{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.11180", "kind": "paper", "url": "https://arxiv.org/abs/2609.11180"}], "authors": ["Qibai Chen", "Zeming Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.11180", "source_url": "https://arxiv.org/abs/2609.11180"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "A benchmark of LLM version-constraint resolution semantics across npm, PEP 440, and Cargo, with 240 machine-checkable items."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.11180", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.11180", "title": "SemVerBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Brown University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.11180", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.11180", "source_url": "https://openalex.org/W7212243807"}, "key": "claire-radar:2609.11180", "modality": null, "name": "SemVerBench", "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_semverbench_81ce3f52", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "af4700fdc56982385837d33e3f561fd992ec7a89364e922ab980f4d4cf490413", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-14T00:43:53.625753Z", "source_url": "https://arxiv.org/abs/2609.11180"}, "publisher": null, "released": "2026-09-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.11180", "source_url": "https://arxiv.org/abs/2609.11180"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-11180", "source": "claire_radar", "source_benchmark_id": "2609.11180", "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/2609.11180", "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 topic is relevant to LLM code capabilities but the absence of artifacts will cap early engagement.", "score": 30}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-14T00:43:53.625753Z", "inputHash": "0769445541d8a29085f89e350c4249891b27984837b8bb3825857d47e0b227f5", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "No dataset or code is provided, and the paper does not establish a public reusable path.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-14T00:43:53.625753Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark of LLM version-constraint resolution semantics across npm, PEP 440, and Cargo, with 240 machine-checkable items.", "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 SemVerBench, the first benchmark of LLM version-constraint resolution semantics across three ecosystems (npm, PEP 440, Cargo): 240 machine-checkable items with unique answers, built author-neutrally from four balanced sources (each ecosystem's official test suite plus three frontier LLM proposers) and labeled by a non-circular two-implementation oracle."}, "familyId": "bmf_66f09ec0c858", "firstSeenAt": "2026-09-11", "heat": null, "id": "bm_semverbench_81ce3f52", "indexedAt": "2026-09-11T00:48:15.671466Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.11180", "pdf": "https://arxiv.org/pdf/2609.11180", "project": null, "report": "https://arxiv.org/abs/2609.11180"}, "metrics": [], "motivation": "Large language model (LLM) coding agents constantly decide whether a version satisfies a constraint such as ^1.2.3 or >=2.0,<3, yet their grasp of version-constraint semantics has never been measured directly.", "name": "SemVerBench", "oneLine": "A benchmark of LLM version-constraint resolution semantics across npm, PEP 440, and Cargo, with 240 machine-checkable items.", "paperTitle": "SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at the 38th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2026). 8 pages, 6 tables", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.11180", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "38th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2026)", "verifiedAt": "2026-09-11T00:48:15.671466Z"}, "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": "2026-09-10", "source": {"authors": ["Qibai Chen", "Zeming Liu"], "categories": ["cs.AI", "cs.SE"], "id": "2609.11180", "title": "SemVerBench: Benchmarking LLM Comprehension of Version-Constraint Resolution Semantics", "type": "arxiv", "url": "https://arxiv.org/abs/2609.11180"}, "sourceUpdatedAt": "2026-09-10T07:34:44Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "Accepted at the 38th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2026). 8 pages, 6 tables", "evidence": [{"level": "author-claim", "observedAt": "2026-09-11T00:48:15.671466Z", "rawValue": "Accepted at the 38th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2026). 8 pages, 6 tables", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.11180"}], "reviewStatus": "accepted", "venueName": "38th IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2026)"}], "whyItMatters": "Tests whether LLMs correctly interpret version constraints, a critical skill for software engineering tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
