{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:62AXTH25FIUVR7GYWW3RFYR3HG","short_pith_number":"pith:62AXTH25","schema_version":"1.0","canonical_sha256":"f681799f5d2a2958fcd8b5b712e23b39972a8274ee805f5e5046d21ecd89fb3a","source":{"kind":"arxiv","id":"2607.23808","version":1},"attestation_state":"computed","paper":{"title":"Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Mehndiratta, Deovrat Mehendale, Dhruv Rathi, Kaushal Bhogale, Mitesh M. Khapra","submitted_at":"2026-07-26T19:12:39Z","abstract_excerpt":"In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India. This corpus comprises approximately 108 hours of natural multi-speaker audio from near-field meetings, far-field recordings, and in-the-wild audios. All annotations are human-corrected with time-aligned speaker attributed transcriptions. The dataset captures conversational nuance prevalent in Indian speech, such as English code-mixing, dialectal variation, and frequent speaker overlap. To establish a baseline for joint ASR and diarization capabilities we eva"},"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":"2607.23808","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-26T19:12:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af4a132834be62bf0ef76c9bd758527037590fee29dce40fccf1c31242f3e76f","abstract_canon_sha256":"6d313796ba2f582765107b16f93498d2c7effe65acd578d080ef3f00f2b2852d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:12.203275Z","signature_b64":"qy1dRs3CQWfPCjpTQOMYdVKDGOPOELctS+Symk3gDuxHGbgeegQ6Q/WtGhw64vZsV5FU4QSB4vKlJIEaNilaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f681799f5d2a2958fcd8b5b712e23b39972a8274ee805f5e5046d21ecd89fb3a","last_reissued_at":"2026-07-28T01:23:12.202511Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:12.202511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Indic DiarBench: A Multilingual Joint Diarization and ASR Benchmark for Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Mehndiratta, Deovrat Mehendale, Dhruv Rathi, Kaushal Bhogale, Mitesh M. Khapra","submitted_at":"2026-07-26T19:12:39Z","abstract_excerpt":"In this work, we introduce Indic DiarBench, a speaker diarization and ASR benchmark dataset spanning all 22 scheduled languages of India. This corpus comprises approximately 108 hours of natural multi-speaker audio from near-field meetings, far-field recordings, and in-the-wild audios. All annotations are human-corrected with time-aligned speaker attributed transcriptions. The dataset captures conversational nuance prevalent in Indian speech, such as English code-mixing, dialectal variation, and frequent speaker overlap. To establish a baseline for joint ASR and diarization capabilities we eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23808","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/2607.23808/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":"2607.23808","created_at":"2026-07-28T01:23:12.202910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23808v1","created_at":"2026-07-28T01:23:12.202910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23808","created_at":"2026-07-28T01:23:12.202910+00:00"},{"alias_kind":"pith_short_12","alias_value":"62AXTH25FIUV","created_at":"2026-07-28T01:23:12.202910+00:00"},{"alias_kind":"pith_short_16","alias_value":"62AXTH25FIUVR7GY","created_at":"2026-07-28T01:23:12.202910+00:00"},{"alias_kind":"pith_short_8","alias_value":"62AXTH25","created_at":"2026-07-28T01:23:12.202910+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/62AXTH25FIUVR7GYWW3RFYR3HG","json":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG.json","graph_json":"https://pith.science/api/pith-number/62AXTH25FIUVR7GYWW3RFYR3HG/graph.json","events_json":"https://pith.science/api/pith-number/62AXTH25FIUVR7GYWW3RFYR3HG/events.json","paper":"https://pith.science/paper/62AXTH25"},"agent_actions":{"view_html":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG","download_json":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG.json","view_paper":"https://pith.science/paper/62AXTH25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23808&json=true","fetch_graph":"https://pith.science/api/pith-number/62AXTH25FIUVR7GYWW3RFYR3HG/graph.json","fetch_events":"https://pith.science/api/pith-number/62AXTH25FIUVR7GYWW3RFYR3HG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/action/storage_attestation","attest_author":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/action/author_attestation","sign_citation":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/action/citation_signature","submit_replication":"https://pith.science/pith/62AXTH25FIUVR7GYWW3RFYR3HG/action/replication_record"}},"created_at":"2026-07-28T01:23:12.202910+00:00","updated_at":"2026-07-28T01:23:12.202910+00:00"}