{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3ZKYCB7JVECDYYE6J7NHNUSOKV","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":"935a5b94df176b46613079b4df807103ac43633eb4f35faf84553830e1a05506","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T14:50:16Z","title_canon_sha256":"687ab549c74bfc0b622eb136ec606ec3c9b138b03260fdfdf194d5e79afc31ea"},"schema_version":"1.0","source":{"id":"2606.28152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.28152","created_at":"2026-06-29T01:15:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.28152v1","created_at":"2026-06-29T01:15:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28152","created_at":"2026-06-29T01:15:07Z"},{"alias_kind":"pith_short_12","alias_value":"3ZKYCB7JVECD","created_at":"2026-06-29T01:15:07Z"},{"alias_kind":"pith_short_16","alias_value":"3ZKYCB7JVECDYYE6","created_at":"2026-06-29T01:15:07Z"},{"alias_kind":"pith_short_8","alias_value":"3ZKYCB7J","created_at":"2026-06-29T01:15:07Z"}],"graph_snapshots":[{"event_id":"sha256:bd135b13c4c82764ea23f77154b0baf4204aa7c3b8f1db5a27f2490a3f6be422","target":"graph","created_at":"2026-06-29T01:15:07Z","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/2606.28152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose KL-Coupled Policy Regularization (KCPR), a policy coordination framework for Reward-Punishment Reinforcement Learning (RPRL). Based on KCPR, we derive KL-Coupled Soft Optimality (KCSO) and develop its deep realization, klDMP. Unlike existing RPRL approaches that optimize reward-seeking and punishment-related policies largely independently, KCPR enables direct interactions between companion policies by treating each as a dynamically learned prior for the other. KCSO yields coupled soft-optimal policies and KL-regularized Bellman operators, allowing reward and punishment information t","authors_text":"Eiji Uchibe, Jiexin Wang","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T14:50:16Z","title":"Regularized Reward-Punishment Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28152","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":"sha256:52fb9b3487ef091559cb06926eb8db545299cd107aba1ac8797cc67b738e8365","target":"record","created_at":"2026-06-29T01:15:07Z","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":"935a5b94df176b46613079b4df807103ac43633eb4f35faf84553830e1a05506","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T14:50:16Z","title_canon_sha256":"687ab549c74bfc0b622eb136ec606ec3c9b138b03260fdfdf194d5e79afc31ea"},"schema_version":"1.0","source":{"id":"2606.28152","kind":"arxiv","version":1}},"canonical_sha256":"de558107e9a9043c609e4fda76d24e5569ea2430f90d6496db8e5629ced01f43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de558107e9a9043c609e4fda76d24e5569ea2430f90d6496db8e5629ced01f43","first_computed_at":"2026-06-29T01:15:07.563761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:15:07.563761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lAq5NESfb/1SU55yfd/wfAzduC+itoQ9KV3QUNCYmkTYsdRmcus/V7t7TWzBWIK1UEuAfyJ09HYiliFdc7ioCQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:15:07.564174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.28152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52fb9b3487ef091559cb06926eb8db545299cd107aba1ac8797cc67b738e8365","sha256:bd135b13c4c82764ea23f77154b0baf4204aa7c3b8f1db5a27f2490a3f6be422"],"state_sha256":"c547f4b0619693b043107f6851127c9835445814c4e82a012601003ea5370dea"}