{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NM4HKDWGAMW2TH66LEBGGF62XS","short_pith_number":"pith:NM4HKDWG","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"},"canonical_sha256":"6b38750ec6032da99fde59026317dabcb12957ee2f6ddf6f8bffd626c198f096","source":{"kind":"arxiv","id":"2505.14272","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14272","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14272v2","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14272","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"NM4HKDWGAMW2","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"NM4HKDWGAMW2TH66","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"NM4HKDWG","created_at":"2026-07-05T11:09:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NM4HKDWGAMW2TH66LEBGGF62XS","target":"record","payload":{"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"},"canonical_sha256":"6b38750ec6032da99fde59026317dabcb12957ee2f6ddf6f8bffd626c198f096","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"},"source_kind":"arxiv","source_id":"2505.14272","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b1bs3hgmzmmurObPbDm4qNKaodDq1d0fWo044RPJ2nJABvCdgKVvc+hPtCV+KaKs2PRr+UQRvICA6OuLY1sgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:47:26.423405Z"},"content_sha256":"0b3e5fca7037b9d1f8b8c1fdf244db817c88031c58c70f2637ac9b3d9b249be9","schema_version":"1.0","event_id":"sha256:0b3e5fca7037b9d1f8b8c1fdf244db817c88031c58c70f2637ac9b3d9b249be9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NM4HKDWGAMW2TH66LEBGGF62XS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tMKKP7BPtTCd5vt09uOO+OOP3Bh9L90XqndxXkQJqTkUINfJEZAXvZ/3AxakIV9c/ZAgNCfOmXDB6mAImw5kBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T05:47:26.424354Z"},"content_sha256":"db879e5929bf780908e0667087d695c8f295f17f069b507db6025e64bc12e0c9","schema_version":"1.0","event_id":"sha256:db879e5929bf780908e0667087d695c8f295f17f069b507db6025e64bc12e0c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/bundle.json","state_url":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NM4HKDWGAMW2TH66LEBGGF62XS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T05:47:26Z","links":{"resolver":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS","bundle":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/bundle.json","state":"https://pith.science/pith/NM4HKDWGAMW2TH66LEBGGF62XS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NM4HKDWGAMW2TH66LEBGGF62XS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NM4HKDWGAMW2TH66LEBGGF62XS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7ae341eaf68fb5f50fd06744903485f038fe0dbc2c95884dcc2910e62fa464ce","cross_cats_sorted":["cs.CY","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:25:33Z","title_canon_sha256":"ad8d03d2d8ce9441b7460759ca54ab95c1d14343011223b844047a9b1f015cb0"},"schema_version":"1.0","source":{"id":"2505.14272","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.14272","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"arxiv_version","alias_value":"2505.14272v2","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14272","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_12","alias_value":"NM4HKDWGAMW2","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_16","alias_value":"NM4HKDWGAMW2TH66","created_at":"2026-07-05T11:09:14Z"},{"alias_kind":"pith_short_8","alias_value":"NM4HKDWG","created_at":"2026-07-05T11:09:14Z"}],"graph_snapshots":[{"event_id":"sha256:db879e5929bf780908e0667087d695c8f295f17f069b507db6025e64bc12e0c9","target":"graph","created_at":"2026-07-05T11:09:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.14272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alexander Fraser, Daryna Dementieva, Faeze Ghorbanpour","cross_cats":["cs.CY","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:25:33Z","title":"Data-Efficient Hate Speech Detection via Cross-Lingual Nearest Neighbor Retrieval with Limited Labeled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14272","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0b3e5fca7037b9d1f8b8c1fdf244db817c88031c58c70f2637ac9b3d9b249be9","target":"record","created_at":"2026-07-05T11:09:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7ae341eaf68fb5f50fd06744903485f038fe0dbc2c95884dcc2910e62fa464ce","cross_cats_sorted":["cs.CY","cs.MM"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T12:25:33Z","title_canon_sha256":"ad8d03d2d8ce9441b7460759ca54ab95c1d14343011223b844047a9b1f015cb0"},"schema_version":"1.0","source":{"id":"2505.14272","kind":"arxiv","version":2}},"canonical_sha256":"6b38750ec6032da99fde59026317dabcb12957ee2f6ddf6f8bffd626c198f096","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b38750ec6032da99fde59026317dabcb12957ee2f6ddf6f8bffd626c198f096","first_computed_at":"2026-07-05T11:09:14.389692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:14.389692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wja38nHY1oGwnxXaf8FYezYCXBYbFpO5BsAbU/lYeZ6FNU/kFyoQOeyjHaRirVtn6m9PsReoqlOswfkJZByYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:14.390158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.14272","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b3e5fca7037b9d1f8b8c1fdf244db817c88031c58c70f2637ac9b3d9b249be9","sha256:db879e5929bf780908e0667087d695c8f295f17f069b507db6025e64bc12e0c9"],"state_sha256":"71986fed52406f6da876977bb75d93e5252c1073fb978300feea1423c6b0eac6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LDY/qMw35URIUqYANfkYpiMArs4sTlzdl3Dx6JwdzenIgIRAApgmVwJ3LQU/5VJstRmKDbpN7QdoU9zERq3LCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T05:47:26.430878Z","bundle_sha256":"8a6a688cffa5e8c77475c6e621f71bac9a31021bd847ba4a19cea1ed708e660e"}}