{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QE6USNKIF62IBIHVD3V6D57UGW","short_pith_number":"pith:QE6USNKI","schema_version":"1.0","canonical_sha256":"813d4935482fb480a0f51eebe1f7f4358af4a9c8be36a75a12d1611e5f2c57af","source":{"kind":"arxiv","id":"2403.01858","version":3},"attestation_state":"computed","paper":{"title":"An Improved Traditional Chinese Evaluation Suite for Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong-Han Shuai, Jun-Da Chen, Sega Cheng, Wei-Min Chu, Ya-Ting Pai, Yen-Wei Lee, Zhi-Rui Tam","submitted_at":"2024-03-04T09:13:33Z","abstract_excerpt":"We present TMMLU+, a new benchmark designed for Traditional Chinese language understanding. TMMLU+ is a multi-choice question-answering dataset with 66 subjects from elementary to professional level. It is six times larger and boasts a more balanced subject distribution than its predecessor, Taiwan Massive Multitask Language Understanding (TMMLU). We also benchmark closed-source models and 26 open-weight Chinese large language models (LLMs) of parameters ranging from 1.8B to 72B on the proposed TMMLU+. Our findings reveal that (1.) Traditional Chinese models still trail behind their Simplified"},"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":"2403.01858","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T09:13:33Z","cross_cats_sorted":[],"title_canon_sha256":"f654c381150a916f167fa0ab4f8cf8a7af6e3a9f7bc9134a05813c87b85836d6","abstract_canon_sha256":"7da42da739542a35f1d35f73faf825a5864cd228402f8e349a26f0d17f3ef602"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:33.638136Z","signature_b64":"FfrVVVRK3kT6Fza5X/Y/sxQD5NGxL6CiZ+SdXi7u8Khfgw9heXO+NXf20itgHPmen0CVz9NuzeKG3lH2JKNDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813d4935482fb480a0f51eebe1f7f4358af4a9c8be36a75a12d1611e5f2c57af","last_reissued_at":"2026-07-05T08:42:33.637622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:33.637622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Improved Traditional Chinese Evaluation Suite for Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong-Han Shuai, Jun-Da Chen, Sega Cheng, Wei-Min Chu, Ya-Ting Pai, Yen-Wei Lee, Zhi-Rui Tam","submitted_at":"2024-03-04T09:13:33Z","abstract_excerpt":"We present TMMLU+, a new benchmark designed for Traditional Chinese language understanding. TMMLU+ is a multi-choice question-answering dataset with 66 subjects from elementary to professional level. It is six times larger and boasts a more balanced subject distribution than its predecessor, Taiwan Massive Multitask Language Understanding (TMMLU). We also benchmark closed-source models and 26 open-weight Chinese large language models (LLMs) of parameters ranging from 1.8B to 72B on the proposed TMMLU+. Our findings reveal that (1.) Traditional Chinese models still trail behind their Simplified"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01858","kind":"arxiv","version":3},"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/2403.01858/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":"2403.01858","created_at":"2026-07-05T08:42:33.637683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01858v3","created_at":"2026-07-05T08:42:33.637683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01858","created_at":"2026-07-05T08:42:33.637683+00:00"},{"alias_kind":"pith_short_12","alias_value":"QE6USNKIF62I","created_at":"2026-07-05T08:42:33.637683+00:00"},{"alias_kind":"pith_short_16","alias_value":"QE6USNKIF62IBIHV","created_at":"2026-07-05T08:42:33.637683+00:00"},{"alias_kind":"pith_short_8","alias_value":"QE6USNKI","created_at":"2026-07-05T08:42:33.637683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01274","citing_title":"Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW","json":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW.json","graph_json":"https://pith.science/api/pith-number/QE6USNKIF62IBIHVD3V6D57UGW/graph.json","events_json":"https://pith.science/api/pith-number/QE6USNKIF62IBIHVD3V6D57UGW/events.json","paper":"https://pith.science/paper/QE6USNKI"},"agent_actions":{"view_html":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW","download_json":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW.json","view_paper":"https://pith.science/paper/QE6USNKI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01858&json=true","fetch_graph":"https://pith.science/api/pith-number/QE6USNKIF62IBIHVD3V6D57UGW/graph.json","fetch_events":"https://pith.science/api/pith-number/QE6USNKIF62IBIHVD3V6D57UGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW/action/storage_attestation","attest_author":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW/action/author_attestation","sign_citation":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW/action/citation_signature","submit_replication":"https://pith.science/pith/QE6USNKIF62IBIHVD3V6D57UGW/action/replication_record"}},"created_at":"2026-07-05T08:42:33.637683+00:00","updated_at":"2026-07-05T08:42:33.637683+00:00"}