{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UG7FKCUQKAIJIQTFVPNLBVPQL3","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":"0d850671973de17a9d545c00c1e474079b56e6f9f0900d6c236571a70f4bfbe3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-03T09:07:31Z","title_canon_sha256":"044cda94a7fe0b060dcbd0669c358666a91ab21fcb5a123da8c1183c533ba21c"},"schema_version":"1.0","source":{"id":"2412.02291","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02291","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02291v2","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02291","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_12","alias_value":"UG7FKCUQKAIJ","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_16","alias_value":"UG7FKCUQKAIJIQTF","created_at":"2026-07-05T09:45:59Z"},{"alias_kind":"pith_short_8","alias_value":"UG7FKCUQ","created_at":"2026-07-05T09:45:59Z"}],"graph_snapshots":[{"event_id":"sha256:bcd93f38aadd9a2a601fbe46c4b236d4f3733720bed434c71997c13f5ca08b4c","target":"graph","created_at":"2026-07-05T09:45:59Z","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/2412.02291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training deep reinforcement learning (RL) agents necessitates overcoming the highly unstable nonconvex stochastic optimization inherent in the trial-and-error mechanism. To tackle this challenge, we propose a physics-inspired optimization algorithm called relativistic adaptive gradient descent (RAD), which enhances long-term training stability. By conceptualizing neural network (NN) training as the evolution of a conformal Hamiltonian system, we present a universal framework for transferring long-term stability from conformal symplectic integrators to iterative NN updating rules, where the cho","authors_text":"Jingliang Duan, Keqiang Li, Lei He, Letian Tao, Qing Xu, Shengbo Eben Li, Xiangteng Zhang, Yao Lyu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-03T09:07:31Z","title":"Conformal Symplectic Optimization for Stable Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02291","kind":"arxiv","version":2},"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":"sha256:2c440b54c5f56f4bb6fb19a91b099367314a0107c95b148b2777b1be75ba72a8","target":"record","created_at":"2026-07-05T09:45:59Z","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":"0d850671973de17a9d545c00c1e474079b56e6f9f0900d6c236571a70f4bfbe3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-03T09:07:31Z","title_canon_sha256":"044cda94a7fe0b060dcbd0669c358666a91ab21fcb5a123da8c1183c533ba21c"},"schema_version":"1.0","source":{"id":"2412.02291","kind":"arxiv","version":2}},"canonical_sha256":"a1be550a905010944265abdab0d5f05effb2777616a3758d95171290a9eeeebb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1be550a905010944265abdab0d5f05effb2777616a3758d95171290a9eeeebb","first_computed_at":"2026-07-05T09:45:59.680810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:59.680810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+QQMql7PXt8P/p6dhnwQ2hRvbViKPvtQ6+UrfNYLlOq5GWLBgYlpBGKhqoxtZdQS6cL3KuOTKnvND6ZGPgHECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:59.681378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02291","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c440b54c5f56f4bb6fb19a91b099367314a0107c95b148b2777b1be75ba72a8","sha256:bcd93f38aadd9a2a601fbe46c4b236d4f3733720bed434c71997c13f5ca08b4c"],"state_sha256":"cc9f7ee3de8b3431767f2560a66f66855e00d0f59519616fcae3f2a2dd85e5e0"}