{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:V4A7IQJTZ4AYFHAXO3HSAUFX2C","short_pith_number":"pith:V4A7IQJT","canonical_record":{"source":{"id":"1909.03172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-07T02:36:46Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"13d7c4317107f9a41bbf89c419913ccd78825359d6fd6ebd7db71ec2037b1698","abstract_canon_sha256":"9783e5dba4def80e94adca3b38651980c4fd0c9dd11742e325220cbef63088eb"},"schema_version":"1.0"},"canonical_sha256":"af01f44133cf01829c1776cf2050b7d0bfa212b3664f021bb632791ad5bb258a","source":{"kind":"arxiv","id":"1909.03172","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03172","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03172v1","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03172","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"pith_short_12","alias_value":"V4A7IQJTZ4AY","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"pith_short_16","alias_value":"V4A7IQJTZ4AYFHAX","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"pith_short_8","alias_value":"V4A7IQJT","created_at":"2026-07-05T00:03:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:V4A7IQJTZ4AYFHAXO3HSAUFX2C","target":"record","payload":{"canonical_record":{"source":{"id":"1909.03172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-07T02:36:46Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"13d7c4317107f9a41bbf89c419913ccd78825359d6fd6ebd7db71ec2037b1698","abstract_canon_sha256":"9783e5dba4def80e94adca3b38651980c4fd0c9dd11742e325220cbef63088eb"},"schema_version":"1.0"},"canonical_sha256":"af01f44133cf01829c1776cf2050b7d0bfa212b3664f021bb632791ad5bb258a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:03.228095Z","signature_b64":"7cKgk04kL6jsZCD/k51rlzOVlUe7DjDLoaYytJspP6Y/tl8GwNYHcZRNyu94C9kYlV19uC3muH8FkWvtF/ytBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af01f44133cf01829c1776cf2050b7d0bfa212b3664f021bb632791ad5bb258a","last_reissued_at":"2026-07-05T00:03:03.227690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:03.227690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.03172","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":"2026-07-05T00:03:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fccWfpVIt1SRts3v8MsdZx35CtIfIYMnBQKV+crDZpGFXSGQvBpZYrVI/IIbK1PcaseRHFqQr82jw646AmPiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:36:59.331533Z"},"content_sha256":"8dc81d3e84196e074592b148daf7ea0580e7b49ca167384e9e6a266fdc031b9e","schema_version":"1.0","event_id":"sha256:8dc81d3e84196e074592b148daf7ea0580e7b49ca167384e9e6a266fdc031b9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:V4A7IQJTZ4AYFHAXO3HSAUFX2C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Understanding the Importance of Noise in Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dachao Lin, Enlu Zhou, Mo Zhou, Tianyi Liu, Tuo Zhao, Yan Li","submitted_at":"2019-09-07T02:36:46Z","abstract_excerpt":"Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem through training a simple two-layer convolutional neural network model. Although training such a network requires solving a nonconvex optimization problem with a spurious local optimum and a global optimum, we prove that perturbed gradient descent and perturbed mini-batch stochastic gradient algorithms in conjunction with noise annealing is guaranteed to converge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03172","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/1909.03172/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":"2026-07-05T00:03:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TZTfWAz7OX6u/3LfQADiPb9Zy6YFVnWzCmnL9yu1dcNYJQokRjAuDVL/3WUq8nh2T2hiDyB5tlqYXwHr3ATUBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:36:59.331910Z"},"content_sha256":"9010be12c593e10672e34bd06e2608eeaae4f37303911d675c667f05bce2bf8b","schema_version":"1.0","event_id":"sha256:9010be12c593e10672e34bd06e2608eeaae4f37303911d675c667f05bce2bf8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V4A7IQJTZ4AYFHAXO3HSAUFX2C/bundle.json","state_