{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AM7QWWRX6H6HAZL3L2UMUEYLK7","short_pith_number":"pith:AM7QWWRX","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"},"canonical_sha256":"033f0b5a37f1fc70657b5ea8ca130b57c2b13f69e429b70c355ab53a5f06f78f","source":{"kind":"arxiv","id":"2303.04715","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04715","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04715v2","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04715","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"pith_short_12","alias_value":"AM7QWWRX6H6H","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"pith_short_16","alias_value":"AM7QWWRX6H6HAZL3","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"pith_short_8","alias_value":"AM7QWWRX","created_at":"2026-07-05T06:23:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AM7QWWRX6H6HAZL3L2UMUEYLK7","target":"record","payload":{"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"},"canonical_sha256":"033f0b5a37f1fc70657b5ea8ca130b57c2b13f69e429b70c355ab53a5f06f78f","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"},"source_kind":"arxiv","source_id":"2303.04715","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":"2026-07-05T06:23:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9cfAjJCSBrzdhyVi/r43FwuIQ/19ydkRwopaO3a0Bu69dYHW8v+A0CBlacWpYP3j9m8BKYdmFln1IsOmZSn1Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:54:46.810816Z"},"content_sha256":"de971a6331d183866667171f5bca762f28fb732a49fe590d5e4ad94213dc7440","schema_version":"1.0","event_id":"sha256:de971a6331d183866667171f5bca762f28fb732a49fe590d5e4ad94213dc7440"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AM7QWWRX6H6HAZL3L2UMUEYLK7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:23:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2uTW0M1yGjF7+29qd9f0/Rhg/NfwRxAKcfs7DOdqXjz7wQ8eJNHOeHu/bkC6LWoK7TMzNZzIECOA/PadwDeHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:54:46.811334Z"},"content_sha256":"fddf2369d2e178004e15d61d92c5ab7b7649264205b6dc712430b515b78557ee","schema_version":"1.0","event_id":"sha256:fddf2369d2e178004e15d61d92c5ab7b7649264205b6dc712430b515b78557ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/bundle.json","state_url":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/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":"2026-08-03T16:54:46Z","links":{"resolver":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7","bundle":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/bundle.json","state":"https://pith.science/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AM7QWWRX6H6HAZL3L2UMUEYLK7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AM7QWWRX6H6HAZL3L2UMUEYLK7","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":"1c2f2cdfee4618a730136c504f86313244039be1791f72e71934954edcb19943","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T16:53:19Z","title_canon_sha256":"93b5d42f866d24cc78e545a2bc176fa8b5cec209883aed4e87f3b135c67ae01d"},"schema_version":"1.0","source":{"id":"2303.04715","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04715","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04715v2","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04715","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"pith_short_12","alias_value":"AM7QWWRX6H6H","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"pith_short_16","alias_value":"AM7QWWRX6H6HAZL3","created_at":"2026-07-05T06:23:59Z"},{"alias_kind":"pith_short_8","alias_value":"AM7QWWRX","created_at":"2026-07-05T06:23:59Z"}],"graph_snapshots":[{"event_id":"sha256:fddf2369d2e178004e15d61d92c5ab7b7649264205b6dc712430b515b78557ee","target":"graph","created_at":"2026-07-05T06:23:59Z","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/2303.04715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T16:53:19Z","title":"Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04715","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:de971a6331d183866667171f5bca762f28fb732a49fe590d5e4ad94213dc7440","target":"record","created_at":"2026-07-05T06:23:59Z","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":"1c2f2cdfee4618a730136c504f86313244039be1791f72e71934954edcb19943","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-08T16:53:19Z","title_canon_sha256":"93b5d42f866d24cc78e545a2bc176fa8b5cec209883aed4e87f3b135c67ae01d"},"schema_version":"1.0","source":{"id":"2303.04715","kind":"arxiv","version":2}},"canonical_sha256":"033f0b5a37f1fc70657b5ea8ca130b57c2b13f69e429b70c355ab53a5f06f78f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"033f0b5a37f1fc70657b5ea8ca130b57c2b13f69e429b70c355ab53a5f06f78f","first_computed_at":"2026-07-05T06:23:59.448049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:59.448049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vVKaPRm5VFI320MON+GtHRTjJxkqxv0qXIOAgtdH3g9zT616+gTETl8nJUWdwl+q/gojjfK1KdwE6xhmz5kQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:59.448450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.04715","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de971a6331d183866667171f5bca762f28fb732a49fe590d5e4ad94213dc7440","sha256:fddf2369d2e178004e15d61d92c5ab7b7649264205b6dc712430b515b78557ee"],"state_sha256":"08ea4126cd421129acdb6f829e097e601960c3f0fce13828a2a99927cb68f41a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DxfJz85f+Is0IywUQ/g4tW3/O70elSGjh12+WA9uFE2sB3/e82vgVpnkXza2J/7rw3Igyyr1/vyOv1+Kxdx/Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:54:46.816008Z","bundle_sha256":"b02e304fb8a97b80d62b14393644519c30de07d1a48262a4ada2a674990d647c"}}