{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YZJEL5IRYVIZASJZJKOGJKC5MH","short_pith_number":"pith:YZJEL5IR","canonical_record":{"source":{"id":"2306.11112","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T18:25:44Z","cross_cats_sorted":["cs.CY","cs.DS","stat.ML"],"title_canon_sha256":"2ab1708196d953fffffad4ba848f1ee26edc86dfc0d9279d52e9d4cb4b16321d","abstract_canon_sha256":"f02f7dcb597053c187f783039772366d45620cb6bc00bf5bc249105a37b883b3"},"schema_version":"1.0"},"canonical_sha256":"c65245f511c5519049394a9c64a85d61d1eb8c6c4205e70c84260504ea5bc5a2","source":{"kind":"arxiv","id":"2306.11112","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11112","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11112v4","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11112","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"YZJEL5IRYVIZ","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"YZJEL5IRYVIZASJZ","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"YZJEL5IR","created_at":"2026-07-05T08:26:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YZJEL5IRYVIZASJZJKOGJKC5MH","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11112","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T18:25:44Z","cross_cats_sorted":["cs.CY","cs.DS","stat.ML"],"title_canon_sha256":"2ab1708196d953fffffad4ba848f1ee26edc86dfc0d9279d52e9d4cb4b16321d","abstract_canon_sha256":"f02f7dcb597053c187f783039772366d45620cb6bc00bf5bc249105a37b883b3"},"schema_version":"1.0"},"canonical_sha256":"c65245f511c5519049394a9c64a85d61d1eb8c6c4205e70c84260504ea5bc5a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:42.502639Z","signature_b64":"u7O6BE/aCVuj1G0yiyWR3LmLwgGRYnJabQNuxZ7BPCfnp8UtiXLuHP3QK26S3a9ySuKnTn6lpvddYDC4+6QSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c65245f511c5519049394a9c64a85d61d1eb8c6c4205e70c84260504ea5bc5a2","last_reissued_at":"2026-07-05T08:26:42.502161Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:42.502161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11112","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uDiX70diRBwDvn6UCQF2qV7bE5P8zzVFP1Y+jrDiyWA4zFoaWtABZpmUkfDtUSC2xRfB+F9Aw4Nr0zptSVbEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:04:58.507244Z"},"content_sha256":"ed16611eebac464dd70e93e070e3bc071a5356d992d6bf8b178f17bd3e16adb5","schema_version":"1.0","event_id":"sha256:ed16611eebac464dd70e93e070e3bc071a5356d992d6bf8b178f17bd3e16adb5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YZJEL5IRYVIZASJZJKOGJKC5MH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Correcting Underrepresentation and Intersectional Bias for Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Williams Tolbert, Emily Diana","submitted_at":"2023-06-19T18:25:44Z","abstract_excerpt":"We consider the problem of learning from data corrupted by underrepresentation bias, where positive examples are filtered from the data at different, unknown rates for a fixed number of sensitive groups. We show that with a small amount of unbiased data, we can efficiently estimate the group-wise drop-out rates, even in settings where intersectional group membership makes learning each intersectional rate computationally infeasible. Using these estimates, we construct a reweighting scheme that allows us to approximate the loss of any hypothesis on the true distribution, even if we only observe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11112","kind":"arxiv","version":4},"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/2306.11112/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":"2026-07-05T08:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NowRIJyjPuvARzix+MbFRsdgg27rf76LnYkEUgvlAd9poOInNSxFwEm3chAxaGEq0igHLJSE/Lf6kVOXEHJ4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:04:58.507831Z"},"content_sha256":"44bc6243de43a1cc38a1aa97a37b3c602ed4f4900de70dac31bb119656e46e56","schema_version":"1.0","event_id":"sha256:44bc6243de43a1cc38a1aa97a37b3c602ed4f4900de70dac31bb119656e46e56"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZJEL5IRYVIZASJZJKOGJKC5MH/bundle.json","state_url":"https://pith.science/pith/YZJEL5IRYVIZASJZJKOGJKC5MH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZJEL5IRYVIZASJZJKOGJKC5MH/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":"2026-08-08T22:04:58Z","links":{"resolver":"https://pith.science/pith/YZJEL5IRYVIZASJZJKOGJKC5MH","bundle":"https://pith.science/pith/YZJEL5IRYVIZASJZJKOGJKC5MH/bundle.json","state":"https://pith.science/pith/YZJEL5IRYVIZASJZJKOGJKC5MH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZJEL5IRYVIZASJZJKOGJKC5MH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YZJEL5IRYVIZASJZJKOGJKC5MH","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":"f02f7dcb597053c187f783039772366d45620cb6bc00bf5bc249105a37b883b3","cross_cats_sorted":["cs.CY","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T18:25:44Z","title_canon_sha256":"2ab1708196d953fffffad4ba848f1ee26edc86dfc0d9279d52e9d4cb4b16321d"},"schema_version":"1.0","source":{"id":"2306.11112","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11112","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11112v4","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11112","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"YZJEL5IRYVIZ","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"YZJEL5IRYVIZASJZ","created_at":"2026-07-05T08:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"YZJEL5IR","created_at":"2026-07-05T08:26:42Z"}],"graph_snapshots":[{"event_id":"sha256:44bc6243de43a1cc38a1aa97a37b3c602ed4f4900de70dac31bb119656e46e56","target":"graph","created_at":"2026-07-05T08:26:42Z","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/2306.11112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of learning from data corrupted by underrepresentation bias, where positive examples are filtered from the data at different, unknown rates for a fixed number of sensitive groups. We show that with a small amount of unbiased data, we can efficiently estimate the group-wise drop-out rates, even in settings where intersectional group membership makes learning each intersectional rate computationally infeasible. Using these estimates, we construct a reweighting scheme that allows us to approximate the loss of any hypothesis on the true distribution, even if we only observe","authors_text":"Alexander Williams Tolbert, Emily Diana","cross_cats":["cs.CY","cs.DS","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T18:25:44Z","title":"Correcting Underrepresentation and Intersectional Bias for Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11112","kind":"arxiv","version":4},"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:ed16611eebac464dd70e93e070e3bc071a5356d992d6bf8b178f17bd3e16adb5","target":"record","created_at":"2026-07-05T08:26:42Z","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":"f02f7dcb597053c187f783039772366d45620cb6bc00bf5bc249105a37b883b3","cross_cats_sorted":["cs.CY","cs.DS","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T18:25:44Z","title_canon_sha256":"2ab1708196d953fffffad4ba848f1ee26edc86dfc0d9279d52e9d4cb4b16321d"},"schema_version":"1.0","source":{"id":"2306.11112","kind":"arxiv","version":4}},"canonical_sha256":"c65245f511c5519049394a9c64a85d61d1eb8c6c4205e70c84260504ea5bc5a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c65245f511c5519049394a9c64a85d61d1eb8c6c4205e70c84260504ea5bc5a2","first_computed_at":"2026-07-05T08:26:42.502161Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:42.502161Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u7O6BE/aCVuj1G0yiyWR3LmLwgGRYnJabQNuxZ7BPCfnp8UtiXLuHP3QK26S3a9ySuKnTn6lpvddYDC4+6QSBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:42.502639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11112","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed16611eebac464dd70e93e070e3bc071a5356d992d6bf8b178f17bd3e16adb5","sha256:44bc6243de43a1cc38a1aa97a37b3c602ed4f4900de70dac31bb119656e46e56"],"state_sha256":"64a92a6612e6023f109dd4c4a67a6cd9cb7891bcc390f6bbe959cf3b65268545"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DSgV8k3YO99/yXb47u/RPo9rN/2o0Sg8CwyJbh3dAQKXISGo5DmAgSbeFuRMEFWxoGnusTBx4MjqwpTmVa3LCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:04:58.513159Z","bundle_sha256":"6aa081df090359471527a85a3963363a08fec91cc0e4ae6d8f7e06c4177f1a29"}}