{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H3BFE3RDCEH3M6ZWLJ2GFQWJWC","short_pith_number":"pith:H3BFE3RD","schema_version":"1.0","canonical_sha256":"3ec2526e23110fb67b365a7462c2c9b0b729e32d3a4db3b7f032206dabebf6f8","source":{"kind":"arxiv","id":"2202.01263","version":2},"attestation_state":"computed","paper":{"title":"NoisyMix: Boosting Model Robustness to Common Corruptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francisco Utrera, Michael W. Mahoney, N. Benjamin Erichson, Soon Hoe Lim, Winnie Xu, Ziang Cao","submitted_at":"2022-02-02T19:53:35Z","abstract_excerpt":"For many real-world applications, obtaining stable and robust statistical performance is more important than simply achieving state-of-the-art predictive test accuracy, and thus robustness of neural networks is an increasingly important topic. Relatedly, data augmentation schemes have been shown to improve robustness with respect to input perturbations and domain shifts. Motivated by this, we introduce NoisyMix, a novel training scheme that promotes stability as well as leverages noisy augmentations in input and feature space to improve both model robustness and in-domain accuracy. NoisyMix pr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2202.01263","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-02T19:53:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a219bc97c9859e831ecffed5939a1e1ed7de3c317e87500e1d09da50de98a6e","abstract_canon_sha256":"5cbe44ab6c7a08349f6e42631c0b5dbfb9c1c354925c2f6233af22ff61ee0153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:15.367088Z","signature_b64":"YIA1SlIXeGGJn9lf3Xv7OU8+0Ztu0NzUmrEB3JvjpUsFvsK3twWy+SP38pl9jSiIoH8tqajgRo8UTd9CvAtNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ec2526e23110fb67b365a7462c2c9b0b729e32d3a4db3b7f032206dabebf6f8","last_reissued_at":"2026-07-05T04:25:15.366589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:15.366589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NoisyMix: Boosting Model Robustness to Common Corruptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francisco Utrera, Michael W. Mahoney, N. Benjamin Erichson, Soon Hoe Lim, Winnie Xu, Ziang Cao","submitted_at":"2022-02-02T19:53:35Z","abstract_excerpt":"For many real-world applications, obtaining stable and robust statistical performance is more important than simply achieving state-of-the-art predictive test accuracy, and thus robustness of neural networks is an increasingly important topic. Relatedly, data augmentation schemes have been shown to improve robustness with respect to input perturbations and domain shifts. Motivated by this, we introduce NoisyMix, a novel training scheme that promotes stability as well as leverages noisy augmentations in input and feature space to improve both model robustness and in-domain accuracy. NoisyMix pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01263","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/2202.01263/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2202.01263","created_at":"2026-07-05T04:25:15.366650+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01263v2","created_at":"2026-07-05T04:25:15.366650+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01263","created_at":"2026-07-05T04:25:15.366650+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3BFE3RDCEH3","created_at":"2026-07-05T04:25:15.366650+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3BFE3RDCEH3M6ZW","created_at":"2026-07-05T04:25:15.366650+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3BFE3RD","created_at":"2026-07-05T04:25:15.366650+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17451","citing_title":"SegTTA: Training-Free Test-Time Augmentation for Zero-Shot Medical Imaging Segmentation","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC","json":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC.json","graph_json":"https://pith.science/api/pith-number/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/graph.json","events_json":"https://pith.science/api/pith-number/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/events.json","paper":"https://pith.science/paper/H3BFE3RD"},"agent_actions":{"view_html":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC","download_json":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC.json","view_paper":"https://pith.science/paper/H3BFE3RD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01263&json=true","fetch_graph":"https://pith.science/api/pith-number/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/graph.json","fetch_events":"https://pith.science/api/pith-number/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/action/storage_attestation","attest_author":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/action/author_attestation","sign_citation":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/action/citation_signature","submit_replication":"https://pith.science/pith/H3BFE3RDCEH3M6ZWLJ2GFQWJWC/action/replication_record"}},"created_at":"2026-07-05T04:25:15.366650+00:00","updated_at":"2026-07-05T04:25:15.366650+00:00"}