{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.12002", "kind": "paper", "url": "https://arxiv.org/abs/2608.12002"}], "authors": ["Xingyu Yan", "Tingting Dai", "Antonio De Domenico", "Mohamed Sana", "Nicola Piovesan", "Changchang Li", "Bowen Liu", "Kun Jiang", "Mengjie Zhang", "Dingcheng Shan", "Jing-Cheng Pang", "Chenwei Wu", "Sijie Wu", "Lianying Chao", "Haoran Cai", "Jiantao Ye", "Xubin Li", "Simon Mark Lucas", "Xin Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.12002", "source_url": "https://arxiv.org/abs/2608.12002"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "Evaluates AI agents on telecom network troubleshooting tasks, focusing on root cause analysis and path restoration, using expert-grounded metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.12002", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.12002", "title": "CTBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Huawei Technologies (China)", "Huawei Technologies (France)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.12002", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.12002", "source_url": "https://openalex.org/W7202392698"}, "key": "claire-radar:2608.12002", "modality": null, "name": "CTBench", "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": "unknown", "origin_record_id": "bm_ctbench_d210f8ea", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "92247f37ca0a4c2be69d65d66c8c2e70b16e49ec93724cad9c77575dcbd22669", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.12002"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.12002", "source_url": "https://arxiv.org/abs/2608.12002"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-12002", "source": "claire_radar", "source_benchmark_id": "2608.12002", "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/2608.12002", "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"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "fad9dec77a807219b275ceb8cd3b26136f319213f2e66a328a5f67f484c238a7", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates AI agents on telecom network troubleshooting tasks, focusing on root cause analysis and path restoration, using expert-grounded metrics.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "In this paper, we introduce CTBench, a public benchmark for assessing whether an agent behaves like a competent telecom troubleshooting engineer."}, "familyId": "bmf_a5ad32879a12", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_ctbench_d210f8ea", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.12002", "paper": "https://arxiv.org/abs/2608.12002", "pdf": "https://arxiv.org/pdf/2608.12002", "project": null, "report": "https://arxiv.org/abs/2608.12002"}, "metrics": [], "motivation": "Agents are increasingly considered for automating network operations and maintenance, where engineers must diagnose network faults, optimize configurations to enhance services, and reduce operational costs while acting under strict constraints.", "name": "CTBench", "oneLine": "Evaluates AI agents on telecom network troubleshooting tasks, focusing on root cause analysis and path restoration, using expert-grounded metrics.", "paperTitle": "CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.12002", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"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": "2026-08-12", "source": {"authors": ["Xingyu Yan", "Tingting Dai", "Antonio De Domenico", "Mohamed Sana", "Nicola Piovesan", "Changchang Li", "Bowen Liu", "Kun Jiang", "Mengjie Zhang", "Dingcheng Shan", "Jing-Cheng Pang", "Chenwei Wu", "Sijie Wu", "Lianying Chao", "Haoran Cai", "Jiantao Ye", "Xubin Li", "Simon Mark Lucas", "Xin Chen"], "categories": ["cs.AI"], "id": "2608.12002", "title": "CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations", "type": "arxiv", "url": "https://arxiv.org/abs/2608.12002"}, "sourceUpdatedAt": "2026-08-12T12:37:02Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Fills the gap in evaluating AI agents for realistic telecom operations, emphasizing evidence-based diagnosis and practical constraints."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
