{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:M3YWY4QQRWWEX6BGPARH7T3M63","short_pith_number":"pith:M3YWY4QQ","canonical_record":{"source":{"id":"2006.06878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T23:55:54Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"ec98980e5347881b71a26d90e1c5303a82bd227474bfd352cfa7411f82afe9bc","abstract_canon_sha256":"cf66613bdd7a758e553df4a3ba70d166387a2351cbb5bb7418f0efd4796b01ff"},"schema_version":"1.0"},"canonical_sha256":"66f16c72108dac4bf82678227fcf6cf6fc308315d0340685513ef694b31e2039","source":{"kind":"arxiv","id":"2006.06878","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06878","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06878v1","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06878","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"M3YWY4QQRWWE","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"M3YWY4QQRWWEX6BG","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"M3YWY4QQ","created_at":"2026-07-05T01:09:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:M3YWY4QQRWWEX6BGPARH7T3M63","target":"record","payload":{"canonical_record":{"source":{"id":"2006.06878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T23:55:54Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"ec98980e5347881b71a26d90e1c5303a82bd227474bfd352cfa7411f82afe9bc","abstract_canon_sha256":"cf66613bdd7a758e553df4a3ba70d166387a2351cbb5bb7418f0efd4796b01ff"},"schema_version":"1.0"},"canonical_sha256":"66f16c72108dac4bf82678227fcf6cf6fc308315d0340685513ef694b31e2039","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:47.798775Z","signature_b64":"vrvoQxerOZ4FNGOChVCdCCcjtmqOsLJs7mg9Tp0V8CpLEvVtEOY4D9rDnxHCWW8MyJ0lRD2wc58lxBEAKb29Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66f16c72108dac4bf82678227fcf6cf6fc308315d0340685513ef694b31e2039","last_reissued_at":"2026-07-05T01:09:47.798369Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:47.798369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.06878","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":"2026-07-05T01:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BiI6CZh5P1dsKv5etB7DoRWUNrhQYYnKWXv0Kvf1nM5w97sagVK8MwTVXJHJNYQH0+iD+0YkQ0LU5d3gMTY3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:06:50.646157Z"},"content_sha256":"14a3ecf687ebbb561b04827e9895e698390d50ab49da466f4bc3ca31ad6bb2d9","schema_version":"1.0","event_id":"sha256:14a3ecf687ebbb561b04827e9895e698390d50ab49da466f4bc3ca31ad6bb2d9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:M3YWY4QQRWWEX6BGPARH7T3M63","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimization Theory for ReLU Neural Networks Trained with Normalization Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guido Mont\\'ufar, Quanquan Gu, Yonatan Dukler","submitted_at":"2020-06-11T23:55:54Z","abstract_excerpt":"The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they improve generalization performance and speed up training significantly. Nonetheless, the vast majority of current deep learning theory and non-convex optimization literature focuses on the un-normalized setting, where the functions under consideration do not exhibit the properties of commonly normalized neural networks. In this paper, we bridge this gap by giving the first global co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06878","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/2006.06878/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":"2026-07-05T01:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vFGkFSlUMAkIFOzmebbMRkuOMNGnJeEWMI/9jipIl6/aH0by7vovluqefzXhqiMufCNCPHS38uEpVIoagiBPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:06:50.646662Z"},"content_sha256":"1b7ddf82db6fb6c2aa014255bdf431fe4f6b2687976e4da93e51468fb2b9c348","schema_version":"1.0","event_id":"sha256:1b7ddf82db6fb6c2aa014255bdf431fe4f6b2687976e4da93e51468fb2b9c348"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3YWY4QQRWWEX6BGPARH7T3M63/bundle.json","state_url":"https://pith.science/pith/M3YWY4QQRWWEX6BGPARH7T3M63/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3YWY4QQRWWEX6BGPARH7T3M63/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":"2026-07-07T03:06:50Z","links":{"resolver":"https://pith.science/pith/M3YWY4QQRWWEX6BGPARH7T3M63","bundle":"https://pith.science/pith/M3YWY4QQRWWEX6BGPARH7T3M63/bundle.json","state":"https://pith.science/pith/M3YWY4QQRWWEX6BGPARH7T3M63/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3YWY4QQRWWEX6BGPARH7T3M63/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:M3YWY4QQRWWEX6BGPARH7T3M63","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":"cf66613bdd7a758e553df4a3ba70d166387a2351cbb5bb7418f0efd4796b01ff","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T23:55:54Z","title_canon_sha256":"ec98980e5347881b71a26d90e1c5303a82bd227474bfd352cfa7411f82afe9bc"},"schema_version":"1.0","source":{"id":"2006.06878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06878","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06878v1","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06878","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"M3YWY4QQRWWE","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_16","alias_value":"M3YWY4QQRWWEX6BG","created_at":"2026-07-05T01:09:47Z"},{"alias_kind":"pith_short_8","alias_value":"M3YWY4QQ","created_at":"2026-07-05T01:09:47Z"}],"graph_snapshots":[{"event_id":"sha256:1b7ddf82db6fb6c2aa014255bdf431fe4f6b2687976e4da93e51468fb2b9c348","target":"graph","created_at":"2026-07-05T01:09:47Z","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/2006.06878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of deep neural networks is in part due to the use of normalization layers. Normalization layers like Batch Normalization, Layer Normalization and Weight Normalization are ubiquitous in practice, as they improve generalization performance and speed up training significantly. Nonetheless, the vast majority of current deep learning theory and non-convex optimization literature focuses on the un-normalized setting, where the functions under consideration do not exhibit the properties of commonly normalized neural networks. In this paper, we bridge this gap by giving the first global co","authors_text":"Guido Mont\\'ufar, Quanquan Gu, Yonatan Dukler","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T23:55:54Z","title":"Optimization Theory for ReLU Neural Networks Trained with Normalization Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06878","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":"sha256:14a3ecf687ebbb561b04827e9895e698390d50ab49da466f4bc3ca31ad6bb2d9","target":"record","created_at":"2026-07-05T01:09:47Z","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":"cf66613bdd7a758e553df4a3ba70d166387a2351cbb5bb7418f0efd4796b01ff","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T23:55:54Z","title_canon_sha256":"ec98980e5347881b71a26d90e1c5303a82bd227474bfd352cfa7411f82afe9bc"},"schema_version":"1.0","source":{"id":"2006.06878","kind":"arxiv","version":1}},"canonical_sha256":"66f16c72108dac4bf82678227fcf6cf6fc308315d0340685513ef694b31e2039","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66f16c72108dac4bf82678227fcf6cf6fc308315d0340685513ef694b31e2039","first_computed_at":"2026-07-05T01:09:47.798369Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:47.798369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vrvoQxerOZ4FNGOChVCdCCcjtmqOsLJs7mg9Tp0V8CpLEvVtEOY4D9rDnxHCWW8MyJ0lRD2wc58lxBEAKb29Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:47.798775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14a3ecf687ebbb561b04827e9895e698390d50ab49da466f4bc3ca31ad6bb2d9","sha256:1b7ddf82db6fb6c2aa014255bdf431fe4f6b2687976e4da93e51468fb2b9c348"],"state_sha256":"1a97306730dead4711bd5207f0bf340055620e6214d406ebee04ea81d14071b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6sMmHsCrztk5/QlvX+wnq2khxvlm0vT7j77zzG9jNpgEwieRjkaTdeOBLWMO7iNO5pbI7ecKcTYp42mBaS/uDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:06:50.649135Z","bundle_sha256":"e6b560acfca5274ff00ad9c70a416b9609a5face8237ade177c696cd704378fa"}}