{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RXCRWB2AKI376YT247TKUICBUD","short_pith_number":"pith:RXCRWB2A","canonical_record":{"source":{"id":"2408.01215","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-02T12:04:19Z","cross_cats_sorted":[],"title_canon_sha256":"03ff6d85ef7602889318696aa696aaa29877bf296d2866bee91f268d2772873e","abstract_canon_sha256":"f2cfb524b387dbc39e69b016e2f068f0ae4c124ff58a9db824944c5706897edd"},"schema_version":"1.0"},"canonical_sha256":"8dc51b07405237ff627ae7e6aa2041a0e11ea7738861d74c02ff03368c13a3df","source":{"kind":"arxiv","id":"2408.01215","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01215","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01215v6","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01215","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"pith_short_12","alias_value":"RXCRWB2AKI37","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"pith_short_16","alias_value":"RXCRWB2AKI376YT2","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"pith_short_8","alias_value":"RXCRWB2A","created_at":"2026-07-05T09:45:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RXCRWB2AKI376YT247TKUICBUD","target":"record","payload":{"canonical_record":{"source":{"id":"2408.01215","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-02T12:04:19Z","cross_cats_sorted":[],"title_canon_sha256":"03ff6d85ef7602889318696aa696aaa29877bf296d2866bee91f268d2772873e","abstract_canon_sha256":"f2cfb524b387dbc39e69b016e2f068f0ae4c124ff58a9db824944c5706897edd"},"schema_version":"1.0"},"canonical_sha256":"8dc51b07405237ff627ae7e6aa2041a0e11ea7738861d74c02ff03368c13a3df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:52.298070Z","signature_b64":"4QHMZI3gt+wZA7Aarbc/9Lf3GNESymnBS16T6vPZhdF+VabTnMRjk+61tE8LP8E4JNxWJ8NZw49v25baysjwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc51b07405237ff627ae7e6aa2041a0e11ea7738861d74c02ff03368c13a3df","last_reissued_at":"2026-07-05T09:45:52.297536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:52.297536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.01215","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:45:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qWmt1WLjXdMuyyYt+1CbvvAzGzlnaoNyjuEn8pLxIl4IzdGb5KVMiIXf7J5z7AFnlliJsZDWWOEr5dFfapAvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:40:01.928708Z"},"content_sha256":"f3cdfb447325a560b4c20f5bfb6b88fae3dafdbcc325eb4416c776c7112afbad","schema_version":"1.0","event_id":"sha256:f3cdfb447325a560b4c20f5bfb6b88fae3dafdbcc325eb4416c776c7112afbad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RXCRWB2AKI376YT247TKUICBUD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training without Architectural Modification","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Juyoung Yun","submitted_at":"2024-08-02T12:04:19Z","abstract_excerpt":"The rapid advancements in deep learning necessitate better training methods for deep neural networks (DNNs). As models grow in complexity, vanishing and exploding gradients impede performance, particularly in skip-connected architectures like Deep Residual Networks. We propose Z-Score Normalization for Gradient Descent (ZNorm), an innovative technique that adjusts only the gradients without modifying the network architecture to accelerate training and improve model performance. ZNorm normalizes the overall gradients, providing consistent gradient scaling across layers, effectively reducing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01215","kind":"arxiv","version":6},"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/2408.01215/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":"2026-07-05T09:45:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NYq0TxCmTIAlirilrLolE4o7JHgMuaehuvfIVNSSpi6v+k/QEU5RdWZF+XgP2ab76sMej00rrWEbwdf6EGhFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:40:01.929542Z"},"content_sha256":"034b0f1d191182e2f8f07b7fce6ea3bd6367368fc03013ef3395f20a3779edd1","schema_version":"1.0","event_id":"sha256:034b0f1d191182e2f8f07b7fce6ea3bd6367368fc03013ef3395f20a3779edd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXCRWB2AKI376YT247TKUICBUD/bundle.json","state_url":"https://pith.science/pith/RXCRWB2AKI376YT247