{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SATFN2H76O46VZOQTBFQGJ2HEV","short_pith_number":"pith:SATFN2H7","schema_version":"1.0","canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","source":{"kind":"arxiv","id":"2501.00029","version":1},"attestation_state":"computed","paper":{"title":"A Breadth-First Catalog of Text Processing, Speech Processing and Multimodal Research in South Asian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pranav Gupta","submitted_at":"2024-12-20T20:08:48Z","abstract_excerpt":"We review the recent literature (January 2022- October 2024) in South Asian languages on text-based language processing, multimodal models, and speech processing, and provide a spotlight analysis focused on 21 low-resource South Asian languages, namely Saraiki, Assamese, Balochi, Bhojpuri, Bodo, Burmese, Chhattisgarhi, Dhivehi, Gujarati, Kannada, Kashmiri, Konkani, Khasi, Malayalam, Meitei, Nepali, Odia, Pashto, Rajasthani, Sindhi, and Telugu. We identify trends, challenges, and future research directions, using a step-wise approach that incorporates relevance classification and clustering bas"},"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":"2501.00029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"46a1957b0fe4aed7afb8638938fea9af174dcffe9577eb92211f714808171897","abstract_canon_sha256":"11a943b876030052440eaa738e22aa5f79f78827c67ae43dc84f093a531b73b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:37.891093Z","signature_b64":"foQyH6CA3pbYWgImxtlRnlgxzRlzLjIeM11fS8p5AdLzmgCvvW978MkBEehxxwyXExP73OCuan2owb+B22bZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","last_reissued_at":"2026-07-05T09:55:37.890629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:37.890629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Breadth-First Catalog of Text Processing, Speech Processing and Multimodal Research in South Asian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pranav Gupta","submitted_at":"2024-12-20T20:08:48Z","abstract_excerpt":"We review the recent literature (January 2022- October 2024) in South Asian languages on text-based language processing, multimodal models, and speech processing, and provide a spotlight analysis focused on 21 low-resource South Asian languages, namely Saraiki, Assamese, Balochi, Bhojpuri, Bodo, Burmese, Chhattisgarhi, Dhivehi, Gujarati, Kannada, Kashmiri, Konkani, Khasi, Malayalam, Meitei, Nepali, Odia, Pashto, Rajasthani, Sindhi, and Telugu. We identify trends, challenges, and future research directions, using a step-wise approach that incorporates relevance classification and clustering bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00029","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/2501.00029/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":"2501.00029","created_at":"2026-07-05T09:55:37.890706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00029v1","created_at":"2026-07-05T09:55:37.890706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00029","created_at":"2026-07-05T09:55:37.890706+00:00"},{"alias_kind":"pith_short_12","alias_value":"SATFN2H76O46","created_at":"2026-07-05T09:55:37.890706+00:00"},{"alias_kind":"pith_short_16","alias_value":"SATFN2H76O46VZOQ","created_at":"2026-07-05T09:55:37.890706+00:00"},{"alias_kind":"pith_short_8","alias_value":"SATFN2H7","created_at":"2026-07-05T09:55:37.890706+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/SATFN2H76O46VZOQTBFQGJ2HEV","json":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV.json","graph_json":"https://pith.science/api/pith-number/SATFN2H76O46VZOQTBFQGJ2HEV/graph.json","events_json":"https://pith.science/api/pith-number/SATFN2H76O46VZOQTBFQGJ2HEV/events.json","paper":"https://pith.science/paper/SATFN2H7"},"agent_actions":{"view_html":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV","download_json":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV.json","view_paper":"https://pith.science/paper/SATFN2H7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00029&json=true","fetch_graph":"https://pith.science/api/pith-number/SATFN2H76O46VZOQTBFQGJ2HEV/graph.json","fetch_events":"https://pith.science/api/pith-number/SATFN2H76O46VZOQTBFQGJ2HEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/action/storage_attestation","attest_author":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/action/author_attestation","sign_citation":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/action/citation_signature","submit_replication":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/action/replication_record"}},"created_at":"2026-07-05T09:55:37.890706+00:00","updated_at":"2026-07-05T09:55:37.890706+00:00"}