{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3OY6U5QD2HTVDYDY74ZOH5CZMF","short_pith_number":"pith:3OY6U5QD","schema_version":"1.0","canonical_sha256":"dbb1ea7603d1e751e078ff32e3f45961605b2272825df9e10a69d6d768ab0c2e","source":{"kind":"arxiv","id":"2507.04569","version":1},"attestation_state":"computed","paper":{"title":"Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdelaziz Bounhar, Ahmad Chamma, Amr Mohamed, Eric Xing, Guokan Shang, Hadi Abdine, Michalis Vazirgiannis, Mohamed Anwar, Omar El Herraoui, Preslav Nakov","submitted_at":"2025-07-06T22:53:41Z","abstract_excerpt":"We introduce Nile-Chat-4B, 3x4B-A6B, and 12B, a collection of LLMs for Egyptian dialect, uniquely designed to understand and generate texts written in both Arabic and Latin scripts. Specifically, with Nile-Chat-3x4B-A6B, we introduce a novel language adaptation approach by leveraging the Branch-Train-MiX strategy to merge script-specialized experts, into a single MoE model. Our Nile-Chat models significantly outperform leading multilingual and Arabic LLMs, such as LLaMa, Jais, and ALLaM, on our newly introduced Egyptian evaluation benchmarks, which span both understanding and generative tasks."},"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":"2507.04569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-06T22:53:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bee7afbd6311733c15e5ba567bfab70d03bdd9694be53f66904faee5e7a4a986","abstract_canon_sha256":"6d0090ef73e4d2d8d55c424d36bdd26b70e9fef8b0a785f73868cf3187459901"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:49.908811Z","signature_b64":"6La27ciJTnygpjazWTnXZ3d3l7APfVN9BocZ0QMZnvyRgE9hnCNaK/eicbVYqQ4C2cKrga8zyHapV1S/8395CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbb1ea7603d1e751e078ff32e3f45961605b2272825df9e10a69d6d768ab0c2e","last_reissued_at":"2026-07-05T11:32:49.908328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:49.908328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdelaziz Bounhar, Ahmad Chamma, Amr Mohamed, Eric Xing, Guokan Shang, Hadi Abdine, Michalis Vazirgiannis, Mohamed Anwar, Omar El Herraoui, Preslav Nakov","submitted_at":"2025-07-06T22:53:41Z","abstract_excerpt":"We introduce Nile-Chat-4B, 3x4B-A6B, and 12B, a collection of LLMs for Egyptian dialect, uniquely designed to understand and generate texts written in both Arabic and Latin scripts. Specifically, with Nile-Chat-3x4B-A6B, we introduce a novel language adaptation approach by leveraging the Branch-Train-MiX strategy to merge script-specialized experts, into a single MoE model. Our Nile-Chat models significantly outperform leading multilingual and Arabic LLMs, such as LLaMa, Jais, and ALLaM, on our newly introduced Egyptian evaluation benchmarks, which span both understanding and generative tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04569","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/2507.04569/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":"2507.04569","created_at":"2026-07-05T11:32:49.908400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04569v1","created_at":"2026-07-05T11:32:49.908400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04569","created_at":"2026-07-05T11:32:49.908400+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OY6U5QD2HTV","created_at":"2026-07-05T11:32:49.908400+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OY6U5QD2HTVDYDY","created_at":"2026-07-05T11:32:49.908400+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OY6U5QD","created_at":"2026-07-05T11:32:49.908400+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/3OY6U5QD2HTVDYDY74ZOH5CZMF","json":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF.json","graph_json":"https://pith.science/api/pith-number/3OY6U5QD2HTVDYDY74ZOH5CZMF/graph.json","events_json":"https://pith.science/api/pith-number/3OY6U5QD2HTVDYDY74ZOH5CZMF/events.json","paper":"https://pith.science/paper/3OY6U5QD"},"agent_actions":{"view_html":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF","download_json":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF.json","view_paper":"https://pith.science/paper/3OY6U5QD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04569&json=true","fetch_graph":"https://pith.science/api/pith-number/3OY6U5QD2HTVDYDY74ZOH5CZMF/graph.json","fetch_events":"https://pith.science/api/pith-number/3OY6U5QD2HTVDYDY74ZOH5CZMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/action/storage_attestation","attest_author":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/action/author_attestation","sign_citation":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/action/citation_signature","submit_replication":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/action/replication_record"}},"created_at":"2026-07-05T11:32:49.908400+00:00","updated_at":"2026-07-05T11:32:49.908400+00:00"}