{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EZKRRE2WQIOAP3P6QSKOUAJGDM","short_pith_number":"pith:EZKRRE2W","schema_version":"1.0","canonical_sha256":"2655189356821c07edfe8494ea01261b05cbd6ce03512cd15ddc082eff073646","source":{"kind":"arxiv","id":"2508.01274","version":1},"attestation_state":"computed","paper":{"title":"Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bing-Cheng Xie, Bing-Jia Tan, Hao-Yuan Chen, He-Rong Zheng, Jui-Ming Yao, Peter Shaojui Wang, Sheng-Wei Peng, Shun-Feng Su","submitted_at":"2025-08-02T09:10:15Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) process visual, acoustic, and textual inputs, addressing the limitations of single-modality LLMs. However, existing benchmarks often overlook tri-modal evaluation in Traditional Chinese and do not consider inference latency. To address this, we introduce Multi-TW, the first Traditional Chinese benchmark for evaluating the performance and latency of any-to-any multimodal models. Multi-TW includes 900 multiple-choice questions (image and text, audio and text pairs) sourced from official proficiency tests developed with the Steering Committee for the Test "},"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":"2508.01274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-02T09:10:15Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"8e736a831413bde3a57f00ec9b8fb57b0fe6a6012979e0ac9fecea9276226892","abstract_canon_sha256":"448ef528bf2929cb3afe87a2755d3d847543e5551b57a7975954198154c872e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:36.332282Z","signature_b64":"xdOfMjF2+dy81gpN5hGegTO/3MInRn2wwJm+2zcA+/jrWsy3SMWBqFybTRsaf11HSG7G1BSGOZpnQ2pvLh0jCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2655189356821c07edfe8494ea01261b05cbd6ce03512cd15ddc082eff073646","last_reissued_at":"2026-07-05T11:47:36.331876Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:36.331876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-TW: Benchmarking Multimodal Models on Traditional Chinese Question Answering in Taiwan","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bing-Cheng Xie, Bing-Jia Tan, Hao-Yuan Chen, He-Rong Zheng, Jui-Ming Yao, Peter Shaojui Wang, Sheng-Wei Peng, Shun-Feng Su","submitted_at":"2025-08-02T09:10:15Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) process visual, acoustic, and textual inputs, addressing the limitations of single-modality LLMs. However, existing benchmarks often overlook tri-modal evaluation in Traditional Chinese and do not consider inference latency. To address this, we introduce Multi-TW, the first Traditional Chinese benchmark for evaluating the performance and latency of any-to-any multimodal models. Multi-TW includes 900 multiple-choice questions (image and text, audio and text pairs) sourced from official proficiency tests developed with the Steering Committee for the Test "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01274","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/2508.01274/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":"2508.01274","created_at":"2026-07-05T11:47:36.331933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01274v1","created_at":"2026-07-05T11:47:36.331933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01274","created_at":"2026-07-05T11:47:36.331933+00:00"},{"alias_kind":"pith_short_12","alias_value":"EZKRRE2WQIOA","created_at":"2026-07-05T11:47:36.331933+00:00"},{"alias_kind":"pith_short_16","alias_value":"EZKRRE2WQIOAP3P6","created_at":"2026-07-05T11:47:36.331933+00:00"},{"alias_kind":"pith_short_8","alias_value":"EZKRRE2W","created_at":"2026-07-05T11:47:36.331933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM","json":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM.json","graph_json":"https://pith.science/api/pith-number/EZKRRE2WQIOAP3P6QSKOUAJGDM/graph.json","events_json":"https://pith.science/api/pith-number/EZKRRE2WQIOAP3P6QSKOUAJGDM/events.json","paper":"https://pith.science/paper/EZKRRE2W"},"agent_actions":{"view_html":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM","download_json":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM.json","view_paper":"https://pith.science/paper/EZKRRE2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01274&json=true","fetch_graph":"https://pith.science/api/pith-number/EZKRRE2WQIOAP3P6QSKOUAJGDM/graph.json","fetch_events":"https://pith.science/api/pith-number/EZKRRE2WQIOAP3P6QSKOUAJGDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM/action/storage_attestation","attest_author":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM/action/author_attestation","sign_citation":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM/action/citation_signature","submit_replication":"https://pith.science/pith/EZKRRE2WQIOAP3P6QSKOUAJGDM/action/replication_record"}},"created_at":"2026-07-05T11:47:36.331933+00:00","updated_at":"2026-07-05T11:47:36.331933+00:00"}