{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P3VFBKMUSCECEJHCGDWMNKALFI","short_pith_number":"pith:P3VFBKMU","canonical_record":{"source":{"id":"2506.15535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T15:10:38Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e046fe331b11173eafaed6b8adc0e1314be4ba3c91a2adf46450aca208659589","abstract_canon_sha256":"4eec82d61d87a0f965d827ca83ed1325586f34b2f15f7d4d77750ab906320d6b"},"schema_version":"1.0"},"canonical_sha256":"7eea50a99490882224e230ecc6a80b2a315ef1296014b6683df9fb51c158f537","source":{"kind":"arxiv","id":"2506.15535","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15535","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15535v1","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15535","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"P3VFBKMUSCEC","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"pith_short_16","alias_value":"P3VFBKMUSCECEJHC","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"pith_short_8","alias_value":"P3VFBKMU","created_at":"2026-07-05T11:23:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P3VFBKMUSCECEJHCGDWMNKALFI","target":"record","payload":{"canonical_record":{"source":{"id":"2506.15535","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T15:10:38Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"e046fe331b11173eafaed6b8adc0e1314be4ba3c91a2adf46450aca208659589","abstract_canon_sha256":"4eec82d61d87a0f965d827ca83ed1325586f34b2f15f7d4d77750ab906320d6b"},"schema_version":"1.0"},"canonical_sha256":"7eea50a99490882224e230ecc6a80b2a315ef1296014b6683df9fb51c158f537","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:45.770586Z","signature_b64":"UK4WvVy1ovwxoMDClZcEf0OTEwBuq6ufW+OtvfcO2KmpmhjgZWJ+5/DlG7AcI0N6QDZ8ABihKftbAk5ndGo2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eea50a99490882224e230ecc6a80b2a315ef1296014b6683df9fb51c158f537","last_reissued_at":"2026-07-05T11:23:45.770091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:45.770091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.15535","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":"2026-07-05T11:23:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G96j4bD4EQRUxkA5951nOHfVE15h9yWZVLE5xZZIQZFCcpPYDCZsxl+UkSf6CwXheFUo35/EotlTJCwxt4bQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:35:42.947966Z"},"content_sha256":"7252c0021b80e998280539780df35cfd7a785e8b408971fa67ef6a816767c027","schema_version":"1.0","event_id":"sha256:7252c0021b80e998280539780df35cfd7a785e8b408971fa67ef6a816767c027"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P3VFBKMUSCECEJHCGDWMNKALFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Simplified Analysis of SGD for Linear Regression with Weight Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandru Meterez, Cengiz Pehlevan, Costin-Andrei Oncescu, Depen Morwani, Jingfeng Wu, Sham Kakade","submitted_at":"2025-06-18T15:10:38Z","abstract_excerpt":"Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\\citet{zou2021benign} provides sharp rates for SGD optimization in linear regression using constant learning rate, both with and without tail iterate averaging, based on a bias-variance decomposition of the risk. In our work, we provide a simplified analysis recovering the same bias and variance bounds provided in~\\citep{zou2021benign} based on simple linear algebra tools, bypassing the req"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15535","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/2506.15535/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":"2026-07-05T11:23:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2AfsbWlatMmUaRhK7WoOoisbd0Zk+1DznE0AzQ0Gr8zyM5Jz/CEMIqr7feoktYgarKAohTUvoIT6dNHzHk4LAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:35:42.948358Z"},"content_sha256":"bf51c36a9fef3d959cccd37afff47087e3be74bab730e8daddd9a4af98d80116","schema_version":"1.0","event_id":"sha256:bf51c36a9fef3d959cccd37afff47087e3be74bab730e8daddd9a4af98d80116"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P3VFBKMUSCECEJHCGDWMNKALFI/bundle.json","state_url":"https://pith.science/pith/P3VFBKMUSCECEJHCGDWMNKALFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P3VFBKMUSCECEJHCGDWMNKALFI/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":"2026-07-07T04:35:42Z","links":{"resolver":"https://pith.science/pith/P3VFBKMUSCECEJHCGDWMNKALFI","bundle":"https://pith.science/pith/P3VFBKMUSCECEJHCGDWMNKALFI/bundle.json","state":"https://pith.science/pith/P3VFBKMUSCECEJHCGDWMNKALFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P3VFBKMUSCECEJHCGDWMNKALFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P3VFBKMUSCECEJHCGDWMNKALFI","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":"4eec82d61d87a0f965d827ca83ed1325586f34b2f15f7d4d77750ab906320d6b","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T15:10:38Z","title_canon_sha256":"e046fe331b11173eafaed6b8adc0e1314be4ba3c91a2adf46450aca208659589"},"schema_version":"1.0","source":{"id":"2506.15535","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15535","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15535v1","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15535","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"pith_short_12","alias_value":"P3VFBKMUSCEC","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"pith_short_16","alias_value":"P3VFBKMUSCECEJHC","created_at":"2026-07-05T11:23:45Z"},{"alias_kind":"pith_short_8","alias_value":"P3VFBKMU","created_at":"2026-07-05T11:23:45Z"}],"graph_snapshots":[{"event_id":"sha256:bf51c36a9fef3d959cccd37afff47087e3be74bab730e8daddd9a4af98d80116","target":"graph","created_at":"2026-07-05T11:23:45Z","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/2506.15535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Theoretically understanding stochastic gradient descent (SGD) in overparameterized models has led to the development of several optimization algorithms that are widely used in practice today. Recent work by~\\citet{zou2021benign} provides sharp rates for SGD optimization in linear regression using constant learning rate, both with and without tail iterate averaging, based on a bias-variance decomposition of the risk. In our work, we provide a simplified analysis recovering the same bias and variance bounds provided in~\\citep{zou2021benign} based on simple linear algebra tools, bypassing the req","authors_text":"Alexandru Meterez, Cengiz Pehlevan, Costin-Andrei Oncescu, Depen Morwani, Jingfeng Wu, Sham Kakade","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T15:10:38Z","title":"A Simplified Analysis of SGD for Linear Regression with Weight Averaging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15535","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":"sha256:7252c0021b80e998280539780df35cfd7a785e8b408971fa67ef6a816767c027","target":"record","created_at":"2026-07-05T11:23:45Z","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":"4eec82d61d87a0f965d827ca83ed1325586f34b2f15f7d4d77750ab906320d6b","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T15:10:38Z","title_canon_sha256":"e046fe331b11173eafaed6b8adc0e1314be4ba3c91a2adf46450aca208659589"},"schema_version":"1.0","source":{"id":"2506.15535","kind":"arxiv","version":1}},"canonical_sha256":"7eea50a99490882224e230ecc6a80b2a315ef1296014b6683df9fb51c158f537","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7eea50a99490882224e230ecc6a80b2a315ef1296014b6683df9fb51c158f537","first_computed_at":"2026-07-05T11:23:45.770091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:45.770091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UK4WvVy1ovwxoMDClZcEf0OTEwBuq6ufW+OtvfcO2KmpmhjgZWJ+5/DlG7AcI0N6QDZ8ABihKftbAk5ndGo2CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:45.770586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15535","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7252c0021b80e998280539780df35cfd7a785e8b408971fa67ef6a816767c027","sha256:bf51c36a9fef3d959cccd37afff47087e3be74bab730e8daddd9a4af98d80116"],"state_sha256":"22147ad31241a239c1e17b7ff0d7b3e103f6fed4b5c5a6736b209dbc711ff717"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XMuqRyxX84ZV0NpZ6wFB711K+VQsNlKOc8Cb8R9ivz1Fot0bw3NzeNwoZ+ygt7GJHlaaY0JfDZrb7xKRLtYOBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:35:42.950340Z","bundle_sha256":"f9559281fafd1c269b3cd13bd9b699ea8a84c6da2dbdff643326d1ebfd26f1f1"}}