{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OR4MYZ2PPQANWWGRAJORPIOQJP","short_pith_number":"pith:OR4MYZ2P","schema_version":"1.0","canonical_sha256":"7478cc674f7c00db58d1025d17a1d04bfae57377babcd5e3cdfe9367c93dda9b","source":{"kind":"arxiv","id":"2201.11391","version":2},"attestation_state":"computed","paper":{"title":"Prabhupadavani: A Code-mixed Speech Translation Data for 25 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ayush Daksh, Jivnesh Sandhan, Laxmidhar Behera, Om Adideva Paranjay, Pawan Goyal","submitted_at":"2022-01-27T09:24:36Z","abstract_excerpt":"Nowadays, the interest in code-mixing has become ubiquitous in Natural Language Processing (NLP); however, not much attention has been given to address this phenomenon for Speech Translation (ST) task. This can be solely attributed to the lack of code-mixed ST task labelled data. Thus, we introduce Prabhupadavani, which is a multilingual code-mixed ST dataset for 25 languages. It is multi-domain, covers ten language families, containing 94 hours of speech by 130+ speakers, manually aligned with corresponding text in the target language. The Prabhupadavani is about Vedic culture and heritage fr"},"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":"2201.11391","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-27T09:24:36Z","cross_cats_sorted":[],"title_canon_sha256":"1ae4f5d5c1ff6931937dee5c9069d3e4208572d8915e5ef312dec5f7b64afa7a","abstract_canon_sha256":"35b788dddf3acaf2fdaff565cb5063733704092848695f0c72574a0bd91c6d50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:18.065491Z","signature_b64":"PGFYFBS063nTPPWDtVuhVCX7H+wRdor9E1YIC8hlXOp83wrUxZtEw6KOauN16Bl3gpdhFaqSM/MzI9sobZgiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7478cc674f7c00db58d1025d17a1d04bfae57377babcd5e3cdfe9367c93dda9b","last_reissued_at":"2026-07-05T04:54:18.065111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:18.065111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prabhupadavani: A Code-mixed Speech Translation Data for 25 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ayush Daksh, Jivnesh Sandhan, Laxmidhar Behera, Om Adideva Paranjay, Pawan Goyal","submitted_at":"2022-01-27T09:24:36Z","abstract_excerpt":"Nowadays, the interest in code-mixing has become ubiquitous in Natural Language Processing (NLP); however, not much attention has been given to address this phenomenon for Speech Translation (ST) task. This can be solely attributed to the lack of code-mixed ST task labelled data. Thus, we introduce Prabhupadavani, which is a multilingual code-mixed ST dataset for 25 languages. It is multi-domain, covers ten language families, containing 94 hours of speech by 130+ speakers, manually aligned with corresponding text in the target language. The Prabhupadavani is about Vedic culture and heritage fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11391","kind":"arxiv","version":2},"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/2201.11391/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":"2201.11391","created_at":"2026-07-05T04:54:18.065168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.11391v2","created_at":"2026-07-05T04:54:18.065168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11391","created_at":"2026-07-05T04:54:18.065168+00:00"},{"alias_kind":"pith_short_12","alias_value":"OR4MYZ2PPQAN","created_at":"2026-07-05T04:54:18.065168+00:00"},{"alias_kind":"pith_short_16","alias_value":"OR4MYZ2PPQANWWGR","created_at":"2026-07-05T04:54:18.065168+00:00"},{"alias_kind":"pith_short_8","alias_value":"OR4MYZ2P","created_at":"2026-07-05T04:54:18.065168+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/OR4MYZ2PPQANWWGRAJORPIOQJP","json":"https://pith.science/pith/OR4MYZ2PPQANWWGRAJORPIOQJP.json","graph_json":"https://pith.science/api/pith-number/OR4MYZ2PPQANWWGRAJORPIOQJP/graph.json","events_json":"https://pith.science/api/pith-number/OR4MYZ2PPQANWWGRAJORPIOQJP/events.json","paper":"https://pith.science/paper/OR4MYZ2P"},"agent_actions":{"view_html":"https://pith.science/pith/OR4MYZ2PPQANWWGRAJORPIOQJP","download_json":"https://pith.science/pith/OR4MYZ2PPQANWWGRAJORPIOQJP.json","view_paper":"https://pith.science/paper/OR4MYZ2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.11391&json=true","fetch_graph":"https://pith.science/api/pith-number/OR4MYZ2PPQANWWGRAJORPIOQJP/graph.json","fetch_events":"https://pith.science/api/pith-number/OR4MYZ2PPQANWWGRAJORPIOQJP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OR4MYZ2PPQANWWGRAJORPIOQJP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OR4MYZ2PPQANWWGRAJORPIOQJP/action/storage_attestation","attest_author":"https://pith.science/pith/OR4MYZ2PPQANWWGRAJORPIOQJP/action/author_attestation","sign_citation":"https://pith.science/pith/OR4MYZ2PPQANWWGRAJORPIOQJP/action/citation_signature","submit_replication":"https://pith.science/pith/OR4MYZ2PPQANWWGRAJORPIOQJP/action/replication_record"}},"created_at":"2026-07-05T04:54:18.065168+00:00","updated_at":"2026-07-05T04:54:18.065168+00:00"}