{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TYFBZBALMABKWDKQBJN36VXX6H","short_pith_number":"pith:TYFBZBAL","schema_version":"1.0","canonical_sha256":"9e0a1c840b6002ab0d500a5bbf56f7f1c8d0d72a7cbef386e79eb165fd3a494f","source":{"kind":"arxiv","id":"2305.18881","version":1},"attestation_state":"computed","paper":{"title":"MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andy W. H. Khong, Fei Ting Woon, Hexin Liu, Jinyi Wong, Justin Dauwels, Leibny Paola Garcia Perera, Sanjeev Khudanpur, Suzy J. Styles, Victoria Y. H. Chua, Xiangyu Zhang","submitted_at":"2023-05-30T09:26:20Z","abstract_excerpt":"To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns. We present the MERLIon CCS challenge, featuring a first-of-its-kind Zoom video call dataset of parent-child shared book reading, of over 30 hours with over 300 recordings, annotated by multilingual transcribers using a high-fidelity linguistic transcription protocol. The audio corpus features spontaneous and "},"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":"2305.18881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T09:26:20Z","cross_cats_sorted":[],"title_canon_sha256":"cfb50aa0c1f8c5cf22f18014c6b5c8c0ffe3d9e875780b2d795b55bb5a3ace42","abstract_canon_sha256":"3402160863ab0f9841924eef2f1854d53c1b8c71e80338f4dbe27172ef0f703b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:34.355354Z","signature_b64":"1mwLvLjEZe3sI89nLBLKSk8uVmgM28ZOSXWXlXEd/SKc4iX/snzVbpCaJP6iLw0LVx1rI7FyhwvfHy6wrdgeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e0a1c840b6002ab0d500a5bbf56f7f1c8d0d72a7cbef386e79eb165fd3a494f","last_reissued_at":"2026-07-05T06:15:34.354915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:34.354915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Andy W. H. Khong, Fei Ting Woon, Hexin Liu, Jinyi Wong, Justin Dauwels, Leibny Paola Garcia Perera, Sanjeev Khudanpur, Suzy J. Styles, Victoria Y. H. Chua, Xiangyu Zhang","submitted_at":"2023-05-30T09:26:20Z","abstract_excerpt":"To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns. We present the MERLIon CCS challenge, featuring a first-of-its-kind Zoom video call dataset of parent-child shared book reading, of over 30 hours with over 300 recordings, annotated by multilingual transcribers using a high-fidelity linguistic transcription protocol. The audio corpus features spontaneous and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18881","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/2305.18881/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":"2305.18881","created_at":"2026-07-05T06:15:34.354979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18881v1","created_at":"2026-07-05T06:15:34.354979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18881","created_at":"2026-07-05T06:15:34.354979+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYFBZBALMABK","created_at":"2026-07-05T06:15:34.354979+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYFBZBALMABKWDKQ","created_at":"2026-07-05T06:15:34.354979+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYFBZBAL","created_at":"2026-07-05T06:15:34.354979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09032","citing_title":"Speaker Role and Language Diarization for Analyzing Multilingual Interviews for Language Proficiency of Older Adults","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H","json":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H.json","graph_json":"https://pith.science/api/pith-number/TYFBZBALMABKWDKQBJN36VXX6H/graph.json","events_json":"https://pith.science/api/pith-number/TYFBZBALMABKWDKQBJN36VXX6H/events.json","paper":"https://pith.science/paper/TYFBZBAL"},"agent_actions":{"view_html":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H","download_json":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H.json","view_paper":"https://pith.science/paper/TYFBZBAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18881&json=true","fetch_graph":"https://pith.science/api/pith-number/TYFBZBALMABKWDKQBJN36VXX6H/graph.json","fetch_events":"https://pith.science/api/pith-number/TYFBZBALMABKWDKQBJN36VXX6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/action/storage_attestation","attest_author":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/action/author_attestation","sign_citation":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/action/citation_signature","submit_replication":"https://pith.science/pith/TYFBZBALMABKWDKQBJN36VXX6H/action/replication_record"}},"created_at":"2026-07-05T06:15:34.354979+00:00","updated_at":"2026-07-05T06:15:34.354979+00:00"}