{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3RF3RFDIGI4Q7DKTRMNN5L4U6M","short_pith_number":"pith:3RF3RFDI","canonical_record":{"source":{"id":"1901.04966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T18:40:06Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b22e4a5d6e962674b3e03e70c3734bfbdc677576af7c5724869284de38e5bb6f","abstract_canon_sha256":"d8ce9bd991976d56c0fcfb09a5519fbebbe8ff1c751389123afe61178b5ae1d8"},"schema_version":"1.0"},"canonical_sha256":"dc4bb8946832390f8d538b1adeaf94f30e137ca8179466e5c0dec1192b393fd8","source":{"kind":"arxiv","id":"1901.04966","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.04966","created_at":"2026-05-17T23:56:15Z"},{"alias_kind":"arxiv_version","alias_value":"1901.04966v1","created_at":"2026-05-17T23:56:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.04966","created_at":"2026-05-17T23:56:15Z"},{"alias_kind":"pith_short_12","alias_value":"3RF3RFDIGI4Q","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3RF3RFDIGI4Q7DKT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3RF3RFDI","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3RF3RFDIGI4Q7DKTRMNN5L4U6M","target":"record","payload":{"canonical_record":{"source":{"id":"1901.04966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T18:40:06Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b22e4a5d6e962674b3e03e70c3734bfbdc677576af7c5724869284de38e5bb6f","abstract_canon_sha256":"d8ce9bd991976d56c0fcfb09a5519fbebbe8ff1c751389123afe61178b5ae1d8"},"schema_version":"1.0"},"canonical_sha256":"dc4bb8946832390f8d538b1adeaf94f30e137ca8179466e5c0dec1192b393fd8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:15.997548Z","signature_b64":"FDRdHUtrXjTNDWGomG0FBEfBkhuE2i0wOntUl/YVz092Cp3BOhjUPREeaiOZvGB+sQGQ4ehYKp8jHR5OtctVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc4bb8946832390f8d538b1adeaf94f30e137ca8179466e5c0dec1192b393fd8","last_reissued_at":"2026-05-17T23:56:15.996977Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:15.996977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.04966","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":"2026-05-17T23:56:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LneGIQ1zDUqGo9ZvdLEe7JGEHDDDaAyWVHsYxPNF7GEfIMXCd1rX6d1nyaWNhppwx8hbu3ghrm+eOSzHg9pUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:23:34.688757Z"},"content_sha256":"e53bcf7ddbd3e669e66bbf01cde1a78ba1e5901c16c6f0efae8c095abc82dbc2","schema_version":"1.0","event_id":"sha256:e53bcf7ddbd3e669e66bbf01cde1a78ba1e5901c16c6f0efae8c095abc82dbc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3RF3RFDIGI4Q7DKTRMNN5L4U6M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifying and Correcting Label Bias in Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Heinrich Jiang, Ofir Nachum","submitted_at":"2019-01-15T18:40:06Z","abstract_excerpt":"Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical formulation of how this bias can arise. We do so by assuming the existence of underlying, unknown, and unbiased labels which are overwritten by an agent who intends to provide accurate labels but may have biases against certain groups. Despite the fact that we only observe the biased labels, we are able to show that the bias may nevertheless be corrected by re-weighting the data points without changing the labels. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.04966","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":""},"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":"2026-05-17T23:56:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FtzNM2CCPCWYCKMaZFk0dixobe/f9CnQEa6mTVGY9888QM7b9NQidtNZpODgv9GBYaxhjQcmVaKQHqHUafBOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:23:34.689475Z"},"content_sha256":"bf7bb13c167e76a01199285eb53cf8946b1451cc1fbcb11032fbbc5ec3f8de43","schema_version":"1.0","event_id":"sha256:bf7bb13c167e76a01199285eb53cf8946b1451cc1fbcb11032fbbc5ec3f8de43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RF3RFDIGI4Q7DKTRMNN5L4U6M/bundle.json","state