{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OC3EW7FEWNNUNTMAFOIGSQV5BY","short_pith_number":"pith:OC3EW7FE","schema_version":"1.0","canonical_sha256":"70b64b7ca4b35b46cd802b906942bd0e02146415ce290e24a1ae84ffdf6093fd","source":{"kind":"arxiv","id":"1809.10610","version":2},"attestation_state":"computed","paper":{"title":"Counterfactual Fairness in Text Classification through Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Beutel, Ankur Taly, Ed H. Chi, Nicole Limtiaco, Sahaj Garg, Vincent Perot","submitted_at":"2018-09-27T16:21:39Z","abstract_excerpt":"In this paper, we study counterfactual fairness in text classification, which asks the question: How would the prediction change if the sensitive attribute referenced in the example were different? Toxicity classifiers demonstrate a counterfactual fairness issue by predicting that \"Some people are gay\" is toxic while \"Some people are straight\" is nontoxic. We offer a metric, counterfactual token fairness (CTF), for measuring this particular form of fairness in text classifiers, and describe its relationship with group fairness. Further, we offer three approaches, blindness, counterfactual augm"},"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":"1809.10610","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-27T16:21:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3878c6da1eeae59fb4b330b9bb2c5043c809944380d419dfe5ed31c2538c2ffe","abstract_canon_sha256":"cc77fa2af06c4024f855c19c02b9e3cb7e3d4e68af3043a752328c72830bd834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:02.544793Z","signature_b64":"Rk5Ae/ILfPsV9v2nrR4BVuaB6oawkXWdmtreMuP1WwQ54bMmYFanx9iCWYtQbK1DqLpN1WjTpPTlVe0Q1MytCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70b64b7ca4b35b46cd802b906942bd0e02146415ce290e24a1ae84ffdf6093fd","last_reissued_at":"2026-05-17T23:54:02.544269Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:02.544269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Fairness in Text Classification through Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Beutel, Ankur Taly, Ed H. Chi, Nicole Limtiaco, Sahaj Garg, Vincent Perot","submitted_at":"2018-09-27T16:21:39Z","abstract_excerpt":"In this paper, we study counterfactual fairness in text classification, which asks the question: How would the prediction change if the sensitive attribute referenced in the example were different? Toxicity classifiers demonstrate a counterfactual fairness issue by predicting that \"Some people are gay\" is toxic while \"Some people are straight\" is nontoxic. We offer a metric, counterfactual token fairness (CTF), for measuring this particular form of fairness in text classifiers, and describe its relationship with group fairness. Further, we offer three approaches, blindness, counterfactual augm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.10610","kind":"arxiv","version":2},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.10610","created_at":"2026-05-17T23:54:02.544354+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.10610v2","created_at":"2026-05-17T23:54:02.544354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.10610","created_at":"2026-05-17T23:54:02.544354+00:00"},{"alias_kind":"pith_short_12","alias_value":"OC3EW7FEWNNU","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OC3EW7FEWNNUNTMA","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OC3EW7FE","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2112.04359","citing_title":"Ethical and social risks of harm from Language Models","ref_index":87,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY","json":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY.json","graph_json":"https://pith.science/api/pith-number/OC3EW7FEWNNUNTMAFOIGSQV5BY/graph.json","events_json":"https://pith.science/api/pith-number/OC3EW7FEWNNUNTMAFOIGSQV5BY/events.json","paper":"https://pith.science/paper/OC3EW7FE"},"agent_actions":{"view_html":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY","download_json":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY.json","view_paper":"https://pith.science/paper/OC3EW7FE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.10610&json=true","fetch_graph":"https://pith.science/api/pith-number/OC3EW7FEWNNUNTMAFOIGSQV5BY/graph.json","fetch_events":"https://pith.science/api/pith-number/OC3EW7FEWNNUNTMAFOIGSQV5BY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY/action/storage_attestation","attest_author":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY/action/author_attestation","sign_citation":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY/action/citation_signature","submit_replication":"https://pith.science/pith/OC3EW7FEWNNUNTMAFOIGSQV5BY/action/replication_record"}},"created_at":"2026-05-17T23:54:02.544354+00:00","updated_at":"2026-05-17T23:54:02.544354+00:00"}