{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JT3PJSFRQDPXQG5J7PDKPBYZPY","short_pith_number":"pith:JT3PJSFR","schema_version":"1.0","canonical_sha256":"4cf6f4c8b180df781ba9fbc6a787197e068db70d6d08a172bc98d8edbcd033b6","source":{"kind":"arxiv","id":"2502.18913","version":2},"attestation_state":"computed","paper":{"title":"CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aobo Kong, Haoqin Sun, Hui Wang, Jiabei He, Jiaming Zhou, Shiwan Zhao, Shiyao Wang, Xi Yang, Yequan Wang, Yonghua Lin, Yong Qin, Yujie Guo","submitted_at":"2025-02-26T07:59:55Z","abstract_excerpt":"Code-switching (CS), the alternation between two or more languages within a single conversation, presents significant challenges for automatic speech recognition (ASR) systems. Existing Mandarin-English code-switching datasets often suffer from limitations in size, spontaneity, and the lack of full-length dialogue recordings with transcriptions, hindering the development of robust ASR models for real-world conversational scenarios. This paper introduces CS-Dialogue, a novel large-scale Mandarin-English code-switching speech dataset comprising 104 hours of spontaneous conversations from 200 spe"},"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":"2502.18913","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T07:59:55Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"38f7fc05f63b853490fdb8d3b9042fd1b190fb8660351ac0116a70a101c3e7f7","abstract_canon_sha256":"76df1b05ad452ad55afa1e8a2c1f5860739e6ead33bff0bf8e12e8a590ca05f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:34.950735Z","signature_b64":"jwgahKjkSf/vmj8EmYQVjEWIc6jJuEi0EjZjCwJEvMRBi5sUjrXcdM6uPDKEOxRVFftmFxZ4yQwvFv12Er6rDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cf6f4c8b180df781ba9fbc6a787197e068db70d6d08a172bc98d8edbcd033b6","last_reissued_at":"2026-07-05T10:29:34.950210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:34.950210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Aobo Kong, Haoqin Sun, Hui Wang, Jiabei He, Jiaming Zhou, Shiwan Zhao, Shiyao Wang, Xi Yang, Yequan Wang, Yonghua Lin, Yong Qin, Yujie Guo","submitted_at":"2025-02-26T07:59:55Z","abstract_excerpt":"Code-switching (CS), the alternation between two or more languages within a single conversation, presents significant challenges for automatic speech recognition (ASR) systems. Existing Mandarin-English code-switching datasets often suffer from limitations in size, spontaneity, and the lack of full-length dialogue recordings with transcriptions, hindering the development of robust ASR models for real-world conversational scenarios. This paper introduces CS-Dialogue, a novel large-scale Mandarin-English code-switching speech dataset comprising 104 hours of spontaneous conversations from 200 spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18913","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/2502.18913/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":"2502.18913","created_at":"2026-07-05T10:29:34.950267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18913v2","created_at":"2026-07-05T10:29:34.950267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18913","created_at":"2026-07-05T10:29:34.950267+00:00"},{"alias_kind":"pith_short_12","alias_value":"JT3PJSFRQDPX","created_at":"2026-07-05T10:29:34.950267+00:00"},{"alias_kind":"pith_short_16","alias_value":"JT3PJSFRQDPXQG5J","created_at":"2026-07-05T10:29:34.950267+00:00"},{"alias_kind":"pith_short_8","alias_value":"JT3PJSFR","created_at":"2026-07-05T10:29:34.950267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18105","citing_title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2606.05846","citing_title":"Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30899","citing_title":"A Unified and Reproducible Experimentation Framework for Speech Understanding","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23975","citing_title":"Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29430","citing_title":"Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16378","citing_title":"Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18105","citing_title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08003","citing_title":"Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY","json":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY.json","graph_json":"https://pith.science/api/pith-number/JT3PJSFRQDPXQG5J7PDKPBYZPY/graph.json","events_json":"https://pith.science/api/pith-number/JT3PJSFRQDPXQG5J7PDKPBYZPY/events.json","paper":"https://pith.science/paper/JT3PJSFR"},"agent_actions":{"view_html":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY","download_json":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY.json","view_paper":"https://pith.science/paper/JT3PJSFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18913&json=true","fetch_graph":"https://pith.science/api/pith-number/JT3PJSFRQDPXQG5J7PDKPBYZPY/graph.json","fetch_events":"https://pith.science/api/pith-number/JT3PJSFRQDPXQG5J7PDKPBYZPY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/action/storage_attestation","attest_author":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/action/author_attestation","sign_citation":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/action/citation_signature","submit_replication":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/action/replication_record"}},"created_at":"2026-07-05T10:29:34.950267+00:00","updated_at":"2026-07-05T10:29:34.950267+00:00"}