{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2WHIM4UHIL2UAWPEBWZXJSV5OX","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":"41781c45d764a8a169cd465101c2c8e11d40f5a598eaeb846f447e92f46eb009","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T19:54:23Z","title_canon_sha256":"7b64a98409c0e9e0c760a73456f1cae5683ead1f5a3e8faaf0165919e48715f4"},"schema_version":"1.0","source":{"id":"2509.03677","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.03677","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.03677v2","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03677","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"2WHIM4UHIL2U","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"2WHIM4UHIL2UAWPE","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"2WHIM4UH","created_at":"2026-07-05T12:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:1ec40b56cea6164bd9f6fc8cab4ea3e98419a68c6b3b02aa77a2419b9c97a09e","target":"graph","created_at":"2026-07-05T12:06:20Z","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/2509.03677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient dynamics play a central role in determining the stability and generalization of deep neural networks. In this work, we provide an empirical analysis of how variance and standard deviation of gradients evolve during training, showing consistent changes across layers and at the global scale in convolutional networks. Motivated by these observations, we propose a hyperparameter-free gradient normalization method that aligns gradient scaling with their natural evolution. This approach prevents unintended amplification, stabilizes optimization, and preserves convergence guarantees. Experim","authors_text":"Vincent-Daniel Yun","cross_cats":["cs.AI","cs.CV","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T19:54:23Z","title":"Insights from Gradient Dynamics: Gradient Autoscaled Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03677","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":"sha256:673357c0fa6fc5b94ce2cf1b3150e75ca52b24d021a0cb897f2bef05466fed6b","target":"record","created_at":"2026-07-05T12:06:20Z","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":"41781c45d764a8a169cd465101c2c8e11d40f5a598eaeb846f447e92f46eb009","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T19:54:23Z","title_canon_sha256":"7b64a98409c0e9e0c760a73456f1cae5683ead1f5a3e8faaf0165919e48715f4"},"schema_version":"1.0","source":{"id":"2509.03677","kind":"arxiv","version":2}},"canonical_sha256":"d58e86728742f54059e40db374cabd75d26aab546ed6a16dc0694a62edb99103","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d58e86728742f54059e40db374cabd75d26aab546ed6a16dc0694a62edb99103","first_computed_at":"2026-07-05T12:06:20.228727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:20.228727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"daFhzApnrFa6JrLsXtrk4GdU2P56zsnnMkyNWbMSEBUoS0EgMvxSJz1bUsCB6CoKxerhKwSREHqTFDQNbIEjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:20.229212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.03677","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:673357c0fa6fc5b94ce2cf1b3150e75ca52b24d021a0cb897f2bef05466fed6b","sha256:1ec40b56cea6164bd9f6fc8cab4ea3e98419a68c6b3b02aa77a2419b9c97a09e"],"state_sha256":"55ea20aeb4738868131b20c7d4fc94b20aa6c03701885a01418f8c20a275f41f"}