{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IZRA3KFQSQ4GVXNJ6KLWL676ZQ","short_pith_number":"pith:IZRA3KFQ","canonical_record":{"source":{"id":"2502.10200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T14:50:05Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"cb8d871b239b0a9cda33ed169e09532aeb7c613c52b3e3a1a9387a79031c6940","abstract_canon_sha256":"8bf5a03644871516d991c2fe1126a6430c6fe1957469a78dbca7f2303f0c4692"},"schema_version":"1.0"},"canonical_sha256":"46620da8b094386adda9f29765fbfecc25ee7e5f237547e5b9d056bcfcec5082","source":{"kind":"arxiv","id":"2502.10200","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10200","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10200v1","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10200","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"pith_short_12","alias_value":"IZRA3KFQSQ4G","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"pith_short_16","alias_value":"IZRA3KFQSQ4GVXNJ","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"pith_short_8","alias_value":"IZRA3KFQ","created_at":"2026-07-05T10:14:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IZRA3KFQSQ4GVXNJ6KLWL676ZQ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T14:50:05Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"cb8d871b239b0a9cda33ed169e09532aeb7c613c52b3e3a1a9387a79031c6940","abstract_canon_sha256":"8bf5a03644871516d991c2fe1126a6430c6fe1957469a78dbca7f2303f0c4692"},"schema_version":"1.0"},"canonical_sha256":"46620da8b094386adda9f29765fbfecc25ee7e5f237547e5b9d056bcfcec5082","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:29.861287Z","signature_b64":"bVVkwBh5YsUuldEppuit+aWYBOQW6SK1vohhDr7P4oX4gJmVBwe70Ty/F5VFQA8tPXu0xNEDKHX7xNggIrfkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46620da8b094386adda9f29765fbfecc25ee7e5f237547e5b9d056bcfcec5082","last_reissued_at":"2026-07-05T10:14:29.860781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:29.860781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10200","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":"2026-07-05T10:14:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Icfgb+L9i/8HbshgqGRVNBlD4O8huUdkU66P5Aj67nKEdIcOWZMHF9jKu8gVwtruQYpBVhP4tBm4iG0yDZYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:33:11.048934Z"},"content_sha256":"735966c18a3bee20e90ae0dd411472a7248d75716511ea0c9689ee1f406bad50","schema_version":"1.0","event_id":"sha256:735966c18a3bee20e90ae0dd411472a7248d75716511ea0c9689ee1f406bad50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IZRA3KFQSQ4GVXNJ6KLWL676ZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Reinforcement Learning for Actors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Katsunari Shibata","submitted_at":"2025-02-14T14:50:05Z","abstract_excerpt":"Dynamic Reinforcement Learning (Dynamic RL), proposed in this paper, directly controls system dynamics, instead of the actor (action-generating neural network) outputs at each moment, bringing about a major qualitative shift in reinforcement learning (RL) from static to dynamic. The actor is initially designed to generate chaotic dynamics through the loop with its environment, enabling the agent to perform flexible and deterministic exploration. Dynamic RL controls global system dynamics using a local index called \"sensitivity,\" which indicates how much the input neighborhood contracts or expa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10200","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/2502.10200/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":"2026-07-05T10:14:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vOio8UQdRChRs6dImhaj7HG0/P6TGsqssJ1Rbdb1dcjxeZNC1a4jSZfhVKFwCpzGYcSYSqsJOJSbiWGZTgLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:33:11.049472Z"},"content_sha256":"f422f8748fd87079256a71625ea7b5e084f2154cdec697149eeba08953cd5384","schema_version":"1.0","event_id":"sha256:f422f8748fd87079256a71625ea7b5e084f2154cdec697149eeba08953cd5384"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZRA3KFQSQ4GVXNJ6KLWL676ZQ/bundle.json","state_url":"https://pith.science/pith