{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6HYFSPRGZ3YCGMAMQDJ77OWY4A","short_pith_number":"pith:6HYFSPRG","schema_version":"1.0","canonical_sha256":"f1f0593e26cef023300c80d3ffbad8e017267a50d687bdae0ba15edd0073298d","source":{"kind":"arxiv","id":"2608.01291","version":1},"attestation_state":"computed","paper":{"title":"ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kholoud Khalil Aldous, Mabrouka Bessghaier, Md. Rafiul Biswas, Wajdi Zaghouani","submitted_at":"2026-08-02T15:00:58Z","abstract_excerpt":"We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syrian, Egyptian, Algerian, Palestinian, and Moroccan. The dataset is annotated with dialect labels and seven fine-grained harm categories. We introduce a dual-task evaluation framework for binary safe/unsafe detection and granular harm classification across dialects. Benchmarking seven supervised and generative models, we find that fine-tuned MARBERTv2 achieves the strongest performance, with Macro-F1 scores of 0.95 for binary classification and 0.90 f"},"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":"2608.01291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-02T15:00:58Z","cross_cats_sorted":[],"title_canon_sha256":"1d47594998cd6b1b3b0cc4611fcb9dfa7c814d5a7d7a355729b7dfee3142037c","abstract_canon_sha256":"1b03c7c4facd62e44c0f54c0d3364b1e075632b74962fc50fe94d1efea826d35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:03:11.121198Z","signature_b64":"NAvx/qjFipndFaawB4XvpfONaRdNSrSAEJgW1uHYQThh4akLqcFrE8SbJrVEK95aQdaydqzLbvfibNaKIJQJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1f0593e26cef023300c80d3ffbad8e017267a50d687bdae0ba15edd0073298d","last_reissued_at":"2026-08-04T02:03:11.119384Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:03:11.119384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ArabicDialectSafety: A Dialect-Aware Benchmark for Arabic Content Safety Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kholoud Khalil Aldous, Mabrouka Bessghaier, Md. Rafiul Biswas, Wajdi Zaghouani","submitted_at":"2026-08-02T15:00:58Z","abstract_excerpt":"We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syrian, Egyptian, Algerian, Palestinian, and Moroccan. The dataset is annotated with dialect labels and seven fine-grained harm categories. We introduce a dual-task evaluation framework for binary safe/unsafe detection and granular harm classification across dialects. Benchmarking seven supervised and generative models, we find that fine-tuned MARBERTv2 achieves the strongest performance, with Macro-F1 scores of 0.95 for binary classification and 0.90 f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01291","kind":"arxiv","version":1},"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/2608.01291/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":"2608.01291","created_at":"2026-08-04T02:03:11.120888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01291v1","created_at":"2026-08-04T02:03:11.120888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01291","created_at":"2026-08-04T02:03:11.120888+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HYFSPRGZ3YC","created_at":"2026-08-04T02:03:11.120888+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HYFSPRGZ3YCGMAM","created_at":"2026-08-04T02:03:11.120888+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HYFSPRG","created_at":"2026-08-04T02:03:11.120888+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/6HYFSPRGZ3YCGMAMQDJ77OWY4A","json":"https://pith.science/pith/6HYFSPRGZ3YCGMAMQDJ77OWY4A.json","graph_json":"https://pith.science/api/pith-number/6HYFSPRGZ3YCGMAMQDJ77OWY4A/graph.json","events_json":"https://pith.science/api/pith-number/6HYFSPRGZ3YCGMAMQDJ77OWY4A/events.json","paper":"https://pith.science/paper/6HYFSPRG"},"agent_actions":{"view_html":"https://pith.science/pith/6HYFSPRGZ3YCGMAMQDJ77OWY4A","download_json":"https://pith.science/pith/6HYFSPRGZ3YCGMAMQDJ77OWY4A.json","view_paper":"https://pith.science/paper/6HYFSPRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01291&json=true","fetch_graph":"https://pith.science/api/pith-number/6HYFSPRGZ3YCGMAMQDJ77OWY4A/graph.json","fetch_events":"https://pith.science/api/pith-number/6HYFSPRGZ3YCGMAMQDJ77OWY4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HYFSPRGZ3YCGMAMQDJ77OWY4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HYFSPRGZ3YCGMAMQDJ77OWY4A/action/storage_attestation","attest_author":"https://pith.science/pith/6HYFSPRGZ3YCGMAMQDJ77OWY4A/action/author_attestation","sign_citation":"https://pith.science/pith/6HYFSPRGZ3YCGMAMQDJ77OWY4A/action/citation_signature","submit_replication":"https://pith.science/pith/6HYFSPRGZ3YCGMAMQDJ77OWY4A/action/replication_record"}},"created_at":"2026-08-04T02:03:11.120888+00:00","updated_at":"2026-08-04T02:03:11.120888+00:00"}