{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:64UVOOELJXDKYE4KLVYQ7NJWIG","short_pith_number":"pith:64UVOOEL","canonical_record":{"source":{"id":"2505.02288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-04T22:57:33Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bc72eb6738e332dfaccb04c57481fe247b9164a7e3919218234cd47254c1fceb","abstract_canon_sha256":"9d94cd2769fa51f118d6ab36ed20012abadb0db8e41aadcb82801235eac0b2a8"},"schema_version":"1.0"},"canonical_sha256":"f72957388b4dc6ac138a5d710fb53641a5f85384fdfb622458f8e420f4bcf422","source":{"kind":"arxiv","id":"2505.02288","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02288","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02288v1","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02288","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"pith_short_12","alias_value":"64UVOOELJXDK","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"pith_short_16","alias_value":"64UVOOELJXDKYE4K","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"pith_short_8","alias_value":"64UVOOEL","created_at":"2026-07-05T10:58:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:64UVOOELJXDKYE4KLVYQ7NJWIG","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-04T22:57:33Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bc72eb6738e332dfaccb04c57481fe247b9164a7e3919218234cd47254c1fceb","abstract_canon_sha256":"9d94cd2769fa51f118d6ab36ed20012abadb0db8e41aadcb82801235eac0b2a8"},"schema_version":"1.0"},"canonical_sha256":"f72957388b4dc6ac138a5d710fb53641a5f85384fdfb622458f8e420f4bcf422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:35.104083Z","signature_b64":"vVFYgAjsoqbXvYFlHLyfpCuWci4ytkV8BXUUDIYI7brcpsQBUaIrUTP1fQ7ypvzWEAhThrLoOw8Hs4t7b1hwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f72957388b4dc6ac138a5d710fb53641a5f85384fdfb622458f8e420f4bcf422","last_reissued_at":"2026-07-05T10:58:35.103665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:35.103665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02288","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":"2026-07-05T10:58:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXLoe0qBAHpyQ+boi5pMN2n/hVlZa8ZAFQ26O3kjGn2Ltn2+qp5SXiklCMkxiyEpxgJGAf7B0OF1cuvuCN2sBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:07:42.323987Z"},"content_sha256":"7182c1163a81bca54302606f758669e9fe2238b9e0087290a68583a3359e76c2","schema_version":"1.0","event_id":"sha256:7182c1163a81bca54302606f758669e9fe2238b9e0087290a68583a3359e76c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:64UVOOELJXDKYE4KLVYQ7NJWIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Universal Approximation Theorem of Deep Q-Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Qian Qi","submitted_at":"2025-05-04T22:57:33Z","abstract_excerpt":"We establish a continuous-time framework for analyzing Deep Q-Networks (DQNs) via stochastic control and Forward-Backward Stochastic Differential Equations (FBSDEs). Considering a continuous-time Markov Decision Process (MDP) driven by a square-integrable martingale, we analyze DQN approximation properties. We show that DQNs can approximate the optimal Q-function on compact sets with arbitrary accuracy and high probability, leveraging residual network approximation theorems and large deviation bounds for the state-action process. We then analyze the convergence of a general Q-learning algorith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02288","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/2505.02288/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":"2026-07-05T10:58:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Eu/yqWJlFvzNouEECpr/MwdYPlTvg27CU2C20rlhmqJPlFJEdZvRUV+MGOGDDXKmryPIIHaVAuMifwBADxyLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:07:42.324376Z"},"content_sha256":"6f88fbbc186f0239aedb446c4fdb70366becfa7878ac0bf1a424232ee3a12b58","schema_version":"1.0","event_id":"sha256:6f88fbbc186f0239aedb446c4fdb70366becfa7878ac0bf1a424232ee3a12b58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/64UVOOELJXDKYE4KLVYQ7NJWIG/bundle.json","state_url":"https://pith.science