{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PT25LPFSGZVFWJX4QN5EJNO4DW","short_pith_number":"pith:PT25LPFS","canonical_record":{"source":{"id":"2307.06092","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T11:35:37Z","cross_cats_sorted":["cs.AI","math.PR","stat.ML"],"title_canon_sha256":"70ade5ab8316b10be7158cbf70ab652984d15189c065cca15392ed4e7d3621dc","abstract_canon_sha256":"20073c2d746cd971916915008f6988e63836b5777cdb7cdb1273127dff86e789"},"schema_version":"1.0"},"canonical_sha256":"7cf5d5bcb2366a5b26fc837a44b5dc1db56598e98deaa31c21369d66ccfe7b4f","source":{"kind":"arxiv","id":"2307.06092","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06092","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06092v5","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06092","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"pith_short_12","alias_value":"PT25LPFSGZVF","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"pith_short_16","alias_value":"PT25LPFSGZVFWJX4","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"pith_short_8","alias_value":"PT25LPFS","created_at":"2026-07-05T08:32:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PT25LPFSGZVFWJX4QN5EJNO4DW","target":"record","payload":{"canonical_record":{"source":{"id":"2307.06092","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T11:35:37Z","cross_cats_sorted":["cs.AI","math.PR","stat.ML"],"title_canon_sha256":"70ade5ab8316b10be7158cbf70ab652984d15189c065cca15392ed4e7d3621dc","abstract_canon_sha256":"20073c2d746cd971916915008f6988e63836b5777cdb7cdb1273127dff86e789"},"schema_version":"1.0"},"canonical_sha256":"7cf5d5bcb2366a5b26fc837a44b5dc1db56598e98deaa31c21369d66ccfe7b4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:30.565932Z","signature_b64":"90tgj0hZsVEsJHvUNiJK4wzRZOqqbU8BaQ77iZJBGp3sS6Je2AFvwrCBkABY7ZpyeTWD77+t+BKE2crDtfc1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf5d5bcb2366a5b26fc837a44b5dc1db56598e98deaa31c21369d66ccfe7b4f","last_reissued_at":"2026-07-05T08:32:30.565389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:30.565389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.06092","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p0z83inRDhoJr/LfM5AGH+O/iw4saaN0RPTIWDjJ2guba8b9Ge9AjXv5sfybbV8e4fU9vDacVlQsKi5izJChAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:22:30.533951Z"},"content_sha256":"2007dd33b1578ce434815235e17725edb1494ae171168268defce7b8b756d55f","schema_version":"1.0","event_id":"sha256:2007dd33b1578ce434815235e17725edb1494ae171168268defce7b8b756d55f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PT25LPFSGZVFWJX4QN5EJNO4DW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantitative CLTs in Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Boris Hanin, Domenico Marinucci, Giovanni Peccati, Ivan Nourdin, Stefano Favaro","submitted_at":"2023-07-12T11:35:37Z","abstract_excerpt":"We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$. Under mild assumptions on the non-linearity, we obtain quantitative bounds on normal approximations valid at large but finite $n$ and any fixed network depth. Our theorems show both for the finite-dimensional distributions and the entire process, that the distance between a random fully connected network (and its derivatives) to the corresponding infinite width Gaussian process scales like $n^{-\\gamma}$ for $\\gamma>0$, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06092","kind":"arxiv","version":5},"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/2307.06092/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":"2026-07-05T08:32:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l1Ajry1dAAhkOMePHpuWNw/ZGZ8ki2fDsN5Ej0hnaVTxvYtZA+/inMXkpurQX2g0slDPY2+TWfTHhCc9bZHHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T23:22:30.534492Z"},"content_sha256":"2a1fe8eb29b79cc5b54f541464afa194bee34bc7539a96b6956baa1a2f8a4358","schema_version":"1.0","event_id":"sha256:2a1fe8eb29b79cc5b54f541464afa194bee34bc7539a96b6956baa1a2f8a4358"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PT25LPFSGZVFWJX4QN5EJNO4DW/bundle.json","state_url":"https://pith.science/pith/PT25LPFSGZVFWJX4QN5EJNO4DW