{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.31308", "kind": "paper", "url": "https://arxiv.org/abs/2606.31308"}], "authors": ["Lisa Taldir", "Muhammad Ahmad Saeed", "David Defour", "Pablo de Oliveira Castro", "Eric Petit"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.31308", "source_url": "https://arxiv.org/abs/2606.31308"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "InterFLOPBench is a benchmark of 90 C kernels and 1,130 test samples for evaluating LLMs on floating-point error classification across six categories: cancellation, comparison, division by zero, overflow, underflow, and NaN."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.31308", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.31308", "title": "InterFLOPBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Laboratoire d’informatique Parallélisme Réseaux Algorithmes Distribués"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.31308", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.31308", "source_url": "https://openalex.org/W7166816148"}, "key": "claire-radar:2606.31308", "modality": null, "name": "InterFLOPBench", "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_interflopbench_d649e042", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "aceadc594f8624a2e5f3ac2a1645f83eac772049599724876c9f730b92b2e74d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.31308"}, "publisher": null, "released": "2026-06-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.31308", "source_url": "https://arxiv.org/abs/2606.31308"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-31308", "source": "claire_radar", "source_benchmark_id": "2606.31308", "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/2606.31308", "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": "b18394eee69131223a87b869faa349657c075afa90557d84f88fb0cd3a002a4e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "InterFLOPBench is a benchmark of 90 C kernels and 1,130 test samples for evaluating LLMs on floating-point error classification across six categories: cancellation, comparison, division by zero, overflow, underflow, and NaN.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce InterFLOPBench, a benchmark of 90 C kernels with 1 130 test samples designed to evaluate LLMs across six categories of floating-point error: cancellation, comparison, division by zero, overflow, underflow and NaN, compared across 14 LLMs."}, "familyId": "bmf_601ef5f2c623", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_interflopbench_d649e042", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.31308", "paper": "https://arxiv.org/abs/2606.31308", "pdf": "https://arxiv.org/pdf/2606.31308", "project": null, "report": "https://arxiv.org/abs/2606.31308"}, "metrics": [], "motivation": "This paper investigates the capability of Large Language Models (LLMs) to detect and classify floating-point errors statically in software code.", "name": "InterFLOPBench", "oneLine": "InterFLOPBench is a benchmark of 90 C kernels and 1,130 test samples for evaluating LLMs on floating-point error classification across six categories: cancellation, comparison, division by zero, overflow, underflow, and NaN.", "paperTitle": "Benchmarking Large Language Models on Floating-Point Error Classification", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.31308", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-30", "source": {"authors": ["Lisa Taldir", "Muhammad Ahmad Saeed", "David Defour", "Pablo de Oliveira Castro (LI-PaRAD)", "Eric Petit"], "categories": ["cs.AI"], "id": "2606.31308", "title": "Benchmarking Large Language Models on Floating-Point Error Classification", "type": "arxiv", "url": "https://arxiv.org/abs/2606.31308"}, "sourceUpdatedAt": "2026-06-30T08:18:45Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Provides a targeted evaluation for LLM capabilities in static floating-point error detection, a niche but important area. Enables comparison across models and error types."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
