{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.07784", "kind": "paper", "url": "https://arxiv.org/abs/2609.07784"}], "authors": ["Yongchang Peng", "Qingshui Gu", "Liya Zhu", "Ge Zhang", "Duo Wang", "Haodong Wang", "Jingzhe Ding", "Tianhao Yu", "Letian Gao", "Yongjie Zhong", "Chaoxin Li", "Zixin Su", "Jinchao Tao", "Xingyu Ma", "Xin'ao Guo", "Feng Tian", "Shiyuan Dong", "Xiaoyan He", "Sen Liu", "Xin Chen", "Jiajun Li", "Zejia Zhang", "Xi Lin", "Wen Zhang", "Yi Zhu", "Duju Zeng", "Xiang Gao", "Yunyang Wang", "Jiahao Wang", "Yujia Qin", "Jiaheng Liu", "Shen Yan", "Xiaolong Chang", "Wenhao Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.07784", "source_url": "https://arxiv.org/abs/2609.07784"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates LLMs on 248 tasks across 51 scenarios in personal life, white-collar work, learning and research, and cross-domain activities using binary rubrics for explicit and implicit requirements."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.07784", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.07784", "title": "xDailyBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.07784", "modality": null, "name": "xDailyBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_xdailybench_fe82cbbd", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "443798be779f291fd3147c685eebd955b6ec9b479461e4f4037c0c74ade3fdec", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-09T06:27:57.312318Z", "source_url": "https://arxiv.org/abs/2609.07784"}, "publisher": null, "released": "2026-09-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.07784", "source_url": "https://arxiv.org/abs/2609.07784"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-07784", "source": "claire_radar", "source_benchmark_id": "2609.07784", "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": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.07784", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The benchmark targets a practical real-world niche with broad applicability, but lack of artifact release may limit immediate attention.", "score": 55}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T06:27:57.312318Z", "inputHash": "bc7e573dc6b6c081297aefd10dd60617d8141e203f4648e8dcbc3f30c07eec1b", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "Deferred because the paper does not provide evidence of a released task suite, evaluator, or public path for external teams to run or inspect the benchmark.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-09T06:27:57.312318Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLMs on 248 tasks across 51 scenarios in personal life, white-collar work, learning and research, and cross-domain activities using binary rubrics for explicit and implicit requirements.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce xDailyBench, a benchmark of 248 carefully curated tasks spanning 51 scenarios across personal life, white-collar work, learning and research, and cross-domain activities."}, "familyId": "bmf_645de4b84ba4", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_xdailybench_fe82cbbd", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.07784", "pdf": "https://arxiv.org/pdf/2609.07784", "project": null, "report": "https://arxiv.org/abs/2609.07784"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly used for everyday assistance, yet existing benchmarks only partially reflect the requests users naturally make in practice.", "name": "xDailyBench", "oneLine": "Evaluates LLMs on 248 tasks across 51 scenarios in personal life, white-collar work, learning and research, and cross-domain activities using binary rubrics for explicit and implicit requirements.", "paperTitle": "xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.07784", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-07", "source": {"authors": ["Yongchang Peng", "Qingshui Gu", "Liya Zhu", "Ge Zhang", "Duo Wang", "Haodong Wang", "Jingzhe Ding", "Tianhao Yu", "Letian Gao", "Yongjie Zhong", "Chaoxin Li", "Zixin Su", "Jinchao Tao", "Xingyu Ma", "Xin'ao Guo", "Feng Tian", "Shiyuan Dong", "Xiaoyan He", "Sen Liu", "Xin Chen", "Jiajun Li", "Zejia Zhang", "Xi Lin", "Wen Zhang", "Yi Zhu", "Duju Zeng", "Xiang Gao", "Yunyang Wang", "Jiahao Wang", "Yujia Qin", "Jiaheng Liu", "Shen Yan", "Xiaolong Chang", "Wenhao Huang"], "categories": ["cs.AI"], "id": "2609.07784", "title": "xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems", "type": "arxiv", "url": "https://arxiv.org/abs/2609.07784"}, "sourceUpdatedAt": "2026-09-07T17:30:58Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Addresses the gap between existing benchmarks and real-world user requests by focusing on implicit requirement inference and professional consultation tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
