{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OCM4D4QSDKR63DAWCDQI5CSEQR","short_pith_number":"pith:OCM4D4QS","schema_version":"1.0","canonical_sha256":"7099c1f2121aa3ed8c1610e08e8a44847f54a1e2cf05c14155ca817819f488e8","source":{"kind":"arxiv","id":"2406.09559","version":1},"attestation_state":"computed","paper":{"title":"Decoding the Diversity: A Review of the Indic AI Research Landscape","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aman Chadha, Sankalp KJ, Sreyoshi Bhaduri, Tamoghna Roy, Vinija Jain","submitted_at":"2024-06-13T19:55:20Z","abstract_excerpt":"This review paper provides a comprehensive overview of large language model (LLM) research directions within Indic languages. Indic languages are those spoken in the Indian subcontinent, including India, Pakistan, Bangladesh, Sri Lanka, Nepal, and Bhutan, among others. These languages have a rich cultural and linguistic heritage and are spoken by over 1.5 billion people worldwide. With the tremendous market potential and growing demand for natural language processing (NLP) based applications in diverse languages, generative applications for Indic languages pose unique challenges and opportunit"},"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":"2406.09559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T19:55:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d4c0b570e3e152a2422362cd51c4a070f02ad2d2e0e4458e5fbbbf8efd600391","abstract_canon_sha256":"8166f7c608a4251891c9825fbb2e84e53c149a5c1ef679064d70599c0e1f9538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:55.863348Z","signature_b64":"xDNetEwv7PJDlA2SOpl5d/Z4LYMb/rnF9Jz4+E7tJWXd3yEmH2DEGKYaaVWIzsz9KFgzEJY0RJOLHkXcMT/cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7099c1f2121aa3ed8c1610e08e8a44847f54a1e2cf05c14155ca817819f488e8","last_reissued_at":"2026-07-05T08:31:55.862903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:55.862903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoding the Diversity: A Review of the Indic AI Research Landscape","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aman Chadha, Sankalp KJ, Sreyoshi Bhaduri, Tamoghna Roy, Vinija Jain","submitted_at":"2024-06-13T19:55:20Z","abstract_excerpt":"This review paper provides a comprehensive overview of large language model (LLM) research directions within Indic languages. Indic languages are those spoken in the Indian subcontinent, including India, Pakistan, Bangladesh, Sri Lanka, Nepal, and Bhutan, among others. These languages have a rich cultural and linguistic heritage and are spoken by over 1.5 billion people worldwide. With the tremendous market potential and growing demand for natural language processing (NLP) based applications in diverse languages, generative applications for Indic languages pose unique challenges and opportunit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09559","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/2406.09559/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":"2406.09559","created_at":"2026-07-05T08:31:55.862962+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09559v1","created_at":"2026-07-05T08:31:55.862962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09559","created_at":"2026-07-05T08:31:55.862962+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCM4D4QSDKR6","created_at":"2026-07-05T08:31:55.862962+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCM4D4QSDKR63DAW","created_at":"2026-07-05T08:31:55.862962+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCM4D4QS","created_at":"2026-07-05T08:31:55.862962+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06544","citing_title":"Rethinking Indic AI from a Lens of Cultural Heritage Preservation","ref_index":108,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR","json":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR.json","graph_json":"https://pith.science/api/pith-number/OCM4D4QSDKR63DAWCDQI5CSEQR/graph.json","events_json":"https://pith.science/api/pith-number/OCM4D4QSDKR63DAWCDQI5CSEQR/events.json","paper":"https://pith.science/paper/OCM4D4QS"},"agent_actions":{"view_html":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR","download_json":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR.json","view_paper":"https://pith.science/paper/OCM4D4QS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09559&json=true","fetch_graph":"https://pith.science/api/pith-number/OCM4D4QSDKR63DAWCDQI5CSEQR/graph.json","fetch_events":"https://pith.science/api/pith-number/OCM4D4QSDKR63DAWCDQI5CSEQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR/action/storage_attestation","attest_author":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR/action/author_attestation","sign_citation":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR/action/citation_signature","submit_replication":"https://pith.science/pith/OCM4D4QSDKR63DAWCDQI5CSEQR/action/replication_record"}},"created_at":"2026-07-05T08:31:55.862962+00:00","updated_at":"2026-07-05T08:31:55.862962+00:00"}