{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AM7QWWRX6H6HAZL3L2UMUEYLK7","short_pith_number":"pith:AM7QWWRX","schema_version":"1.0","canonical_sha256":"033f0b5a37f1fc70657b5ea8ca130b57c2b13f69e429b70c355ab53a5f06f78f","source":{"kind":"arxiv","id":"2303.04715","version":2},"attestation_state":"computed","paper":{"title":"Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang-Le Liu, Chan-Jan Hsu, Chin-Tung Lin, Da-shan Shiu, Philipp Ennen, Po-chun Hsu, Wei-Yun Ma, Yen-Chen Wu, Yin-Hsiang Liao","submitted_at":"2023-03-08T16:53:19Z","abstract_excerpt":"In this paper we present the multilingual language model BLOOM-zh that features enhanced support for Traditional Chinese. BLOOM-zh has its origins in the open-source BLOOM models presented by BigScience in 2022. Starting from released models, we extended the pre-training of BLOOM by additional 7.4 billion tokens in Traditional Chinese and English covering a variety of domains such as news articles, books, encyclopedias, educational materials as well as spoken language. In order to show the properties of BLOOM-zh, both existing and newly created benchmark scenarios are used for evaluating the p"},"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":"2303.04715","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T16:53:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93b5d42f866d24cc78e545a2bc176fa8b5cec209883aed4e87f3b135c67ae01d","abstract_canon_sha256":"1c2f2cdfee4618a730136c504f86313244039be1791f72e71934954edcb19943"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:59.448450Z","signature_b64":"vVKaPRm5VFI320MON+GtHRTjJxkqxv0qXIOAgtdH3g9zT616+gTETl8nJUWdwl+q/gojjfK1KdwE6xhmz5kQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"033f0b5a37f1fc70657b5ea8ca130b57c2b13f69e429b70c355ab53a5f06f78f","last_reissued_at":"2026-07-05T06:23:59.448049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:59.448049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang-Le Liu, Chan-Jan Hsu, Chin-Tung Lin, Da-shan Shiu, Philipp Ennen, Po-chun Hsu, Wei-Yun Ma, Yen-Chen Wu, Yin-Hsiang Liao","submitted_at":"2023-03-08T16:53:19Z","abstract_excerpt":"In this paper we present the multilingual language model BLOOM-zh that features enhanced support for Traditional Chinese. BLOOM-zh has its origins in the open-source BLOOM models presented by BigScience in 2022. Starting from released models, we extended the pre-training of BLOOM by additional 7.4 billion tokens in Traditional Chinese and English covering a variety of domains such as news articles, books, encyclopedias, educational materials as well as spoken language. In order to show the properties of BLOOM-zh, both existing and newly created benchmark scenarios are used for evaluating the p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04715","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/2303.04715/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":"2303.04715","created_at":"2026-07-05T06:23:59.448105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04715v2","created_at":"2026-07-05T06:23:59.448105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04715","created_at":"2026-07-05T06:23:59.448105+00:00"},{"alias_kind":"pith_short_12","alias_value":"AM7QWWRX6H6H","created_at":"2026-07-05T06:23:59.448105+00:00"},{"alias_kind":"pith_short_16","alias_value":"AM7QWWRX6H6HAZL3","created_at":"2026-07-05T06:23:59.448105+00:00"},{"alias_kind":"pith_short_8","alias_value":"AM7QWWRX","created_at":"2026-07-05T06:23:59.448105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22645","citing_title":"Characterizing Bias: Benchmarking Large Language Models in Simplified versus Traditional Chinese","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7","json":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7.json","graph_json":"https://pith.science/api/pith-number/AM7QWWRX6H6HAZL3L2UMUEYLK7/graph.json","events_json":"https://pith.science/api/pith-number/AM7QWWRX6H6HAZL3L2UMUEYLK7/events.json","paper":"https://pith.science/paper/AM7QWWRX"},"agent_actions":{"view_html":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7","download_json":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7.json","view_paper":"https://pith.science/paper/AM7QWWRX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04715&json=true","fetch_graph":"https://pith.science/api/pith-number/AM7QWWRX6H6HAZL3L2UMUEYLK7/graph.json","fetch_events":"https://pith.science/api/pith-number/AM7QWWRX6H6HAZL3L2UMUEYLK7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/action/storage_attestation","attest_author":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/action/author_attestation","sign_citation":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/action/citation_signature","submit_replication":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/action/replication_record"}},"created_at":"2026-07-05T06:23:59.448105+00:00","updated_at":"2026-07-05T06:23:59.448105+00:00"}