{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.27021", "kind": "paper", "url": "https://arxiv.org/abs/2608.27021"}], "authors": ["Kuan-Hao Tseng", "Niruth Bogahawatta", "Yasod Ginige", "Kunjan Patel", "Kosta Dakic", "Suranga Seneviratne"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.27021", "source_url": "https://arxiv.org/abs/2608.27021"}, "categories": ["General AI", "Language & Knowledge", "cs.NI"], "description": {"en": "A benchmark of 200 troubleshooting scenarios across eight network topologies evaluating network troubleshooting LLM agents under unreliable user tickets, including false fault reports and incorrect device attribution."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.27021", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.27021", "title": "FaulT-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["The University of Sydney"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.27021", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.27021", "source_url": "https://openalex.org/W7204566174"}, "key": "claire-radar:2608.27021", "modality": null, "name": "FaulT-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-indexed", "display_eligible": "true", "origin_record_id": "bm_fault-bench_59abb402", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "b98e13870f8c2a6877eab80271e515eb3cc9681f9dc28998c280089d82dcd290", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-31T07:23:36.749451Z", "source_url": "https://arxiv.org/abs/2608.27021"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.27021", "source_url": "https://arxiv.org/abs/2608.27021"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-27021", "source": "claire_radar", "source_benchmark_id": "2608.27021", "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/2608.27021", "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": "Medium", "horizon": "7d", "reason": "The benchmark addresses practical network troubleshooting agent robustness and is likely to attract interest from the agent evaluation community.", "score": 50}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-31T07:23:36.749451Z", "inputHash": "94ce339ee83656aa195aeb02ee7e37e42cb0c317aff4393b4a4e13a7a34ae632", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets", "canonicalNameSource": "paper_title", "decisionReason": "Paper title formally declares FaulT-Bench, describes a repeatable harness and scoring, but no code or data link is provided; publication is provisional.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-31T07:23:36.749451Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark of 200 troubleshooting scenarios across eight network topologies evaluating network troubleshooting LLM agents under unreliable user tickets, including false fault reports and incorrect device attribution.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We present FaulT-Bench, a benchmark of 200 troubleshooting scenarios across eight network topologies, five reimplemented from public practitioner labs, spanning genuine faults, false fault reports, incorrect device attribution, and incorrect root-cause claims."}, "familyId": "bmf_e1ed34f7f725", "firstSeenAt": "2026-08-30", "heat": null, "id": "bm_fault-bench_59abb402", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.27021", "pdf": "https://arxiv.org/pdf/2608.27021", "project": null, "report": "https://arxiv.org/abs/2608.27021"}, "metrics": [], "motivation": "LLM-based agents are increasingly proposed for network fault diagnosis, but existing benchmarks evaluate them only on accurate tickets and always assume a fault is present, conditions rarely met in practice.", "name": "FaulT-Bench", "oneLine": "A benchmark of 200 troubleshooting scenarios across eight network topologies evaluating network troubleshooting LLM agents under unreliable user tickets, including false fault reports and incorrect device attribution.", "paperTitle": "FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.27021", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-30T06:59:55.242506Z"}, "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": 0.85, "relation": "introduces", "releasedAt": "2026-08-27", "source": {"authors": ["Kuan-Hao Tseng", "Niruth Bogahawatta", "Yasod Ginige", "Kunjan Patel", "Kosta Dakic", "Suranga Seneviratne"], "categories": ["cs.NI", "cs.AI"], "id": "2608.27021", "title": "FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets", "type": "arxiv", "url": "https://arxiv.org/abs/2608.27021"}, "sourceUpdatedAt": "2026-08-27T12:07:10Z", "topics": ["cs.NI"], "venueAttempts": [], "whyItMatters": "Evaluates the robustness of network troubleshooting agents against noisy, real-world tickets rather than only accurate inputs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
