{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4W43GXA6BNKWATF266ZZEXEILT","short_pith_number":"pith:4W43GXA6","schema_version":"1.0","canonical_sha256":"e5b9b35c1e0b55604cbaf7b3925c885cf1b9849f819b0610d36c4e9ea603f982","source":{"kind":"arxiv","id":"2502.15392","version":1},"attestation_state":"computed","paper":{"title":"Chitrarth: Bridging Vision and Language for a Billion People","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Abhinav Ravi, Akshat Patidar, Ali Faraz, Anagha Bhangare, Ayush Tarun, Chandra Khatri, Praveen Kumar Pokala, Raja Kolla, Shaharukh Khan, Shubham Agarwal","submitted_at":"2025-02-21T11:38:40Z","abstract_excerpt":"Recent multimodal foundation models are primarily trained on English or high resource European language data, which hinders their applicability to other medium and low-resource languages. To address this limitation, we introduce Chitrarth (Chitra: Image; Artha: Meaning), an inclusive Vision-Language Model (VLM), specifically targeting the rich linguistic diversity and visual reasoning across 10 prominent Indian languages. Our model effectively integrates a state-of-the-art (SOTA) multilingual Large Language Model (LLM) with a vision module, primarily trained on multilingual image-text data. Fu"},"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":"2502.15392","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-21T11:38:40Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"7e41937b08c96992f0ef37a5aaee52b62bc6e5db5e929e0cf2d6525a02c6b5af","abstract_canon_sha256":"3375eff664660b0db427cbf2316ba9ebf912fb6a94f693db5c641463496f9ff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:01.179637Z","signature_b64":"/WViXriLhiVZfVL34oPSg64Qpd11FQdp4vZbBjprtba/HGWV8wuODrZnVNLTu7VHTnp3jexFDmwx8dS2I4uUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5b9b35c1e0b55604cbaf7b3925c885cf1b9849f819b0610d36c4e9ea603f982","last_reissued_at":"2026-07-05T10:18:01.179011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:01.179011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chitrarth: Bridging Vision and Language for a Billion People","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Abhinav Ravi, Akshat Patidar, Ali Faraz, Anagha Bhangare, Ayush Tarun, Chandra Khatri, Praveen Kumar Pokala, Raja Kolla, Shaharukh Khan, Shubham Agarwal","submitted_at":"2025-02-21T11:38:40Z","abstract_excerpt":"Recent multimodal foundation models are primarily trained on English or high resource European language data, which hinders their applicability to other medium and low-resource languages. To address this limitation, we introduce Chitrarth (Chitra: Image; Artha: Meaning), an inclusive Vision-Language Model (VLM), specifically targeting the rich linguistic diversity and visual reasoning across 10 prominent Indian languages. Our model effectively integrates a state-of-the-art (SOTA) multilingual Large Language Model (LLM) with a vision module, primarily trained on multilingual image-text data. Fu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15392","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/2502.15392/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":"2502.15392","created_at":"2026-07-05T10:18:01.179064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15392v1","created_at":"2026-07-05T10:18:01.179064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15392","created_at":"2026-07-05T10:18:01.179064+00:00"},{"alias_kind":"pith_short_12","alias_value":"4W43GXA6BNKW","created_at":"2026-07-05T10:18:01.179064+00:00"},{"alias_kind":"pith_short_16","alias_value":"4W43GXA6BNKWATF2","created_at":"2026-07-05T10:18:01.179064+00:00"},{"alias_kind":"pith_short_8","alias_value":"4W43GXA6","created_at":"2026-07-05T10:18:01.179064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT","json":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT.json","graph_json":"https://pith.science/api/pith-number/4W43GXA6BNKWATF266ZZEXEILT/graph.json","events_json":"https://pith.science/api/pith-number/4W43GXA6BNKWATF266ZZEXEILT/events.json","paper":"https://pith.science/paper/4W43GXA6"},"agent_actions":{"view_html":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT","download_json":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT.json","view_paper":"https://pith.science/paper/4W43GXA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15392&json=true","fetch_graph":"https://pith.science/api/pith-number/4W43GXA6BNKWATF266ZZEXEILT/graph.json","fetch_events":"https://pith.science/api/pith-number/4W43GXA6BNKWATF266ZZEXEILT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT/action/storage_attestation","attest_author":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT/action/author_attestation","sign_citation":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT/action/citation_signature","submit_replication":"https://pith.science/pith/4W43GXA6BNKWATF266ZZEXEILT/action/replication_record"}},"created_at":"2026-07-05T10:18:01.179064+00:00","updated_at":"2026-07-05T10:18:01.179064+00:00"}