{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AGC54T76DF3EMXVLOZZOQOXE57","short_pith_number":"pith:AGC54T76","schema_version":"1.0","canonical_sha256":"0185de4ffe1976465eab7672e83ae4efe9612ddc26caa24554aa984cd00c24c5","source":{"kind":"arxiv","id":"1812.08769","version":4},"attestation_state":"computed","paper":{"title":"What are the biases in my word embedding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Tauman Kalai, Maria De-Arteaga, Mark DM Leiserson, Nathaniel Swinger, Neil Thomas Heffernan IV","submitted_at":"2018-12-20T18:53:05Z","abstract_excerpt":"This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including a supposedly \"debiased\" embedding. These biases are concerning in light of the widespread use of word embeddings. The associations are identified by geometric patterns in word embeddings that run parallel between people's names and common lower-case tokens. The algorithm is highly unsupervised: it does not even require the sensitive features to be pre-specified"},"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":"1812.08769","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-20T18:53:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"39ac99b5a911f3ad000d4a08c1e200fbcd473934e86201d8fcc640a03b984d8f","abstract_canon_sha256":"d22ed984c1c6e61bb5a561336a18cbd3ab9c6d9b0127f16a20fe9229ed7bc6a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:53.534300Z","signature_b64":"0CKp2pso+7SFwlLs2hnEBYoTSBG4XZl9/3HtlninwE3qMl7jaUfzLrwaYT1hv+1RtGQSsYQ+4zBhEGXcybUhDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0185de4ffe1976465eab7672e83ae4efe9612ddc26caa24554aa984cd00c24c5","last_reissued_at":"2026-05-17T23:42:53.533764Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:53.533764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What are the biases in my word embedding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Tauman Kalai, Maria De-Arteaga, Mark DM Leiserson, Nathaniel Swinger, Neil Thomas Heffernan IV","submitted_at":"2018-12-20T18:53:05Z","abstract_excerpt":"This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including a supposedly \"debiased\" embedding. These biases are concerning in light of the widespread use of word embeddings. The associations are identified by geometric patterns in word embeddings that run parallel between people's names and common lower-case tokens. The algorithm is highly unsupervised: it does not even require the sensitive features to be pre-specified"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08769","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":""},"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":"1812.08769","created_at":"2026-05-17T23:42:53.533865+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08769v4","created_at":"2026-05-17T23:42:53.533865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08769","created_at":"2026-05-17T23:42:53.533865+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGC54T76DF3E","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGC54T76DF3EMXVL","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGC54T76","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57","json":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57.json","graph_json":"https://pith.science/api/pith-number/AGC54T76DF3EMXVLOZZOQOXE57/graph.json","events_json":"https://pith.science/api/pith-number/AGC54T76DF3EMXVLOZZOQOXE57/events.json","paper":"https://pith.science/paper/AGC54T76"},"agent_actions":{"view_html":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57","download_json":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57.json","view_paper":"https://pith.science/paper/AGC54T76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08769&json=true","fetch_graph":"https://pith.science/api/pith-number/AGC54T76DF3EMXVLOZZOQOXE57/graph.json","fetch_events":"https://pith.science/api/pith-number/AGC54T76DF3EMXVLOZZOQOXE57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57/action/storage_attestation","attest_author":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57/action/author_attestation","sign_citation":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57/action/citation_signature","submit_replication":"https://pith.science/pith/AGC54T76DF3EMXVLOZZOQOXE57/action/replication_record"}},"created_at":"2026-05-17T23:42:53.533865+00:00","updated_at":"2026-05-17T23:42:53.533865+00:00"}