{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05001", "kind": "paper", "url": "https://arxiv.org/abs/2606.05001"}], "authors": ["Pranshav Gajjar", "Ali Mamaghani", "Dinesh Bharadia", "Vijay K Shah"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05001", "source_url": "https://arxiv.org/abs/2606.05001"}, "categories": ["Agents", "Code", "Code & Software", "Software & AI Compute"], "description": {"en": "TeleSWEBench is a commit-driven benchmark with 734 questions derived from real developer commits in the srsRAN 5G repository. It evaluates LLM-powered software engineering agents in the telecommunications domain using executable unit tests and a hierarchical LLM-as-a-Judge framework across three difficulty tiers."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05001", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05001", "title": "TeleSWEBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["North Carolina State University", "University of California San Diego"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.05001", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.05001", "source_url": "https://openalex.org/W7163529031"}, "key": "claire-radar:2606.05001", "modality": null, "name": "TeleSWEBench", "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": "unknown", "origin_record_id": "bm_teleswebench_49d08856", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "b6167441c3f3bec8a29e7ad69f1059ed223b2cb88999a8f2fbfc0bac67a7607e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05001"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05001", "source_url": "https://arxiv.org/abs/2606.05001"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05001", "source": "claire_radar", "source_benchmark_id": "2606.05001", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["Software & AI Compute"], "area": "Code & Software", "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/2606.05001", "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": "Medium", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "5e92635cd9765bbd9dff8904880eb25ede448fc14a5a22b998e2c055aa3e2ddd", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "TeleSWEBench is a commit-driven benchmark with 734 questions derived from real developer commits in the srsRAN 5G repository. It evaluates LLM-powered software engineering agents in the telecommunications domain using executable unit tests and a hierarchical LLM-as-a-Judge framework across three difficulty tiers.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "In this paper, we introduce TeleSWEBench, the first commit-driven benchmark specifically designed to measure an agent's performance in the telecom domain."}, "familyId": "bmf_ac181644ed2c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_teleswebench_49d08856", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.05001", "paper": "https://arxiv.org/abs/2606.05001", "pdf": "https://arxiv.org/pdf/2606.05001", "project": null, "report": "https://arxiv.org/abs/2606.05001"}, "metrics": [], "motivation": "With the telecommunications field embracing zero touch management alongside novel O-RAN and AI-RAN frameworks, contemporary telecom networks now function as immensely intricate and heavily softwareized codebases.", "name": "TeleSWEBench", "oneLine": "TeleSWEBench is a commit-driven benchmark with 734 questions derived from real developer commits in the srsRAN 5G repository. It evaluates LLM-powered software engineering agents in the telecommunications domain using executable unit tests and a hierarchical LLM-as-a-Judge framework across three difficulty tiers.", "paperTitle": "TeleSWEBench: A Commit-Driven Benchmark for Evaluating LLM-Powered Software Engineering in Telecommunications", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05001", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.05001"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Pranshav Gajjar", "Ali Mamaghani", "Dinesh Bharadia", "Vijay K Shah"], "categories": ["cs.SE"], "id": "2606.05001", "title": "TeleSWEBench: A Commit-Driven Benchmark for Evaluating LLM-Powered Software Engineering in Telecommunications", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05001"}, "sourceUpdatedAt": "2026-06-03T15:19:40Z", "topics": ["Agents", "Code"], "venueAttempts": [], "whyItMatters": "General-purpose coding benchmarks fail to capture the stateful logic and strict requirements of telecom software, leaving a gap in evaluating ASE tools for this domain. TeleSWEBench provides a domain-specific benchmark with executable tests and a judge framework."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
