{"record": {"aliases": ["Benchmarking Automated Security Patch Backporting: How Far Are We?"], "artifacts": [{"id": "arxiv:2608.17671", "kind": "paper", "url": "https://arxiv.org/abs/2608.17671"}], "authors": ["Jincheng Yang", "Yulong Fu", "Chengwei Liu", "Lyuye Zhang", "Fangyuan Zhang", "Bingyang Ren", "Yang Liu", "Hui Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.17671", "source_url": "https://arxiv.org/abs/2608.17671"}, "categories": ["Code & Software", "Software & AI Compute", "cs.SE"], "description": {"en": "Porting Benchmark evaluates automated security patch backporting using 1,234 curated cases across cross-version, cross-branch, and cross-repository scenarios, with a common evaluation framework and dynamic validation on a subset."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.17671", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.17671", "title": "Porting Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.17671", "modality": null, "name": "Porting Benchmark", "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": "true", "origin_record_id": "bm_benchmarking-automated-security-patch-back_bac96e83", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "e98f264f455b170a5cdfaf7bc1b428645a4053d4b2bcaea1f66355348d9a4ef6", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-25T23:23:46.758372Z", "source_url": "https://arxiv.org/abs/2608.17671"}, "publisher": null, "released": "2026-08-18", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.17671", "source_url": "https://arxiv.org/abs/2608.17671"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-17671", "source": "claire_radar", "source_benchmark_id": "2608.17671", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Benchmarking Automated Security Patch Backporting: How Far Are We?"], "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/2608.17671", "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": "Medium", "horizon": "7d", "reason": "The benchmark is accepted at ASE 2026 with a public artifact and addresses a practical security automation problem, likely drawing interest from software engineering and security communities.", "score": 58}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T23:23:46.758372Z", "inputHash": "05486539de8349aee234d34e43920a768f5db57853f5331184803cc3146ab042", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We present Porting Benchmark, a curated dataset of 1,234 security patch backporting cases spanning cross-version, cross-branch, and cross-repository scenarios, paired with a common evaluation framework.", "canonicalNameSource": "abstract", "decisionReason": "The benchmark is explicitly named, has a curated dataset and common evaluation framework, and the Artifact DOI is provided as a public path.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T23:23:46.758372Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Porting Benchmark evaluates automated security patch backporting using 1,234 curated cases across cross-version, cross-branch, and cross-repository scenarios, with a common evaluation framework and dynamic validation on a subset.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We present Porting Benchmark, a curated dataset of 1,234 security patch backporting cases spanning cross-version, cross-branch, and cross-repository scenarios, paired with a common evaluation framework."}, "familyId": "bmf_47f9bd1f1452", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_benchmarking-automated-security-patch-back_bac96e83", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.17671", "pdf": "https://arxiv.org/pdf/2608.17671", "project": "https://doi.org/10.5281/zenodo.21785770", "report": "https://arxiv.org/abs/2608.17671"}, "metrics": [], "motivation": "Automated security patch backporting is critical for mitigating N-day vulnerabilities.", "name": "Porting Benchmark", "oneLine": "Porting Benchmark evaluates automated security patch backporting using 1,234 curated cases across cross-version, cross-branch, and cross-repository scenarios, with a common evaluation framework and dynamic validation on a subset.", "paperTitle": "Benchmarking Automated Security Patch Backporting: How Far Are We?", "primaryDomain": "Software & AI Compute", "publication": {"evidence": "13 pages, 3 figures. Accepted at ASE 2026. Artifact: https://doi.org/10.5281/zenodo.21785770", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.17671", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ASE 2026", "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "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": 0.55, "relation": "introduces", "releasedAt": "2026-08-18", "source": {"authors": ["Jincheng Yang", "Yulong Fu", "Chengwei Liu", "Lyuye Zhang", "Fangyuan Zhang", "Bingyang Ren", "Yang Liu", "Hui Li"], "categories": ["cs.SE", "cs.AI", "cs.CR"], "id": "2608.17671", "title": "Benchmarking Automated Security Patch Backporting: How Far Are We?", "type": "arxiv", "url": "https://arxiv.org/abs/2608.17671"}, "sourceUpdatedAt": "2026-08-18T11:43:10Z", "topics": ["cs.SE"], "venueAttempts": [{"decisionRaw": "13 pages, 3 figures. Accepted at ASE 2026. Artifact: https://doi.org/10.5281/zenodo.21785770", "evidence": [{"level": "author-claim", "observedAt": "2026-08-19T11:05:13.395391Z", "rawValue": "13 pages, 3 figures. Accepted at ASE 2026. Artifact: https://doi.org/10.5281/zenodo.21785770", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.17671"}], "reviewStatus": "accepted", "venueName": "ASE 2026"}], "whyItMatters": "The benchmark aligns evaluation conditions across five tools and reveals substantial performance degradation on complex patches, highlighting the need for generalizable backporting approaches and realistic executable validation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
