{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PTKEMHS2B5IIR5DTFXYWB47KPO","short_pith_number":"pith:PTKEMHS2","canonical_record":{"source":{"id":"2310.17953","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-27T08:01:55Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"d02b2d88e5337ad547b9459c7dadb4f2c529ed4154194156ed3397931e3c0b40","abstract_canon_sha256":"82009d6872b9e28513f384f6426c471fc11c0588346d7c4ea8a4b185d4e59364"},"schema_version":"1.0"},"canonical_sha256":"7cd4461e5a0f5088f4732df160f3ea7b972a740662399964b1f5d7113ca72c5c","source":{"kind":"arxiv","id":"2310.17953","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17953","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17953v4","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17953","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"PTKEMHS2B5II","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"PTKEMHS2B5IIR5DT","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"PTKEMHS2","created_at":"2026-07-05T10:21:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PTKEMHS2B5IIR5DTFXYWB47KPO","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17953","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-27T08:01:55Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"d02b2d88e5337ad547b9459c7dadb4f2c529ed4154194156ed3397931e3c0b40","abstract_canon_sha256":"82009d6872b9e28513f384f6426c471fc11c0588346d7c4ea8a4b185d4e59364"},"schema_version":"1.0"},"canonical_sha256":"7cd4461e5a0f5088f4732df160f3ea7b972a740662399964b1f5d7113ca72c5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:56.399937Z","signature_b64":"vvJVN2n74+My3nc5N5fOcuyKvvBT7Tn3q6bDhOKIUROTRVGhprg9VSFx6M71gwHDeMFQxHNp0gYwwPLujf5YCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cd4461e5a0f5088f4732df160f3ea7b972a740662399964b1f5d7113ca72c5c","last_reissued_at":"2026-07-05T10:21:56.399508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:56.399508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17953","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5uixv33UrxymU+MD3K0GXsoKe/27evxAg/NTfd2qX7gGxHx1qrot8UdlSqc4B3t5VizLKSSk+wYeDVOh+cLhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:26:40.783240Z"},"content_sha256":"b0820cedf0e3354e1fd0ec9ef2c35245b2d665f853ee189fd9538cb2089d8900","schema_version":"1.0","event_id":"sha256:b0820cedf0e3354e1fd0ec9ef2c35245b2d665f853ee189fd9538cb2089d8900"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PTKEMHS2B5IIR5DTFXYWB47KPO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong's Polylingual Dynamics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kani Chen, Peng Xie","submitted_at":"2023-10-27T08:01:55Z","abstract_excerpt":"The existing audio datasets are predominantly tailored towards single languages, overlooking the complex linguistic behaviors of multilingual communities that engage in code-switching. This practice, where individuals frequently mix two or more languages in their daily interactions, is particularly prevalent in multilingual regions such as Hong Kong, China. To bridge this gap, we have developed a 34.8-hour dataset of Mixed Cantonese and English (MCE) audio using our Multi-Agent Data Generation Framework (MADGF). We fine-tuned the open-source multilingual Automatic Speech Recognition (ASR) mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17953","kind":"arxiv","version":4},"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/2310.17953/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":"2026-07-05T10:21:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vmjmCcotmG1Z2VOdasODSM9B8aP56Y71+5C93xiSelcTBPh3NLQfLi/JXOhh0BIVNgZu5v/y9sGclPx/qGbwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:26:40.783744Z"},"content_sha256":"5fcdd0879c0aa73a38be35a9cc25fefb1e5714165959df00db661d1b7521820c","schema_version":"1.0","event_id":"sha256:5fcdd0879c0aa73a38be35a9cc25fefb1e5714165959df00db661d1b7521820c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTKEMHS2B5IIR5DTFXYWB47KPO/bundle.json","state_url":"https://pith.science/pith/PTKEMHS2B5IIR5DTFXYWB47KPO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTKEMHS2B5IIR5DTFXYWB47KPO/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":"2026-08-07T18:26:40Z","links":{"resolver":"https://pith.science/pith/PTKEMHS2B5IIR5DTFXYWB47KPO","bundle":"https://pith.science/pith/PTKEMHS2B5IIR5DTFXYWB47KPO/bundle.json","state":"https://pith.science/pith/PTKEMHS2B5IIR5DTFXYWB47KPO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTKEMHS2B5IIR5DTFXYWB47KPO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PTKEMHS2B5IIR5DTFXYWB47KPO","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":"82009d6872b9e28513f384f6426c471fc11c0588346d7c4ea8a4b185d4e59364","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-27T08:01:55Z","title_canon_sha256":"d02b2d88e5337ad547b9459c7dadb4f2c529ed4154194156ed3397931e3c0b40"},"schema_version":"1.0","source":{"id":"2310.17953","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17953","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17953v4","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17953","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_12","alias_value":"PTKEMHS2B5II","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_16","alias_value":"PTKEMHS2B5IIR5DT","created_at":"2026-07-05T10:21:56Z"},{"alias_kind":"pith_short_8","alias_value":"PTKEMHS2","created_at":"2026-07-05T10:21:56Z"}],"graph_snapshots":[{"event_id":"sha256:5fcdd0879c0aa73a38be35a9cc25fefb1e5714165959df00db661d1b7521820c","target":"graph","created_at":"2026-07-05T10:21:56Z","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/2310.17953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The existing audio datasets are predominantly tailored towards single languages, overlooking the complex linguistic behaviors of multilingual communities that engage in code-switching. This practice, where individuals frequently mix two or more languages in their daily interactions, is particularly prevalent in multilingual regions such as Hong Kong, China. To bridge this gap, we have developed a 34.8-hour dataset of Mixed Cantonese and English (MCE) audio using our Multi-Agent Data Generation Framework (MADGF). We fine-tuned the open-source multilingual Automatic Speech Recognition (ASR) mode","authors_text":"Kani Chen, Peng Xie","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-27T08:01:55Z","title":"Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong's Polylingual Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17953","kind":"arxiv","version":4},"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:b0820cedf0e3354e1fd0ec9ef2c35245b2d665f853ee189fd9538cb2089d8900","target":"record","created_at":"2026-07-05T10:21:56Z","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":"82009d6872b9e28513f384f6426c471fc11c0588346d7c4ea8a4b185d4e59364","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2023-10-27T08:01:55Z","title_canon_sha256":"d02b2d88e5337ad547b9459c7dadb4f2c529ed4154194156ed3397931e3c0b40"},"schema_version":"1.0","source":{"id":"2310.17953","kind":"arxiv","version":4}},"canonical_sha256":"7cd4461e5a0f5088f4732df160f3ea7b972a740662399964b1f5d7113ca72c5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cd4461e5a0f5088f4732df160f3ea7b972a740662399964b1f5d7113ca72c5c","first_computed_at":"2026-07-05T10:21:56.399508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:56.399508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vvJVN2n74+My3nc5N5fOcuyKvvBT7Tn3q6bDhOKIUROTRVGhprg9VSFx6M71gwHDeMFQxHNp0gYwwPLujf5YCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:56.399937Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17953","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0820cedf0e3354e1fd0ec9ef2c35245b2d665f853ee189fd9538cb2089d8900","sha256:5fcdd0879c0aa73a38be35a9cc25fefb1e5714165959df00db661d1b7521820c"],"state_sha256":"626acac910e4c8e798ff915081207e76f7557c04a47eb23493a2fdaa9b10373d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0kB6g2KNfkGWlHTV+Spurl8aNKAo4z+9Fieg4eFS8y54/A6h6qkf5AwfZSeLYbEaobxn67PfFqSP/08HY85+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:26:40.787491Z","bundle_sha256":"c8afc0045480d79c190cf1589cc0847bfeee2f5360d06bc76bfdf6e895689e5e"}}