{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CPRSEBK67YHVNVGBSOKEBFKFAH","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":"81ad68278706bda72a0f959391a8da62d7e73d15584ad22a151e5d84ad6b7b89","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T16:44:17Z","title_canon_sha256":"069a1949de10f13b1d72b91592c3f757b17955e13d440dc27c4ed660ee5d0baa"},"schema_version":"1.0","source":{"id":"2402.03177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03177","created_at":"2026-07-05T07:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03177v1","created_at":"2026-07-05T07:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03177","created_at":"2026-07-05T07:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"CPRSEBK67YHV","created_at":"2026-07-05T07:41:31Z"},{"alias_kind":"pith_short_16","alias_value":"CPRSEBK67YHVNVGB","created_at":"2026-07-05T07:41:31Z"},{"alias_kind":"pith_short_8","alias_value":"CPRSEBK6","created_at":"2026-07-05T07:41:31Z"}],"graph_snapshots":[{"event_id":"sha256:b18891ebf60ec30459b790cd9858a4e215bfb75237077c9fb0051c77cab029a0","target":"graph","created_at":"2026-07-05T07:41:31Z","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/2402.03177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning has emerged as a prominent methodology for teaching Large Language Models (LLMs) to follow instructions. However, current instruction datasets predominantly cater to English or are derived from English-dominated LLMs, resulting in inherent biases toward Western culture. This bias significantly impacts the linguistic structures of non-English languages such as Arabic, which has a distinct grammar reflective of the diverse cultures across the Arab region. This paper addresses this limitation by introducing CIDAR: https://hf.co/datasets/arbml/CIDAR, the first open Arabic instru","authors_text":"Ahmed Ashraf, Deema Alnuhait, Gamil Ahmed, Gubran A. Q. Abdulrahman, Khalid Almubarak, Maged S. Al-shaibani, Mustafa Ghaleb, Qais Gawah, Saied Alshahrani, Yousef Ali, Zaid Alyafeai, Zead Saleh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T16:44:17Z","title":"CIDAR: Culturally Relevant Instruction Dataset For Arabic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03177","kind":"arxiv","version":1},"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":"sha256:2c5499f0508de165187291041cf6ada365e5dd8545e53f20a1315156db08fa73","target":"record","created_at":"2026-07-05T07:41:31Z","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":"81ad68278706bda72a0f959391a8da62d7e73d15584ad22a151e5d84ad6b7b89","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T16:44:17Z","title_canon_sha256":"069a1949de10f13b1d72b91592c3f757b17955e13d440dc27c4ed660ee5d0baa"},"schema_version":"1.0","source":{"id":"2402.03177","kind":"arxiv","version":1}},"canonical_sha256":"13e322055efe0f56d4c1939440954501f8206fd3d3c1207dfbcd96f46b27a918","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13e322055efe0f56d4c1939440954501f8206fd3d3c1207dfbcd96f46b27a918","first_computed_at":"2026-07-05T07:41:31.991061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:31.991061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cGPxpY1pyThOIO0x8YbTFysKmrgDji/3Obs83iupa4Yt5qXzPN405w/vFP8KN+v3GUVI8It/YfHlPKSJX8/jBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:31.991480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c5499f0508de165187291041cf6ada365e5dd8545e53f20a1315156db08fa73","sha256:b18891ebf60ec30459b790cd9858a4e215bfb75237077c9fb0051c77cab029a0"],"state_sha256":"19667b29f9c534b0a13846625a043d74671345741c282c9f7c3c71443222b31d"}