{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ISRZQ5NNELKEWR6DTT5OGF2ZOP","short_pith_number":"pith:ISRZQ5NN","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"},"canonical_sha256":"44a39875ad22d44b47c39cfae3175973e76d9c68a18edf68b24a213232a3e4ca","source":{"kind":"arxiv","id":"2503.03702","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03702","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03702v1","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03702","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"ISRZQ5NNELKE","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_16","alias_value":"ISRZQ5NNELKEWR6D","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_8","alias_value":"ISRZQ5NN","created_at":"2026-07-05T10:24:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ISRZQ5NNELKEWR6DTT5OGF2ZOP","target":"record","payload":{"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"},"canonical_sha256":"44a39875ad22d44b47c39cfae3175973e76d9c68a18edf68b24a213232a3e4ca","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"},"source_kind":"arxiv","source_id":"2503.03702","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:24:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NSMd3Y9NzjwhoplFDpgQQdPJp0DljL2ftCKd0WG/5LijMYtZDxVqhUDuW1zUYWhi8lVrBC3suYwnibHE5qpOAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:46:24.055294Z"},"content_sha256":"06371ca63aac6f0e4da7aef6d0a34698517f63b464b3796de95596af99f88e81","schema_version":"1.0","event_id":"sha256:06371ca63aac6f0e4da7aef6d0a34698517f63b464b3796de95596af99f88e81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ISRZQ5NNELKEWR6DTT5OGF2ZOP","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:24:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ELPBKSDdWEx388wNqC7odwmA6ilxbkegyiCyed1DEUHCGwFm0TmPCo4PoALmL0DzY+9m4t3lPpUjvrBkyaQIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:46:24.055829Z"},"content_sha256":"393a1dbaf1a7f85b62e989703d5bfc3e4cbf777619caac7fea459f38d6244c50","schema_version":"1.0","event_id":"sha256:393a1dbaf1a7f85b62e989703d5bfc3e4cbf777619caac7fea459f38d6244c50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/bundle.json","state_url":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/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":"2026-07-07T03:46:24Z","links":{"resolver":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP","bundle":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/bundle.json","state":"https://pith.science/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ISRZQ5NNELKEWR6DTT5OGF2ZOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ISRZQ5NNELKEWR6DTT5OGF2ZOP","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":"73815e50f6055266161f4789a65c18479ca98ca92c6ed7ccece3e6110f12a893","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T17:53:07Z","title_canon_sha256":"d999e5415fee5108ccc99e7224afea30784479aba9cbf80e6d9d89c3010d5a92"},"schema_version":"1.0","source":{"id":"2503.03702","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03702","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03702v1","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03702","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"ISRZQ5NNELKE","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_16","alias_value":"ISRZQ5NNELKEWR6D","created_at":"2026-07-05T10:24:59Z"},{"alias_kind":"pith_short_8","alias_value":"ISRZQ5NN","created_at":"2026-07-05T10:24:59Z"}],"graph_snapshots":[{"event_id":"sha256:393a1dbaf1a7f85b62e989703d5bfc3e4cbf777619caac7fea459f38d6244c50","target":"graph","created_at":"2026-07-05T10:24:59Z","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/2503.03702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alfred Kar Yin Truong, Chuan Wu, Jiuming Wang, Jiyue Jiang, Lingpeng Kong, Pengan Chen, Qinghang Bao, Sheng Wang, Yanyu Chen, Yu Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T17:53:07Z","title":"Developing and Utilizing a Large-Scale Cantonese Dataset for Multi-Tasking in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03702","kind":"arxiv","version":1},"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":"sha256:06371ca63aac6f0e4da7aef6d0a34698517f63b464b3796de95596af99f88e81","target":"record","created_at":"2026-07-05T10:24:59Z","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":"73815e50f6055266161f4789a65c18479ca98ca92c6ed7ccece3e6110f12a893","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T17:53:07Z","title_canon_sha256":"d999e5415fee5108ccc99e7224afea30784479aba9cbf80e6d9d89c3010d5a92"},"schema_version":"1.0","source":{"id":"2503.03702","kind":"arxiv","version":1}},"canonical_sha256":"44a39875ad22d44b47c39cfae3175973e76d9c68a18edf68b24a213232a3e4ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44a39875ad22d44b47c39cfae3175973e76d9c68a18edf68b24a213232a3e4ca","first_computed_at":"2026-07-05T10:24:59.199886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:59.199886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NomUzeTJTySky4Qgip30ajUx3N1IufT7PXxMq1XFy3EsOJm59mCO/3Bq6hzpNXg/s0spz/Hf1Yleg3oGXhBcCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:59.200489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03702","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06371ca63aac6f0e4da7aef6d0a34698517f63b464b3796de95596af99f88e81","sha256:393a1dbaf1a7f85b62e989703d5bfc3e4cbf777619caac7fea459f38d6244c50"],"state_sha256":"85b4163f2890f2ad76b571f2ca3dceebecdfae1f4eca6a7a71d3456d6e147931"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LdznxLyasOgZOz4iN4hppqMOiNv9CbLe3PR/AczfIdk9u/Awzdg/Xkv4iCo1mlRgDtfbFaronl4ml6ngfMGBDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:46:24.057863Z","bundle_sha256":"07eef93bd539df58900c80f9144fb59bb70bdaec7599bd491321bfb45fcda7ad"}}