url":"https://pith.science/pith/V4A7IQJTZ4AYFHAXO3HSAUFX2C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V4A7IQJTZ4AYFHAXO3HSAUFX2C/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":"2026-07-07T12:36:59Z","links":{"resolver":"https://pith.science/pith/V4A7IQJTZ4AYFHAXO3HSAUFX2C","bundle":"https://pith.science/pith/V4A7IQJTZ4AYFHAXO3HSAUFX2C/bundle.json","state":"https://pith.science/pith/V4A7IQJTZ4AYFHAXO3HSAUFX2C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V4A7IQJTZ4AYFHAXO3HSAUFX2C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:V4A7IQJTZ4AYFHAXO3HSAUFX2C","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":"9783e5dba4def80e94adca3b38651980c4fd0c9dd11742e325220cbef63088eb","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-07T02:36:46Z","title_canon_sha256":"13d7c4317107f9a41bbf89c419913ccd78825359d6fd6ebd7db71ec2037b1698"},"schema_version":"1.0","source":{"id":"1909.03172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03172","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03172v1","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03172","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"pith_short_12","alias_value":"V4A7IQJTZ4AY","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"pith_short_16","alias_value":"V4A7IQJTZ4AYFHAX","created_at":"2026-07-05T00:03:03Z"},{"alias_kind":"pith_short_8","alias_value":"V4A7IQJT","created_at":"2026-07-05T00:03:03Z"}],"graph_snapshots":[{"event_id":"sha256:9010be12c593e10672e34bd06e2608eeaae4f37303911d675c667f05bce2bf8b","target":"graph","created_at":"2026-07-05T00:03:03Z","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/1909.03172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem through training a simple two-layer convolutional neural network model. Although training such a network requires solving a nonconvex optimization problem with a spurious local optimum and a global optimum, we prove that perturbed gradient descent and perturbed mini-batch stochastic gradient algorithms in conjunction with noise annealing is guaranteed to converge","authors_text":"Dachao Lin, Enlu Zhou, Mo Zhou, Tianyi Liu, Tuo Zhao, Yan Li","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-07T02:36:46Z","title":"Towards Understanding the Importance of Noise in Training Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03172","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":"sha256:8dc81d3e84196e074592b148daf7ea0580e7b49ca167384e9e6a266fdc031b9e","target":"record","created_at":"2026-07-05T00:03:03Z","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":"9783e5dba4def80e94adca3b38651980c4fd0c9dd11742e325220cbef63088eb","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-07T02:36:46Z","title_canon_sha256":"13d7c4317107f9a41bbf89c419913ccd78825359d6fd6ebd7db71ec2037b1698"},"schema_version":"1.0","source":{"id":"1909.03172","kind":"arxiv","version":1}},"canonical_sha256":"af01f44133cf01829c1776cf2050b7d0bfa212b3664f021bb632791ad5bb258a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af01f44133cf01829c1776cf2050b7d0bfa212b3664f021bb632791ad5bb258a","first_computed_at":"2026-07-05T00:03:03.227690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:03:03.227690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7cKgk04kL6jsZCD/k51rlzOVlUe7DjDLoaYytJspP6Y/tl8GwNYHcZRNyu94C9kYlV19uC3muH8FkWvtF/ytBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:03:03.228095Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.03172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dc81d3e84196e074592b148daf7ea0580e7b49ca167384e9e6a266fdc031b9e","sha256:9010be12c593e10672e34bd06e2608eeaae4f37303911d675c667f05bce2bf8b"],"state_sha256":"3587eac2410c0844eb8019eca5782f910a7bbcbebec026c3847f1dd77b5139ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2jO5HdptBfA/DGZAKjPXdQiw6HiP57hvM200AcQcDd7paQHW34R5bmWFumi3DWmmEg85GILaYsgrAVTRttDhCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:36:59.333781Z","bundle_sha256":"b8029483f63e46f3e6174bd664ffb45fde7d5448b53ccf0f18171829f89e2e9b"}}