/pith/64UVOOELJXDKYE4KLVYQ7NJWIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/64UVOOELJXDKYE4KLVYQ7NJWIG/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":"2026-08-21T18:07:42Z","links":{"resolver":"https://pith.science/pith/64UVOOELJXDKYE4KLVYQ7NJWIG","bundle":"https://pith.science/pith/64UVOOELJXDKYE4KLVYQ7NJWIG/bundle.json","state":"https://pith.science/pith/64UVOOELJXDKYE4KLVYQ7NJWIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/64UVOOELJXDKYE4KLVYQ7NJWIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:64UVOOELJXDKYE4KLVYQ7NJWIG","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":"9d94cd2769fa51f118d6ab36ed20012abadb0db8e41aadcb82801235eac0b2a8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-04T22:57:33Z","title_canon_sha256":"bc72eb6738e332dfaccb04c57481fe247b9164a7e3919218234cd47254c1fceb"},"schema_version":"1.0","source":{"id":"2505.02288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02288","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02288v1","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02288","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"pith_short_12","alias_value":"64UVOOELJXDK","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"pith_short_16","alias_value":"64UVOOELJXDKYE4K","created_at":"2026-07-05T10:58:35Z"},{"alias_kind":"pith_short_8","alias_value":"64UVOOEL","created_at":"2026-07-05T10:58:35Z"}],"graph_snapshots":[{"event_id":"sha256:6f88fbbc186f0239aedb446c4fdb70366becfa7878ac0bf1a424232ee3a12b58","target":"graph","created_at":"2026-07-05T10:58:35Z","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/2505.02288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We establish a continuous-time framework for analyzing Deep Q-Networks (DQNs) via stochastic control and Forward-Backward Stochastic Differential Equations (FBSDEs). Considering a continuous-time Markov Decision Process (MDP) driven by a square-integrable martingale, we analyze DQN approximation properties. We show that DQNs can approximate the optimal Q-function on compact sets with arbitrary accuracy and high probability, leveraging residual network approximation theorems and large deviation bounds for the state-action process. We then analyze the convergence of a general Q-learning algorith","authors_text":"Qian Qi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-04T22:57:33Z","title":"Universal Approximation Theorem of Deep Q-Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02288","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":"sha256:7182c1163a81bca54302606f758669e9fe2238b9e0087290a68583a3359e76c2","target":"record","created_at":"2026-07-05T10:58:35Z","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":"9d94cd2769fa51f118d6ab36ed20012abadb0db8e41aadcb82801235eac0b2a8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-04T22:57:33Z","title_canon_sha256":"bc72eb6738e332dfaccb04c57481fe247b9164a7e3919218234cd47254c1fceb"},"schema_version":"1.0","source":{"id":"2505.02288","kind":"arxiv","version":1}},"canonical_sha256":"f72957388b4dc6ac138a5d710fb53641a5f85384fdfb622458f8e420f4bcf422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f72957388b4dc6ac138a5d710fb53641a5f85384fdfb622458f8e420f4bcf422","first_computed_at":"2026-07-05T10:58:35.103665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:35.103665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vVFYgAjsoqbXvYFlHLyfpCuWci4ytkV8BXUUDIYI7brcpsQBUaIrUTP1fQ7ypvzWEAhThrLoOw8Hs4t7b1hwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:35.104083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7182c1163a81bca54302606f758669e9fe2238b9e0087290a68583a3359e76c2","sha256:6f88fbbc186f0239aedb446c4fdb70366becfa7878ac0bf1a424232ee3a12b58"],"state_sha256":"d1ba1128d49593ab483772f62685d248cf976082523358c420a288be7cbf8692"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhQC/yt5gVg/CoQtkX+QTSuPN8CdJ8kHW9uZHzdAlnfu9cm1xjbwCkoeBv7+XsyfhP28Zl7WP3YaZj67kffZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:07:42.327326Z","bundle_sha256":"a33ab0dc029b962b5c1c693c5c0dfa4f9ab4220a7d07660593b3b9c4d08e0f1f"}}