{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3ZKYCB7JVECDYYE6J7NHNUSOKV","short_pith_number":"pith:3ZKYCB7J","canonical_record":{"source":{"id":"2606.28152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T14:50:16Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"687ab549c74bfc0b622eb136ec606ec3c9b138b03260fdfdf194d5e79afc31ea","abstract_canon_sha256":"935a5b94df176b46613079b4df807103ac43633eb4f35faf84553830e1a05506"},"schema_version":"1.0"},"canonical_sha256":"de558107e9a9043c609e4fda76d24e5569ea2430f90d6496db8e5629ced01f43","source":{"kind":"arxiv","id":"2606.28152","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3ZKYCB7JVECDYYE6J7NHNUSOKV","target":"record","payload":{"canonical_record":{"source":{"id":"2606.28152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T14:50:16Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"687ab549c74bfc0b622eb136ec606ec3c9b138b03260fdfdf194d5e79afc31ea","abstract_canon_sha256":"935a5b94df176b46613079b4df807103ac43633eb4f35faf84553830e1a05506"},"schema_version":"1.0"},"canonical_sha256":"de558107e9a9043c609e4fda76d24e5569ea2430f90d6496db8e5629ced01f43","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:07.564174Z","signature_b64":"lAq5NESfb/1SU55yfd/wfAzduC+itoQ9KV3QUNCYmkTYsdRmcus/V7t7TWzBWIK1UEuAfyJ09HYiliFdc7ioCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de558107e9a9043c609e4fda76d24e5569ea2430f90d6496db8e5629ced01f43","last_reissued_at":"2026-06-29T01:15:07.563761Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:07.563761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.28152","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":"2026-06-29T01:15:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmofH5gq5KhnSZuVkSOav3WwOBGmTaRJjb9bl5VLYDAIHZvMj6AMxpa3wU95383HxBMe1O8C/ZuH4/Z6t5R4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T11:31:57.985100Z"},"content_sha256":"52fb9b3487ef091559cb06926eb8db545299cd107aba1ac8797cc67b738e8365","schema_version":"1.0","event_id":"sha256:52fb9b3487ef091559cb06926eb8db545299cd107aba1ac8797cc67b738e8365"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3ZKYCB7JVECDYYE6J7NHNUSOKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularized Reward-Punishment Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Eiji Uchibe, Jiexin Wang","submitted_at":"2026-06-26T14:50:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28152","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/2606.28152/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":"2026-06-29T01:15:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KBJmpi6dByy+dvdxXKOk6D2gMxrB/QA3ATIn6b96nSOnRwCk69uT6cJWQjouwzRLQXiqdGpduwpp84jkuN1dAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T11:31:57.985490Z"},"content_sha256":"bd135b13c4c82764ea23f77154b0baf4204aa7c3b8f1db5a27f2490a3f6be422","schema_version":"1.0","event_id":"sha256:bd135b13c4c82764ea23f77154b0baf4204aa7c3b8f1db5a27f2490a3f6be422"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/bundle.json","state_url":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/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":"2026-06-30T11:31:57Z","links":{"resolver":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV","bundle":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/bundle.json","state":"https://pith.science/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZKYCB7JVECDYYE6J7NHNUSOKV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b89QbFTVmz4eHjbq3lFY+1ws/aCc7tB+ixRsxAad/rkzxk//wPidUw0JlDIFBIk8OHj8HcnRt97mUb1Ky6IwDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T11:31:57.987396Z","bundle_sha256":"95e385ece3f82b57d929c268f028a4d12dec3212a6140fa704abb7d53e459b57"}}