{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VDMX6AXOFFVAD4CADBNWIXPZNM","short_pith_number":"pith:VDMX6AXO","canonical_record":{"source":{"id":"2412.11768","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T13:41:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"372606e95afc988818cec250411fba803dca0d57b2311c01ccd8d60285f19998","abstract_canon_sha256":"a316e542fecd6d84f3179e46da965d3e7ed7f3855f5305e56321a1d947bf0d70"},"schema_version":"1.0"},"canonical_sha256":"a8d97f02ee296a01f040185b645df96b3c3910104157dacca4a8b58be33ac454","source":{"kind":"arxiv","id":"2412.11768","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11768","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11768v2","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11768","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"VDMX6AXOFFVA","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"VDMX6AXOFFVAD4CA","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"VDMX6AXO","created_at":"2026-07-05T09:50:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VDMX6AXOFFVAD4CADBNWIXPZNM","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11768","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T13:41:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"372606e95afc988818cec250411fba803dca0d57b2311c01ccd8d60285f19998","abstract_canon_sha256":"a316e542fecd6d84f3179e46da965d3e7ed7f3855f5305e56321a1d947bf0d70"},"schema_version":"1.0"},"canonical_sha256":"a8d97f02ee296a01f040185b645df96b3c3910104157dacca4a8b58be33ac454","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:09.448643Z","signature_b64":"zt0D0ikner4Z8ZUdU4dLPlE3kctwq5b04skg3lTANwlhL4SX/eq3ZMYgwRksyFtPzNme03TUYjUDGXtuLhpcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8d97f02ee296a01f040185b645df96b3c3910104157dacca4a8b58be33ac454","last_reissued_at":"2026-07-05T09:50:09.448139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:09.448139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11768","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":"2026-07-05T09:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D/4A8ZE48nwwPDCPEIvo2uRsjIb9seQi0KUgp3X3VkwqoJCvYSR7Rvs3XTvK7Tk7s/mqE1ZWtEgcau4CGR+iBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:44:40.717810Z"},"content_sha256":"8dd5ff7438f8a924b8b4ff3533d3ff03fa306cafeae167cfed8eba373d122310","schema_version":"1.0","event_id":"sha256:8dd5ff7438f8a924b8b4ff3533d3ff03fa306cafeae167cfed8eba373d122310"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VDMX6AXOFFVAD4CADBNWIXPZNM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongkai Wen, Lichuan Xiang, Minghao Xu, Xu Cai","submitted_at":"2024-12-16T13:41:37Z","abstract_excerpt":"In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent with momentum (SGDM). SGD-SaI performs learning rate Scaling at Initialization (SaI) to distinct parameter groups, guided by their respective gradient signal-to-noise ratios (g-SNR). By adjusting learning rates without relying on adaptive second-order momentum, SGD-SaI helps prevent training imbalances from the very first iteration and cuts the optimizer's memory usage by half compared to AdamW. Despite its simplici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11768","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/2412.11768/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":"2026-07-05T09:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPTRWmEV3h6Sw5IiY9Gk3nYvZQNiOrreVv7oQxz1/iePeOVJsSufWmXI6A15AOGgHZPWXTI/T+AR4NfkIrETAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:44:40.718325Z"},"content_sha256":"47396ef75a510bf8c3c088f51f68e63cae32981cc3ed1d21d20df490c7ad017f","schema_version":"1.0","event_id":"sha256:47396ef75a510bf8c3c088f51f68e63cae32981cc3ed1d21d20df490c7ad017f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDMX6AXOFFVAD4CADBNWIXPZNM/bundle.json","state_url":"https://pith.science/pith/VDMX6AXOFFVAD4CADBNWIXPZNM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDMX6AXOFFVAD4CADBNWIXPZNM/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":"2026-08-07T23:44:40Z","links":{"resolver":"https://pith.science/pith/VDMX6AXOFFVAD4CADBNWIXPZNM","bundle":"https://pith.science/pith/VDMX6AXOFFVAD4CADBNWIXPZNM/bundle.json","state":"https://pith.science/pith/VDMX6AXOFFVAD4CADBNWIXPZNM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDMX6AXOFFVAD4CADBNWIXPZNM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VDMX6AXOFFVAD4CADBNWIXPZNM","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":"a316e542fecd6d84f3179e46da965d3e7ed7f3855f5305e56321a1d947bf0d70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T13:41:37Z","title_canon_sha256":"372606e95afc988818cec250411fba803dca0d57b2311c01ccd8d60285f19998"},"schema_version":"1.0","source":{"id":"2412.11768","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11768","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11768v2","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11768","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"VDMX6AXOFFVA","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"VDMX6AXOFFVAD4CA","created_at":"2026-07-05T09:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"VDMX6AXO","created_at":"2026-07-05T09:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:47396ef75a510bf8c3c088f51f68e63cae32981cc3ed1d21d20df490c7ad017f","target":"graph","created_at":"2026-07-05T09:50:09Z","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/2412.11768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we question the necessity of adaptive gradient methods for training deep neural networks. SGD-SaI is a simple yet effective enhancement to stochastic gradient descent with momentum (SGDM). SGD-SaI performs learning rate Scaling at Initialization (SaI) to distinct parameter groups, guided by their respective gradient signal-to-noise ratios (g-SNR). By adjusting learning rates without relying on adaptive second-order momentum, SGD-SaI helps prevent training imbalances from the very first iteration and cuts the optimizer's memory usage by half compared to AdamW. Despite its simplici","authors_text":"Hongkai Wen, Lichuan Xiang, Minghao Xu, Xu Cai","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T13:41:37Z","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11768","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":"sha256:8dd5ff7438f8a924b8b4ff3533d3ff03fa306cafeae167cfed8eba373d122310","target":"record","created_at":"2026-07-05T09:50:09Z","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":"a316e542fecd6d84f3179e46da965d3e7ed7f3855f5305e56321a1d947bf0d70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T13:41:37Z","title_canon_sha256":"372606e95afc988818cec250411fba803dca0d57b2311c01ccd8d60285f19998"},"schema_version":"1.0","source":{"id":"2412.11768","kind":"arxiv","version":2}},"canonical_sha256":"a8d97f02ee296a01f040185b645df96b3c3910104157dacca4a8b58be33ac454","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8d97f02ee296a01f040185b645df96b3c3910104157dacca4a8b58be33ac454","first_computed_at":"2026-07-05T09:50:09.448139Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:09.448139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zt0D0ikner4Z8ZUdU4dLPlE3kctwq5b04skg3lTANwlhL4SX/eq3ZMYgwRksyFtPzNme03TUYjUDGXtuLhpcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:09.448643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11768","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dd5ff7438f8a924b8b4ff3533d3ff03fa306cafeae167cfed8eba373d122310","sha256:47396ef75a510bf8c3c088f51f68e63cae32981cc3ed1d21d20df490c7ad017f"],"state_sha256":"f0225ac87c0aa7eb57d662ba22afcb12316c3584a4219c0beec606c5aa9ce73a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5VtpfNygK5S0GFC8AO+aE99A9p90MKkoo7CZ2rlHfXQToJ6AXaDcAXUMTO9y99zdAiww7UMOoXybxx1gtVCFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:44:40.724078Z","bundle_sha256":"eb369c18b18028a5e4a0a0b0acf4750a27b1a8acee3ed74327ecf72df0e22b35"}}