{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FPEVKMNQJ2SP4IBZ6ZSNXVQO74","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":"d728048b5cc09b4776ca9b425d7beeda56b1ef055faf0f1a69256a6e3380152b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-18T15:13:18Z","title_canon_sha256":"8a841b4bd237e91e1fafa7aedf21a30e9cbbf265998ae3f62b409b94ecc41d51"},"schema_version":"1.0","source":{"id":"2605.18528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18528","created_at":"2026-05-20T00:06:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18528v1","created_at":"2026-05-20T00:06:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18528","created_at":"2026-05-20T00:06:06Z"},{"alias_kind":"pith_short_12","alias_value":"FPEVKMNQJ2SP","created_at":"2026-05-20T00:06:06Z"},{"alias_kind":"pith_short_16","alias_value":"FPEVKMNQJ2SP4IBZ","created_at":"2026-05-20T00:06:06Z"},{"alias_kind":"pith_short_8","alias_value":"FPEVKMNQ","created_at":"2026-05-20T00:06:06Z"}],"graph_snapshots":[{"event_id":"sha256:e57ef5606a86684d2e1cfaf78458139f1334e96288d8cbd4c984897494b2b5d5","target":"graph","created_at":"2026-05-20T00:06:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.18528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A growing lesson from neural network optimization is that optimizer design should respect how the model is parametrized. Scale-invariant methods become important because their normalized layerwise updates can not only support hyperparameter transfer across model sizes but exploit input-output matrix norm geometry. At the same time, stochastic gradient noises in deep learning are often far from sub-Gaussian and may exhibit heavy tails. These crucial observations have shaped recent algorithmic principles for training neural networks, yet their joint theoretical consequences remain underexplored.","authors_text":"Jiayu Zhang, Tianyi Lin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-18T15:13:18Z","title":"Scale-Invariant Neural Network Optimization: Norm Geometry and Heavy-Tailed Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18528","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":"sha256:04a60d36232f4db4d0ea524b509faa01b93be9c6f2e877bda38ecba3e2842da4","target":"record","created_at":"2026-05-20T00:06:06Z","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":"d728048b5cc09b4776ca9b425d7beeda56b1ef055faf0f1a69256a6e3380152b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-18T15:13:18Z","title_canon_sha256":"8a841b4bd237e91e1fafa7aedf21a30e9cbbf265998ae3f62b409b94ecc41d51"},"schema_version":"1.0","source":{"id":"2605.18528","kind":"arxiv","version":1}},"canonical_sha256":"2bc95531b04ea4fe2039f664dbd60eff2d7a043626480bad08a8c0cb12515212","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bc95531b04ea4fe2039f664dbd60eff2d7a043626480bad08a8c0cb12515212","first_computed_at":"2026-05-20T00:06:06.039402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:06.039402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vAcYqZuuYg7zoXu4xHc91RcJ+ci1NGRDRXV31zUnLmvYhJweWNeOlzAP5R/JTmR03QnQhoVs3ip7CzebDvl3Dw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:06.040337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04a60d36232f4db4d0ea524b509faa01b93be9c6f2e877bda38ecba3e2842da4","sha256:e57ef5606a86684d2e1cfaf78458139f1334e96288d8cbd4c984897494b2b5d5"],"state_sha256":"5b31d1ca3a3370182da292493c01e80f677da30f8791a054a6584084c0288695"}