{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3ZNL2RXCE5ATPAFYNPOIK6HVM5","short_pith_number":"pith:3ZNL2RXC","schema_version":"1.0","canonical_sha256":"de5abd46e227413780b86bdc8578f56761cefcad05b984aaa93d3169d5a962be","source":{"kind":"arxiv","id":"2603.28714","version":3},"attestation_state":"computed","paper":{"title":"VAANI: Capturing the language landscape for an inclusive digital India","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Abhayjeet Singh, Agneedh Basu, Amrita Kamat, Dinesh Tewari, Harsh Dhand, Nihar Desai, Partha Talukdar, Pavan Kumar J, Pranav D Bhat, Prasanta Kumar Ghosh, Raghu Dharmaraju, Raj Acharya, Ritika Gupta, Sathvik Udupa, Saurabh Kumar, Shikhar Vashishth, Sujith Pulikodan, Sukhwinder Singh, Sumit Sharma, Visruth Sanka","submitted_at":"2026-03-30T17:30:53Z","abstract_excerpt":"Voice based technologies have the potential to bridge digital accessibility gaps; however, existing datasets fail to capture the linguistic and regional diversity of Indic languages. We present Project VAANI, a large scale multimodal dataset designed to represent India's linguistic landscape across 165 districts. Speech data is collected using image based prompts to elicit spontaneous responses, while images are curated through a separate pipeline covering diverse themes across regions. The dataset undergoes a rigorous multi stage quality control process, combining automated and manual evaluat"},"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":"2603.28714","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-03-30T17:30:53Z","cross_cats_sorted":[],"title_canon_sha256":"67cc8027c59d35a47cf3f84b17f26d62dac3e0a1cd167c7f2e30940aa23b6a21","abstract_canon_sha256":"bf721aba10ec3ab902fa0d264bf9e324ce1f0142c37b613f2992def7a0f075e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:08.400418Z","signature_b64":"csmMi+E1qkP8f0UlNC5ifhyRztpx1UeiA/AGRu8Wj8KPZr7N744Iz6tqpDcPi0gylfC5+/A3pIM4wrJjqqASCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de5abd46e227413780b86bdc8578f56761cefcad05b984aaa93d3169d5a962be","last_reissued_at":"2026-05-28T01:04:08.399686Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:08.399686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VAANI: Capturing the language landscape for an inclusive digital India","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Abhayjeet Singh, Agneedh Basu, Amrita Kamat, Dinesh Tewari, Harsh Dhand, Nihar Desai, Partha Talukdar, Pavan Kumar J, Pranav D Bhat, Prasanta Kumar Ghosh, Raghu Dharmaraju, Raj Acharya, Ritika Gupta, Sathvik Udupa, Saurabh Kumar, Shikhar Vashishth, Sujith Pulikodan, Sukhwinder Singh, Sumit Sharma, Visruth Sanka","submitted_at":"2026-03-30T17:30:53Z","abstract_excerpt":"Voice based technologies have the potential to bridge digital accessibility gaps; however, existing datasets fail to capture the linguistic and regional diversity of Indic languages. We present Project VAANI, a large scale multimodal dataset designed to represent India's linguistic landscape across 165 districts. Speech data is collected using image based prompts to elicit spontaneous responses, while images are curated through a separate pipeline covering diverse themes across regions. The dataset undergoes a rigorous multi stage quality control process, combining automated and manual evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.28714","kind":"arxiv","version":3},"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/2603.28714/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":"2603.28714","created_at":"2026-05-28T01:04:08.399778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.28714v3","created_at":"2026-05-28T01:04:08.399778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.28714","created_at":"2026-05-28T01:04:08.399778+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZNL2RXCE5AT","created_at":"2026-05-28T01:04:08.399778+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZNL2RXCE5ATPAFY","created_at":"2026-05-28T01:04:08.399778+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZNL2RXC","created_at":"2026-05-28T01:04:08.399778+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/3ZNL2RXCE5ATPAFYNPOIK6HVM5","json":"https://pith.science/pith/3ZNL2RXCE5ATPAFYNPOIK6HVM5.json","graph_json":"https://pith.science/api/pith-number/3ZNL2RXCE5ATPAFYNPOIK6HVM5/graph.json","events_json":"https://pith.science/api/pith-number/3ZNL2RXCE5ATPAFYNPOIK6HVM5/events.json","paper":"https://pith.science/paper/3ZNL2RXC"},"agent_actions":{"view_html":"https://pith.science/pith/3ZNL2RXCE5ATPAFYNPOIK6HVM5","download_json":"https://pith.science/pith/3ZNL2RXCE5ATPAFYNPOIK6HVM5.json","view_paper":"https://pith.science/paper/3ZNL2RXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.28714&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZNL2RXCE5ATPAFYNPOIK6HVM5/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZNL2RXCE5ATPAFYNPOIK6HVM5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZNL2RXCE5ATPAFYNPOIK6HVM5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZNL2RXCE5ATPAFYNPOIK6HVM5/action/storage_attestation","attest_author":"https://pith.science/pith/3ZNL2RXCE5ATPAFYNPOIK6HVM5/action/author_attestation","sign_citation":"https://pith.science/pith/3ZNL2RXCE5ATPAFYNPOIK6HVM5/action/citation_signature","submit_replication":"https://pith.science/pith/3ZNL2RXCE5ATPAFYNPOIK6HVM5/action/replication_record"}},"created_at":"2026-05-28T01:04:08.399778+00:00","updated_at":"2026-05-28T01:04:08.399778+00:00"}