{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PYZQ7EYQUEV2NDKFISQX64Z7U5","short_pith_number":"pith:PYZQ7EYQ","canonical_record":{"source":{"id":"2506.12543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:37:31Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"2dc1b20ce21fb812f7bb97abd825da1d419be904c5c40dc1ce7bbd0e2e071824","abstract_canon_sha256":"1db946658505b424f255425b7d82754c4be19c548dbd4d05b07e5066388581b1"},"schema_version":"1.0"},"canonical_sha256":"7e330f9310a12ba68d4544a17f733fa7622c51012eda9a418c2d829e9dbd8d9a","source":{"kind":"arxiv","id":"2506.12543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12543","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12543v1","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12543","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_12","alias_value":"PYZQ7EYQUEV2","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_16","alias_value":"PYZQ7EYQUEV2NDKF","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_8","alias_value":"PYZQ7EYQ","created_at":"2026-07-05T11:21:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PYZQ7EYQUEV2NDKFISQX64Z7U5","target":"record","payload":{"canonical_record":{"source":{"id":"2506.12543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:37:31Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"2dc1b20ce21fb812f7bb97abd825da1d419be904c5c40dc1ce7bbd0e2e071824","abstract_canon_sha256":"1db946658505b424f255425b7d82754c4be19c548dbd4d05b07e5066388581b1"},"schema_version":"1.0"},"canonical_sha256":"7e330f9310a12ba68d4544a17f733fa7622c51012eda9a418c2d829e9dbd8d9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:55.034926Z","signature_b64":"9KebPrw+HXO0tmzHgJDn8wbmXYn5wpoUht8LAqXW9SLwXYwTNcYz+nuvAFlrI6NhE+mQwQBL+aauTJzH7yF9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e330f9310a12ba68d4544a17f733fa7622c51012eda9a418c2d829e9dbd8d9a","last_reissued_at":"2026-07-05T11:21:55.034474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:55.034474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.12543","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HSy8B/cmmxsuGj8sR/7J/w1jyHtxGC08r95Clbj6UET6StTa2xOlAIk1f1wl5LfNZcBCSW0TEF1TgapLPSbHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:10:59.427390Z"},"content_sha256":"25c41cbd4096b01e55c8cc810c5dfae2d4121de48f304f6de0297f25097d85a5","schema_version":"1.0","event_id":"sha256:25c41cbd4096b01e55c8cc810c5dfae2d4121de48f304f6de0297f25097d85a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PYZQ7EYQUEV2NDKFISQX64Z7U5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Antonio Orvieto, Jonas Geiping, Teodora Sre\\'ckovi\\'c","submitted_at":"2025-06-14T15:37:31Z","abstract_excerpt":"Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this work, we revisit this \"optimizer gap\" through a series of comprehensively tuned baseline training runs for language modeling with Transformers. We exhaustively study how momentum, gradient clipping, and batch size affect the gap between SGD and Adam. Our empirical findings show that SGD with momentum can actually perform similarly to Adam in small-batch settings, if tuned correctly. We revisit existing explanations "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12543","kind":"arxiv","version":1},"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/2506.12543/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":"2026-07-05T11:21:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"haPGMT455t8FrMm7sVmk1Ir5bCD+2aXwN+w2joOBdrTLZ+xcxsN1CqNsRrOA29yMfGZ2uT+znod9p0UTbJWsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:10:59.428015Z"},"content_sha256":"0cea18f7b6b3af77cf80fe6993efcf1923767d6d4b9e72e8cde1a97a9b98b2f5","schema_version":"1.0","event_id":"sha256:0cea18f7b6b3af77cf80fe6993efcf1923767d6d4b9e72e8cde1a97a9b98b2f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYZQ7EYQUEV2NDKFISQX64Z7U5/bundle.json","state_url":"https://pith.science/pith