{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JT3PJSFRQDPXQG5J7PDKPBYZPY","short_pith_number":"pith:JT3PJSFR","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"},"canonical_sha256":"4cf6f4c8b180df781ba9fbc6a787197e068db70d6d08a172bc98d8edbcd033b6","source":{"kind":"arxiv","id":"2502.18913","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18913","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18913v2","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18913","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_12","alias_value":"JT3PJSFRQDPX","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"JT3PJSFRQDPXQG5J","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"JT3PJSFR","created_at":"2026-07-05T10:29:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JT3PJSFRQDPXQG5J7PDKPBYZPY","target":"record","payload":{"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"},"canonical_sha256":"4cf6f4c8b180df781ba9fbc6a787197e068db70d6d08a172bc98d8edbcd033b6","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"},"source_kind":"arxiv","source_id":"2502.18913","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QJdx9l10tYpPa1z67HNEmHdRiPuxbZLOkjZM4C7yqrRHylD0q9vh7m2wRg8dsYZ6F72BT/naaCyBV9OIMtgQDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T08:43:07.562805Z"},"content_sha256":"263c2fa67f81cfedcdafc6656fcd140647faaec2d125bf78e0a98f2ff0e77d56","schema_version":"1.0","event_id":"sha256:263c2fa67f81cfedcdafc6656fcd140647faaec2d125bf78e0a98f2ff0e77d56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JT3PJSFRQDPXQG5J7PDKPBYZPY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1fkCa2u2IjtaTK89wzOHnWGOw4J5X2ISFD9pKez+evMsMGRHEpSlJfndTH2uXMGD9uBQilHO0tMX3tco2V6jDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T08:43:07.563238Z"},"content_sha256":"92ea32fdc44f5dd21bc46db60449d29c3a81493356a6d2ab38b59a9b48d4d1e5","schema_version":"1.0","event_id":"sha256:92ea32fdc44f5dd21bc46db60449d29c3a81493356a6d2ab38b59a9b48d4d1e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/bundle.json","state_url":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T08:43:07Z","links":{"resolver":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY","bundle":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/bundle.json","state":"https://pith.science/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JT3PJSFRQDPXQG5J7PDKPBYZPY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JT3PJSFRQDPXQG5J7PDKPBYZPY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"76df1b05ad452ad55afa1e8a2c1f5860739e6ead33bff0bf8e12e8a590ca05f2","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T07:59:55Z","title_canon_sha256":"38f7fc05f63b853490fdb8d3b9042fd1b190fb8660351ac0116a70a101c3e7f7"},"schema_version":"1.0","source":{"id":"2502.18913","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18913","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18913v2","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18913","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_12","alias_value":"JT3PJSFRQDPX","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"JT3PJSFRQDPXQG5J","created_at":"2026-07-05T10:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"JT3PJSFR","created_at":"2026-07-05T10:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:92ea32fdc44f5dd21bc46db60449d29c3a81493356a6d2ab38b59a9b48d4d1e5","target":"graph","created_at":"2026-07-05T10:29:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.18913/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T07:59:55Z","title":"CS-Dialogue: A 104-Hour Dataset of Spontaneous Mandarin-English Code-Switching Dialogues for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18913","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:263c2fa67f81cfedcdafc6656fcd140647faaec2d125bf78e0a98f2ff0e77d56","target":"record","created_at":"2026-07-05T10:29:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"76df1b05ad452ad55afa1e8a2c1f5860739e6ead33bff0bf8e12e8a590ca05f2","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T07:59:55Z","title_canon_sha256":"38f7fc05f63b853490fdb8d3b9042fd1b190fb8660351ac0116a70a101c3e7f7"},"schema_version":"1.0","source":{"id":"2502.18913","kind":"arxiv","version":2}},"canonical_sha256":"4cf6f4c8b180df781ba9fbc6a787197e068db70d6d08a172bc98d8edbcd033b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cf6f4c8b180df781ba9fbc6a787197e068db70d6d08a172bc98d8edbcd033b6","first_computed_at":"2026-07-05T10:29:34.950210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:34.950210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jwgahKjkSf/vmj8EmYQVjEWIc6jJuEi0EjZjCwJEvMRBi5sUjrXcdM6uPDKEOxRVFftmFxZ4yQwvFv12Er6rDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:34.950735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18913","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:263c2fa67f81cfedcdafc6656fcd140647faaec2d125bf78e0a98f2ff0e77d56","sha256:92ea32fdc44f5dd21bc46db60449d29c3a81493356a6d2ab38b59a9b48d4d1e5"],"state_sha256":"9741a85a130710558a49586cbdb0fbf4ea2bf151838bc4609d4ba1e4e9bb5c00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mMIlQNGc5xRCzh9H8olWKr/uM2HEFbCLpKDNvwcw5WnOxVxKHznal7ffapO7C0UeHDdf2MbRa91QcATu/Xt2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T08:43:07.565929Z","bundle_sha256":"7ba36b7c53ce5424c76be4beac7083afdb2a0f3ef362e80fbb06292db49607b9"}}