{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.30300", "kind": "paper", "url": "https://arxiv.org/abs/2608.30300"}], "authors": ["Zijian Luo", "Runzhi He", "Pengfei Gao", "Yu Kang", "Zeqi Lin", "Minghua Ma", "Qingwei Lin", "Saravan Rajmohan", "Yongqiang Tian"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.30300", "source_url": "https://arxiv.org/abs/2608.30300"}, "categories": ["Code & Software", "General AI", "cs.SE"], "description": {"en": "Evaluates coding agents on 203 real-world dependency-upgrade tasks requiring source adaptation, scored by task completion rate."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.30300", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.30300", "title": "DEPBENCH"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.30300", "modality": null, "name": "DEPBENCH", "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_depbench_c7c815d1", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "84917664d40028b1d2c677100601b4e8b05fd185cc5bf2aa9f8a28b292f7edee", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-02T05:23:11.715633Z", "source_url": "https://arxiv.org/abs/2608.30300"}, "publisher": null, "released": "2026-08-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.30300", "source_url": "https://arxiv.org/abs/2608.30300"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-30300", "source": "claire_radar", "source_benchmark_id": "2608.30300", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T05:12:51.621571Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.30300", "observedAt": "2026-08-31T04:56:28.279469Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T05:12:51.621571Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Insufficient public release evidence limits anticipated attention during the first week.", "score": 0}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-02T05:23:11.715633Z", "inputHash": "cfb61ff37f3a3491ec928707f7a2734d6466063f2402c9f343eaf3e17724e74d", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The benchmark is named DEPBENCH in the abstract, but the paper title does not include the benchmark name and no public artifact evidence is provided, making a stable release unclear.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-02T05:23:11.715633Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates coding agents on 203 real-world dependency-upgrade tasks requiring source adaptation, scored by task completion rate.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "In this paper, we introduce DEPBENCH, a benchmark consisting of 203 real-world dependency-upgrade tasks across five package ecosystems spanning five language communities, each involving hidden code-level changes that require source code adaptation."}, "familyId": "bmf_6fd9e62d329e", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_depbench_c7c815d1", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.30300", "pdf": "https://arxiv.org/pdf/2608.30300", "project": null, "report": "https://arxiv.org/abs/2608.30300"}, "metrics": [], "motivation": "Modern software systems rely heavily on third-party dependencies, but upgrading those dependencies remains a costly maintenance activity.", "name": "DEPBENCH", "oneLine": "Evaluates coding agents on 203 real-world dependency-upgrade tasks requiring source adaptation, scored by task completion rate.", "paperTitle": "Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.30300", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "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": null, "historyDate": null, "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": "2026-08-31", "source": {"authors": ["Zijian Luo", "Runzhi He", "Pengfei Gao", "Yu Kang", "Zeqi Lin", "Minghua Ma", "Qingwei Lin", "Saravan Rajmohan", "Yongqiang Tian"], "categories": ["cs.SE"], "id": "2608.30300", "title": "Update from Hell: Can Coding Agents Survive Hidden Breakage in Dependency Upgrades?", "type": "arxiv", "url": "https://arxiv.org/abs/2608.30300"}, "sourceUpdatedAt": "2026-08-31T06:13:51Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Highlights a gap in agent capability for hidden dependency breakage, a common maintenance challenge."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
