{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WNXIBVWOEHKXLKISXITXSDYRS4","short_pith_number":"pith:WNXIBVWO","schema_version":"1.0","canonical_sha256":"b36e80d6ce21d575a912ba27790f11973ad36c0e3b85bb02e987b3cd2d544a41","source":{"kind":"arxiv","id":"2505.11969","version":2},"attestation_state":"computed","paper":{"title":"An Annotated Corpus of Arabic Tweets for Hate Speech Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Md. Rafiul Biswas, Wajdi Zaghouani","submitted_at":"2025-05-17T12:08:22Z","abstract_excerpt":"Identifying hate speech content in the Arabic language is challenging due to the rich quality of dialectal variations. This study introduces a multilabel hate speech dataset in the Arabic language. We have collected 10000 Arabic tweets and annotated each tweet, whether it contains offensive content or not. If a text contains offensive content, we further classify it into different hate speech targets such as religion, gender, politics, ethnicity, origin, and others. A text can contain either single or multiple targets. Multiple annotators are involved in the data annotation task. We calculated"},"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":"2505.11969","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T12:08:22Z","cross_cats_sorted":[],"title_canon_sha256":"96ed37bc3af19e909d9ffd11334bc8d938cf8c942025e9fd273670bcb2989a6b","abstract_canon_sha256":"cd8450cae899167296f1624110042fdd3d773c3bb22668230352a1499d7d179e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:20.776687Z","signature_b64":"luFyfFn2wf+MTDriQ8omqdllQbjwEtgE6gKMD8uorR9+k7v0o97UluxYcdEvN+xA2V2WNvemjs0X8nUfiiU3BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b36e80d6ce21d575a912ba27790f11973ad36c0e3b85bb02e987b3cd2d544a41","last_reissued_at":"2026-07-05T11:08:20.776213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:20.776213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Annotated Corpus of Arabic Tweets for Hate Speech Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Md. Rafiul Biswas, Wajdi Zaghouani","submitted_at":"2025-05-17T12:08:22Z","abstract_excerpt":"Identifying hate speech content in the Arabic language is challenging due to the rich quality of dialectal variations. This study introduces a multilabel hate speech dataset in the Arabic language. We have collected 10000 Arabic tweets and annotated each tweet, whether it contains offensive content or not. If a text contains offensive content, we further classify it into different hate speech targets such as religion, gender, politics, ethnicity, origin, and others. A text can contain either single or multiple targets. Multiple annotators are involved in the data annotation task. We calculated"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11969","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/2505.11969/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":"2505.11969","created_at":"2026-07-05T11:08:20.776269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11969v2","created_at":"2026-07-05T11:08:20.776269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11969","created_at":"2026-07-05T11:08:20.776269+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNXIBVWOEHKX","created_at":"2026-07-05T11:08:20.776269+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNXIBVWOEHKXLKIS","created_at":"2026-07-05T11:08:20.776269+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNXIBVWO","created_at":"2026-07-05T11:08:20.776269+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/WNXIBVWOEHKXLKISXITXSDYRS4","json":"https://pith.science/pith/WNXIBVWOEHKXLKISXITXSDYRS4.json","graph_json":"https://pith.science/api/pith-number/WNXIBVWOEHKXLKISXITXSDYRS4/graph.json","events_json":"https://pith.science/api/pith-number/WNXIBVWOEHKXLKISXITXSDYRS4/events.json","paper":"https://pith.science/paper/WNXIBVWO"},"agent_actions":{"view_html":"https://pith.science/pith/WNXIBVWOEHKXLKISXITXSDYRS4","download_json":"https://pith.science/pith/WNXIBVWOEHKXLKISXITXSDYRS4.json","view_paper":"https://pith.science/paper/WNXIBVWO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11969&json=true","fetch_graph":"https://pith.science/api/pith-number/WNXIBVWOEHKXLKISXITXSDYRS4/graph.json","fetch_events":"https://pith.science/api/pith-number/WNXIBVWOEHKXLKISXITXSDYRS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNXIBVWOEHKXLKISXITXSDYRS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNXIBVWOEHKXLKISXITXSDYRS4/action/storage_attestation","attest_author":"https://pith.science/pith/WNXIBVWOEHKXLKISXITXSDYRS4/action/author_attestation","sign_citation":"https://pith.science/pith/WNXIBVWOEHKXLKISXITXSDYRS4/action/citation_signature","submit_replication":"https://pith.science/pith/WNXIBVWOEHKXLKISXITXSDYRS4/action/replication_record"}},"created_at":"2026-07-05T11:08:20.776269+00:00","updated_at":"2026-07-05T11:08:20.776269+00:00"}