{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:63VM5QHQGJDSY7X5B7YT4YJ43B","short_pith_number":"pith:63VM5QHQ","canonical_record":{"source":{"id":"1902.06720","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-18T18:37:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3df410a2a8834ba4a89aa99418103bbcb3866e4c416aa2dade7f3f499309a16","abstract_canon_sha256":"ca740481f114c893cd0bf3134499dfb29264845d80ee2633da41565aad0757c5"},"schema_version":"1.0"},"canonical_sha256":"f6eacec0f032472c7efd0ff13e613cd8475770541190d6fe5e3150dd995b37fd","source":{"kind":"arxiv","id":"1902.06720","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.06720","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"1902.06720v4","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06720","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"63VM5QHQGJDS","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"63VM5QHQGJDSY7X5","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"63VM5QHQ","created_at":"2026-07-05T02:11:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:63VM5QHQGJDSY7X5B7YT4YJ43B","target":"record","payload":{"canonical_record":{"source":{"id":"1902.06720","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-18T18:37:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a3df410a2a8834ba4a89aa99418103bbcb3866e4c416aa2dade7f3f499309a16","abstract_canon_sha256":"ca740481f114c893cd0bf3134499dfb29264845d80ee2633da41565aad0757c5"},"schema_version":"1.0"},"canonical_sha256":"f6eacec0f032472c7efd0ff13e613cd8475770541190d6fe5e3150dd995b37fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:11:38.333651Z","signature_b64":"60q+EPH1e5zQ3mpJmJqM4RqTIZGN4kY9hzBo789/oB2+or1fRfadmkOWw7CbKxGZA2Zlzhcc3tv6QLfgstnMCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6eacec0f032472c7efd0ff13e613cd8475770541190d6fe5e3150dd995b37fd","last_reissued_at":"2026-07-05T02:11:38.333224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:11:38.333224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.06720","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rF3d+LFYiZBa//zgsVvExjRmCZ1E3Rdk9FmtYlu7cUAjVak4VXilPV4Lr0/Jom9daYTbKyDGcF/YC8qLVJy3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:18:11.995873Z"},"content_sha256":"36cbb4126e9f17912abf134fcf7c9c3916b6502892c85b478e38211bced36cf5","schema_version":"1.0","event_id":"sha256:36cbb4126e9f17912abf134fcf7c9c3916b6502892c85b478e38211bced36cf5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:63VM5QHQGJDSY7X5B7YT4YJ43B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jaehoon Lee, Jascha Sohl-Dickstein, Jeffrey Pennington, Lechao Xiao, Roman Novak, Samuel S. Schoenholz, Yasaman Bahri","submitted_at":"2019-02-18T18:37:49Z","abstract_excerpt":"A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we show that for wide neural networks the learning dynamics simplify considerably and that, in the infinite width limit, they are governed by a linear model obtained from the first-order Taylor expansion of the network around its initial parameters. Furthermore, mirroring the correspondence between wide Bayesian neural networks and Gaussian processes, gradient-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06720","kind":"arxiv","version":4},"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/1902.06720/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":"2026-07-05T02:11:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"02S1xSbgBQxl0lAl0unTFDtdMNBImQYkm312Cg6dyCjCKwNHZDqLrJam1YuhSv6HiltTHwSAfcTYJR44ZhavBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T22:18:11.996764Z"},"content_sha256":"ab36f3f10b70eb5cba89eec75bcc17c1055d49ddb827e8046ebfc097c00cc1de","schema_version":"1.0","event_id":"sha256:ab36f3f10b70eb5cba89eec75bcc17c1055d49ddb827e8046ebfc097c00cc1de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/63VM5QHQGJDSY7X5B7YT4YJ43B/bundle.json","state_url":"https://pith.science/pith/63VM5QHQGJDSY7X5B7YT4YJ43B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/63VM5QHQGJDSY7X5B7YT4YJ43B/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":"2026-08-15T22:18:12Z","links":{"resolver":"https://pith.science/pith/63VM5QHQGJDSY7X5B7YT4YJ43B","bundle":"https://pith.science/pith/63VM5QHQGJDSY7X5B7YT4YJ43B/bundle.json","state":"https://pith.science/pith/63VM5QHQGJDSY7X5B7YT4YJ43B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/63VM5QHQGJDSY7X5B7YT4YJ43B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:63VM5QHQGJDSY7X5B7YT4YJ43B","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":"ca740481f114c893cd0bf3134499dfb29264845d80ee2633da41565aad0757c5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-18T18:37:49Z","title_canon_sha256":"a3df410a2a8834ba4a89aa99418103bbcb3866e4c416aa2dade7f3f499309a16"},"schema_version":"1.0","source":{"id":"1902.06720","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.06720","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"arxiv_version","alias_value":"1902.06720v4","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06720","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"pith_short_12","alias_value":"63VM5QHQGJDS","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"pith_short_16","alias_value":"63VM5QHQGJDSY7X5","created_at":"2026-07-05T02:11:38Z"},{"alias_kind":"pith_short_8","alias_value":"63VM5QHQ","created_at":"2026-07-05T02:11:38Z"}],"graph_snapshots":[{"event_id":"sha256:ab36f3f10b70eb5cba89eec75bcc17c1055d49ddb827e8046ebfc097c00cc1de","target":"graph","created_at":"2026-07-05T02:11:38Z","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/1902.06720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A longstanding goal in deep learning research has been to precisely characterize training and generalization. However, the often complex loss landscapes of neural networks have made a theory of learning dynamics elusive. In this work, we show that for wide neural networks the learning dynamics simplify considerably and that, in the infinite width limit, they are governed by a linear model obtained from the first-order Taylor expansion of the network around its initial parameters. Furthermore, mirroring the correspondence between wide Bayesian neural networks and Gaussian processes, gradient-ba","authors_text":"Jaehoon Lee, Jascha Sohl-Dickstein, Jeffrey Pennington, Lechao Xiao, Roman Novak, Samuel S. Schoenholz, Yasaman Bahri","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-18T18:37:49Z","title":"Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06720","kind":"arxiv","version":4},"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":"sha256:36cbb4126e9f17912abf134fcf7c9c3916b6502892c85b478e38211bced36cf5","target":"record","created_at":"2026-07-05T02:11:38Z","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":"ca740481f114c893cd0bf3134499dfb29264845d80ee2633da41565aad0757c5","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-18T18:37:49Z","title_canon_sha256":"a3df410a2a8834ba4a89aa99418103bbcb3866e4c416aa2dade7f3f499309a16"},"schema_version":"1.0","source":{"id":"1902.06720","kind":"arxiv","version":4}},"canonical_sha256":"f6eacec0f032472c7efd0ff13e613cd8475770541190d6fe5e3150dd995b37fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6eacec0f032472c7efd0ff13e613cd8475770541190d6fe5e3150dd995b37fd","first_computed_at":"2026-07-05T02:11:38.333224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:11:38.333224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"60q+EPH1e5zQ3mpJmJqM4RqTIZGN4kY9hzBo789/oB2+or1fRfadmkOWw7CbKxGZA2Zlzhcc3tv6QLfgstnMCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:11:38.333651Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.06720","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36cbb4126e9f17912abf134fcf7c9c3916b6502892c85b478e38211bced36cf5","sha256:ab36f3f10b70eb5cba89eec75bcc17c1055d49ddb827e8046ebfc097c00cc1de"],"state_sha256":"0f3c353e17785d38c4dd43ac40dae936242ce7eb75e035400da84fd0831f0ffe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhuciriT/wkH0Ep4Dy3Ug/SNgpmYzO/vPK0RqUUppG1aNDqklxbqraTMH7kO5eNDuVIU5iH5TzZ9iwzx8GdBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T22:18:12.002917Z","bundle_sha256":"acf6e5c6e2ca0847574c1fc333028ed7359580f41bba351c86864ba6040e77cf"}}