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PT25LPFSGZVFWJX4QN5EJNO4DW/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":"2026-08-13T23:22:30Z","links":{"resolver":"https://pith.science/pith/PT25LPFSGZVFWJX4QN5EJNO4DW","bundle":"https://pith.science/pith/PT25LPFSGZVFWJX4QN5EJNO4DW/bundle.json","state":"https://pith.science/pith/PT25LPFSGZVFWJX4QN5EJNO4DW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PT25LPFSGZVFWJX4QN5EJNO4DW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PT25LPFSGZVFWJX4QN5EJNO4DW","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":"20073c2d746cd971916915008f6988e63836b5777cdb7cdb1273127dff86e789","cross_cats_sorted":["cs.AI","math.PR","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T11:35:37Z","title_canon_sha256":"70ade5ab8316b10be7158cbf70ab652984d15189c065cca15392ed4e7d3621dc"},"schema_version":"1.0","source":{"id":"2307.06092","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.06092","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"arxiv_version","alias_value":"2307.06092v5","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.06092","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"pith_short_12","alias_value":"PT25LPFSGZVF","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"pith_short_16","alias_value":"PT25LPFSGZVFWJX4","created_at":"2026-07-05T08:32:30Z"},{"alias_kind":"pith_short_8","alias_value":"PT25LPFS","created_at":"2026-07-05T08:32:30Z"}],"graph_snapshots":[{"event_id":"sha256:2a1fe8eb29b79cc5b54f541464afa194bee34bc7539a96b6956baa1a2f8a4358","target":"graph","created_at":"2026-07-05T08:32:30Z","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/2307.06092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$. Under mild assumptions on the non-linearity, we obtain quantitative bounds on normal approximations valid at large but finite $n$ and any fixed network depth. Our theorems show both for the finite-dimensional distributions and the entire process, that the distance between a random fully connected network (and its derivatives) to the corresponding infinite width Gaussian process scales like $n^{-\\gamma}$ for $\\gamma>0$, ","authors_text":"Boris Hanin, Domenico Marinucci, Giovanni Peccati, Ivan Nourdin, Stefano Favaro","cross_cats":["cs.AI","math.PR","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T11:35:37Z","title":"Quantitative CLTs in Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.06092","kind":"arxiv","version":5},"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":"sha256:2007dd33b1578ce434815235e17725edb1494ae171168268defce7b8b756d55f","target":"record","created_at":"2026-07-05T08:32:30Z","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":"20073c2d746cd971916915008f6988e63836b5777cdb7cdb1273127dff86e789","cross_cats_sorted":["cs.AI","math.PR","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-12T11:35:37Z","title_canon_sha256":"70ade5ab8316b10be7158cbf70ab652984d15189c065cca15392ed4e7d3621dc"},"schema_version":"1.0","source":{"id":"2307.06092","kind":"arxiv","version":5}},"canonical_sha256":"7cf5d5bcb2366a5b26fc837a44b5dc1db56598e98deaa31c21369d66ccfe7b4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cf5d5bcb2366a5b26fc837a44b5dc1db56598e98deaa31c21369d66ccfe7b4f","first_computed_at":"2026-07-05T08:32:30.565389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:30.565389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"90tgj0hZsVEsJHvUNiJK4wzRZOqqbU8BaQ77iZJBGp3sS6Je2AFvwrCBkABY7ZpyeTWD77+t+BKE2crDtfc1Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:30.565932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.06092","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2007dd33b1578ce434815235e17725edb1494ae171168268defce7b8b756d55f","sha256:2a1fe8eb29b79cc5b54f541464afa194bee34bc7539a96b6956baa1a2f8a4358"],"state_sha256":"1032427e4d0e094e06488d4ec1e26156bfffc3a0c3bd66280c263d803d625832"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"msk8Zfyxc2sScP7WapadqefEeg3E+zn2AI1MxYA30YZ+7RM/zXrICX1CFGU+HIUgO+E4hXYaxHCe5aeJmHrGCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T23:22:30.550472Z","bundle_sha256":"1b77f7dd3af7babd721b0eae27b9bd35c93a691e045e015c1ff8a6174a636cef"}}