{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6SHJGYHIABE27KYFGFGES66NLL","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":"35ab9b5852f5596e63bedd03ca31de24babbeffd5768c326d3b12fd0f909a432","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-26T05:02:21Z","title_canon_sha256":"7ee8f870dc2032bacbb91692e1d83a50f16bfc3efc4fd0f965b066f426a06086"},"schema_version":"1.0","source":{"id":"2504.20096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20096","created_at":"2026-07-05T10:55:36Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20096v1","created_at":"2026-07-05T10:55:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20096","created_at":"2026-07-05T10:55:36Z"},{"alias_kind":"pith_short_12","alias_value":"6SHJGYHIABE2","created_at":"2026-07-05T10:55:36Z"},{"alias_kind":"pith_short_16","alias_value":"6SHJGYHIABE27KYF","created_at":"2026-07-05T10:55:36Z"},{"alias_kind":"pith_short_8","alias_value":"6SHJGYHI","created_at":"2026-07-05T10:55:36Z"}],"graph_snapshots":[{"event_id":"sha256:2206898c1427c33f4d1211dd1090a510a1f2d7893e37c4a95523925f10913436","target":"graph","created_at":"2026-07-05T10:55:36Z","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/2504.20096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"First-order optimization methods remain the standard for training deep neural networks (DNNs). Optimizers like Adam incorporate limited curvature information by preconditioning the stochastic gradient with a diagonal matrix. Despite the widespread adoption of first-order methods, second-order optimization algorithms often exhibit superior convergence compared to methods like Adam and SGD. However, their practicality in training DNNs is still limited by a significantly higher per-iteration computational cost compared to first-order methods. In this thesis, we present AdaFisher, a novel adaptive","authors_text":"Damien Martins Gomes","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-26T05:02:21Z","title":"Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20096","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":"sha256:271f963b90ca2eddfbe7d45dda2a60628f7bc9dfb465959de744ce4653b86dd7","target":"record","created_at":"2026-07-05T10:55:36Z","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":"35ab9b5852f5596e63bedd03ca31de24babbeffd5768c326d3b12fd0f909a432","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-26T05:02:21Z","title_canon_sha256":"7ee8f870dc2032bacbb91692e1d83a50f16bfc3efc4fd0f965b066f426a06086"},"schema_version":"1.0","source":{"id":"2504.20096","kind":"arxiv","version":1}},"canonical_sha256":"f48e9360e80049afab05314c497bcd5ae02e2fb51fda28f7ac2282cee5a4a040","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f48e9360e80049afab05314c497bcd5ae02e2fb51fda28f7ac2282cee5a4a040","first_computed_at":"2026-07-05T10:55:36.377789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:55:36.377789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8e6fLb1ha3uUUaejJn9LDTsWeC54nekoWOc00by3nqApHFxRr7JU1kZo5goudIlor56C8gb8+4ihSDnZZeUdDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:55:36.378284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:271f963b90ca2eddfbe7d45dda2a60628f7bc9dfb465959de744ce4653b86dd7","sha256:2206898c1427c33f4d1211dd1090a510a1f2d7893e37c4a95523925f10913436"],"state_sha256":"1688a366be1962216596692b776549d46b967b3b7a276d73a771c95499410108"}