{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OXAC2W3MH7L5I2H72WFU27MUTV","short_pith_number":"pith:OXAC2W3M","schema_version":"1.0","canonical_sha256":"75c02d5b6c3fd7d468ffd58b4d7d949d6773eca079b9a06945bf6adb4a1e97f5","source":{"kind":"arxiv","id":"2605.17846","version":1},"attestation_state":"computed","paper":{"title":"UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Attia Nafees ul Haq, Chunjiang He, Jingbin Hu, Lei Xie, Zeyu Zhu","submitted_at":"2026-05-18T04:40:31Z","abstract_excerpt":"Despite 230 million speakers, Urdu remains critically under-resourced in speech technology. We introduce UrduSpeech: a large high-fidelity Urdu corpus comprising 156 hours of audio with 12-dimension paralinguistic metadata, encompassing US-Std, US-CS, US-EngPk. To address Right-to-Left script constraints and frequent code-switching, we developed UrduSpeech, a LLM-driven pipeline to curate data across 12 diverse categories, including news, drama, and rare literary forms like Bait-Bazi. We also release a 9-hour US-Benchmark set, manually corrected by native annotators to serve as a standard. Hum"},"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":"2605.17846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-18T04:40:31Z","cross_cats_sorted":[],"title_canon_sha256":"2f0d8071a23cd141ef2fa0bd62de4f21c635b6249c70126d943aeb7585a8ce47","abstract_canon_sha256":"40bb46b375683467d1e3199e2acd70dcba48aa4e773722c9f8d67ef6c45dde80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:01.466182Z","signature_b64":"C7h9gU0qSiImD/FyKMvWJDYncRtBa3JiZZJoBwwB+NWxODKplkeZu3/+hoUduWOm9cIN+XPMtFj95L7ezzdIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75c02d5b6c3fd7d468ffd58b4d7d949d6773eca079b9a06945bf6adb4a1e97f5","last_reissued_at":"2026-05-20T00:05:01.465377Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:01.465377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Attia Nafees ul Haq, Chunjiang He, Jingbin Hu, Lei Xie, Zeyu Zhu","submitted_at":"2026-05-18T04:40:31Z","abstract_excerpt":"Despite 230 million speakers, Urdu remains critically under-resourced in speech technology. We introduce UrduSpeech: a large high-fidelity Urdu corpus comprising 156 hours of audio with 12-dimension paralinguistic metadata, encompassing US-Std, US-CS, US-EngPk. To address Right-to-Left script constraints and frequent code-switching, we developed UrduSpeech, a LLM-driven pipeline to curate data across 12 diverse categories, including news, drama, and rare literary forms like Bait-Bazi. We also release a 9-hour US-Benchmark set, manually corrected by native annotators to serve as a standard. Hum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17846","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/2605.17846/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":"2605.17846","created_at":"2026-05-20T00:05:01.465522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17846v1","created_at":"2026-05-20T00:05:01.465522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17846","created_at":"2026-05-20T00:05:01.465522+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXAC2W3MH7L5","created_at":"2026-05-20T00:05:01.465522+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXAC2W3MH7L5I2H7","created_at":"2026-05-20T00:05:01.465522+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXAC2W3M","created_at":"2026-05-20T00:05:01.465522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17846","citing_title":"UrduSpeech: A 156-Hour Urdu Speech Corpus with 12-Dimension Paralinguistic Annotations","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV","json":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV.json","graph_json":"https://pith.science/api/pith-number/OXAC2W3MH7L5I2H72WFU27MUTV/graph.json","events_json":"https://pith.science/api/pith-number/OXAC2W3MH7L5I2H72WFU27MUTV/events.json","paper":"https://pith.science/paper/OXAC2W3M"},"agent_actions":{"view_html":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV","download_json":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV.json","view_paper":"https://pith.science/paper/OXAC2W3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17846&json=true","fetch_graph":"https://pith.science/api/pith-number/OXAC2W3MH7L5I2H72WFU27MUTV/graph.json","fetch_events":"https://pith.science/api/pith-number/OXAC2W3MH7L5I2H72WFU27MUTV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/action/storage_attestation","attest_author":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/action/author_attestation","sign_citation":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/action/citation_signature","submit_replication":"https://pith.science/pith/OXAC2W3MH7L5I2H72WFU27MUTV/action/replication_record"}},"created_at":"2026-05-20T00:05:01.465522+00:00","updated_at":"2026-05-20T00:05:01.465522+00:00"}