{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QE6USNKIF62IBIHVD3V6D57UGW","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":"7da42da739542a35f1d35f73faf825a5864cd228402f8e349a26f0d17f3ef602","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T09:13:33Z","title_canon_sha256":"f654c381150a916f167fa0ab4f8cf8a7af6e3a9f7bc9134a05813c87b85836d6"},"schema_version":"1.0","source":{"id":"2403.01858","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01858","created_at":"2026-07-05T08:42:33Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01858v3","created_at":"2026-07-05T08:42:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01858","created_at":"2026-07-05T08:42:33Z"},{"alias_kind":"pith_short_12","alias_value":"QE6USNKIF62I","created_at":"2026-07-05T08:42:33Z"},{"alias_kind":"pith_short_16","alias_value":"QE6USNKIF62IBIHV","created_at":"2026-07-05T08:42:33Z"},{"alias_kind":"pith_short_8","alias_value":"QE6USNKI","created_at":"2026-07-05T08:42:33Z"}],"graph_snapshots":[{"event_id":"sha256:2327601ce249f4213d69ea7409289e89d0378966990484bfab53562ba050229e","target":"graph","created_at":"2026-07-05T08:42:33Z","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/2403.01858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hong-Han Shuai, Jun-Da Chen, Sega Cheng, Wei-Min Chu, Ya-Ting Pai, Yen-Wei Lee, Zhi-Rui Tam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T09:13:33Z","title":"An Improved Traditional Chinese Evaluation Suite for Foundation Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01858","kind":"arxiv","version":3},"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":"sha256:70ba8914f93757ce506c4e72f56137facbdeadbd4c223a149a77a9efc5182d3a","target":"record","created_at":"2026-07-05T08:42:33Z","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":"7da42da739542a35f1d35f73faf825a5864cd228402f8e349a26f0d17f3ef602","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-04T09:13:33Z","title_canon_sha256":"f654c381150a916f167fa0ab4f8cf8a7af6e3a9f7bc9134a05813c87b85836d6"},"schema_version":"1.0","source":{"id":"2403.01858","kind":"arxiv","version":3}},"canonical_sha256":"813d4935482fb480a0f51eebe1f7f4358af4a9c8be36a75a12d1611e5f2c57af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"813d4935482fb480a0f51eebe1f7f4358af4a9c8be36a75a12d1611e5f2c57af","first_computed_at":"2026-07-05T08:42:33.637622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:33.637622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FfrVVVRK3kT6Fza5X/Y/sxQD5NGxL6CiZ+SdXi7u8Khfgw9heXO+NXf20itgHPmen0CVz9NuzeKG3lH2JKNDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:33.638136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01858","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70ba8914f93757ce506c4e72f56137facbdeadbd4c223a149a77a9efc5182d3a","sha256:2327601ce249f4213d69ea7409289e89d0378966990484bfab53562ba050229e"],"state_sha256":"6018b5f083b337e2b7e80c5d6e1d04f2392774f3691c4e0f7c077cc19953aa55"}