{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RP3D6C44DJVKYRJMWBGCSED37N","short_pith_number":"pith:RP3D6C44","schema_version":"1.0","canonical_sha256":"8bf63f0b9c1a6aac452cb04c29107bfb7d323b45b2697c463d850d73cdd3ca11","source":{"kind":"arxiv","id":"1903.10561","version":1},"attestation_state":"computed","paper":{"title":"On Measuring Social Biases in Sentence Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Alex Wang, Chandler May, Rachel Rudinger, Samuel R. Bowman, Shikha Bordia","submitted_at":"2019-03-25T19:30:21Z","abstract_excerpt":"The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text representations has begun to explore sentence-level texts, with some sentence encoders seeing enthusiastic adoption. Accordingly, we extend the Word Embedding Association Test to measure bias in sentence encoders. We then test several sentence encoders, including state-of-the-art methods such as ELMo and BERT, for the social biases studied in prior work and t"},"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":"1903.10561","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-25T19:30:21Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"efb4acfe1a2905ad1697f637a0a55282136466050bd4aa30f55af7f2874750e6","abstract_canon_sha256":"01094644dc222533073511392bbf2cdeaa48773317d30ec8af980eeb39b14b2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:18.465905Z","signature_b64":"H1N8iz1/yPIMhNzMWZvkX/SpyIkYLWWy3UXBmyuGTn5CbMftJQQ24Oidc3ktr5Bk6l/Ko20NT0glNELvbTYoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bf63f0b9c1a6aac452cb04c29107bfb7d323b45b2697c463d850d73cdd3ca11","last_reissued_at":"2026-05-17T23:50:18.465086Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:18.465086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Measuring Social Biases in Sentence Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Alex Wang, Chandler May, Rachel Rudinger, Samuel R. Bowman, Shikha Bordia","submitted_at":"2019-03-25T19:30:21Z","abstract_excerpt":"The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text representations has begun to explore sentence-level texts, with some sentence encoders seeing enthusiastic adoption. Accordingly, we extend the Word Embedding Association Test to measure bias in sentence encoders. We then test several sentence encoders, including state-of-the-art methods such as ELMo and BERT, for the social biases studied in prior work and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.10561","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1903.10561","created_at":"2026-05-17T23:50:18.465224+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.10561v1","created_at":"2026-05-17T23:50:18.465224+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.10561","created_at":"2026-05-17T23:50:18.465224+00:00"},{"alias_kind":"pith_short_12","alias_value":"RP3D6C44DJVK","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RP3D6C44DJVKYRJM","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RP3D6C44","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.10256","citing_title":"Good Secretaries, Bad Truck Drivers? Occupational Gender Stereotypes in Sentiment Analysis","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2411.10915","citing_title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16113","citing_title":"DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2201.08239","citing_title":"LaMDA: Language Models for Dialog Applications","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"1908.10084","citing_title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N","json":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N.json","graph_json":"https://pith.science/api/pith-number/RP3D6C44DJVKYRJMWBGCSED37N/graph.json","events_json":"https://pith.science/api/pith-number/RP3D6C44DJVKYRJMWBGCSED37N/events.json","paper":"https://pith.science/paper/RP3D6C44"},"agent_actions":{"view_html":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N","download_json":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N.json","view_paper":"https://pith.science/paper/RP3D6C44","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.10561&json=true","fetch_graph":"https://pith.science/api/pith-number/RP3D6C44DJVKYRJMWBGCSED37N/graph.json","fetch_events":"https://pith.science/api/pith-number/RP3D6C44DJVKYRJMWBGCSED37N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N/action/storage_attestation","attest_author":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N/action/author_attestation","sign_citation":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N/action/citation_signature","submit_replication":"https://pith.science/pith/RP3D6C44DJVKYRJMWBGCSED37N/action/replication_record"}},"created_at":"2026-05-17T23:50:18.465224+00:00","updated_at":"2026-05-17T23:50:18.465224+00:00"}