{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:A5GNHRV5AGHJOQEKNLUFVBHW2E","short_pith_number":"pith:A5GNHRV5","canonical_record":{"source":{"id":"1908.02419","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-05T20:19:39Z","cross_cats_sorted":["cs.LG","cs.NE","math.OC"],"title_canon_sha256":"e4f665aa9c8c9e0fc13a6a1ca72339531c4d16d3eccd9eec297b59fd9c39909e","abstract_canon_sha256":"b17a0940bd0be1faa8998b8666cf29662ceb795fabefbb73ad82fddb0d74d6f7"},"schema_version":"1.0"},"canonical_sha256":"074cd3c6bd018e97408a6ae85a84f6d10a755237a6382c62cc3d2ea30b9ad3ab","source":{"kind":"arxiv","id":"1908.02419","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02419","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02419v3","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02419","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"pith_short_12","alias_value":"A5GNHRV5AGHJ","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"pith_short_16","alias_value":"A5GNHRV5AGHJOQEK","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"pith_short_8","alias_value":"A5GNHRV5","created_at":"2026-07-05T01:10:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:A5GNHRV5AGHJOQEKNLUFVBHW2E","target":"record","payload":{"canonical_record":{"source":{"id":"1908.02419","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-05T20:19:39Z","cross_cats_sorted":["cs.LG","cs.NE","math.OC"],"title_canon_sha256":"e4f665aa9c8c9e0fc13a6a1ca72339531c4d16d3eccd9eec297b59fd9c39909e","abstract_canon_sha256":"b17a0940bd0be1faa8998b8666cf29662ceb795fabefbb73ad82fddb0d74d6f7"},"schema_version":"1.0"},"canonical_sha256":"074cd3c6bd018e97408a6ae85a84f6d10a755237a6382c62cc3d2ea30b9ad3ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:10:55.630983Z","signature_b64":"EMiONxjxMZN0tiA2sUfx+9ntGwBcJ5kFmcwG+hzGxku+lKgIqu4rmKF78gfQ/wUJgxwV82XCAPFZrfXJ1n8eAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"074cd3c6bd018e97408a6ae85a84f6d10a755237a6382c62cc3d2ea30b9ad3ab","last_reissued_at":"2026-07-05T01:10:55.630593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:10:55.630593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.02419","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:10:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tk/axteVQfbioWvQDo29yfUxNlx5ukkOuR9G2Nyum1jiks432ASlZ1G/kpQaWFDDx+zAErWwLHbT/VUdefc9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T01:34:08.741201Z"},"content_sha256":"9ac6e5f9455edc080c18a339783ca97209c6d46a3a5c36927996ca53fc847ead","schema_version":"1.0","event_id":"sha256:9ac6e5f9455edc080c18a339783ca97209c6d46a3a5c36927996ca53fc847ead"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:A5GNHRV5AGHJOQEKNLUFVBHW2E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","math.OC"],"primary_cat":"stat.ML","authors_text":"Jiaoyang Huang, Kenji Kawaguchi","submitted_at":"2019-08-05T20:19:39Z","abstract_excerpt":"In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper only requires the practical degrees of over-parameterization unlike previous theories. Our theory only requires the number of trainable parameters to increase linearly as the number of training samples increases. This allows the size of the deep neural networks to be consistent with practice and to be several orders of magnitude smaller than that required by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02419","kind":"arxiv","version":3},"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/1908.02419/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":"2026-07-05T01:10:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BpOWTbgnsanKzmESzExDYXwdKu9gi5ZySHpeCL9OOXhDKUsUyri4VxtcY+iTlAviDn8czS+Vhrla3gW5Tm68Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T01:34:08.741697Z"},"content_sha256":"99b4217bed44ca134ef5f87f0f70232e539706beef50ba539fe238478a11d7ce","schema_version":"1.0","event_id":"sha256:99b4217bed44ca134ef5f87f0f70232e539706beef50ba539fe238478a11d7ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5GNHRV5AGHJOQEKNLUFVBHW2E/bundle.json","state_url":"https://pith.science/pith/A5GNHRV5AGHJOQEKNLUFVBHW2E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5GNHRV5AGHJOQEKNLUFVBHW2E/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":"2026-08-23T01:34:08Z","links":{"resolver":"https://pith.science/pith/A5GNHRV5AGHJOQEKNLUFVBHW2E","bundle":"https://pith.science/pith/A5GNHRV5AGHJOQEKNLUFVBHW2E/bundle.json","state":"https://pith.science/pith/A5GNHRV5AGHJOQEKNLUFVBHW2E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5GNHRV5AGHJOQEKNLUFVBHW2E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:A5GNHRV5AGHJOQEKNLUFVBHW2E","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":"b17a0940bd0be1faa8998b8666cf29662ceb795fabefbb73ad82fddb0d74d6f7","cross_cats_sorted":["cs.LG","cs.NE","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-05T20:19:39Z","title_canon_sha256":"e4f665aa9c8c9e0fc13a6a1ca72339531c4d16d3eccd9eec297b59fd9c39909e"},"schema_version":"1.0","source":{"id":"1908.02419","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.02419","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"arxiv_version","alias_value":"1908.02419v3","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.02419","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"pith_short_12","alias_value":"A5GNHRV5AGHJ","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"pith_short_16","alias_value":"A5GNHRV5AGHJOQEK","created_at":"2026-07-05T01:10:55Z"},{"alias_kind":"pith_short_8","alias_value":"A5GNHRV5","created_at":"2026-07-05T01:10:55Z"}],"graph_snapshots":[{"event_id":"sha256:99b4217bed44ca134ef5f87f0f70232e539706beef50ba539fe238478a11d7ce","target":"graph","created_at":"2026-07-05T01:10:55Z","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/1908.02419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper only requires the practical degrees of over-parameterization unlike previous theories. Our theory only requires the number of trainable parameters to increase linearly as the number of training samples increases. This allows the size of the deep neural networks to be consistent with practice and to be several orders of magnitude smaller than that required by","authors_text":"Jiaoyang Huang, Kenji Kawaguchi","cross_cats":["cs.LG","cs.NE","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-05T20:19:39Z","title":"Gradient Descent Finds Global Minima for Generalizable Deep Neural Networks of Practical Sizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.02419","kind":"arxiv","version":3},"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":"sha256:9ac6e5f9455edc080c18a339783ca97209c6d46a3a5c36927996ca53fc847ead","target":"record","created_at":"2026-07-05T01:10:55Z","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":"b17a0940bd0be1faa8998b8666cf29662ceb795fabefbb73ad82fddb0d74d6f7","cross_cats_sorted":["cs.LG","cs.NE","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-08-05T20:19:39Z","title_canon_sha256":"e4f665aa9c8c9e0fc13a6a1ca72339531c4d16d3eccd9eec297b59fd9c39909e"},"schema_version":"1.0","source":{"id":"1908.02419","kind":"arxiv","version":3}},"canonical_sha256":"074cd3c6bd018e97408a6ae85a84f6d10a755237a6382c62cc3d2ea30b9ad3ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"074cd3c6bd018e97408a6ae85a84f6d10a755237a6382c62cc3d2ea30b9ad3ab","first_computed_at":"2026-07-05T01:10:55.630593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:55.630593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EMiONxjxMZN0tiA2sUfx+9ntGwBcJ5kFmcwG+hzGxku+lKgIqu4rmKF78gfQ/wUJgxwV82XCAPFZrfXJ1n8eAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:55.630983Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.02419","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ac6e5f9455edc080c18a339783ca97209c6d46a3a5c36927996ca53fc847ead","sha256:99b4217bed44ca134ef5f87f0f70232e539706beef50ba539fe238478a11d7ce"],"state_sha256":"c5931777dae9998497ba4305f0e6ce89fef2f0886c3af017ec30e6c3da8523ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OReG4OTFAwuYOqVbBhVVWGLk4FzJDCyM+KhWKXwgsQt+nSaiRGKmepV13KjKdwfQnquZBDswgRZkifj1jPgEAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T01:34:08.746538Z","bundle_sha256":"abf40653116880e03f6b7a5038229d3b2622533a030eb799aa2b573f36b4e816"}}