{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ECCBNCWCFMTR3WS3RGY472ZBMI","short_pith_number":"pith:ECCBNCWC","canonical_record":{"source":{"id":"2201.02419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-07T12:09:15Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d0c21e6d1dd9d01e10ada86689e74748700b1b20127b871b1ca2046ca16b2e35","abstract_canon_sha256":"1b38705bd294cc6ad53e354e6adaf631bd56ffb78ed62aebcd580974c540a29c"},"schema_version":"1.0"},"canonical_sha256":"2084168ac22b271dda5b89b1cfeb21620e79b100175f53bd9d2fd55ed7c6de2b","source":{"kind":"arxiv","id":"2201.02419","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02419","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02419v2","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02419","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"pith_short_12","alias_value":"ECCBNCWCFMTR","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"pith_short_16","alias_value":"ECCBNCWCFMTR3WS3","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"pith_short_8","alias_value":"ECCBNCWC","created_at":"2026-07-05T03:48:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ECCBNCWCFMTR3WS3RGY472ZBMI","target":"record","payload":{"canonical_record":{"source":{"id":"2201.02419","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-07T12:09:15Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"d0c21e6d1dd9d01e10ada86689e74748700b1b20127b871b1ca2046ca16b2e35","abstract_canon_sha256":"1b38705bd294cc6ad53e354e6adaf631bd56ffb78ed62aebcd580974c540a29c"},"schema_version":"1.0"},"canonical_sha256":"2084168ac22b271dda5b89b1cfeb21620e79b100175f53bd9d2fd55ed7c6de2b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:48:48.882157Z","signature_b64":"9sL/ZUlqDcfsRu75naEj6JSs7s/DLWJLHlJ/r/3Hu9VUmzyfwcJEjTl6sILxScc7nk2GANY1uHgYA5rlOQ6wCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2084168ac22b271dda5b89b1cfeb21620e79b100175f53bd9d2fd55ed7c6de2b","last_reissued_at":"2026-07-05T03:48:48.881817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:48:48.881817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.02419","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":"2026-07-05T03:48:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ufEmzoAEweW623Q02SQM9aiN7/ZWE7HQ/axmMhhVduTiRVunQVC1ZHNyN1ft5hzZuo6kuAOuPZPCZWRdCPXBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:06:00.793484Z"},"content_sha256":"7d5091df72cecf8599b46f38736ecaad17493b6d0453459197acb245c5bfc183","schema_version":"1.0","event_id":"sha256:7d5091df72cecf8599b46f38736ecaad17493b6d0453459197acb245c5bfc183"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ECCBNCWCFMTR3WS3RGY472ZBMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bertram E. Shi, Cheuk Tung Shadow Yiu, Elham J. Barezi, Holy Lovenia, Pascale Fung, Peng Xu, Qifeng Chen, Rita Frieske, Samuel Cahyawijaya, Tiezheng Yu, Wenliang Dai, Xiaojuan Ma","submitted_at":"2022-01-07T12:09:15Z","abstract_excerpt":"Automatic speech recognition (ASR) on low resource languages improves the access of linguistic minorities to technological advantages provided by artificial intelligence (AI). In this paper, we address the problem of data scarcity for the Hong Kong Cantonese language by creating a new Cantonese dataset. Our dataset, Multi-Domain Cantonese Corpus (MDCC), consists of 73.6 hours of clean read speech paired with transcripts, collected from Cantonese audiobooks from Hong Kong. It comprises philosophy, politics, education, culture, lifestyle and family domains, covering a wide range of topics. We al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02419","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/2201.02419/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":"2026-07-05T03:48:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SuA2XkY67JXyVFuPss9fesyrClA5EOJ7DdfnI58UU/kvVBGUNU8bo76Kxus0oY+qpCJnYaIwaex1KRhysRgXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T02:06:00.793869Z"},"content_sha256":"3c8008f4dbbb7b3fbdb5f727f92295d6ca6fb8b50887be91f48b9d2de136cecf","schema_version":"1.0","event_id":"sha256:3c8008f4dbbb7b3fbdb5f727f92295d6ca6fb8b50887be91f48b9d2de136cecf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECCBNCWCFMTR3WS3RGY472ZBMI/bundle.json","state_url":"https://pith.science/pith/ECCBNCWCFMTR3WS3RGY472ZBMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECCBNCWCFMTR3WS3RGY472ZBMI/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":"2026-07-09T02:06:00Z","links":{"resolver":"https://pith.science/pith/ECCBNCWCFMTR3WS3RGY472ZBMI","bundle":"https://pith.science/pith/ECCBNCWCFMTR3WS3RGY472ZBMI/bundle.json","state":"https://pith.science/pith/ECCBNCWCFMTR3WS3RGY472ZBMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECCBNCWCFMTR3WS3RGY472ZBMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ECCBNCWCFMTR3WS3RGY472ZBMI","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":"1b38705bd294cc6ad53e354e6adaf631bd56ffb78ed62aebcd580974c540a29c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-07T12:09:15Z","title_canon_sha256":"d0c21e6d1dd9d01e10ada86689e74748700b1b20127b871b1ca2046ca16b2e35"},"schema_version":"1.0","source":{"id":"2201.02419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02419","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02419v2","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02419","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"pith_short_12","alias_value":"ECCBNCWCFMTR","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"pith_short_16","alias_value":"ECCBNCWCFMTR3WS3","created_at":"2026-07-05T03:48:48Z"},{"alias_kind":"pith_short_8","alias_value":"ECCBNCWC","created_at":"2026-07-05T03:48:48Z"}],"graph_snapshots":[{"event_id":"sha256:3c8008f4dbbb7b3fbdb5f727f92295d6ca6fb8b50887be91f48b9d2de136cecf","target":"graph","created_at":"2026-07-05T03:48:48Z","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/2201.02419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic speech recognition (ASR) on low resource languages improves the access of linguistic minorities to technological advantages provided by artificial intelligence (AI). In this paper, we address the problem of data scarcity for the Hong Kong Cantonese language by creating a new Cantonese dataset. Our dataset, Multi-Domain Cantonese Corpus (MDCC), consists of 73.6 hours of clean read speech paired with transcripts, collected from Cantonese audiobooks from Hong Kong. It comprises philosophy, politics, education, culture, lifestyle and family domains, covering a wide range of topics. We al","authors_text":"Bertram E. Shi, Cheuk Tung Shadow Yiu, Elham J. Barezi, Holy Lovenia, Pascale Fung, Peng Xu, Qifeng Chen, Rita Frieske, Samuel Cahyawijaya, Tiezheng Yu, Wenliang Dai, Xiaojuan Ma","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-07T12:09:15Z","title":"Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02419","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":"sha256:7d5091df72cecf8599b46f38736ecaad17493b6d0453459197acb245c5bfc183","target":"record","created_at":"2026-07-05T03:48:48Z","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":"1b38705bd294cc6ad53e354e6adaf631bd56ffb78ed62aebcd580974c540a29c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-07T12:09:15Z","title_canon_sha256":"d0c21e6d1dd9d01e10ada86689e74748700b1b20127b871b1ca2046ca16b2e35"},"schema_version":"1.0","source":{"id":"2201.02419","kind":"arxiv","version":2}},"canonical_sha256":"2084168ac22b271dda5b89b1cfeb21620e79b100175f53bd9d2fd55ed7c6de2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2084168ac22b271dda5b89b1cfeb21620e79b100175f53bd9d2fd55ed7c6de2b","first_computed_at":"2026-07-05T03:48:48.881817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:48:48.881817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9sL/ZUlqDcfsRu75naEj6JSs7s/DLWJLHlJ/r/3Hu9VUmzyfwcJEjTl6sILxScc7nk2GANY1uHgYA5rlOQ6wCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:48:48.882157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.02419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d5091df72cecf8599b46f38736ecaad17493b6d0453459197acb245c5bfc183","sha256:3c8008f4dbbb7b3fbdb5f727f92295d6ca6fb8b50887be91f48b9d2de136cecf"],"state_sha256":"6f1feba6354466dd4239a6024f75bf75250762feba3ad36ee044fd4369b7790b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cxPSG2bizBsw3gXjcWMr2jtJPHA/mXtvGR49WqSorB1t/CsR88ACugNkeroB02pyzIOWUqRjxtS5hHYNzDmVCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T02:06:00.795998Z","bundle_sha256":"05f21011bf04790e23fda16f0849a130896af4657cc56962d50ad093d2beddc8"}}