{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LQTA56L7UBBJEM467DSOJ344Z4","short_pith_number":"pith:LQTA56L7","canonical_record":{"source":{"id":"2110.02180","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T17:13:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08d3f24c86465c3694bef1dc11b8e83b1cc099303b57f4bd2bc4beb432d64393","abstract_canon_sha256":"aac560bc51750b9e3468ec093655342da8cb6f51847d5759c4ee2e85d82aa524"},"schema_version":"1.0"},"canonical_sha256":"5c260ef97fa04292339ef8e4e4ef9ccf0a9fffda70f9091adae44ccc08fbd0f3","source":{"kind":"arxiv","id":"2110.02180","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02180","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02180v2","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02180","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"LQTA56L7UBBJ","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"LQTA56L7UBBJEM46","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"LQTA56L7","created_at":"2026-07-05T06:11:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LQTA56L7UBBJEM467DSOJ344Z4","target":"record","payload":{"canonical_record":{"source":{"id":"2110.02180","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T17:13:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08d3f24c86465c3694bef1dc11b8e83b1cc099303b57f4bd2bc4beb432d64393","abstract_canon_sha256":"aac560bc51750b9e3468ec093655342da8cb6f51847d5759c4ee2e85d82aa524"},"schema_version":"1.0"},"canonical_sha256":"5c260ef97fa04292339ef8e4e4ef9ccf0a9fffda70f9091adae44ccc08fbd0f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:53.813379Z","signature_b64":"2Hpyu2VRFMVZZzfgiPepOqsOaVP5sAq83+HRAQQNtiod7jS0JsTSd+NjhQ9MxIQ5xExT4pf47TLvzcVELfPJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c260ef97fa04292339ef8e4e4ef9ccf0a9fffda70f9091adae44ccc08fbd0f3","last_reissued_at":"2026-07-05T06:11:53.812942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:53.812942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.02180","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j5Q9sGRsOni4DaO4eznop7WeedXVP3KbEhGmhRJkf+xOqE7EH1a3RSZw2ENqJtK/G1eS4xAkeu5o04j84zSQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:58:03.997355Z"},"content_sha256":"d1148e6e82601b88dbffd46a3e22736081406e1e1fa362470e3bf7066862b3d2","schema_version":"1.0","event_id":"sha256:d1148e6e82601b88dbffd46a3e22736081406e1e1fa362470e3bf7066862b3d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LQTA56L7UBBJEM467DSOJ344Z4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Noisy Feature Mixup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francisco Utrera, Michael W. Mahoney, N. Benjamin Erichson, Soon Hoe Lim, Winnie Xu","submitted_at":"2021-10-05T17:13:51Z","abstract_excerpt":"We introduce Noisy Feature Mixup (NFM), an inexpensive yet effective method for data augmentation that combines the best of interpolation based training and noise injection schemes. Rather than training with convex combinations of pairs of examples and their labels, we use noise-perturbed convex combinations of pairs of data points in both input and feature space. This method includes mixup and manifold mixup as special cases, but it has additional advantages, including better smoothing of decision boundaries and enabling improved model robustness. We provide theory to understand this as well "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02180","kind":"arxiv","version":2},"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/2110.02180/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":"2026-07-05T06:11:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXDk32TUmq84tYq4nXp4i+Mr/AOcFZdRzjjmJgNPI7WUoPWa/lFg9m3GdMXrCFBQHzqnX1PvgsunE4q4PMkIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:58:03.997740Z"},"content_sha256":"12fd6692a147284a81f4c3f487687486675cd53be29697cc3d431f0331c0734b","schema_version":"1.0","event_id":"sha256:12fd6692a147284a81f4c3f487687486675cd53be29697cc3d431f0331c0734b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQTA56L7UBBJEM467DSOJ344Z4/bundle.json","state_url":"https://pith.science/pith/LQTA56L7UBBJEM467DSOJ344Z4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQTA56L7UBBJEM467DSOJ344Z4/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":"2026-08-03T19:58:03Z","links":{"resolver":"https://pith.science/pith/LQTA56L7UBBJEM467DSOJ344Z4","bundle":"https://pith.science/pith/LQTA56L7UBBJEM467DSOJ344Z4/bundle.json","state":"https://pith.science/pith/LQTA56L7UBBJEM467DSOJ344Z4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQTA56L7UBBJEM467DSOJ344Z4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LQTA56L7UBBJEM467DSOJ344Z4","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":"aac560bc51750b9e3468ec093655342da8cb6f51847d5759c4ee2e85d82aa524","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T17:13:51Z","title_canon_sha256":"08d3f24c86465c3694bef1dc11b8e83b1cc099303b57f4bd2bc4beb432d64393"},"schema_version":"1.0","source":{"id":"2110.02180","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02180","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02180v2","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02180","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"LQTA56L7UBBJ","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"LQTA56L7UBBJEM46","created_at":"2026-07-05T06:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"LQTA56L7","created_at":"2026-07-05T06:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:12fd6692a147284a81f4c3f487687486675cd53be29697cc3d431f0331c0734b","target":"graph","created_at":"2026-07-05T06:11:53Z","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/2110.02180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Noisy Feature Mixup (NFM), an inexpensive yet effective method for data augmentation that combines the best of interpolation based training and noise injection schemes. Rather than training with convex combinations of pairs of examples and their labels, we use noise-perturbed convex combinations of pairs of data points in both input and feature space. This method includes mixup and manifold mixup as special cases, but it has additional advantages, including better smoothing of decision boundaries and enabling improved model robustness. We provide theory to understand this as well ","authors_text":"Francisco Utrera, Michael W. Mahoney, N. Benjamin Erichson, Soon Hoe Lim, Winnie Xu","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T17:13:51Z","title":"Noisy Feature Mixup"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02180","kind":"arxiv","version":2},"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:d1148e6e82601b88dbffd46a3e22736081406e1e1fa362470e3bf7066862b3d2","target":"record","created_at":"2026-07-05T06:11:53Z","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":"aac560bc51750b9e3468ec093655342da8cb6f51847d5759c4ee2e85d82aa524","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T17:13:51Z","title_canon_sha256":"08d3f24c86465c3694bef1dc11b8e83b1cc099303b57f4bd2bc4beb432d64393"},"schema_version":"1.0","source":{"id":"2110.02180","kind":"arxiv","version":2}},"canonical_sha256":"5c260ef97fa04292339ef8e4e4ef9ccf0a9fffda70f9091adae44ccc08fbd0f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c260ef97fa04292339ef8e4e4ef9ccf0a9fffda70f9091adae44ccc08fbd0f3","first_computed_at":"2026-07-05T06:11:53.812942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:53.812942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Hpyu2VRFMVZZzfgiPepOqsOaVP5sAq83+HRAQQNtiod7jS0JsTSd+NjhQ9MxIQ5xExT4pf47TLvzcVELfPJCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:53.813379Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02180","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1148e6e82601b88dbffd46a3e22736081406e1e1fa362470e3bf7066862b3d2","sha256:12fd6692a147284a81f4c3f487687486675cd53be29697cc3d431f0331c0734b"],"state_sha256":"7375a0c54f19c95e8df553338ee2d853d071e12a5d49974b59181a99ee7cfa53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jCtcmy931YIMLSP4BqXOQ4wScYPbUxfUzqE1b1gh3YOb6ZddoAVFnAV8V7SGA4Slmo1y89RVknS2grCMDShVCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:58:04.000372Z","bundle_sha256":"d79e09217be68a6406ef37373cbd174c6da5f43327a66c9a8502f6b0b5498fe9"}}