, it has been limited to ``local'' Lipschitz continuity due to a tradeoff between smoothness and expressiveness. However, it has become apparent that the original implementation is cumbersome and does not provide sufficient smoothing, leading to a preference for simpler implementations. This stems from a discrepancy between theory and implementation, and a more appropriate implementation ca"},"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":"2606.13169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-11T10:40:43Z","cross_cats_sorted":[],"title_canon_sha256":"7b9186b7bea3eb04eb9c476dbec1f6b5536f45a25abdd973cd15c4164f105da5","abstract_canon_sha256":"c499957ef249dd9453b5a109ffbbfaf36199c200b879d7b3ce979dc787cd2929"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:44.419754Z","signature_b64":"IVvnQCmB4AD6WGVn5eILkUmOFn6XckvFKFCO3EhUPjeihI0uTMv4NZD/e7YW/cpnFIvayJwbhQWY6sdtY8NwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fa55d8b7fa7ae20520843c99080679fa87feea8d739a197a78efdcfb74c274b","last_reissued_at":"2026-06-12T01:09:44.418792Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:44.418792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Redesigning Regularization for Effective Policy Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Naoto Yamanaka, Taisuke Kobayashi","submitted_at":"2026-06-11T10:40:43Z","abstract_excerpt":"This paper proposes a novel regularization design to effectively smooth policy functions in reinforcement learning. While regularization that enhances ``global'' Lipschitz continuity was initially considered, it has been limited to ``local'' Lipschitz continuity due to a tradeoff between smoothness and expressiveness. However, it has become apparent that the original implementation is cumbersome and does not provide sufficient smoothing, leading to a preference for simpler implementations. This stems from a discrepancy between theory and implementation, and a more appropriate implementation ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13169","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/2606.13169/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.13169","created_at":"2026-06-12T01:09:44.418928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13169v1","created_at":"2026-06-12T01:09:44.418928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13169","created_at":"2026-06-12T01:09:44.418928+00:00"},{"alias_kind":"pith_short_12","alias_value":"T6SV3C37U6XC","created_at":"2026-06-12T01:09:44.418928+00:00"},{"alias_kind":"pith_short_16","alias_value":"T6SV3C37U6XCAUQI","created_at":"2026-06-12T01:09:44.418928+00:00"},{"alias_kind":"pith_short_8","alias_value":"T6SV3C37","created_at":"2026-06-12T01:09:44.418928+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/T6SV3C37U6XCAUQIIPEZBADHT6","json":"https://pith.science/pith/T6SV3C37U6XCAUQIIPEZBADHT6.json","graph_json":"https://pith.science/api/pith-number/T6SV3C37U6XCAUQIIPEZBADHT6/graph.json","events_json":"https://pith.science/api/pith-number/T6SV3C37U6XCAUQIIPEZBADHT6/events.json","paper":"https://pith.science/paper/T6SV3C37"},"agent_actions":{"view_html":"https://pith.science/pith/T6SV3C37U6XCAUQIIPEZBADHT6","download_json":"https://pith.science/pith/T6SV3C37U6XCAUQIIPEZBADHT6.json","view_paper":"https://pith.science/paper/T6SV3C37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13169&json=true","fetch_graph":"https://pith.science/api/pith-number/T6SV3C37U6XCAUQIIPEZBADHT6/graph.json","fetch_events":"https://pith.science/api/pith-number/T6SV3C37U6XCAUQIIPEZBADHT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T6SV3C37U6XCAUQIIPEZBADHT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T6SV3C37U6XCAUQIIPEZBADHT6/action/storage_attestation","attest_author":"https://pith.science/pith/T6SV3C37U6XCAUQIIPEZBADHT6/action/author_attestation","sign_citation":"https://pith.science/pith/T6SV3C37U6XCAUQIIPEZBADHT6/action/citation_signature","submit_replication":"https://pith.science/pith/T6SV3C37U6XCAUQIIPEZBADHT6/action/replication_record"}},"created_at":"2026-06-12T01:09:44.418928+00:00","updated_at":"2026-06-12T01:09:44.418928+00:00"}