{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FQVFYG4EVBJDLVRWWY4VQAIKBG","short_pith_number":"pith:FQVFYG4E","schema_version":"1.0","canonical_sha256":"2c2a5c1b84a85235d636b63958010a099c1b1ff2f3cc8ea213f845f2e12db9c9","source":{"kind":"arxiv","id":"2306.06800","version":1},"attestation_state":"computed","paper":{"title":"AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abbas Ghaddar, Asaad Alghamdi, Baoxing Huai, Mehdi Rezagholizadeh, Peilun Cheng, Qingrong Xia, Wei Jiang, Xinyu Duan, Yimeng Wu, Yi Zheng, Zhefeng Wang, Zhenhai Wang","submitted_at":"2023-06-11T22:55:18Z","abstract_excerpt":"Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP). In this work, we present AraMUS, the largest Arabic PLM with 11B parameters trained on 529GB of high-quality Arabic textual data. AraMUS achieves state-of-the-art performances on a diverse set of Arabic classification and generative tasks. Moreover, AraMUS shows impressive few-shot learning abilities compared with the best existing Arabic PLMs."},"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":"2306.06800","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-11T22:55:18Z","cross_cats_sorted":[],"title_canon_sha256":"410ce3afbd6b520356f79e5935adde9fb63738cfbf2637048c50570893a8a19c","abstract_canon_sha256":"394423924522f98b5d5a83d895912cb38d33db772eb72aa3c17495ef92ba3aaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:44.260977Z","signature_b64":"lkJEUUEn/pznnZJYF6/PL48BkMAxdlfg6UyxIMm7AHjdJPOocUtD/QgsPJ1S+oRtdELMzepGbficNkgkdzAgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c2a5c1b84a85235d636b63958010a099c1b1ff2f3cc8ea213f845f2e12db9c9","last_reissued_at":"2026-07-05T06:19:44.260430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:44.260430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abbas Ghaddar, Asaad Alghamdi, Baoxing Huai, Mehdi Rezagholizadeh, Peilun Cheng, Qingrong Xia, Wei Jiang, Xinyu Duan, Yimeng Wu, Yi Zheng, Zhefeng Wang, Zhenhai Wang","submitted_at":"2023-06-11T22:55:18Z","abstract_excerpt":"Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP). In this work, we present AraMUS, the largest Arabic PLM with 11B parameters trained on 529GB of high-quality Arabic textual data. AraMUS achieves state-of-the-art performances on a diverse set of Arabic classification and generative tasks. Moreover, AraMUS shows impressive few-shot learning abilities compared with the best existing Arabic PLMs."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06800","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/2306.06800/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":"2306.06800","created_at":"2026-07-05T06:19:44.260505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06800v1","created_at":"2026-07-05T06:19:44.260505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06800","created_at":"2026-07-05T06:19:44.260505+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQVFYG4EVBJD","created_at":"2026-07-05T06:19:44.260505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQVFYG4EVBJDLVRW","created_at":"2026-07-05T06:19:44.260505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQVFYG4E","created_at":"2026-07-05T06:19:44.260505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04277","citing_title":"Arabic Stable LM: Adapting Stable LM 2 1.6B to Arabic","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG","json":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG.json","graph_json":"https://pith.science/api/pith-number/FQVFYG4EVBJDLVRWWY4VQAIKBG/graph.json","events_json":"https://pith.science/api/pith-number/FQVFYG4EVBJDLVRWWY4VQAIKBG/events.json","paper":"https://pith.science/paper/FQVFYG4E"},"agent_actions":{"view_html":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG","download_json":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG.json","view_paper":"https://pith.science/paper/FQVFYG4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06800&json=true","fetch_graph":"https://pith.science/api/pith-number/FQVFYG4EVBJDLVRWWY4VQAIKBG/graph.json","fetch_events":"https://pith.science/api/pith-number/FQVFYG4EVBJDLVRWWY4VQAIKBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG/action/storage_attestation","attest_author":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG/action/author_attestation","sign_citation":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG/action/citation_signature","submit_replication":"https://pith.science/pith/FQVFYG4EVBJDLVRWWY4VQAIKBG/action/replication_record"}},"created_at":"2026-07-05T06:19:44.260505+00:00","updated_at":"2026-07-05T06:19:44.260505+00:00"}