{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3OY6U5QD2HTVDYDY74ZOH5CZMF","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":"6d0090ef73e4d2d8d55c424d36bdd26b70e9fef8b0a785f73868cf3187459901","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-06T22:53:41Z","title_canon_sha256":"bee7afbd6311733c15e5ba567bfab70d03bdd9694be53f66904faee5e7a4a986"},"schema_version":"1.0","source":{"id":"2507.04569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04569","created_at":"2026-07-05T11:32:49Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04569v1","created_at":"2026-07-05T11:32:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04569","created_at":"2026-07-05T11:32:49Z"},{"alias_kind":"pith_short_12","alias_value":"3OY6U5QD2HTV","created_at":"2026-07-05T11:32:49Z"},{"alias_kind":"pith_short_16","alias_value":"3OY6U5QD2HTVDYDY","created_at":"2026-07-05T11:32:49Z"},{"alias_kind":"pith_short_8","alias_value":"3OY6U5QD","created_at":"2026-07-05T11:32:49Z"}],"graph_snapshots":[{"event_id":"sha256:b595fad365d94f4c7b4210da4cfc1244de80a5a0e1e46184188c27174cc81294","target":"graph","created_at":"2026-07-05T11:32:49Z","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/2507.04569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Abdelaziz Bounhar, Ahmad Chamma, Amr Mohamed, Eric Xing, Guokan Shang, Hadi Abdine, Michalis Vazirgiannis, Mohamed Anwar, Omar El Herraoui, Preslav Nakov","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-06T22:53:41Z","title":"Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04569","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:d403b05991323e66a008b9407fc7f9606cb7a62aaf725d159008298533f684a0","target":"record","created_at":"2026-07-05T11:32:49Z","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":"6d0090ef73e4d2d8d55c424d36bdd26b70e9fef8b0a785f73868cf3187459901","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-06T22:53:41Z","title_canon_sha256":"bee7afbd6311733c15e5ba567bfab70d03bdd9694be53f66904faee5e7a4a986"},"schema_version":"1.0","source":{"id":"2507.04569","kind":"arxiv","version":1}},"canonical_sha256":"dbb1ea7603d1e751e078ff32e3f45961605b2272825df9e10a69d6d768ab0c2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbb1ea7603d1e751e078ff32e3f45961605b2272825df9e10a69d6d768ab0c2e","first_computed_at":"2026-07-05T11:32:49.908328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:49.908328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6La27ciJTnygpjazWTnXZ3d3l7APfVN9BocZ0QMZnvyRgE9hnCNaK/eicbVYqQ4C2cKrga8zyHapV1S/8395CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:49.908811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d403b05991323e66a008b9407fc7f9606cb7a62aaf725d159008298533f684a0","sha256:b595fad365d94f4c7b4210da4cfc1244de80a5a0e1e46184188c27174cc81294"],"state_sha256":"c1c47b99bd653981762a2463f985432bc975bcc037258509e21b439611ddf77f"}