_url":"https://pith.science/pith/3RF3RFDIGI4Q7DKTRMNN5L4U6M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RF3RFDIGI4Q7DKTRMNN5L4U6M/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":"2026-05-25T18:23:34Z","links":{"resolver":"https://pith.science/pith/3RF3RFDIGI4Q7DKTRMNN5L4U6M","bundle":"https://pith.science/pith/3RF3RFDIGI4Q7DKTRMNN5L4U6M/bundle.json","state":"https://pith.science/pith/3RF3RFDIGI4Q7DKTRMNN5L4U6M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RF3RFDIGI4Q7DKTRMNN5L4U6M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3RF3RFDIGI4Q7DKTRMNN5L4U6M","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":"d8ce9bd991976d56c0fcfb09a5519fbebbe8ff1c751389123afe61178b5ae1d8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T18:40:06Z","title_canon_sha256":"b22e4a5d6e962674b3e03e70c3734bfbdc677576af7c5724869284de38e5bb6f"},"schema_version":"1.0","source":{"id":"1901.04966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.04966","created_at":"2026-05-17T23:56:15Z"},{"alias_kind":"arxiv_version","alias_value":"1901.04966v1","created_at":"2026-05-17T23:56:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.04966","created_at":"2026-05-17T23:56:15Z"},{"alias_kind":"pith_short_12","alias_value":"3RF3RFDIGI4Q","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"3RF3RFDIGI4Q7DKT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"3RF3RFDI","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:bf7bb13c167e76a01199285eb53cf8946b1451cc1fbcb11032fbbc5ec3f8de43","target":"graph","created_at":"2026-05-17T23:56:15Z","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":"Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical formulation of how this bias can arise. We do so by assuming the existence of underlying, unknown, and unbiased labels which are overwritten by an agent who intends to provide accurate labels but may have biases against certain groups. Despite the fact that we only observe the biased labels, we are able to show that the bias may nevertheless be corrected by re-weighting the data points without changing the labels. ","authors_text":"Heinrich Jiang, Ofir Nachum","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T18:40:06Z","title":"Identifying and Correcting Label Bias in Machine Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.04966","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:e53bcf7ddbd3e669e66bbf01cde1a78ba1e5901c16c6f0efae8c095abc82dbc2","target":"record","created_at":"2026-05-17T23:56:15Z","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":"d8ce9bd991976d56c0fcfb09a5519fbebbe8ff1c751389123afe61178b5ae1d8","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-15T18:40:06Z","title_canon_sha256":"b22e4a5d6e962674b3e03e70c3734bfbdc677576af7c5724869284de38e5bb6f"},"schema_version":"1.0","source":{"id":"1901.04966","kind":"arxiv","version":1}},"canonical_sha256":"dc4bb8946832390f8d538b1adeaf94f30e137ca8179466e5c0dec1192b393fd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc4bb8946832390f8d538b1adeaf94f30e137ca8179466e5c0dec1192b393fd8","first_computed_at":"2026-05-17T23:56:15.996977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:15.996977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FDRdHUtrXjTNDWGomG0FBEfBkhuE2i0wOntUl/YVz092Cp3BOhjUPREeaiOZvGB+sQGQ4ehYKp8jHR5OtctVAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:15.997548Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.04966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e53bcf7ddbd3e669e66bbf01cde1a78ba1e5901c16c6f0efae8c095abc82dbc2","sha256:bf7bb13c167e76a01199285eb53cf8946b1451cc1fbcb11032fbbc5ec3f8de43"],"state_sha256":"483e43a51e3025b5b6b2d6164b7b3ec0d7e72498177a789891b34c6e66f39cc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0NeuU3dojGrcnnj2nc0Rre5mUcQMfinB/jkxZZcNpEdHTwJeAbjABjo0TFQ+/srmKFtPS6UwN4V5yczb8lwdBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:23:34.693281Z","bundle_sha256":"77d6e2973c905fb0852dc7d86e148c497f1dc805850632c4c79f8b612ef1b518"}}