{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.12620", "kind": "paper", "url": "https://arxiv.org/abs/2606.12620"}], "authors": ["Luke Patterson", "Li Wang", "Adam Faulkner"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.12620", "source_url": "https://arxiv.org/abs/2606.12620"}, "categories": ["General AI", "Vision & 3D", "cs.SE"], "description": {"en": "HybridCodeAuthorship is a benchmark of Python files with interleaved human- and AI-authored lines, built from CodeSearchNet, for developing and evaluating AI-generated code detection algorithms at line- and chunk-level."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.12620", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.12620", "title": "HybridCodeAuthorship"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.12620", "modality": null, "name": "HybridCodeAuthorship", "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_hybridcodeauthorship_7e92f56f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6248f79227e799e1d5a3602c9e6b2976ff034a6668be5502c1448e5d874a8219", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.12620"}, "publisher": null, "released": "2026-06-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.12620", "source_url": "https://arxiv.org/abs/2606.12620"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-12620", "source": "claire_radar", "source_benchmark_id": "2606.12620", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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/2606.12620", "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": "fc855bb09779b5652619bf4db361935122f3f53543be6fad8ea2cacec60c9b9c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "HybridCodeAuthorship is a benchmark of Python files with interleaved human- and AI-authored lines, built from CodeSearchNet, for developing and evaluating AI-generated code detection algorithms at line- and chunk-level.", "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": "To fill these gaps, we introduce HybridCodeAuthorship, a novel benchmark of Python code files with interleaved human- and AI-authored lines of code to simulate authentic utilization of AI code assistants."}, "familyId": "bmf_bcaf12963fb7", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_hybridcodeauthorship_7e92f56f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.12620", "paper": "https://arxiv.org/abs/2606.12620", "pdf": "https://arxiv.org/pdf/2606.12620", "project": null, "report": "https://arxiv.org/abs/2606.12620"}, "metrics": [], "motivation": "Thanks to the rapid adoption of AI code assistants powered by large language models (LLMs), industry codebases are, increasingly, a hybrid of AI- and human-authored code.", "name": "HybridCodeAuthorship", "oneLine": "HybridCodeAuthorship is a benchmark of Python files with interleaved human- and AI-authored lines, built from CodeSearchNet, for developing and evaluating AI-generated code detection algorithms at line- and chunk-level.", "paperTitle": "HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection", "primaryDomain": "General AI", "publication": {"evidence": "LREC 2026 proceedings (pp. 1520-1532)", "evidenceLevel": "strong-author-metadata", "evidenceUrl": "https://arxiv.org/abs/2606.12620", "source": "arxiv-journal-reference", "status": "publication_reported", "venue": "LREC 2026 proceedings (pp. 1520-1532)", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [{"evidence": [{"level": "strong-author-metadata", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "LREC 2026 proceedings (pp. 1520-1532)", "sourceType": "arxiv-journal-reference", "sourceUrl": "https://arxiv.org/abs/2606.12620"}], "publicationStatus": "published", "venueName": "LREC 2026 proceedings (pp. 1520-1532)"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-10", "source": {"authors": ["Luke Patterson", "Li Wang", "Adam Faulkner"], "categories": ["cs.SE", "cs.AI"], "id": "2606.12620", "title": "HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection", "type": "arxiv", "url": "https://arxiv.org/abs/2606.12620"}, "sourceUpdatedAt": "2026-06-10T19:21:19Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Addresses the need for realistic benchmarks for detecting AI-generated code in industry codebases, which is important for risk management and productivity analysis. Provides a challenging testbed for detection algorithms."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