/PYZQ7EYQUEV2NDKFISQX64Z7U5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYZQ7EYQUEV2NDKFISQX64Z7U5/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":"2026-08-09T19:10:59Z","links":{"resolver":"https://pith.science/pith/PYZQ7EYQUEV2NDKFISQX64Z7U5","bundle":"https://pith.science/pith/PYZQ7EYQUEV2NDKFISQX64Z7U5/bundle.json","state":"https://pith.science/pith/PYZQ7EYQUEV2NDKFISQX64Z7U5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYZQ7EYQUEV2NDKFISQX64Z7U5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PYZQ7EYQUEV2NDKFISQX64Z7U5","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":"1db946658505b424f255425b7d82754c4be19c548dbd4d05b07e5066388581b1","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:37:31Z","title_canon_sha256":"2dc1b20ce21fb812f7bb97abd825da1d419be904c5c40dc1ce7bbd0e2e071824"},"schema_version":"1.0","source":{"id":"2506.12543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12543","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12543v1","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12543","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_12","alias_value":"PYZQ7EYQUEV2","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_16","alias_value":"PYZQ7EYQUEV2NDKF","created_at":"2026-07-05T11:21:55Z"},{"alias_kind":"pith_short_8","alias_value":"PYZQ7EYQ","created_at":"2026-07-05T11:21:55Z"}],"graph_snapshots":[{"event_id":"sha256:0cea18f7b6b3af77cf80fe6993efcf1923767d6d4b9e72e8cde1a97a9b98b2f5","target":"graph","created_at":"2026-07-05T11:21:55Z","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/2506.12543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this work, we revisit this \"optimizer gap\" through a series of comprehensively tuned baseline training runs for language modeling with Transformers. We exhaustively study how momentum, gradient clipping, and batch size affect the gap between SGD and Adam. Our empirical findings show that SGD with momentum can actually perform similarly to Adam in small-batch settings, if tuned correctly. We revisit existing explanations ","authors_text":"Antonio Orvieto, Jonas Geiping, Teodora Sre\\'ckovi\\'c","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:37:31Z","title":"Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12543","kind":"arxiv","version":1},"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":"sha256:25c41cbd4096b01e55c8cc810c5dfae2d4121de48f304f6de0297f25097d85a5","target":"record","created_at":"2026-07-05T11:21:55Z","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":"1db946658505b424f255425b7d82754c4be19c548dbd4d05b07e5066388581b1","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T15:37:31Z","title_canon_sha256":"2dc1b20ce21fb812f7bb97abd825da1d419be904c5c40dc1ce7bbd0e2e071824"},"schema_version":"1.0","source":{"id":"2506.12543","kind":"arxiv","version":1}},"canonical_sha256":"7e330f9310a12ba68d4544a17f733fa7622c51012eda9a418c2d829e9dbd8d9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e330f9310a12ba68d4544a17f733fa7622c51012eda9a418c2d829e9dbd8d9a","first_computed_at":"2026-07-05T11:21:55.034474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:55.034474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9KebPrw+HXO0tmzHgJDn8wbmXYn5wpoUht8LAqXW9SLwXYwTNcYz+nuvAFlrI6NhE+mQwQBL+aauTJzH7yF9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:55.034926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25c41cbd4096b01e55c8cc810c5dfae2d4121de48f304f6de0297f25097d85a5","sha256:0cea18f7b6b3af77cf80fe6993efcf1923767d6d4b9e72e8cde1a97a9b98b2f5"],"state_sha256":"16e3d112d3a95a728f745c73c1f238fb00fb109bf7874ec146f9e0703f576572"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HpTOmYfBMwsCuqfc6q0G5f4jHBKCLe8irOxT7A7AO5bKUslLAOkEv8XrT4rgMlS4UoKUCI4Tl/+vpFX1vKG7CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:10:59.433504Z","bundle_sha256":"0a4e15e35fb6ff1a2952cdd17044e64e16a52602d106fdc9bd92b4831fbbc1b6"}}