/IZRA3KFQSQ4GVXNJ6KLWL676ZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZRA3KFQSQ4GVXNJ6KLWL676ZQ/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":"2026-08-10T07:33:11Z","links":{"resolver":"https://pith.science/pith/IZRA3KFQSQ4GVXNJ6KLWL676ZQ","bundle":"https://pith.science/pith/IZRA3KFQSQ4GVXNJ6KLWL676ZQ/bundle.json","state":"https://pith.science/pith/IZRA3KFQSQ4GVXNJ6KLWL676ZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZRA3KFQSQ4GVXNJ6KLWL676ZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IZRA3KFQSQ4GVXNJ6KLWL676ZQ","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":"8bf5a03644871516d991c2fe1126a6430c6fe1957469a78dbca7f2303f0c4692","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T14:50:05Z","title_canon_sha256":"cb8d871b239b0a9cda33ed169e09532aeb7c613c52b3e3a1a9387a79031c6940"},"schema_version":"1.0","source":{"id":"2502.10200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10200","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10200v1","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10200","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"pith_short_12","alias_value":"IZRA3KFQSQ4G","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"pith_short_16","alias_value":"IZRA3KFQSQ4GVXNJ","created_at":"2026-07-05T10:14:29Z"},{"alias_kind":"pith_short_8","alias_value":"IZRA3KFQ","created_at":"2026-07-05T10:14:29Z"}],"graph_snapshots":[{"event_id":"sha256:f422f8748fd87079256a71625ea7b5e084f2154cdec697149eeba08953cd5384","target":"graph","created_at":"2026-07-05T10:14:29Z","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/2502.10200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dynamic Reinforcement Learning (Dynamic RL), proposed in this paper, directly controls system dynamics, instead of the actor (action-generating neural network) outputs at each moment, bringing about a major qualitative shift in reinforcement learning (RL) from static to dynamic. The actor is initially designed to generate chaotic dynamics through the loop with its environment, enabling the agent to perform flexible and deterministic exploration. Dynamic RL controls global system dynamics using a local index called \"sensitivity,\" which indicates how much the input neighborhood contracts or expa","authors_text":"Katsunari Shibata","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T14:50:05Z","title":"Dynamic Reinforcement Learning for Actors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10200","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":"sha256:735966c18a3bee20e90ae0dd411472a7248d75716511ea0c9689ee1f406bad50","target":"record","created_at":"2026-07-05T10:14:29Z","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":"8bf5a03644871516d991c2fe1126a6430c6fe1957469a78dbca7f2303f0c4692","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T14:50:05Z","title_canon_sha256":"cb8d871b239b0a9cda33ed169e09532aeb7c613c52b3e3a1a9387a79031c6940"},"schema_version":"1.0","source":{"id":"2502.10200","kind":"arxiv","version":1}},"canonical_sha256":"46620da8b094386adda9f29765fbfecc25ee7e5f237547e5b9d056bcfcec5082","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46620da8b094386adda9f29765fbfecc25ee7e5f237547e5b9d056bcfcec5082","first_computed_at":"2026-07-05T10:14:29.860781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:29.860781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bVVkwBh5YsUuldEppuit+aWYBOQW6SK1vohhDr7P4oX4gJmVBwe70Ty/F5VFQA8tPXu0xNEDKHX7xNggIrfkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:29.861287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:735966c18a3bee20e90ae0dd411472a7248d75716511ea0c9689ee1f406bad50","sha256:f422f8748fd87079256a71625ea7b5e084f2154cdec697149eeba08953cd5384"],"state_sha256":"9e5b11a130517c4f7c6470d8dacdaf598d38931d0fcd3e140e958243f66d9f53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G6v9Lih0r9tJGwuNgYQDZccS1omUO52ys+UgI3IOUY0YzqqHp2h8tfTpWGIA2EDGlwSR4zbm3Gn9CwlyLC5ZCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:33:11.053472Z","bundle_sha256":"066d343a75f47372d5ac6501e6b3242ae953491698918fdb64d82b03bde26889"}}