{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WQLLK6535HVO4YECEI272UQWJZ","short_pith_number":"pith:WQLLK653","schema_version":"1.0","canonical_sha256":"b416b57bbbe9eaee60822235fd52164e769211426d2f4c951aa50a7603a202e6","source":{"kind":"arxiv","id":"2404.17874","version":2},"attestation_state":"computed","paper":{"title":"From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diyi Liu, Manuel Tonneau, Paul R\\\"ottger, Ralph Schroeder, Samuel Fraiberger, Scott A. Hale","submitted_at":"2024-04-27T12:10:10Z","abstract_excerpt":"Perceptions of hate can vary greatly across cultural contexts. Hate speech (HS) datasets, however, have traditionally been developed by language. This hides potential cultural biases, as one language may be spoken in different countries home to different cultures. In this work, we evaluate cultural bias in HS datasets by leveraging two interrelated cultural proxies: language and geography. We conduct a systematic survey of HS datasets in eight languages and confirm past findings on their English-language bias, but also show that this bias has been steadily decreasing in the past few years. For"},"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":"2404.17874","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T12:10:10Z","cross_cats_sorted":[],"title_canon_sha256":"92e3969585ff4e1c5960371c8768b6fbafd4056d2632e9cc9de03d25d6ba8270","abstract_canon_sha256":"c67ea9bb6eec99fe63d4bd07d0e6cacb650d90c289173fabb674bf2d6f3c705e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:20.787931Z","signature_b64":"EaSF114E76f7Kd+ScCScNXl3bl2Sfr99Hj3aHO+ERP9W/mDCTVdCXK2PNH8F3ZJNVfl2TtNmiqulhWR/jmrbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b416b57bbbe9eaee60822235fd52164e769211426d2f4c951aa50a7603a202e6","last_reissued_at":"2026-07-05T11:05:20.787552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:20.787552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diyi Liu, Manuel Tonneau, Paul R\\\"ottger, Ralph Schroeder, Samuel Fraiberger, Scott A. Hale","submitted_at":"2024-04-27T12:10:10Z","abstract_excerpt":"Perceptions of hate can vary greatly across cultural contexts. Hate speech (HS) datasets, however, have traditionally been developed by language. This hides potential cultural biases, as one language may be spoken in different countries home to different cultures. In this work, we evaluate cultural bias in HS datasets by leveraging two interrelated cultural proxies: language and geography. We conduct a systematic survey of HS datasets in eight languages and confirm past findings on their English-language bias, but also show that this bias has been steadily decreasing in the past few years. For"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17874","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.17874/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.17874","created_at":"2026-07-05T11:05:20.787609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17874v2","created_at":"2026-07-05T11:05:20.787609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17874","created_at":"2026-07-05T11:05:20.787609+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQLLK6535HVO","created_at":"2026-07-05T11:05:20.787609+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQLLK6535HVO4YEC","created_at":"2026-07-05T11:05:20.787609+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQLLK653","created_at":"2026-07-05T11:05:20.787609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.16183","citing_title":"BIDWESH: A Bangla Regional Based Hate Speech Detection Dataset","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ","json":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ.json","graph_json":"https://pith.science/api/pith-number/WQLLK6535HVO4YECEI272UQWJZ/graph.json","events_json":"https://pith.science/api/pith-number/WQLLK6535HVO4YECEI272UQWJZ/events.json","paper":"https://pith.science/paper/WQLLK653"},"agent_actions":{"view_html":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ","download_json":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ.json","view_paper":"https://pith.science/paper/WQLLK653","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17874&json=true","fetch_graph":"https://pith.science/api/pith-number/WQLLK6535HVO4YECEI272UQWJZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WQLLK6535HVO4YECEI272UQWJZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ/action/storage_attestation","attest_author":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ/action/author_attestation","sign_citation":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ/action/citation_signature","submit_replication":"https://pith.science/pith/WQLLK6535HVO4YECEI272UQWJZ/action/replication_record"}},"created_at":"2026-07-05T11:05:20.787609+00:00","updated_at":"2026-07-05T11:05:20.787609+00:00"}