{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TPGMAGIUCT73UE2AMJOLBR3FEY","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":"0c5d5ab8831f82a7afc8d6c8fee30a323908d7c22f7b8a09312e0274639a9bb6","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-25T08:58:59Z","title_canon_sha256":"0618be7ba25a0e0b81e469c86eda26d01f34c0bc3bf0992f96145619c7386250"},"schema_version":"1.0","source":{"id":"1907.10905","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10905","created_at":"2026-07-05T01:49:47Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10905v4","created_at":"2026-07-05T01:49:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10905","created_at":"2026-07-05T01:49:47Z"},{"alias_kind":"pith_short_12","alias_value":"TPGMAGIUCT73","created_at":"2026-07-05T01:49:47Z"},{"alias_kind":"pith_short_16","alias_value":"TPGMAGIUCT73UE2A","created_at":"2026-07-05T01:49:47Z"},{"alias_kind":"pith_short_8","alias_value":"TPGMAGIU","created_at":"2026-07-05T01:49:47Z"}],"graph_snapshots":[{"event_id":"sha256:14d880933ba7879841c8aba09302579a8c8cf4875592a00fbae9cd6d79650f9e","target":"graph","created_at":"2026-07-05T01:49:47Z","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/1907.10905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation is a widely used trick when training deep neural networks: in addition to the original data, properly transformed data are also added to the training set. However, to the best of our knowledge, a clear mathematical framework to explain the performance benefits of data augmentation is not available. In this paper, we develop such a theoretical framework. We show data augmentation is equivalent to an averaging operation over the orbits of a certain group that keeps the data distribution approximately invariant. We prove that it leads to variance reduction. We study empirical ri","authors_text":"Edgar Dobriban, Jane H Lee, Shuxiao Chen","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-25T08:58:59Z","title":"A Group-Theoretic Framework for Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10905","kind":"arxiv","version":4},"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":"sha256:58d14be6201d6df2c8b7e93641c95b384577a70e9877ef8b76a3a3b330934a4d","target":"record","created_at":"2026-07-05T01:49:47Z","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":"0c5d5ab8831f82a7afc8d6c8fee30a323908d7c22f7b8a09312e0274639a9bb6","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-25T08:58:59Z","title_canon_sha256":"0618be7ba25a0e0b81e469c86eda26d01f34c0bc3bf0992f96145619c7386250"},"schema_version":"1.0","source":{"id":"1907.10905","kind":"arxiv","version":4}},"canonical_sha256":"9bccc0191414ffba1340625cb0c765260c6ad4548e9f2ad20b3f494f844fb031","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bccc0191414ffba1340625cb0c765260c6ad4548e9f2ad20b3f494f844fb031","first_computed_at":"2026-07-05T01:49:47.313169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:47.313169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xN/3Vu+VKPe1YaOEQAYAuvX0m9/RVJVhkaQMZ0JUTQJEsHCNSZyn5RTgj8zrtoTCl1ZVIcCJoC3tLEg5Ra2RCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:47.313596Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.10905","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58d14be6201d6df2c8b7e93641c95b384577a70e9877ef8b76a3a3b330934a4d","sha256:14d880933ba7879841c8aba09302579a8c8cf4875592a00fbae9cd6d79650f9e"],"state_sha256":"266e51cc8fd12a67132ce9a09e989d389b712a28b81c2cc16743c8d8fc78cd33"}