{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZUUMESTNS7HDMCJWR5TS4OQOFU","short_pith_number":"pith:ZUUMESTN","canonical_record":{"source":{"id":"1912.00018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-29T16:56:02Z","cross_cats_sorted":["cs.LG","math.CA"],"title_canon_sha256":"3af76bde47635e27cc1cee567bcdb31bb9d6722e8ea45bfc38aff7e8d922c3bc","abstract_canon_sha256":"9c3d52bbce9be56c4ba6c3c37ef244a2668b2e8aba158007b6b64d6e2dec87ac"},"schema_version":"1.0"},"canonical_sha256":"cd28c24a6d97ce3609368f672e3a0e2d26fc19f33d8934a4f1c2a66d160be6f9","source":{"kind":"arxiv","id":"1912.00018","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00018","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00018v1","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00018","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZUUMESTNS7HD","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZUUMESTNS7HDMCJW","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZUUMESTN","created_at":"2026-07-05T00:22:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZUUMESTNS7HDMCJWR5TS4OQOFU","target":"record","payload":{"canonical_record":{"source":{"id":"1912.00018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-29T16:56:02Z","cross_cats_sorted":["cs.LG","math.CA"],"title_canon_sha256":"3af76bde47635e27cc1cee567bcdb31bb9d6722e8ea45bfc38aff7e8d922c3bc","abstract_canon_sha256":"9c3d52bbce9be56c4ba6c3c37ef244a2668b2e8aba158007b6b64d6e2dec87ac"},"schema_version":"1.0"},"canonical_sha256":"cd28c24a6d97ce3609368f672e3a0e2d26fc19f33d8934a4f1c2a66d160be6f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:54.290833Z","signature_b64":"HmkWpuRBuoiT9HQQRByjS2+hxZDtfVFE4v8a8dmmxJziEPqT7CD01ibtooskfwVYVnb4dLL31HKPnPZ0n8VjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd28c24a6d97ce3609368f672e3a0e2d26fc19f33d8934a4f1c2a66d160be6f9","last_reissued_at":"2026-07-05T00:22:54.290453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:54.290453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.00018","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":"2026-07-05T00:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GySHpD33WDZ6ITi9bADJZxaOG6Nh1lnbdE2G3rhrpm3KmhMbUzscv6JzhBq16ZhZe188rRaXn4mBXDcpG0MJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:06:09.457097Z"},"content_sha256":"a8c76a2a5dd050ba424880abfb2829eaf46d1870be5245a620f2ace7615a54ca","schema_version":"1.0","event_id":"sha256:a8c76a2a5dd050ba424880abfb2829eaf46d1870be5245a620f2ace7615a54ca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZUUMESTNS7HDMCJWR5TS4OQOFU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.CA"],"primary_cat":"stat.ML","authors_text":"Ga\\\"el Richard, Levent Sagun, Mert G\\\"urb\\\"uzbalaban, Thanh Huy Nguyen, Umut \\c{S}im\\c{s}ekli","submitted_at":"2019-11-29T16:56:02Z","abstract_excerpt":"The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \\emph{classical} central limit theorem (CLT) kicks in. This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochastic differential equation (SDE) driven by a Brownian motion. We argue that the Gaussianity assumption might fail to hold in deep learning settings and hence render the Brownian motion-based analyses inappropriate. Inspired by non-Gaussian natural phenomena, we consider the GN in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00018","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/1912.00018/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":"2026-07-05T00:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0G3vLHLbHMHETt7um4/SvzEKdjjOcgj26xjRt/fdyVgHPJvhX2GD50NOPSVMSjDC/Xxl0233pJICng3+K665BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:06:09.458087Z"},"content_sha256":"8e794dec71fb9272e86a146aa68e22e89676d66c17fb18b2424c003fed4366c9","schema_version":"1.0","event_id":"sha256:8e794dec71fb9272e86a146aa68e22e89676d66c17fb18b2424c003fed4366c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZUUMESTNS7HDMCJWR5TS4OQOFU/bundle.json","state_url":"https://pith.science/pith/ZUUMESTNS7HDMCJWR5TS4OQOFU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZUUMESTNS7HDMCJWR5TS4OQOFU/