{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KNA3GHANMLOU4KEDYOPGM5WCQ7","short_pith_number":"pith:KNA3GHAN","canonical_record":{"source":{"id":"2406.09405","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T17:59:35Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"3804dc8bf442ca94025972cb158abd329ebaca4f20aacbae218c94ca3c646cf2","abstract_canon_sha256":"95583cb9c0059913f8755d1175da50a716e147443a3a5c9999cbadca3456a452"},"schema_version":"1.0"},"canonical_sha256":"5341b31c0d62dd4e2883c39e6676c287fd8bd6ed9e208a4f0ea4e3cc0b725b35","source":{"kind":"arxiv","id":"2406.09405","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09405","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09405v2","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09405","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_12","alias_value":"KNA3GHANMLOU","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_16","alias_value":"KNA3GHANMLOU4KED","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_8","alias_value":"KNA3GHAN","created_at":"2026-07-05T09:29:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KNA3GHANMLOU4KEDYOPGM5WCQ7","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09405","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T17:59:35Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"3804dc8bf442ca94025972cb158abd329ebaca4f20aacbae218c94ca3c646cf2","abstract_canon_sha256":"95583cb9c0059913f8755d1175da50a716e147443a3a5c9999cbadca3456a452"},"schema_version":"1.0"},"canonical_sha256":"5341b31c0d62dd4e2883c39e6676c287fd8bd6ed9e208a4f0ea4e3cc0b725b35","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:49.562516Z","signature_b64":"h2sRsTnZvn3Tv4tk6Gk0g6x0mVlIZQP3/dME0e5qAoUq7n74/dI/A99JH+9GcUoDruSG/LBvYvULE+WmLPHhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5341b31c0d62dd4e2883c39e6676c287fd8bd6ed9e208a4f0ea4e3cc0b725b35","last_reissued_at":"2026-07-05T09:29:49.562019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:49.562019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09405","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":"2026-07-05T09:29:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWGasajXo8m0/ynUXFjSGJwCL9bHGN26EL76azzdVGWMCAUe2mJ3QiDmfkR60YEsZ/J0h8/Ic91rdLjeTt78BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:09:36.026366Z"},"content_sha256":"48dc2d561502e523ef9788d584cd6b2fc9cd5cc2e7bb4db1f3a9c71ca4189a94","schema_version":"1.0","event_id":"sha256:48dc2d561502e523ef9788d584cd6b2fc9cd5cc2e7bb4db1f3a9c71ca4189a94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KNA3GHANMLOU4KEDYOPGM5WCQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dayal Singh Kalra, Maissam Barkeshli","submitted_at":"2024-06-13T17:59:35Z","abstract_excerpt":"It is common in deep learning to warm up the learning rate $\\eta$, often by a linear schedule between $\\eta_{\\text{init}} = 0$ and a predetermined target $\\eta_{\\text{trgt}}$. In this paper, we show through systematic experiments using SGD and Adam that the overwhelming benefit of warmup arises from allowing the network to tolerate larger $\\eta_{\\text{trgt}}$ {by forcing the network to more well-conditioned areas of the loss landscape}. The ability to handle larger $\\eta_{\\text{trgt}}$ makes hyperparameter tuning more robust while improving the final performance. We uncover different regimes o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09405","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/2406.09405/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":"2026-07-05T09:29:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dysSTiNHWEr5YnagSDmsgvbC0iqMkXfL10zl85gGDxlAoAUe89Id0ooOc+pyx6/JxY+D0sesx7iJbjgkXbbiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T08:09:36.026892Z"},"content_sha256":"0bb98c43b4efac1065dfe0b6cdec3f2c181f44d53eb44a3adb117718c0289e99","schema_version":"1.0","event_id":"sha256:0bb98c43b4efac1065dfe0b6cdec3f2c181f44d53eb44a3adb117718c0289e99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KNA3GHANMLOU4KEDYOPGM5WCQ7/bundle.json","state_url":"https://pith.science/pith/KNA3GHANMLOU4KEDYOPGM5WCQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KNA3GHANMLOU4KEDYOPGM5WCQ7/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":"2026-08-04T08:09:36Z","links":{"resolver":"https://pith.science/pith/KNA3GHANMLOU4KEDYOPGM5WCQ7","bundle":"https://pith.science/pith/KNA3GHANMLOU4KEDYOPGM5WCQ7/bundle.json","state":"https://pith.science/pith/KNA3GHANMLOU4KEDYOPGM5WCQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KNA3GHANMLOU4KEDYOPGM5WCQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KNA3GHANMLOU4KEDYOPGM5WCQ7","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":"95583cb9c0059913f8755d1175da50a716e147443a3a5c9999cbadca3456a452","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T17:59:35Z","title_canon_sha256":"3804dc8bf442ca94025972cb158abd329ebaca4f20aacbae218c94ca3c646cf2"},"schema_version":"1.0","source":{"id":"2406.09405","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09405","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09405v2","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09405","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_12","alias_value":"KNA3GHANMLOU","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_16","alias_value":"KNA3GHANMLOU4KED","created_at":"2026-07-05T09:29:49Z"},{"alias_kind":"pith_short_8","alias_value":"KNA3GHAN","created_at":"2026-07-05T09:29:49Z"}],"graph_snapshots":[{"event_id":"sha256:0bb98c43b4efac1065dfe0b6cdec3f2c181f44d53eb44a3adb117718c0289e99","target":"graph","created_at":"2026-07-05T09:29:49Z","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/2406.09405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is common in deep learning to warm up the learning rate $\\eta$, often by a linear schedule between $\\eta_{\\text{init}} = 0$ and a predetermined target $\\eta_{\\text{trgt}}$. In this paper, we show through systematic experiments using SGD and Adam that the overwhelming benefit of warmup arises from allowing the network to tolerate larger $\\eta_{\\text{trgt}}$ {by forcing the network to more well-conditioned areas of the loss landscape}. The ability to handle larger $\\eta_{\\text{trgt}}$ makes hyperparameter tuning more robust while improving the final performance. We uncover different regimes o","authors_text":"Dayal Singh Kalra, Maissam Barkeshli","cross_cats":["cond-mat.dis-nn","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T17:59:35Z","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09405","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":"sha256:48dc2d561502e523ef9788d584cd6b2fc9cd5cc2e7bb4db1f3a9c71ca4189a94","target":"record","created_at":"2026-07-05T09:29:49Z","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":"95583cb9c0059913f8755d1175da50a716e147443a3a5c9999cbadca3456a452","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T17:59:35Z","title_canon_sha256":"3804dc8bf442ca94025972cb158abd329ebaca4f20aacbae218c94ca3c646cf2"},"schema_version":"1.0","source":{"id":"2406.09405","kind":"arxiv","version":2}},"canonical_sha256":"5341b31c0d62dd4e2883c39e6676c287fd8bd6ed9e208a4f0ea4e3cc0b725b35","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5341b31c0d62dd4e2883c39e6676c287fd8bd6ed9e208a4f0ea4e3cc0b725b35","first_computed_at":"2026-07-05T09:29:49.562019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:49.562019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h2sRsTnZvn3Tv4tk6Gk0g6x0mVlIZQP3/dME0e5qAoUq7n74/dI/A99JH+9GcUoDruSG/LBvYvULE+WmLPHhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:49.562516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09405","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48dc2d561502e523ef9788d584cd6b2fc9cd5cc2e7bb4db1f3a9c71ca4189a94","sha256:0bb98c43b4efac1065dfe0b6cdec3f2c181f44d53eb44a3adb117718c0289e99"],"state_sha256":"f7ca39d72fd267e0a8719a640e49f6afa37b86ca90e264d48a130042afe6c316"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hDaE+ENDgxLtNDyIiud9FadJwXuJ7o/g4ugGvsbiync1l/sOAO0gmnnVwvYi/DKmuChNxA1GTQBMbOOtKPRACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T08:09:36.031936Z","bundle_sha256":"1ccfa3f5a1135746f5b05b7a101a619740e215e5e378aeb1ddf98afb6f4c7669"}}