{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ISRZQ5NNELKEWR6DTT5OGF2ZOP","short_pith_number":"pith:ISRZQ5NN","schema_version":"1.0","canonical_sha256":"44a39875ad22d44b47c39cfae3175973e76d9c68a18edf68b24a213232a3e4ca","source":{"kind":"arxiv","id":"2503.03702","version":1},"attestation_state":"computed","paper":{"title":"Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alfred Kar Yin Truong, Chuan Wu, Jiuming Wang, Jiyue Jiang, Lingpeng Kong, Pengan Chen, Qinghang Bao, Sheng Wang, Yanyu Chen, Yu Li","submitted_at":"2025-03-05T17:53:07Z","abstract_excerpt":"High-quality data resources play a crucial role in learning large language models (LLMs), particularly for low-resource languages like Cantonese. Despite having more than 85 million native speakers, Cantonese is still considered a low-resource language in the field of natural language processing (NLP) due to factors such as the dominance of Mandarin, lack of cohesion within the Cantonese-speaking community, diversity in character encoding and input methods, and the tendency of overseas Cantonese speakers to prefer using English. In addition, rich colloquial vocabulary of Cantonese, English loa"},"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":"2503.03702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T17:53:07Z","cross_cats_sorted":[],"title_canon_sha256":"d999e5415fee5108ccc99e7224afea30784479aba9cbf80e6d9d89c3010d5a92","abstract_canon_sha256":"73815e50f6055266161f4789a65c18479ca98ca92c6ed7ccece3e6110f12a893"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:59.200489Z","signature_b64":"NomUzeTJTySky4Qgip30ajUx3N1IufT7PXxMq1XFy3EsOJm59mCO/3Bq6hzpNXg/s0spz/Hf1Yleg3oGXhBcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44a39875ad22d44b47c39cfae3175973e76d9c68a18edf68b24a213232a3e4ca","last_reissued_at":"2026-07-05T10:24:59.199886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:59.199886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alfred Kar Yin Truong, Chuan Wu, Jiuming Wang, Jiyue Jiang, Lingpeng Kong, Pengan Chen, Qinghang Bao, Sheng Wang, Yanyu Chen, Yu Li","submitted_at":"2025-03-05T17:53:07Z","abstract_excerpt":"High-quality data resources play a crucial role in learning large language models (LLMs), particularly for low-resource languages like Cantonese. Despite having more than 85 million native speakers, Cantonese is still considered a low-resource language in the field of natural language processing (NLP) due to factors such as the dominance of Mandarin, lack of cohesion within the Cantonese-speaking community, diversity in character encoding and input methods, and the tendency of overseas Cantonese speakers to prefer using English. In addition, rich colloquial vocabulary of Cantonese, English loa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03702","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/2503.03702/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":"2503.03702","created_at":"2026-07-05T10:24:59.199945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03702v1","created_at":"2026-07-05T10:24:59.199945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03702","created_at":"2026-07-05T10:24:59.199945+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISRZQ5NNELKE","created_at":"2026-07-05T10:24:59.199945+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISRZQ5NNELKEWR6D","created_at":"2026-07-05T10:24:59.199945+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISRZQ5NN","created_at":"2026-07-05T10:24:59.199945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP","json":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP.json","graph_json":"https://pith.science/api/pith-number/ISRZQ5NNELKEWR6DTT5OGF2ZOP/graph.json","events_json":"https://pith.science/api/pith-number/ISRZQ5NNELKEWR6DTT5OGF2ZOP/events.json","paper":"https://pith.science/paper/ISRZQ5NN"},"agent_actions":{"view_html":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP","download_json":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP.json","view_paper":"https://pith.science/paper/ISRZQ5NN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03702&json=true","fetch_graph":"https://pith.science/api/pith-number/ISRZQ5NNELKEWR6DTT5OGF2ZOP/graph.json","fetch_events":"https://pith.science/api/pith-number/ISRZQ5NNELKEWR6DTT5OGF2ZOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/action/storage_attestation","attest_author":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/action/author_attestation","sign_citation":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/action/citation_signature","submit_replication":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/action/replication_record"}},"created_at":"2026-07-05T10:24:59.199945+00:00","updated_at":"2026-07-05T10:24:59.199945+00:00"}