{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XIFM6TTLCNGC32YBBALUSNX26P","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":"30ac9246d9cbb11fea397bda91ca4e7fc9f4b81c1b520b8dcd8f6fe93eaeaf29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T15:12:39Z","title_canon_sha256":"996ed0f5482a1dbb95f964b5e5f10cad10ab30437feb9ab6cd573a9464c9bef6"},"schema_version":"1.0","source":{"id":"2312.12226","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12226","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12226v2","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12226","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_12","alias_value":"XIFM6TTLCNGC","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_16","alias_value":"XIFM6TTLCNGC32YB","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_8","alias_value":"XIFM6TTL","created_at":"2026-07-05T08:28:58Z"}],"graph_snapshots":[{"event_id":"sha256:53eee5dde6245ab60f66646f95231d03c3754e7eeb75499d8f7d890c763c0bd6","target":"graph","created_at":"2026-07-05T08:28:58Z","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/2312.12226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Second-order optimization has been developed to accelerate the training of deep neural networks and it is being applied to increasingly larger-scale models. In this study, towards training on further larger scales, we identify a specific parameterization for second-order optimization that promotes feature learning in a stable manner even if the network width increases significantly. Inspired by a maximal update parameterization, we consider a one-step update of the gradient and reveal the appropriate scales of hyperparameters including random initialization, learning rates, and damping terms. ","authors_text":"Ryo Karakida, Satoki Ishikawa","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T15:12:39Z","title":"On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12226","kind":"arxiv","version":2},"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":"sha256:6eac1825899b1952ba18c32b10d48a202851d13dd6d72f1dcccd46ff8daf4b99","target":"record","created_at":"2026-07-05T08:28:58Z","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":"30ac9246d9cbb11fea397bda91ca4e7fc9f4b81c1b520b8dcd8f6fe93eaeaf29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T15:12:39Z","title_canon_sha256":"996ed0f5482a1dbb95f964b5e5f10cad10ab30437feb9ab6cd573a9464c9bef6"},"schema_version":"1.0","source":{"id":"2312.12226","kind":"arxiv","version":2}},"canonical_sha256":"ba0acf4e6b134c2deb0108174936faf3e9502ccf5d643650121d49a7fca3f11d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba0acf4e6b134c2deb0108174936faf3e9502ccf5d643650121d49a7fca3f11d","first_computed_at":"2026-07-05T08:28:58.167503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:58.167503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZhsydlI0F3y+Udjud+NeQ413laR43CA2jqYzXL0e3DvM9sGBnsJCOnd7MohDEGd8f3gEXTGv4s7LD4EEsHHWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:58.167981Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12226","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eac1825899b1952ba18c32b10d48a202851d13dd6d72f1dcccd46ff8daf4b99","sha256:53eee5dde6245ab60f66646f95231d03c3754e7eeb75499d8f7d890c763c0bd6"],"state_sha256":"1ff9a165391c8a2f797b6b38eb560c8c5173de43582b4534027bf4b7d0faf113"}