{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LBXJ5G4DO4TWANLUJTUAXIR6L7","short_pith_number":"pith:LBXJ5G4D","schema_version":"1.0","canonical_sha256":"586e9e9b8377276035744ce80ba23e5fce7fa84d2df475a0f0525f69a9ad9826","source":{"kind":"arxiv","id":"2412.07112","version":1},"attestation_state":"computed","paper":{"title":"Maya: An Instruction Finetuned Multilingual Multimodal Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhipsha Das, Alham Fikri Aji, Anthony Susevski, Ashvanth.S, Bala Krishna S Vegesna, Chen Liu, Drishti Sharma, Genta Indra Winata, Isha Chaturvedi, Karthik Reddy Kanjula, Nahid Alam, Roshan Santhosh, Ryan Sze-Yin Chan, Shayekh Bin Islam, S M Iftekhar Uddin, Snegha A, Snehanshu Mukherjee, Surya Guthikonda, Timothy Chung","submitted_at":"2024-12-10T01:57:17Z","abstract_excerpt":"The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are"},"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":"2412.07112","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T01:57:17Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"10a0640a2d3c4791a0cf9dd90a4a1eeaae28a1e7aca1b18fc8b45aba818b1e05","abstract_canon_sha256":"266244004bf65be8e42e2b977f7956d9041359c49929203d0655f24c952d75ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:04.078288Z","signature_b64":"r3z04s9xYwy8KDy+k82d0rURUAZgbqek/imWpXARYGRfX+7fd8U2iaH82fBlxFDNBytLbgQpej85H/JK0YHIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"586e9e9b8377276035744ce80ba23e5fce7fa84d2df475a0f0525f69a9ad9826","last_reissued_at":"2026-07-05T09:47:04.077811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:04.077811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maya: An Instruction Finetuned Multilingual Multimodal Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Abhipsha Das, Alham Fikri Aji, Anthony Susevski, Ashvanth.S, Bala Krishna S Vegesna, Chen Liu, Drishti Sharma, Genta Indra Winata, Isha Chaturvedi, Karthik Reddy Kanjula, Nahid Alam, Roshan Santhosh, Ryan Sze-Yin Chan, Shayekh Bin Islam, S M Iftekhar Uddin, Snegha A, Snehanshu Mukherjee, Surya Guthikonda, Timothy Chung","submitted_at":"2024-12-10T01:57:17Z","abstract_excerpt":"The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07112","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/2412.07112/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":"2412.07112","created_at":"2026-07-05T09:47:04.077862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07112v1","created_at":"2026-07-05T09:47:04.077862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07112","created_at":"2026-07-05T09:47:04.077862+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBXJ5G4DO4TW","created_at":"2026-07-05T09:47:04.077862+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBXJ5G4DO4TWANLU","created_at":"2026-07-05T09:47:04.077862+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBXJ5G4D","created_at":"2026-07-05T09:47:04.077862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03793","citing_title":"Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17152","citing_title":"Multilingual and Multimodal LLMs in the Wild: Building for Low-Resource Languages","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22123","citing_title":"Multilingual Vision-Language Models, A Survey","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11490","citing_title":"Anthropogenic Regional Adaptation in Multimodal Vision-Language Model","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7","json":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7.json","graph_json":"https://pith.science/api/pith-number/LBXJ5G4DO4TWANLUJTUAXIR6L7/graph.json","events_json":"https://pith.science/api/pith-number/LBXJ5G4DO4TWANLUJTUAXIR6L7/events.json","paper":"https://pith.science/paper/LBXJ5G4D"},"agent_actions":{"view_html":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7","download_json":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7.json","view_paper":"https://pith.science/paper/LBXJ5G4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07112&json=true","fetch_graph":"https://pith.science/api/pith-number/LBXJ5G4DO4TWANLUJTUAXIR6L7/graph.json","fetch_events":"https://pith.science/api/pith-number/LBXJ5G4DO4TWANLUJTUAXIR6L7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7/action/storage_attestation","attest_author":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7/action/author_attestation","sign_citation":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7/action/citation_signature","submit_replication":"https://pith.science/pith/LBXJ5G4DO4TWANLUJTUAXIR6L7/action/replication_record"}},"created_at":"2026-07-05T09:47:04.077862+00:00","updated_at":"2026-07-05T09:47:04.077862+00:00"}