{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6WGDUODORA5255ASDY74QV3IW6","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":"a59da2abd1293ce3b68d211c33bf26b3f77ddd5cf4dfc396ab57e6533bf7e59c","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-28T11:25:44Z","title_canon_sha256":"201d4915bb53a8e8a7fee36a03228572b5cc790232bad6b3810d0fc4633c678d"},"schema_version":"1.0","source":{"id":"2506.22851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22851","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22851v1","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22851","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_12","alias_value":"6WGDUODORA52","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_16","alias_value":"6WGDUODORA5255AS","created_at":"2026-07-05T11:28:46Z"},{"alias_kind":"pith_short_8","alias_value":"6WGDUODO","created_at":"2026-07-05T11:28:46Z"}],"graph_snapshots":[{"event_id":"sha256:e111ac0547aaad4295eb616478bd933080bb83cae9a93a85dc615d3f776da3e5","target":"graph","created_at":"2026-07-05T11:28:46Z","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/2506.22851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Discrete time stochastic optimal control problems and Markov decision processes (MDPs) are fundamental models for sequential decision-making under uncertainty and as such provide the mathematical framework underlying reinforcement learning theory. A central tool for solving MDPs is the Bellman equation and its solution, the so-called $Q$-function. In this article, we construct deep neural network (DNN) approximations for $Q$-functions associated to MDPs with infinite time horizon and finite control set $A$. More specifically, we show that if the the payoff function and the random transition dy","authors_text":"Arnulf Jentzen, Konrad Kleinberg, Thomas Kruse","cross_cats":["cs.LG","cs.NA","math.NA","math.PR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-28T11:25:44Z","title":"Deep neural networks can provably solve Bellman equations for Markov decision processes without the curse of dimensionality"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22851","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:b3c0b4a636c4875255533b24818c89e295b36db57553661f21865c163c5302b4","target":"record","created_at":"2026-07-05T11:28:46Z","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":"a59da2abd1293ce3b68d211c33bf26b3f77ddd5cf4dfc396ab57e6533bf7e59c","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-28T11:25:44Z","title_canon_sha256":"201d4915bb53a8e8a7fee36a03228572b5cc790232bad6b3810d0fc4633c678d"},"schema_version":"1.0","source":{"id":"2506.22851","kind":"arxiv","version":1}},"canonical_sha256":"f58c3a386e883baef4121e3fc85768b79160fb9f70be7b65140f399e7a63ae41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f58c3a386e883baef4121e3fc85768b79160fb9f70be7b65140f399e7a63ae41","first_computed_at":"2026-07-05T11:28:46.654546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:46.654546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Sq+Gm7ZL79xY84y+qusgP8PfjdfSqaGhClMdAcpEysG1CONr6QtxHqSuRbOL19CU6dQoU+I7PIyrt6lUq/f5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:46.654943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3c0b4a636c4875255533b24818c89e295b36db57553661f21865c163c5302b4","sha256:e111ac0547aaad4295eb616478bd933080bb83cae9a93a85dc615d3f776da3e5"],"state_sha256":"178703a8635a7709f3e3d64c25211fae70b2efadc01946ea6fde75d09796b9f1"}