{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4AHHS63XYM6TFPZPG4BMQYOC55","short_pith_number":"pith:4AHHS63X","schema_version":"1.0","canonical_sha256":"e00e797b77c33d32bf2f3702c861c2ef4ec99f7aa05141f15fa45de8e2b22919","source":{"kind":"arxiv","id":"2103.00243","version":1},"attestation_state":"computed","paper":{"title":"Searching for Robustness: Loss Learning for Noisy Classification Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boyan Gao, Henry Gouk, Timothy M. Hospedales","submitted_at":"2021-02-27T15:27:22Z","abstract_excerpt":"We present a \"learning to learn\" approach for automatically constructing white-box classification loss functions that are robust to label noise in the training data. We parameterize a flexible family of loss functions using Taylor polynomials, and apply evolutionary strategies to search for noise-robust losses in this space. To learn re-usable loss functions that can apply to new tasks, our fitness function scores their performance in aggregate across a range of training dataset and architecture combinations. The resulting white-box loss provides a simple and fast \"plug-and-play\" module that e"},"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":"2103.00243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T15:27:22Z","cross_cats_sorted":[],"title_canon_sha256":"b87aa009ec8200fdc6a1263f180e8672fab569ec8c00f56f5aa6cf4c2b628428","abstract_canon_sha256":"fc7e9978a951e6c3a18e898bec1f01bdd97131da53a5d646953ea379bc47cb94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:03.553016Z","signature_b64":"x30L9y946EVGlM2tS3fWtfiCcuo1sOpUvGeHxVM0Rw9nBXOYr5Ykta1h6FwKJR4QOHb11dNs29oxggRtc2fpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e00e797b77c33d32bf2f3702c861c2ef4ec99f7aa05141f15fa45de8e2b22919","last_reissued_at":"2026-07-05T02:19:03.552515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:03.552515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Searching for Robustness: Loss Learning for Noisy Classification Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boyan Gao, Henry Gouk, Timothy M. Hospedales","submitted_at":"2021-02-27T15:27:22Z","abstract_excerpt":"We present a \"learning to learn\" approach for automatically constructing white-box classification loss functions that are robust to label noise in the training data. We parameterize a flexible family of loss functions using Taylor polynomials, and apply evolutionary strategies to search for noise-robust losses in this space. To learn re-usable loss functions that can apply to new tasks, our fitness function scores their performance in aggregate across a range of training dataset and architecture combinations. The resulting white-box loss provides a simple and fast \"plug-and-play\" module that e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00243","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/2103.00243/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":"2103.00243","created_at":"2026-07-05T02:19:03.552585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00243v1","created_at":"2026-07-05T02:19:03.552585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00243","created_at":"2026-07-05T02:19:03.552585+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AHHS63XYM6T","created_at":"2026-07-05T02:19:03.552585+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AHHS63XYM6TFPZP","created_at":"2026-07-05T02:19:03.552585+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AHHS63X","created_at":"2026-07-05T02:19:03.552585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55","json":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55.json","graph_json":"https://pith.science/api/pith-number/4AHHS63XYM6TFPZPG4BMQYOC55/graph.json","events_json":"https://pith.science/api/pith-number/4AHHS63XYM6TFPZPG4BMQYOC55/events.json","paper":"https://pith.science/paper/4AHHS63X"},"agent_actions":{"view_html":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55","download_json":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55.json","view_paper":"https://pith.science/paper/4AHHS63X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00243&json=true","fetch_graph":"https://pith.science/api/pith-number/4AHHS63XYM6TFPZPG4BMQYOC55/graph.json","fetch_events":"https://pith.science/api/pith-number/4AHHS63XYM6TFPZPG4BMQYOC55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/action/storage_attestation","attest_author":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/action/author_attestation","sign_citation":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/action/citation_signature","submit_replication":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/action/replication_record"}},"created_at":"2026-07-05T02:19:03.552585+00:00","updated_at":"2026-07-05T02:19:03.552585+00:00"}