{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NM4HKDWGAMW2TH66LEBGGF62XS","short_pith_number":"pith:NM4HKDWG","schema_version":"1.0","canonical_sha256":"6b38750ec6032da99fde59026317dabcb12957ee2f6ddf6f8bffd626c198f096","source":{"kind":"arxiv","id":"2505.14272","version":2},"attestation_state":"computed","paper":{"title":"Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CY","cs.MM"],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Daryna Dementieva, Faeze Ghorbanpour","submitted_at":"2025-05-20T12:25:33Z","abstract_excerpt":"Considering the importance of detecting hateful language, labeled hate speech data is expensive and time-consuming to collect, particularly for low-resource languages. Prior work has demonstrated the effectiveness of cross-lingual transfer learning and data augmentation in improving performance on tasks with limited labeled data. To develop an efficient and scalable cross-lingual transfer learning approach, we leverage nearest-neighbor retrieval to augment minimal labeled data in the target language, thereby enhancing detection performance. Specifically, we assume access to a small set of labe"},"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":"2505.14272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:25:33Z","cross_cats_sorted":["cs.CY","cs.MM"],"title_canon_sha256":"ad8d03d2d8ce9441b7460759ca54ab95c1d14343011223b844047a9b1f015cb0","abstract_canon_sha256":"7ae341eaf68fb5f50fd06744903485f038fe0dbc2c95884dcc2910e62fa464ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:14.390158Z","signature_b64":"wja38nHY1oGwnxXaf8FYezYCXBYbFpO5BsAbU/lYeZ6FNU/kFyoQOeyjHaRirVtn6m9PsReoqlOswfkJZByYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b38750ec6032da99fde59026317dabcb12957ee2f6ddf6f8bffd626c198f096","last_reissued_at":"2026-07-05T11:09:14.389692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:14.389692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CY","cs.MM"],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Daryna Dementieva, Faeze Ghorbanpour","submitted_at":"2025-05-20T12:25:33Z","abstract_excerpt":"Considering the importance of detecting hateful language, labeled hate speech data is expensive and time-consuming to collect, particularly for low-resource languages. Prior work has demonstrated the effectiveness of cross-lingual transfer learning and data augmentation in improving performance on tasks with limited labeled data. To develop an efficient and scalable cross-lingual transfer learning approach, we leverage nearest-neighbor retrieval to augment minimal labeled data in the target language, thereby enhancing detection performance. Specifically, we assume access to a small set of labe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14272","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/2505.14272/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":"2505.14272","created_at":"2026-07-05T11:09:14.389750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14272v2","created_at":"2026-07-05T11:09:14.389750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14272","created_at":"2026-07-05T11:09:14.389750+00:00"},{"alias_kind":"pith_short_12","alias_value":"NM4HKDWGAMW2","created_at":"2026-07-05T11:09:14.389750+00:00"},{"alias_kind":"pith_short_16","alias_value":"NM4HKDWGAMW2TH66","created_at":"2026-07-05T11:09:14.389750+00:00"},{"alias_kind":"pith_short_8","alias_value":"NM4HKDWG","created_at":"2026-07-05T11:09:14.389750+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/NM4HKDWGAMW2TH66LEBGGF62XS","json":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS.json","graph_json":"https://pith.science/api/pith-number/NM4HKDWGAMW2TH66LEBGGF62XS/graph.json","events_json":"https://pith.science/api/pith-number/NM4HKDWGAMW2TH66LEBGGF62XS/events.json","paper":"https://pith.science/paper/NM4HKDWG"},"agent_actions":{"view_html":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS","download_json":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS.json","view_paper":"https://pith.science/paper/NM4HKDWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14272&json=true","fetch_graph":"https://pith.science/api/pith-number/NM4HKDWGAMW2TH66LEBGGF62XS/graph.json","fetch_events":"https://pith.science/api/pith-number/NM4HKDWGAMW2TH66LEBGGF62XS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/action/storage_attestation","attest_author":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/action/author_attestation","sign_citation":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/action/citation_signature","submit_replication":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/action/replication_record"}},"created_at":"2026-07-05T11:09:14.389750+00:00","updated_at":"2026-07-05T11:09:14.389750+00:00"}