{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M7KYNN4M75CBPS73KTNPEBSYGW","short_pith_number":"pith:M7KYNN4M","schema_version":"1.0","canonical_sha256":"67d586b78cff4417cbfb54daf206583595d623387e949e3d4cd7b423803e9de0","source":{"kind":"arxiv","id":"2606.26901","version":1},"attestation_state":"computed","paper":{"title":"SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhishek Manoharan, Animesh Mukherjee, Astut Kurariya, Diptadhi Mukherjee, Koustav Rudra, Lekhansh Shukla, Prabhat Chand, Prakrithi Shivaprakash, Pratima Murthy, Subham Kumar","submitted_at":"2026-06-25T11:34:07Z","abstract_excerpt":"Automatic Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in multilingual and demographically diverse Indian healthcare context remains largely unknown. In this study, we first conduct the systematic audit of ASR performance on real-world psychiatric interview data spanning Kannada, Hindi and Indian English, comparing eight state-of-the-art models including IndicWhisper, WhisperLargeV3, Sarvam, GoogleS2T, Gemma3n, OmniLingual, Vaani, and Gemini. Our results reveal substantial variability across models and languages, with some systems performin"},"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":"2606.26901","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-25T11:34:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4351229abcbfd39bbed64ef7da6e6ef33894f4ac60a7e14303eff78fea210a66","abstract_canon_sha256":"f6c9f290af918fcac3dfc187d711ca1e5e72dc593a3f18f0005954980a35a7fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:03.509519Z","signature_b64":"xQ37arJFmMGyIyERiL1RjvUDs2Kwel3nO4YULgpulJqjH14E5PrtPw7AivqFrqCaSekXHTgN4OBcreLzgnN2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d586b78cff4417cbfb54daf206583595d623387e949e3d4cd7b423803e9de0","last_reissued_at":"2026-06-26T01:16:03.509097Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:03.509097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SamaVaani: Auditing and Debiasing Multilingual Clinical ASR for Indian Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abhishek Manoharan, Animesh Mukherjee, Astut Kurariya, Diptadhi Mukherjee, Koustav Rudra, Lekhansh Shukla, Prabhat Chand, Prakrithi Shivaprakash, Pratima Murthy, Subham Kumar","submitted_at":"2026-06-25T11:34:07Z","abstract_excerpt":"Automatic Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in multilingual and demographically diverse Indian healthcare context remains largely unknown. In this study, we first conduct the systematic audit of ASR performance on real-world psychiatric interview data spanning Kannada, Hindi and Indian English, comparing eight state-of-the-art models including IndicWhisper, WhisperLargeV3, Sarvam, GoogleS2T, Gemma3n, OmniLingual, Vaani, and Gemini. Our results reveal substantial variability across models and languages, with some systems performin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26901","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/2606.26901/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":"2606.26901","created_at":"2026-06-26T01:16:03.509157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26901v1","created_at":"2026-06-26T01:16:03.509157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26901","created_at":"2026-06-26T01:16:03.509157+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7KYNN4M75CB","created_at":"2026-06-26T01:16:03.509157+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7KYNN4M75CBPS73","created_at":"2026-06-26T01:16:03.509157+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7KYNN4M","created_at":"2026-06-26T01:16:03.509157+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/M7KYNN4M75CBPS73KTNPEBSYGW","json":"https://pith.science/pith/M7KYNN4M75CBPS73KTNPEBSYGW.json","graph_json":"https://pith.science/api/pith-number/M7KYNN4M75CBPS73KTNPEBSYGW/graph.json","events_json":"https://pith.science/api/pith-number/M7KYNN4M75CBPS73KTNPEBSYGW/events.json","paper":"https://pith.science/paper/M7KYNN4M"},"agent_actions":{"view_html":"https://pith.science/pith/M7KYNN4M75CBPS73KTNPEBSYGW","download_json":"https://pith.science/pith/M7KYNN4M75CBPS73KTNPEBSYGW.json","view_paper":"https://pith.science/paper/M7KYNN4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26901&json=true","fetch_graph":"https://pith.science/api/pith-number/M7KYNN4M75CBPS73KTNPEBSYGW/graph.json","fetch_events":"https://pith.science/api/pith-number/M7KYNN4M75CBPS73KTNPEBSYGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7KYNN4M75CBPS73KTNPEBSYGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7KYNN4M75CBPS73KTNPEBSYGW/action/storage_attestation","attest_author":"https://pith.science/pith/M7KYNN4M75CBPS73KTNPEBSYGW/action/author_attestation","sign_citation":"https://pith.science/pith/M7KYNN4M75CBPS73KTNPEBSYGW/action/citation_signature","submit_replication":"https://pith.science/pith/M7KYNN4M75CBPS73KTNPEBSYGW/action/replication_record"}},"created_at":"2026-06-26T01:16:03.509157+00:00","updated_at":"2026-06-26T01:16:03.509157+00:00"}