{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SATFN2H76O46VZOQTBFQGJ2HEV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"11a943b876030052440eaa738e22aa5f79f78827c67ae43dc84f093a531b73b1","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","title_canon_sha256":"46a1957b0fe4aed7afb8638938fea9af174dcffe9577eb92211f714808171897"},"schema_version":"1.0","source":{"id":"2501.00029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00029","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00029v1","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00029","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"SATFN2H76O46","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_16","alias_value":"SATFN2H76O46VZOQ","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_8","alias_value":"SATFN2H7","created_at":"2026-07-05T09:55:37Z"}],"graph_snapshots":[{"event_id":"sha256:ee3b2ab521091a5af32f6428aa990af4500da0b06d1e2379ce939038ff7ed56a","target":"graph","created_at":"2026-07-05T09:55:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.00029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Pranav Gupta","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","title":"A Breadth-First Catalog of Text Processing, Speech Processing and Multimodal Research in South Asian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00029","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc82b377d13ae4286dad12638ee7ba4ad8657a19e98fd2e8e841a4a5acf292cb","target":"record","created_at":"2026-07-05T09:55:37Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"11a943b876030052440eaa738e22aa5f79f78827c67ae43dc84f093a531b73b1","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","title_canon_sha256":"46a1957b0fe4aed7afb8638938fea9af174dcffe9577eb92211f714808171897"},"schema_version":"1.0","source":{"id":"2501.00029","kind":"arxiv","version":1}},"canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","first_computed_at":"2026-07-05T09:55:37.890629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:37.890629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"foQyH6CA3pbYWgImxtlRnlgxzRlzLjIeM11fS8p5AdLzmgCvvW978MkBEehxxwyXExP73OCuan2owb+B22bZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:37.891093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc82b377d13ae4286dad12638ee7ba4ad8657a19e98fd2e8e841a4a5acf292cb","sha256:ee3b2ab521091a5af32f6428aa990af4500da0b06d1e2379ce939038ff7ed56a"],"state_sha256":"5d6f63f755be86cb8e62a9a5ad1dc765818159031ad4cddfb072b956f9879df9"}