TKUICBUD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXCRWB2AKI376YT247TKUICBUD/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":"2026-08-09T21:40:01Z","links":{"resolver":"https://pith.science/pith/RXCRWB2AKI376YT247TKUICBUD","bundle":"https://pith.science/pith/RXCRWB2AKI376YT247TKUICBUD/bundle.json","state":"https://pith.science/pith/RXCRWB2AKI376YT247TKUICBUD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXCRWB2AKI376YT247TKUICBUD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RXCRWB2AKI376YT247TKUICBUD","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":"f2cfb524b387dbc39e69b016e2f068f0ae4c124ff58a9db824944c5706897edd","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-02T12:04:19Z","title_canon_sha256":"03ff6d85ef7602889318696aa696aaa29877bf296d2866bee91f268d2772873e"},"schema_version":"1.0","source":{"id":"2408.01215","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01215","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01215v6","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01215","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"pith_short_12","alias_value":"RXCRWB2AKI37","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"pith_short_16","alias_value":"RXCRWB2AKI376YT2","created_at":"2026-07-05T09:45:52Z"},{"alias_kind":"pith_short_8","alias_value":"RXCRWB2A","created_at":"2026-07-05T09:45:52Z"}],"graph_snapshots":[{"event_id":"sha256:034b0f1d191182e2f8f07b7fce6ea3bd6367368fc03013ef3395f20a3779edd1","target":"graph","created_at":"2026-07-05T09:45:52Z","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/2408.01215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advancements in deep learning necessitate better training methods for deep neural networks (DNNs). As models grow in complexity, vanishing and exploding gradients impede performance, particularly in skip-connected architectures like Deep Residual Networks. We propose Z-Score Normalization for Gradient Descent (ZNorm), an innovative technique that adjusts only the gradients without modifying the network architecture to accelerate training and improve model performance. ZNorm normalizes the overall gradients, providing consistent gradient scaling across layers, effectively reducing the","authors_text":"Juyoung Yun","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-02T12:04:19Z","title":"ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training without Architectural Modification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01215","kind":"arxiv","version":6},"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:f3cdfb447325a560b4c20f5bfb6b88fae3dafdbcc325eb4416c776c7112afbad","target":"record","created_at":"2026-07-05T09:45:52Z","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":"f2cfb524b387dbc39e69b016e2f068f0ae4c124ff58a9db824944c5706897edd","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-02T12:04:19Z","title_canon_sha256":"03ff6d85ef7602889318696aa696aaa29877bf296d2866bee91f268d2772873e"},"schema_version":"1.0","source":{"id":"2408.01215","kind":"arxiv","version":6}},"canonical_sha256":"8dc51b07405237ff627ae7e6aa2041a0e11ea7738861d74c02ff03368c13a3df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dc51b07405237ff627ae7e6aa2041a0e11ea7738861d74c02ff03368c13a3df","first_computed_at":"2026-07-05T09:45:52.297536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:52.297536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4QHMZI3gt+wZA7Aarbc/9Lf3GNESymnBS16T6vPZhdF+VabTnMRjk+61tE8LP8E4JNxWJ8NZw49v25baysjwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:52.298070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01215","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3cdfb447325a560b4c20f5bfb6b88fae3dafdbcc325eb4416c776c7112afbad","sha256:034b0f1d191182e2f8f07b7fce6ea3bd6367368fc03013ef3395f20a3779edd1"],"state_sha256":"ab56ebf68571b20fadd40ab4e3e6ce606b55f680a12de4a31564123fb86f92bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/V4TEzexpehQ8WWiyTeRLkVxtBU3uYhdX+GUMovX//V12cGDIYB0Dvtvv1BASLMOjOfkJPOtuZtCYkesfO7oDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:40:01.935282Z","bundle_sha256":"ddd97d91c868a2a86a4c11afffa365e6ffe055761662bb63d2d506e5914bba21"}}