{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EQU4LAVF5DO7VEFEQTANLP2GFJ","short_pith_number":"pith:EQU4LAVF","canonical_record":{"source":{"id":"2302.12444","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T04:10:54Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"6cf33cde5a78656e343cd7a579f0c4242da36ccd817f380618cee895c3990e8a","abstract_canon_sha256":"73d0ba67741d51cd82db720840b61010225ea20b55fd3ee7973e34e13b74b95f"},"schema_version":"1.0"},"canonical_sha256":"2429c582a5e8ddfa90a484c0d5bf462a6fa6900dd409d6963b4844d9ba15688c","source":{"kind":"arxiv","id":"2302.12444","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EQU4LAVF5DO7VEFEQTANLP2GFJ","target":"record","payload":{"canonical_record":{"source":{"id":"2302.12444","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T04:10:54Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"6cf33cde5a78656e343cd7a579f0c4242da36ccd817f380618cee895c3990e8a","abstract_canon_sha256":"73d0ba67741d51cd82db720840b61010225ea20b55fd3ee7973e34e13b74b95f"},"schema_version":"1.0"},"canonical_sha256":"2429c582a5e8ddfa90a484c0d5bf462a6fa6900dd409d6963b4844d9ba15688c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:31.906611Z","signature_b64":"7Ko+pP/KttU406p/QSYnLF0BohNCVslYqD2QetiCm1qGxxDvAewlTeyyDNSpw7cWUOYNvYgDS9CDy3qM7qFtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2429c582a5e8ddfa90a484c0d5bf462a6fa6900dd409d6963b4844d9ba15688c","last_reissued_at":"2026-07-05T06:40:31.906188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:31.906188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.12444","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:40:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GbJPTr6bRYbCIfVr7kIIWdFB8puV3n/OnCNf9FTT96oC/Eoi3JWiHWECLi/URungpPsI45uOIk6msS8ZOGS8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:15:38.333881Z"},"content_sha256":"4cac9b41be3558f828dfed5f4fbaca867ef08ef8af77d027b9f9153984d7c6fa","schema_version":"1.0","event_id":"sha256:4cac9b41be3558f828dfed5f4fbaca867ef08ef8af77d027b9f9153984d7c6fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EQU4LAVF5DO7VEFEQTANLP2GFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Training Instability of Shuffling SGD with Batch Normalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Chulhee Yun, David X. Wu, Suvrit Sra","submitted_at":"2023-02-24T04:10:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12444","kind":"arxiv","version":3},"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/2302.12444/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":"2026-07-05T06:40:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nhU3hxNSD6Z2a3krvGRqCxa4yMevUIVom4UeMeVeiAaOW/14uNBO5b6W2RalhlU20IY411doL0wAZq/MCiP0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:15:38.334730Z"},"content_sha256":"8d8f2c183d7b6fba5b3cde1746650dee5ab87a28277b50def936588724172f3a","schema_version":"1.0","event_id":"sha256:8d8f2c183d7b6fba5b3cde1746650dee5ab87a28277b50def936588724172f3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQU4LAVF5DO7VEFEQTANLP2GFJ/bundle.json","state_url":"https://pith.science/pith/EQU4LAVF5DO7VEFEQTANLP2GFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQU4LAVF5DO7VEFEQTANLP2GFJ/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":"2026-08-08T09:15:38Z","links":{"resolver":"https://pith.science/pith/EQU4LAVF5DO7VEFEQTANLP2GFJ","bundle":"https://pith.science/pith/EQU4LAVF5DO7VEFEQTANLP2GFJ/bundle.json","state":"https://pith.science/pith/EQU4LAVF5DO7VEFEQTANLP2GFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQU4LAVF5DO7VEFEQTANLP2GFJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Hjo8cfb50wXpTLXTOEOLzp2Ik8btKiXSl2F3qRgGhlCbtZm4Pem0JTRq/mKec+E0C9aYZmB9L5oE9+zAlF6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:15:38.339690Z","bundle_sha256":"1db892d8e33afd89829ba453c34cfb74c6e3bc114f66de6276c17f37696c24f8"}}