{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HJVLXRMZBRDX7PB33DYFNROVR5","short_pith_number":"pith:HJVLXRMZ","canonical_record":{"source":{"id":"1902.04674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T23:42:45Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"bc3228d3cb011f278cb3415b2d6843e44372bf8ee0ba4704167ba678e1f169f8","abstract_canon_sha256":"07f3a9ed79b17c4b3c04a6d3fce27d12384427021b89e555d223034142554811"},"schema_version":"1.0"},"canonical_sha256":"3a6abbc5990c477fbc3bd8f056c5d58f51a2429ee1e918bbeb136e5c4a5a2a2a","source":{"kind":"arxiv","id":"1902.04674","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04674","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04674v1","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04674","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"HJVLXRMZBRDX","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HJVLXRMZBRDX7PB3","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HJVLXRMZ","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HJVLXRMZBRDX7PB33DYFNROVR5","target":"record","payload":{"canonical_record":{"source":{"id":"1902.04674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T23:42:45Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"bc3228d3cb011f278cb3415b2d6843e44372bf8ee0ba4704167ba678e1f169f8","abstract_canon_sha256":"07f3a9ed79b17c4b3c04a6d3fce27d12384427021b89e555d223034142554811"},"schema_version":"1.0"},"canonical_sha256":"3a6abbc5990c477fbc3bd8f056c5d58f51a2429ee1e918bbeb136e5c4a5a2a2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:06.307006Z","signature_b64":"IeYrywqHkOt3m8w4hBGsyl13qGcu6XTjDR6rI+3uxTwKnOJBgMu5S506REwzYRsHG39bn2EkPrGe4eE/fBxaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a6abbc5990c477fbc3bd8f056c5d58f51a2429ee1e918bbeb136e5c4a5a2a2a","last_reissued_at":"2026-05-17T23:54:06.306588Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:06.306588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.04674","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":"2026-05-17T23:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNLrOfVNE8TvzGJeEiyxF2JwuV0crb0fVDM9JCLgWTtKOnq09p3A/sU6yKDQD/sXQlU6LuxN2RJk8j8ZL2HlAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:11:01.582942Z"},"content_sha256":"3bdf618041730d297f9a9461c426d81a8e7b7d53756c8574cc998237f5ece4d9","schema_version":"1.0","event_id":"sha256:3bdf618041730d297f9a9461c426d81a8e7b7d53756c8574cc998237f5ece4d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HJVLXRMZBRDX7PB33DYFNROVR5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Mahdi Soltanolkotabi, Samet Oymak","submitted_at":"2019-02-12T23:42:45Z","abstract_excerpt":"Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the capacity to fit any set of labels including random noise. However, given the highly nonconvex nature of the training landscape it is not clear what level and kind of overparameterization is required for first order methods to converge to a global optima that perfectly interpolate any labels. A number of recent theoretical works have shown that for very wide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04674","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":""},"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":"2026-05-17T23:54:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jdK+nuv5WwQ/xVmt94ObeeZtzXVcl+QZ+rTWLvess6Bc3cDsvrzxCREUghdb0IHLiyqBH481TMyWx6YAJwA1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:11:01.583357Z"},"content_sha256":"41018914f64c4f70fe4082d5be4a6bae5b6fbd03c35c78fb3622f3ae6e89efe9","schema_version":"1.0","event_id":"sha256:41018914f64c4f70fe4082d5be4a6bae5b6fbd03c35c78fb3622f3ae6e89efe9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJVLXRMZBRDX7PB33DYFNROVR5/bundle.json","state_url":"https://pith.science/pith/HJVLXRMZBRDX7PB33DYFNROVR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJVLXRMZBRDX7PB33DYFNROVR5/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":"2026-05-27T07:11:01Z","links":{"resolver":"https://pith.science/pith/HJVLXRMZBRDX7PB33DYFNROVR5","bundle":"https://pith.science/pith/HJVLXRMZBRDX7PB33DYFNROVR5/bundle.json","state":"https://pith.science/pith/HJVLXRMZBRDX7PB33DYFNROVR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJVLXRMZBRDX7PB33DYFNROVR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HJVLXRMZBRDX7PB33DYFNROVR5","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":"07f3a9ed79b17c4b3c04a6d3fce27d12384427021b89e555d223034142554811","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T23:42:45Z","title_canon_sha256":"bc3228d3cb011f278cb3415b2d6843e44372bf8ee0ba4704167ba678e1f169f8"},"schema_version":"1.0","source":{"id":"1902.04674","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04674","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04674v1","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04674","created_at":"2026-05-17T23:54:06Z"},{"alias_kind":"pith_short_12","alias_value":"HJVLXRMZBRDX","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HJVLXRMZBRDX7PB3","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HJVLXRMZ","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:41018914f64c4f70fe4082d5be4a6bae5b6fbd03c35c78fb3622f3ae6e89efe9","target":"graph","created_at":"2026-05-17T23:54:06Z","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"},"paper":{"abstract_excerpt":"Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the capacity to fit any set of labels including random noise. However, given the highly nonconvex nature of the training landscape it is not clear what level and kind of overparameterization is required for first order methods to converge to a global optima that perfectly interpolate any labels. A number of recent theoretical works have shown that for very wide","authors_text":"Mahdi Soltanolkotabi, Samet Oymak","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T23:42:45Z","title":"Towards moderate overparameterization: global convergence guarantees for training shallow neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04674","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":"sha256:3bdf618041730d297f9a9461c426d81a8e7b7d53756c8574cc998237f5ece4d9","target":"record","created_at":"2026-05-17T23:54:06Z","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":"07f3a9ed79b17c4b3c04a6d3fce27d12384427021b89e555d223034142554811","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T23:42:45Z","title_canon_sha256":"bc3228d3cb011f278cb3415b2d6843e44372bf8ee0ba4704167ba678e1f169f8"},"schema_version":"1.0","source":{"id":"1902.04674","kind":"arxiv","version":1}},"canonical_sha256":"3a6abbc5990c477fbc3bd8f056c5d58f51a2429ee1e918bbeb136e5c4a5a2a2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a6abbc5990c477fbc3bd8f056c5d58f51a2429ee1e918bbeb136e5c4a5a2a2a","first_computed_at":"2026-05-17T23:54:06.306588Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:06.306588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IeYrywqHkOt3m8w4hBGsyl13qGcu6XTjDR6rI+3uxTwKnOJBgMu5S506REwzYRsHG39bn2EkPrGe4eE/fBxaDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:06.307006Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.04674","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3bdf618041730d297f9a9461c426d81a8e7b7d53756c8574cc998237f5ece4d9","sha256:41018914f64c4f70fe4082d5be4a6bae5b6fbd03c35c78fb3622f3ae6e89efe9"],"state_sha256":"81af7a221388d773b61a7a2966eff074315a4457338b5ab48a567d33ee62eb06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z/PZAyr6+vpNc0015FQ8zxMQxESBCotsUusv9njXOnlnPcViRFJPth++lNWKGG/pI23+GhCzjyl+W4x45+chCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:11:01.586515Z","bundle_sha256":"57c1be883b3ffbb17d142b8a92aa0ecd53814295f1a3c8a6544567589a1f1b66"}}