{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3OY6U5QD2HTVDYDY74ZOH5CZMF","short_pith_number":"pith:3OY6U5QD","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"},"canonical_sha256":"dbb1ea7603d1e751e078ff32e3f45961605b2272825df9e10a69d6d768ab0c2e","source":{"kind":"arxiv","id":"2507.04569","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3OY6U5QD2HTVDYDY74ZOH5CZMF","target":"record","payload":{"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"},"canonical_sha256":"dbb1ea7603d1e751e078ff32e3f45961605b2272825df9e10a69d6d768ab0c2e","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"},"source_kind":"arxiv","source_id":"2507.04569","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vw4l+ASa9fKUbL8HzmTaJ5taOZhOuxaN4DMFvZfSGQv1OyRwQT/HyNPv7UJXkh6ucL2wmSYVRCqyz0iFGQujBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:40:05.216227Z"},"content_sha256":"d403b05991323e66a008b9407fc7f9606cb7a62aaf725d159008298533f684a0","schema_version":"1.0","event_id":"sha256:d403b05991323e66a008b9407fc7f9606cb7a62aaf725d159008298533f684a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3OY6U5QD2HTVDYDY74ZOH5CZMF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OkdXVFNmivEl2VEDGJDR2NYXoxsbAj5wkqhfJtZroEhNMqf2k8AY2TmbsKG2uBVmuzideu0Xt2jmym40LTp0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:40:05.216841Z"},"content_sha256":"b595fad365d94f4c7b4210da4cfc1244de80a5a0e1e46184188c27174cc81294","schema_version":"1.0","event_id":"sha256:b595fad365d94f4c7b4210da4cfc1244de80a5a0e1e46184188c27174cc81294"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/bundle.json","state_url":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T20:40:05Z","links":{"resolver":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF","bundle":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/bundle.json","state":"https://pith.science/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3OY6U5QD2HTVDYDY74ZOH5CZMF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGsP/xHzlbo0rpKz33FRKgzvXor13S1aISQknorIu5xIq1Mlrwd9BnUJTY25zuaA2GwKx9JGcWzvf8W0xnq9Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:40:05.223713Z","bundle_sha256":"5bc49a9e65cdfb327502ec1aa9db1f70fb0bc0238a7f1e9d44ff17937208f7ca"}}