{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2WHIM4UHIL2UAWPEBWZXJSV5OX","short_pith_number":"pith:2WHIM4UH","canonical_record":{"source":{"id":"2509.03677","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T19:54:23Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT"],"title_canon_sha256":"7b64a98409c0e9e0c760a73456f1cae5683ead1f5a3e8faaf0165919e48715f4","abstract_canon_sha256":"41781c45d764a8a169cd465101c2c8e11d40f5a598eaeb846f447e92f46eb009"},"schema_version":"1.0"},"canonical_sha256":"d58e86728742f54059e40db374cabd75d26aab546ed6a16dc0694a62edb99103","source":{"kind":"arxiv","id":"2509.03677","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2WHIM4UHIL2UAWPEBWZXJSV5OX","target":"record","payload":{"canonical_record":{"source":{"id":"2509.03677","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T19:54:23Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IT","math.IT"],"title_canon_sha256":"7b64a98409c0e9e0c760a73456f1cae5683ead1f5a3e8faaf0165919e48715f4","abstract_canon_sha256":"41781c45d764a8a169cd465101c2c8e11d40f5a598eaeb846f447e92f46eb009"},"schema_version":"1.0"},"canonical_sha256":"d58e86728742f54059e40db374cabd75d26aab546ed6a16dc0694a62edb99103","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:20.229212Z","signature_b64":"daFhzApnrFa6JrLsXtrk4GdU2P56zsnnMkyNWbMSEBUoS0EgMvxSJz1bUsCB6CoKxerhKwSREHqTFDQNbIEjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d58e86728742f54059e40db374cabd75d26aab546ed6a16dc0694a62edb99103","last_reissued_at":"2026-07-05T12:06:20.228727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:20.228727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.03677","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ERHp5xF+109Spk5Y/wJoZ2CaFe4hPkd5bWXhWTqNeP8h55y42PUMZJZguuo86OTeZC/vEFNBeRzIVTPf5Fn4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:46:06.449716Z"},"content_sha256":"673357c0fa6fc5b94ce2cf1b3150e75ca52b24d021a0cb897f2bef05466fed6b","schema_version":"1.0","event_id":"sha256:673357c0fa6fc5b94ce2cf1b3150e75ca52b24d021a0cb897f2bef05466fed6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2WHIM4UHIL2UAWPEBWZXJSV5OX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Insights from Gradient Dynamics: Gradient Autoscaled Normalization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Vincent-Daniel Yun","submitted_at":"2025-09-03T19:54:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03677","kind":"arxiv","version":2},"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/2509.03677/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":"2026-07-05T12:06:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xMXglmn4uKcrDvU+nzaI8Dm6swYLHdv7YFGXCn6NpL6LBQnOL5in43BdGq4Z+toDln9fkg6zaf5FqdmAysYUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:46:06.450239Z"},"content_sha256":"1ec40b56cea6164bd9f6fc8cab4ea3e98419a68c6b3b02aa77a2419b9c97a09e","schema_version":"1.0","event_id":"sha256:1ec40b56cea6164bd9f6fc8cab4ea3e98419a68c6b3b02aa77a2419b9c97a09e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2WHIM4UHIL2UAWPEBWZXJSV5OX/bundle.json","state_url":"https://pith.science/pith/2WHIM4UHIL2UAWPEBWZXJSV5OX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2WHIM4UHIL2UAWPEBWZXJSV5OX/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":"2026-08-07T16:46:06Z","links":{"resolver":"https://pith.science/pith/2WHIM4UHIL2UAWPEBWZXJSV5OX","bundle":"https://pith.science/pith/2WHIM4UHIL2UAWPEBWZXJSV5OX/bundle.json","state":"https://pith.science/pith/2WHIM4UHIL2UAWPEBWZXJSV5OX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2WHIM4UHIL2UAWPEBWZXJSV5OX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FDfFQU1CrlrMeUo3M+omYkcYS24mAxBkk01BAYr4l8NliEuEZrA+KlpQKdhcVhuhldQ01yi2exLcvlzU5ufICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:46:06.455722Z","bundle_sha256":"dda45dbc21c74f3fd5b2bd7c5b18c7bf962332028da1e817713f98e1682cdc2e"}}