{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EQU4LAVF5DO7VEFEQTANLP2GFJ","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":"73d0ba67741d51cd82db720840b61010225ea20b55fd3ee7973e34e13b74b95f","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T04:10:54Z","title_canon_sha256":"6cf33cde5a78656e343cd7a579f0c4242da36ccd817f380618cee895c3990e8a"},"schema_version":"1.0","source":{"id":"2302.12444","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.12444","created_at":"2026-07-05T06:40:31Z"},{"alias_kind":"arxiv_version","alias_value":"2302.12444v3","created_at":"2026-07-05T06:40:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12444","created_at":"2026-07-05T06:40:31Z"},{"alias_kind":"pith_short_12","alias_value":"EQU4LAVF5DO7","created_at":"2026-07-05T06:40:31Z"},{"alias_kind":"pith_short_16","alias_value":"EQU4LAVF5DO7VEFE","created_at":"2026-07-05T06:40:31Z"},{"alias_kind":"pith_short_8","alias_value":"EQU4LAVF","created_at":"2026-07-05T06:40:31Z"}],"graph_snapshots":[{"event_id":"sha256:8d8f2c183d7b6fba5b3cde1746650dee5ab87a28277b50def936588724172f3a","target":"graph","created_at":"2026-07-05T06:40:31Z","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/2302.12444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We uncover how SGD interacts with batch normalization and can exhibit undesirable training dynamics such as divergence. More precisely, we study how Single Shuffle (SS) and Random Reshuffle (RR) -- two widely used variants of SGD -- interact surprisingly differently in the presence of batch normalization: RR leads to much more stable evolution of training loss than SS. As a concrete example, for regression using a linear network with batch normalization, we prove that SS and RR converge to distinct global optima that are \"distorted\" away from gradient descent. Thereafter, for classification we","authors_text":"Chulhee Yun, David X. Wu, Suvrit Sra","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T04:10:54Z","title":"On the Training Instability of Shuffling SGD with Batch Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12444","kind":"arxiv","version":3},"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":"sha256:4cac9b41be3558f828dfed5f4fbaca867ef08ef8af77d027b9f9153984d7c6fa","target":"record","created_at":"2026-07-05T06:40:31Z","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":"73d0ba67741d51cd82db720840b61010225ea20b55fd3ee7973e34e13b74b95f","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T04:10:54Z","title_canon_sha256":"6cf33cde5a78656e343cd7a579f0c4242da36ccd817f380618cee895c3990e8a"},"schema_version":"1.0","source":{"id":"2302.12444","kind":"arxiv","version":3}},"canonical_sha256":"2429c582a5e8ddfa90a484c0d5bf462a6fa6900dd409d6963b4844d9ba15688c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2429c582a5e8ddfa90a484c0d5bf462a6fa6900dd409d6963b4844d9ba15688c","first_computed_at":"2026-07-05T06:40:31.906188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:40:31.906188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Ko+pP/KttU406p/QSYnLF0BohNCVslYqD2QetiCm1qGxxDvAewlTeyyDNSpw7cWUOYNvYgDS9CDy3qM7qFtDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:40:31.906611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.12444","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cac9b41be3558f828dfed5f4fbaca867ef08ef8af77d027b9f9153984d7c6fa","sha256:8d8f2c183d7b6fba5b3cde1746650dee5ab87a28277b50def936588724172f3a"],"state_sha256":"082ef880e58ee4fae95608bde511f3f653abf93f01a5bbe5ffcb9bd8bb068470"}