{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.25996", "kind": "paper", "url": "https://arxiv.org/abs/2607.25996"}], "authors": ["Yanlin Wang", "Suiquan Wang", "Yanli Wang", "Bowen Zhang", "Daya Guo", "Jiachi Chen", "Zibin Zheng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.25996", "source_url": "https://arxiv.org/abs/2607.25996"}, "categories": ["Code & Software", "Long Context", "Reasoning", "Software & AI Compute"], "description": {"en": "Evaluates long-context LLMs on repository-level code reasoning through Output Prediction and Call Chain Prediction tasks, using dynamic tracing and I/O rewriting to reduce memorization."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.25996", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.25996", "title": "RepoReasoner"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Sun Yat-sen University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.25996", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.25996", "source_url": "https://openalex.org/W7171709386"}, "key": "claire-radar:2607.25996", "modality": null, "name": "RepoReasoner", "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_reporeasoner_6d64b1f4", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e877fcdb883ad388f133cfdeb808cad068b906fce9309ee2979897293ce7134d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.25996"}, "publisher": null, "released": "2026-07-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.25996", "source_url": "https://arxiv.org/abs/2607.25996"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-25996", "source": "claire_radar", "source_benchmark_id": "2607.25996", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "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/2607.25996", "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": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-21T04:30:40.934319Z", "inputHash": "9e134949cc2337612f71aabfaf0e36c56bd9e5aacd353607585221c1faa5fbd8", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates long-context LLMs on repository-level code reasoning through Output Prediction and Call Chain Prediction tasks, using dynamic tracing and I/O rewriting to reduce memorization.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning."}, "familyId": "bmf_edc74b50c095", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_reporeasoner_6d64b1f4", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.25996", "paper": "https://arxiv.org/abs/2607.25996", "pdf": "https://arxiv.org/pdf/2607.25996", "project": null, "report": "https://arxiv.org/abs/2607.25996"}, "metrics": [], "motivation": "Recent large language models (LLMs) have shown strong performance on software engineering tasks, yet most existing benchmarks evaluate code reasoning at the function level, where all relevant information is localized.", "name": "RepoReasoner", "oneLine": "Evaluates long-context LLMs on repository-level code reasoning through Output Prediction and Call Chain Prediction tasks, using dynamic tracing and I/O rewriting to reduce memorization.", "paperTitle": "RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.25996", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "RepoReasoner Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.25996"}], "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": "2026-07-28", "source": {"authors": ["Yanlin Wang", "Suiquan Wang", "Yanli Wang", "Bowen Zhang", "Daya Guo", "Jiachi Chen", "Zibin Zheng"], "categories": ["cs.SE"], "id": "2607.25996", "title": "RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2607.25996"}, "sourceUpdatedAt": "2026-07-28T17:12:41Z", "topics": ["Long Context", "Reasoning"], "venueAttempts": [], "whyItMatters": "Assesses cross-file reasoning capabilities that are critical for real-world software engineering, identifying limitations beyond function-level benchmarks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
