{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RY2MU6RDU4E2QJX32MF6PGFLXM","short_pith_number":"pith:RY2MU6RD","canonical_record":{"source":{"id":"1805.11505","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-05-29T14:36:06Z","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"ef0939fdc7afcffe074530d669d4a3461c6d37ad9187604eeae7088c188c7aaa","abstract_canon_sha256":"f95fc9e6ce5eb7a577bed64f544ab4441289debb994c8ef8fa0f7e6330d0a77b"},"schema_version":"1.0"},"canonical_sha256":"8e34ca7a23a709a826fbd30be798abbb033febab4fb7323fdaa61a289e55408c","source":{"kind":"arxiv","id":"1805.11505","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11505","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11505v3","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11505","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"RY2MU6RDU4E2","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RY2MU6RDU4E2QJX3","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RY2MU6RD","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RY2MU6RDU4E2QJX32MF6PGFLXM","target":"record","payload":{"canonical_record":{"source":{"id":"1805.11505","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-05-29T14:36:06Z","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"title_canon_sha256":"ef0939fdc7afcffe074530d669d4a3461c6d37ad9187604eeae7088c188c7aaa","abstract_canon_sha256":"f95fc9e6ce5eb7a577bed64f544ab4441289debb994c8ef8fa0f7e6330d0a77b"},"schema_version":"1.0"},"canonical_sha256":"8e34ca7a23a709a826fbd30be798abbb033febab4fb7323fdaa61a289e55408c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:03.194664Z","signature_b64":"a6K4aSymNkzIcm9ZDP7SfKfcJjGCVaRBkKk5U3y/W1TGrRdlMAKzyy8/Rcx1ep8tJV7Ptv22BtaKGIKhWhy1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e34ca7a23a709a826fbd30be798abbb033febab4fb7323fdaa61a289e55408c","last_reissued_at":"2026-05-17T23:47:03.194018Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:03.194018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.11505","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nERqmHrBUQMQOsan+LeS5XZ7nyh3Vf6HuaghaUJe3kylCENJ7jPFsz7pA2MtkhlA9LAAWm4asxj3Q6DiPWCTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:27:43.547961Z"},"content_sha256":"70b0891feb09f132c37384dfcb0854c2791331c961593171809fd49073df62e2","schema_version":"1.0","event_id":"sha256:70b0891feb09f132c37384dfcb0854c2791331c961593171809fd49073df62e2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RY2MU6RDU4E2QJX32MF6PGFLXM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Classification with imperfect training labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ME","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Richard J. Samworth, Timothy I. Cannings, Yingying Fan","submitted_at":"2018-05-29T14:36:06Z","abstract_excerpt":"We study the effect of imperfect training data labels on the performance of classification methods. In a general setting, where the probability that an observation in the training dataset is mislabelled may depend on both the feature vector and the true label, we bound the excess risk of an arbitrary classifier trained with imperfect labels in terms of its excess risk for predicting a noisy label. This reveals conditions under which a classifier trained with imperfect labels remains consistent for classifying uncorrupted test data points. Furthermore, under stronger conditions, we derive detai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11505","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:47:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hfsBjdQQtNpGgF1xwoO1A18o1qr9jRBCkrlyohOPQAD9yuJSc4Q//WQ3peJDC8mFdP4MC8c52FpBwxaNeClbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T13:27:43.548331Z"},"content_sha256":"958199f2e9b42ef8eddb7ceafd4327818c8f6ca72d18888d0836aa1d8d0789ac","schema_version":"1.0","event_id":"sha256:958199f2e9b42ef8eddb7ceafd4327818c8f6ca72d18888d0836aa1d8d0789ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RY2MU6RDU4E2QJX32MF6PGFLXM/bundle.json","state_url":"https://pith.science/pith/RY2MU6RDU4E2QJX32MF6PGFLXM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RY2MU6RDU4E2QJX32MF6PGFLXM/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":"2026-05-26T13:27:43Z","links":{"resolver":"https://pith.science/pith/RY2MU6RDU4E2QJX32MF6PGFLXM","bundle":"https://pith.science/pith/RY2MU6RDU4E2QJX32MF6PGFLXM/bundle.json","state":"https://pith.science/pith/RY2MU6RDU4E2QJX32MF6PGFLXM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RY2MU6RDU4E2QJX32MF6PGFLXM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RY2MU6RDU4E2QJX32MF6PGFLXM","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":"f95fc9e6ce5eb7a577bed64f544ab4441289debb994c8ef8fa0f7e6330d0a77b","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-05-29T14:36:06Z","title_canon_sha256":"ef0939fdc7afcffe074530d669d4a3461c6d37ad9187604eeae7088c188c7aaa"},"schema_version":"1.0","source":{"id":"1805.11505","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11505","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11505v3","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11505","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"RY2MU6RDU4E2","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RY2MU6RDU4E2QJX3","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RY2MU6RD","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:958199f2e9b42ef8eddb7ceafd4327818c8f6ca72d18888d0836aa1d8d0789ac","target":"graph","created_at":"2026-05-17T23:47:03Z","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"},"paper":{"abstract_excerpt":"We study the effect of imperfect training data labels on the performance of classification methods. In a general setting, where the probability that an observation in the training dataset is mislabelled may depend on both the feature vector and the true label, we bound the excess risk of an arbitrary classifier trained with imperfect labels in terms of its excess risk for predicting a noisy label. This reveals conditions under which a classifier trained with imperfect labels remains consistent for classifying uncorrupted test data points. Furthermore, under stronger conditions, we derive detai","authors_text":"Richard J. Samworth, Timothy I. Cannings, Yingying Fan","cross_cats":["stat.ME","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-05-29T14:36:06Z","title":"Classification with imperfect training labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11505","kind":"arxiv","version":3},"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":"sha256:70b0891feb09f132c37384dfcb0854c2791331c961593171809fd49073df62e2","target":"record","created_at":"2026-05-17T23:47:03Z","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":"f95fc9e6ce5eb7a577bed64f544ab4441289debb994c8ef8fa0f7e6330d0a77b","cross_cats_sorted":["stat.ME","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-05-29T14:36:06Z","title_canon_sha256":"ef0939fdc7afcffe074530d669d4a3461c6d37ad9187604eeae7088c188c7aaa"},"schema_version":"1.0","source":{"id":"1805.11505","kind":"arxiv","version":3}},"canonical_sha256":"8e34ca7a23a709a826fbd30be798abbb033febab4fb7323fdaa61a289e55408c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e34ca7a23a709a826fbd30be798abbb033febab4fb7323fdaa61a289e55408c","first_computed_at":"2026-05-17T23:47:03.194018Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:03.194018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a6K4aSymNkzIcm9ZDP7SfKfcJjGCVaRBkKk5U3y/W1TGrRdlMAKzyy8/Rcx1ep8tJV7Ptv22BtaKGIKhWhy1Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:03.194664Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11505","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70b0891feb09f132c37384dfcb0854c2791331c961593171809fd49073df62e2","sha256:958199f2e9b42ef8eddb7ceafd4327818c8f6ca72d18888d0836aa1d8d0789ac"],"state_sha256":"8e7f48c4a61212a708b161ff0ae835350e06e5f57eabf98f3d556eb3736dbf14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NCbVVtZYaTdpZajFJHOUda9P48KQLUMfu4jEpfvL3hYW33aTniqDIc44OBgOf9ciElpsy+1bYO0va/QR9KPiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T13:27:43.550588Z","bundle_sha256":"9c6ce96b9e45c178dc0f467cca60c4990a109f089b9a8e416ebfa6c4647f8319"}}