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":"2026-08-08T20:06:09Z","links":{"resolver":"https://pith.science/pith/ZUUMESTNS7HDMCJWR5TS4OQOFU","bundle":"https://pith.science/pith/ZUUMESTNS7HDMCJWR5TS4OQOFU/bundle.json","state":"https://pith.science/pith/ZUUMESTNS7HDMCJWR5TS4OQOFU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZUUMESTNS7HDMCJWR5TS4OQOFU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZUUMESTNS7HDMCJWR5TS4OQOFU","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":"9c3d52bbce9be56c4ba6c3c37ef244a2668b2e8aba158007b6b64d6e2dec87ac","cross_cats_sorted":["cs.LG","math.CA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-29T16:56:02Z","title_canon_sha256":"3af76bde47635e27cc1cee567bcdb31bb9d6722e8ea45bfc38aff7e8d922c3bc"},"schema_version":"1.0","source":{"id":"1912.00018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.00018","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"1912.00018v1","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00018","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZUUMESTNS7HD","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZUUMESTNS7HDMCJW","created_at":"2026-07-05T00:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZUUMESTN","created_at":"2026-07-05T00:22:54Z"}],"graph_snapshots":[{"event_id":"sha256:8e794dec71fb9272e86a146aa68e22e89676d66c17fb18b2424c003fed4366c9","target":"graph","created_at":"2026-07-05T00:22:54Z","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/1912.00018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The gradient noise (GN) in the stochastic gradient descent (SGD) algorithm is often considered to be Gaussian in the large data regime by assuming that the \\emph{classical} central limit theorem (CLT) kicks in. This assumption is often made for mathematical convenience, since it enables SGD to be analyzed as a stochastic differential equation (SDE) driven by a Brownian motion. We argue that the Gaussianity assumption might fail to hold in deep learning settings and hence render the Brownian motion-based analyses inappropriate. Inspired by non-Gaussian natural phenomena, we consider the GN in a","authors_text":"Ga\\\"el Richard, Levent Sagun, Mert G\\\"urb\\\"uzbalaban, Thanh Huy Nguyen, Umut \\c{S}im\\c{s}ekli","cross_cats":["cs.LG","math.CA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-29T16:56:02Z","title":"On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00018","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:a8c76a2a5dd050ba424880abfb2829eaf46d1870be5245a620f2ace7615a54ca","target":"record","created_at":"2026-07-05T00:22:54Z","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":"9c3d52bbce9be56c4ba6c3c37ef244a2668b2e8aba158007b6b64d6e2dec87ac","cross_cats_sorted":["cs.LG","math.CA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-29T16:56:02Z","title_canon_sha256":"3af76bde47635e27cc1cee567bcdb31bb9d6722e8ea45bfc38aff7e8d922c3bc"},"schema_version":"1.0","source":{"id":"1912.00018","kind":"arxiv","version":1}},"canonical_sha256":"cd28c24a6d97ce3609368f672e3a0e2d26fc19f33d8934a4f1c2a66d160be6f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd28c24a6d97ce3609368f672e3a0e2d26fc19f33d8934a4f1c2a66d160be6f9","first_computed_at":"2026-07-05T00:22:54.290453Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:22:54.290453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HmkWpuRBuoiT9HQQRByjS2+hxZDtfVFE4v8a8dmmxJziEPqT7CD01ibtooskfwVYVnb4dLL31HKPnPZ0n8VjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:22:54.290833Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.00018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8c76a2a5dd050ba424880abfb2829eaf46d1870be5245a620f2ace7615a54ca","sha256:8e794dec71fb9272e86a146aa68e22e89676d66c17fb18b2424c003fed4366c9"],"state_sha256":"99b0b7900fa9c9f6c7ae8555b82dc6a0615402a5a6752c0e3d950e044ba815b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2g+USwzoGgNNjD7fixGb9bLg0um6RI5mdfLtwFSzjQlhdvZEMoaizFrFGvUHz7ZZkXCcnRo5ROOMRLB0pmNlAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:06:09.464498Z","bundle_sha256":"59f37021198c7077e49b0f3b5a3d7e454926a87394aeb26cc9e2ff6afcbd6797"}}