{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4AHHS63XYM6TFPZPG4BMQYOC55","short_pith_number":"pith:4AHHS63X","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"},"canonical_sha256":"e00e797b77c33d32bf2f3702c861c2ef4ec99f7aa05141f15fa45de8e2b22919","source":{"kind":"arxiv","id":"2103.00243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00243","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00243v1","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00243","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"4AHHS63XYM6T","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"4AHHS63XYM6TFPZP","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"4AHHS63X","created_at":"2026-07-05T02:19:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4AHHS63XYM6TFPZPG4BMQYOC55","target":"record","payload":{"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"},"canonical_sha256":"e00e797b77c33d32bf2f3702c861c2ef4ec99f7aa05141f15fa45de8e2b22919","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"},"source_kind":"arxiv","source_id":"2103.00243","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":"2026-07-05T02:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NW0+A04rlm5SzBd+zmW7u1sga8by97eTPmWoDFudiUofaW3s1Ds2TwzWtRmZCgAkEjjhKFGe7T3D6bO8LshFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:43:34.565189Z"},"content_sha256":"512a260d32aac078593a11e9bd727770971eb357bf9c9263a33ff3c0f8988095","schema_version":"1.0","event_id":"sha256:512a260d32aac078593a11e9bd727770971eb357bf9c9263a33ff3c0f8988095"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4AHHS63XYM6TFPZPG4BMQYOC55","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vPo3biLUhoxT+Oherux8vXqDCYX3EMfCo64RwPe5kO50059x87JUbpu9g6EtJ7Z8GZ5LRJS8LgterwAa6LECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:43:34.565769Z"},"content_sha256":"56227096bce062f6be5c6855606b6253c9bbcc5c9ff6d9328026d8b52d9e0360","schema_version":"1.0","event_id":"sha256:56227096bce062f6be5c6855606b6253c9bbcc5c9ff6d9328026d8b52d9e0360"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/bundle.json","state_url":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AHHS63XYM6TFPZPG4BMQYOC55/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":"2026-08-10T18:43:34Z","links":{"resolver":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55","bundle":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/bundle.json","state":"https://pith.science/pith/4AHHS63XYM6TFPZPG4BMQYOC55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AHHS63XYM6TFPZPG4BMQYOC55/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4AHHS63XYM6TFPZPG4BMQYOC55","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":"fc7e9978a951e6c3a18e898bec1f01bdd97131da53a5d646953ea379bc47cb94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T15:27:22Z","title_canon_sha256":"b87aa009ec8200fdc6a1263f180e8672fab569ec8c00f56f5aa6cf4c2b628428"},"schema_version":"1.0","source":{"id":"2103.00243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00243","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00243v1","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00243","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"4AHHS63XYM6T","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"4AHHS63XYM6TFPZP","created_at":"2026-07-05T02:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"4AHHS63X","created_at":"2026-07-05T02:19:03Z"}],"graph_snapshots":[{"event_id":"sha256:56227096bce062f6be5c6855606b6253c9bbcc5c9ff6d9328026d8b52d9e0360","target":"graph","created_at":"2026-07-05T02:19:03Z","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/2103.00243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Boyan Gao, Henry Gouk, Timothy M. Hospedales","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T15:27:22Z","title":"Searching for Robustness: Loss Learning for Noisy Classification Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00243","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":"sha256:512a260d32aac078593a11e9bd727770971eb357bf9c9263a33ff3c0f8988095","target":"record","created_at":"2026-07-05T02:19:03Z","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":"fc7e9978a951e6c3a18e898bec1f01bdd97131da53a5d646953ea379bc47cb94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T15:27:22Z","title_canon_sha256":"b87aa009ec8200fdc6a1263f180e8672fab569ec8c00f56f5aa6cf4c2b628428"},"schema_version":"1.0","source":{"id":"2103.00243","kind":"arxiv","version":1}},"canonical_sha256":"e00e797b77c33d32bf2f3702c861c2ef4ec99f7aa05141f15fa45de8e2b22919","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e00e797b77c33d32bf2f3702c861c2ef4ec99f7aa05141f15fa45de8e2b22919","first_computed_at":"2026-07-05T02:19:03.552515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:19:03.552515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x30L9y946EVGlM2tS3fWtfiCcuo1sOpUvGeHxVM0Rw9nBXOYr5Ykta1h6FwKJR4QOHb11dNs29oxggRtc2fpBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:19:03.553016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.00243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:512a260d32aac078593a11e9bd727770971eb357bf9c9263a33ff3c0f8988095","sha256:56227096bce062f6be5c6855606b6253c9bbcc5c9ff6d9328026d8b52d9e0360"],"state_sha256":"c4d863707a80e0b3d3d6b1fe22cc8f4bb74f22b4ca86790a8fba9ee1a34d76c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S+h6Re4dr3FHNKbg6VNCx+Od2w+vpB/f5/xxSC8EP8Xe1yhhc2s6HHW4+8nU2sDuri1MG10Iabn+IIRJ9XkeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:43:34.570437Z","bundle_sha256":"0d94b78b43953fa95942e890fc633e42433d04be11e2fee7dae0d96fcce485dd"}}