{"record": {"aliases": [], "artifacts": [{"id": "hf:opentwbench/tw-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/OpenTWBench/tw-bench"}], "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Taiwan benchmark dataset with claimed leaderboard and methodology on an external site."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://huggingface.co/datasets/OpenTWBench/tw-bench", "source": "claire_radar", "source_url": "https://huggingface.co/datasets/OpenTWBench/tw-bench", "title": "tw-bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:huggingface:opentwbench/tw-bench", "modality": null, "name": "tw-bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-candidate", "display_eligible": "false", "origin_record_id": "bm_tw-bench_62d8b3a2", "origin_source": "huggingface", "recognition_confidence": "0.4", "record_sha256": "3fe68d29be89c1b6bd8edce475a34fc40c283ef14054186b6e26adf287b5ac78", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-26T06:15:55.708965Z", "source_url": "https://huggingface.co/datasets/OpenTWBench/tw-bench"}, "publisher": null, "released": "2026-08-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:huggingface:opentwbench/tw-bench", "source_url": "https://huggingface.co/datasets/OpenTWBench/tw-bench"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-huggingface-opentwbench-tw-bench", "source": "claire_radar", "source_benchmark_id": "huggingface:opentwbench/tw-bench", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": "OpenTWBench/tw-bench", "hfDatasetDownloads": 62, "hfDatasetLikes": 0, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-08-24", "state": "stale"}, "hfDatasetLikes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-08-24", "state": "stale"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "stale"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Excluded due to deferred status and insufficient evidence to forecast attention.", "score": 0}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:15:55.708965Z", "inputHash": "64f6d3d481891a9319326729298ddba2126759bd558600533cb93247918f489b", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "Only an unverified Hugging Face dataset link is present; no independent source confirms the benchmark's name or formal release.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:15:55.708965Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Taiwan benchmark dataset with claimed leaderboard and methodology on an external site.", "discoverySources": [{"id": "huggingface:opentwbench/tw-bench", "type": "huggingface", "url": "https://huggingface.co/datasets/OpenTWBench/tw-bench"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["discovered via huggingface", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "🔗 opentwbench.ai · leaderboard, methodology, submissions from datasets import load_dataset ds = load_dataset(\"OpenTWBench/tw-bench\", \"dentistry\", split=\"test\") ds = load_dataset(\"OpenTWBench/tw-bench\", \"field_medicine\", split=\"test\") ds =… See the full description on the dataset page: https://huggingface.co/datasets/OpenTWBench/tw-bench."}, "familyId": "bmf_be1e92b1a963", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_tw-bench_62d8b3a2", "indexedAt": "2026-08-23T05:46:57.857309Z", "industrySectors": [], "links": {"data": "https://huggingface.co/datasets/OpenTWBench/tw-bench", "paper": "https://huggingface.co/datasets/OpenTWBench/tw-bench", "report": "https://huggingface.co/datasets/OpenTWBench/tw-bench"}, "metrics": [], "motivation": "OpenTWBench 255,854 multiple-choice questions across 148 academic subjects, measuring what a language model knows about Taiwan — in Traditional Chinese, from the national examinations that license Taiwan's regulated professions.", "name": "tw-bench", "oneLine": "Taiwan benchmark dataset with claimed leaderboard and methodology on an external site.", "paperTitle": "tw-bench", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://huggingface.co/datasets/OpenTWBench/tw-bench", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T05:46:57.857309Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.3, "datasetDownloadRank": 73, "datasetRankPopulation": 85, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.42665969461956704, "value": 62}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.3, "rank": 83, "score": 48}, "method": "attention-ranking-v13", "rank": 83, "score": 48}}, "readiness": "Inspectable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-22", "source": {"authors": ["OpenTWBench"], "categories": [], "id": "huggingface:opentwbench/tw-bench", "title": "tw-bench", "type": "huggingface", "url": "https://huggingface.co/datasets/OpenTWBench/tw-bench"}, "sourceUpdatedAt": "2026-08-22T13:43:56.000Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Potential localized evaluation resource, but unverified dataset alone does not establish a formal benchmark release."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
