{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZQAMULJYZ5O7JAWXXY3DSWFTLZ","short_pith_number":"pith:ZQAMULJY","canonical_record":{"source":{"id":"2409.17912","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T14:56:38Z","cross_cats_sorted":[],"title_canon_sha256":"42ab4383e5a2c9f4b06b5c6361b6c511cfe4e322f30a13cf6bab425d8d904ffa","abstract_canon_sha256":"06759911a4e845771b980921fda96fce157ef4749df1476d9ca227ea00a94bf5"},"schema_version":"1.0"},"canonical_sha256":"cc00ca2d38cf5df482d7be363958b35e41c66be96e39b986b63435404f082228","source":{"kind":"arxiv","id":"2409.17912","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17912","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17912v2","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17912","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZQAMULJYZ5O7","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZQAMULJYZ5O7JAWX","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZQAMULJY","created_at":"2026-07-05T09:34:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZQAMULJYZ5O7JAWXXY3DSWFTLZ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.17912","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T14:56:38Z","cross_cats_sorted":[],"title_canon_sha256":"42ab4383e5a2c9f4b06b5c6361b6c511cfe4e322f30a13cf6bab425d8d904ffa","abstract_canon_sha256":"06759911a4e845771b980921fda96fce157ef4749df1476d9ca227ea00a94bf5"},"schema_version":"1.0"},"canonical_sha256":"cc00ca2d38cf5df482d7be363958b35e41c66be96e39b986b63435404f082228","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:19.998982Z","signature_b64":"y0GTH5r70AFyOjRSCkvYMXnmfvYltcWBScqcIZl8C1L4D65FZK9fPSz2v7CE7PR0VqyPClYhdNuTph5rFfQxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc00ca2d38cf5df482d7be363958b35e41c66be96e39b986b63435404f082228","last_reissued_at":"2026-07-05T09:34:19.998508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:19.998508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.17912","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hs+l42Z3O/QWYC6lz+VzplGdiHtgVnYzr6WxmJ808OJmYOaUhafcMSYMJfyZwXXg6pxI7aO9sqaFyI3KXkjeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:11:26.104825Z"},"content_sha256":"8487dc4a738fa762205523b306febaca215c91c96d203665673dfb1a5f8b70f1","schema_version":"1.0","event_id":"sha256:8487dc4a738fa762205523b306febaca215c91c96d203665673dfb1a5f8b70f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZQAMULJYZ5O7JAWXXY3DSWFTLZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amr Mohamed, Eric Moulines, Eric Xing, Guokan Shang, Hadi Abdine, Imane Momayiz, Michalis Vazirgiannis, Preslav Nakov, Sofiane Ennadir, Xuguang Ren, Yassine Abbahaddou, Yousef Khoubrane","submitted_at":"2024-09-26T14:56:38Z","abstract_excerpt":"We introduce Atlas-Chat, the first-ever collection of LLMs specifically developed for dialectal Arabic. Focusing on Moroccan Arabic, also known as Darija, we construct our instruction dataset by consolidating existing Darija language resources, creating novel datasets both manually and synthetically, and translating English instructions with stringent quality control. Atlas-Chat-2B, 9B, and 27B models, fine-tuned on the dataset, exhibit superior ability in following Darija instructions and performing standard NLP tasks. Notably, our models outperform both state-of-the-art and Arabic-specialize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17912","kind":"arxiv","version":2},"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/2409.17912/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":"2026-07-05T09:34:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7YJPTVrDr0E2fxsmnJu/HmdYedPxnlRJg4TBgDWYMthYEk3+g26hfQtYxhVmPEUs+V7zBAbRnsp4yoHhThhBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:11:26.105766Z"},"content_sha256":"7ac6485b8578e5202ebb5d171b442412da56b150c99bac5aa2eb830ed97025ea","schema_version":"1.0","event_id":"sha256:7ac6485b8578e5202ebb5d171b442412da56b150c99bac5aa2eb830ed97025ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQAMULJYZ5O7JAWXXY3DSWFTLZ/bundle.json","state_url":"https://pith.science/pith/ZQAMULJYZ5O7JAWXXY3DSWFTLZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQAMULJYZ5O7JAWXXY3DSWFTLZ/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":"2026-08-09T06:11:26Z","links":{"resolver":"https://pith.science/pith/ZQAMULJYZ5O7JAWXXY3DSWFTLZ","bundle":"https://pith.science/pith/ZQAMULJYZ5O7JAWXXY3DSWFTLZ/bundle.json","state":"https://pith.science/pith/ZQAMULJYZ5O7JAWXXY3DSWFTLZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQAMULJYZ5O7JAWXXY3DSWFTLZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQAMULJYZ5O7JAWXXY3DSWFTLZ","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":"06759911a4e845771b980921fda96fce157ef4749df1476d9ca227ea00a94bf5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T14:56:38Z","title_canon_sha256":"42ab4383e5a2c9f4b06b5c6361b6c511cfe4e322f30a13cf6bab425d8d904ffa"},"schema_version":"1.0","source":{"id":"2409.17912","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17912","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17912v2","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17912","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZQAMULJYZ5O7","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"pith_short_16","alias_value":"ZQAMULJYZ5O7JAWX","created_at":"2026-07-05T09:34:19Z"},{"alias_kind":"pith_short_8","alias_value":"ZQAMULJY","created_at":"2026-07-05T09:34:19Z"}],"graph_snapshots":[{"event_id":"sha256:7ac6485b8578e5202ebb5d171b442412da56b150c99bac5aa2eb830ed97025ea","target":"graph","created_at":"2026-07-05T09:34:19Z","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/2409.17912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Atlas-Chat, the first-ever collection of LLMs specifically developed for dialectal Arabic. Focusing on Moroccan Arabic, also known as Darija, we construct our instruction dataset by consolidating existing Darija language resources, creating novel datasets both manually and synthetically, and translating English instructions with stringent quality control. Atlas-Chat-2B, 9B, and 27B models, fine-tuned on the dataset, exhibit superior ability in following Darija instructions and performing standard NLP tasks. Notably, our models outperform both state-of-the-art and Arabic-specialize","authors_text":"Amr Mohamed, Eric Moulines, Eric Xing, Guokan Shang, Hadi Abdine, Imane Momayiz, Michalis Vazirgiannis, Preslav Nakov, Sofiane Ennadir, Xuguang Ren, Yassine Abbahaddou, Yousef Khoubrane","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T14:56:38Z","title":"Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17912","kind":"arxiv","version":2},"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":"sha256:8487dc4a738fa762205523b306febaca215c91c96d203665673dfb1a5f8b70f1","target":"record","created_at":"2026-07-05T09:34:19Z","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":"06759911a4e845771b980921fda96fce157ef4749df1476d9ca227ea00a94bf5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T14:56:38Z","title_canon_sha256":"42ab4383e5a2c9f4b06b5c6361b6c511cfe4e322f30a13cf6bab425d8d904ffa"},"schema_version":"1.0","source":{"id":"2409.17912","kind":"arxiv","version":2}},"canonical_sha256":"cc00ca2d38cf5df482d7be363958b35e41c66be96e39b986b63435404f082228","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc00ca2d38cf5df482d7be363958b35e41c66be96e39b986b63435404f082228","first_computed_at":"2026-07-05T09:34:19.998508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:19.998508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y0GTH5r70AFyOjRSCkvYMXnmfvYltcWBScqcIZl8C1L4D65FZK9fPSz2v7CE7PR0VqyPClYhdNuTph5rFfQxCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:19.998982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17912","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8487dc4a738fa762205523b306febaca215c91c96d203665673dfb1a5f8b70f1","sha256:7ac6485b8578e5202ebb5d171b442412da56b150c99bac5aa2eb830ed97025ea"],"state_sha256":"61d9708f8c2f37346a92621bbd10787355b5b86a089ca862de7d56828756bd68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XgctzBUXLMwNKNmBU0luaXBw5hBTkbfE1B6EKR9c9F9LMXAhIRoWUAjHhq0xzlJxa+ThraGol0be8NQ36v/qCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:11:26.112401Z","bundle_sha256":"8d5c1f32274bd8b568db18efd595fe4eff92227087b5d51cd004d559c87b65ae"}}