{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FE3YFHWUXVWSGGQXCGOLWYE3KO","short_pith_number":"pith:FE3YFHWU","schema_version":"1.0","canonical_sha256":"2937829ed4bd6d231a17119cbb609b53847de63416fbab2756dcacd5473f0583","source":{"kind":"arxiv","id":"2403.01031","version":2},"attestation_state":"computed","paper":{"title":"Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, El Moatez Billah Nagoudi, Fakhraddin Alwajih, Gagan Bhatia, Muhammad Abdul-Mageed","submitted_at":"2024-03-01T23:38:02Z","abstract_excerpt":"Multimodal large language models (MLLMs) have proven effective in a wide range of tasks requiring complex reasoning and linguistic comprehension. However, due to a lack of high-quality multimodal resources in languages other than English, success of MLLMs remains relatively limited to English-based settings. This poses significant challenges in developing comparable models for other languages, including even those with large speaker populations such as Arabic. To alleviate this challenge, we introduce a comprehensive family of Arabic MLLMs, dubbed \\textit{Peacock}, with strong vision and langu"},"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":"2403.01031","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T23:38:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"55d31aa5cce858db319c5d573e39a8c601610ad80354c50ff91bad3ea5f46bd1","abstract_canon_sha256":"f62bd8ab22df485d14962c1054b6f7841d74272e90b34030665a9d1af1e96ccd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:55.724668Z","signature_b64":"7ZSpxi4i13PDOqao1Bq2/pPORKQ2eV1w+StevMBd562JFL//Hp9ZxQKRcOUTCtKx4oKsuIv3WWofic41v3//DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2937829ed4bd6d231a17119cbb609b53847de63416fbab2756dcacd5473f0583","last_reissued_at":"2026-07-05T08:22:55.724238Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:55.724238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Peacock: A Family of Arabic Multimodal Large Language Models and Benchmarks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Mohamed, El Moatez Billah Nagoudi, Fakhraddin Alwajih, Gagan Bhatia, Muhammad Abdul-Mageed","submitted_at":"2024-03-01T23:38:02Z","abstract_excerpt":"Multimodal large language models (MLLMs) have proven effective in a wide range of tasks requiring complex reasoning and linguistic comprehension. However, due to a lack of high-quality multimodal resources in languages other than English, success of MLLMs remains relatively limited to English-based settings. This poses significant challenges in developing comparable models for other languages, including even those with large speaker populations such as Arabic. To alleviate this challenge, we introduce a comprehensive family of Arabic MLLMs, dubbed \\textit{Peacock}, with strong vision and langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01031","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/2403.01031/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":"2403.01031","created_at":"2026-07-05T08:22:55.724299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01031v2","created_at":"2026-07-05T08:22:55.724299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01031","created_at":"2026-07-05T08:22:55.724299+00:00"},{"alias_kind":"pith_short_12","alias_value":"FE3YFHWUXVWS","created_at":"2026-07-05T08:22:55.724299+00:00"},{"alias_kind":"pith_short_16","alias_value":"FE3YFHWUXVWSGGQX","created_at":"2026-07-05T08:22:55.724299+00:00"},{"alias_kind":"pith_short_8","alias_value":"FE3YFHWU","created_at":"2026-07-05T08:22:55.724299+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02295","citing_title":"QARI-OCR: High-Fidelity Arabic Text Recognition through Multimodal Large Language Model Adaptation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO","json":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO.json","graph_json":"https://pith.science/api/pith-number/FE3YFHWUXVWSGGQXCGOLWYE3KO/graph.json","events_json":"https://pith.science/api/pith-number/FE3YFHWUXVWSGGQXCGOLWYE3KO/events.json","paper":"https://pith.science/paper/FE3YFHWU"},"agent_actions":{"view_html":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO","download_json":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO.json","view_paper":"https://pith.science/paper/FE3YFHWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01031&json=true","fetch_graph":"https://pith.science/api/pith-number/FE3YFHWUXVWSGGQXCGOLWYE3KO/graph.json","fetch_events":"https://pith.science/api/pith-number/FE3YFHWUXVWSGGQXCGOLWYE3KO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO/action/storage_attestation","attest_author":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO/action/author_attestation","sign_citation":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO/action/citation_signature","submit_replication":"https://pith.science/pith/FE3YFHWUXVWSGGQXCGOLWYE3KO/action/replication_record"}},"created_at":"2026-07-05T08:22:55.724299+00:00","updated_at":"2026-07-05T08:22:55.724299+00:00"}