{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EJYR2UKB6ZNB3MGKU7LJHA5OFK","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":"04aa6b98a3aa7b83021382b840b5ea90e93c354368366418a08f41ee5180d51f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T06:18:45Z","title_canon_sha256":"51c13201460228afa46232c6f68eb10e0bc03a635cc4e94663b32f250aac8168"},"schema_version":"1.0","source":{"id":"2211.09359","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09359","created_at":"2026-07-05T06:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09359v2","created_at":"2026-07-05T06:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09359","created_at":"2026-07-05T06:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"EJYR2UKB6ZNB","created_at":"2026-07-05T06:58:54Z"},{"alias_kind":"pith_short_16","alias_value":"EJYR2UKB6ZNB3MGK","created_at":"2026-07-05T06:58:54Z"},{"alias_kind":"pith_short_8","alias_value":"EJYR2UKB","created_at":"2026-07-05T06:58:54Z"}],"graph_snapshots":[{"event_id":"sha256:2ff7add7266aa09591cd51aeaae6787dbbd38eac26361af65c38c7c61e8d174f","target":"graph","created_at":"2026-07-05T06:58:54Z","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/2211.09359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"SGD and AdamW are the two most used optimizers for fine-tuning large neural networks in computer vision. When the two methods perform the same, SGD is preferable because it uses less memory (12 bytes/parameter with momentum and 8 bytes/parameter without) than AdamW (16 bytes/parameter). However, on a suite of downstream tasks, especially those with distribution shifts, we find that fine-tuning with AdamW performs substantially better than SGD on modern Vision Transformer and ConvNeXt models. We find that large gaps in performance between SGD and AdamW occur when the fine-tuning gradients in th","authors_text":"Ananya Kumar, Ruoqi Shen, Sebastien Bubeck, Suriya Gunasekar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T06:18:45Z","title":"How to Fine-Tune Vision Models with SGD"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09359","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:b81a56861fbae0f945a4548e6f636aa3d566baa11c7cfaa1516a7ebfac6cca56","target":"record","created_at":"2026-07-05T06:58:54Z","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":"04aa6b98a3aa7b83021382b840b5ea90e93c354368366418a08f41ee5180d51f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T06:18:45Z","title_canon_sha256":"51c13201460228afa46232c6f68eb10e0bc03a635cc4e94663b32f250aac8168"},"schema_version":"1.0","source":{"id":"2211.09359","kind":"arxiv","version":2}},"canonical_sha256":"22711d5141f65a1db0caa7d69383ae2aa16d9b5c6de63146aeaa2b86c68ef666","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22711d5141f65a1db0caa7d69383ae2aa16d9b5c6de63146aeaa2b86c68ef666","first_computed_at":"2026-07-05T06:58:54.064452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:54.064452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EpM2dpQrEdzJtzAIuwezZxMCjflfM2RdfD/sXlzQy5M5wjdt76Wd1F/VP5HyDmNFGpfZ4Oi9mMCtAb8sqTmTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:54.064978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09359","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b81a56861fbae0f945a4548e6f636aa3d566baa11c7cfaa1516a7ebfac6cca56","sha256:2ff7add7266aa09591cd51aeaae6787dbbd38eac26361af65c38c7c61e8d174f"],"state_sha256":"0d9dd0b3ec3284bfe38075de7dba29a2eecea66526b2c65073791692f5cd0568"}