{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.09849", "kind": "paper", "url": "https://arxiv.org/abs/2609.09849"}], "authors": ["Tianzhu Zhang", "Weichen Tao", "Changgang Zheng", "Yusheng Zheng", "Long Chen", "Xiaoyi Fan", "Meikang Qiu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.09849", "source_url": "https://arxiv.org/abs/2609.09849"}, "categories": ["General AI", "Language & Knowledge", "cs.NI"], "description": {"en": "NetArtifactBench evaluates the ability of AI agents to repair inconsistent network experiment records while preserving claims that remain supported. It contains 52 instances with injected inconsistencies ranging from direct contradictions to unstated relations across multiple artifacts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.09849", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.09849", "title": "NetArtifactBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Hong Kong", "Tsinghua University", "University of California, Santa Cruz", "Augusta University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.09849", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.09849", "source_url": "https://openalex.org/W7212172391"}, "key": "claire-radar:2609.09849", "modality": null, "name": "NetArtifactBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "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_netartifactbench_554430c3", "origin_source": "arxiv", "recognition_confidence": "0.65", "record_sha256": "3e993b9dcd11008e60b139ded9d2d345e2e86149dbcbaf015d3e231d764ff2b4", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-11T00:52:53.785364Z", "source_url": "https://arxiv.org/abs/2609.09849"}, "publisher": null, "released": "2026-09-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.09849", "source_url": "https://arxiv.org/abs/2609.09849"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-09849", "source": "claire_radar", "source_benchmark_id": "2609.09849", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-10", "attemptedAt": "2026-09-10T12:24:43.080049Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.09849", "observedAt": "2026-09-09T12:31:07.558041Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-10T12:24:43.080049Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The topical niche of network artifacts and agent repair, combined with a small instance count and no released code link, suggests modest early attention.", "score": 35}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-11T00:52:53.785364Z", "inputHash": "19e362991376e8b0cb0c2a9637fe5af009cfa065d799d001b7c05466ce182440", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "To make this property measurable, we introduce NetArtifactBench, which tests whether AI agents can repair inconsistent records derived from public network-system artifacts while preserving claims that remain supported.", "canonicalNameSource": "abstract", "decisionReason": "The paper explicitly introduces NetArtifactBench with a defined task, deterministic scoring, and a public report that enables other teams to run or inspect the benchmark.", "evaluationEvidence": {"reuse": "The benchmark is listed on arXiv with a report that defines the benchmark and evaluation, enabling public inspection and reproduction by other teams.", "scoring": "We evaluate 23 agent configurations across three general-purpose AI agent runtimes using deterministic scoring. The average contract pass rate is 65.3 % across 5,980 outputs", "task": "The benchmark contains 52 instances with injected inconsistencies ranging from direct contradictions to unstated relations spread across several artifacts."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-11T00:52:53.785364Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "NetArtifactBench evaluates the ability of AI agents to repair inconsistent network experiment records while preserving claims that remain supported. It contains 52 instances with injected inconsistencies ranging from direct contradictions to unstated relations across multiple artifacts.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "evaluation protocol evidence"], "snippet": "To make this property measurable, we introduce NetArtifactBench, which tests whether AI agents can repair inconsistent records derived from public network-system artifacts while preserving claims that remain supported."}, "familyId": "bmf_cd2ef37870c4", "firstSeenAt": "2026-09-10", "heat": null, "id": "bm_netartifactbench_554430c3", "indexedAt": "2026-09-10T00:47:26.889471Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.09849", "pdf": "https://arxiv.org/pdf/2609.09849", "project": null, "report": "https://arxiv.org/abs/2609.09849"}, "metrics": [], "motivation": "In recent years, AI agents have evolved into capable assistants that carry out multi-step tasks in digital environments.", "name": "NetArtifactBench", "oneLine": "NetArtifactBench evaluates the ability of AI agents to repair inconsistent network experiment records while preserving claims that remain supported. It contains 52 instances with injected inconsistencies ranging from direct contradictions to unstated relations across multiple artifacts.", "paperTitle": "Can AI Agents Detect and Repair Artifact Drift in Network Experiments?", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.09849", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-10T00:47:26.889471Z"}, "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}, "today": {"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": 1, "historyDate": "2026-09-09", "rank": null, "score": null, "windowDays": 1}, "level": {"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}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.26, "role": "bonus", "value": 26}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 7}, "method": "attention-ranking-v13", "rank": null, "score": 7}}, "readiness": "Paper only", "recognitionConfidence": 0.65, "relation": "introduces", "releasedAt": "2026-09-09", "source": {"authors": ["Tianzhu Zhang", "Weichen Tao", "Changgang Zheng", "Yusheng Zheng", "Long Chen", "Xiaoyi Fan", "Meikang Qiu"], "categories": ["cs.NI", "cs.AI", "cs.SY", "eess.SY"], "id": "2609.09849", "title": "Can AI Agents Detect and Repair Artifact Drift in Network Experiments?", "type": "arxiv", "url": "https://arxiv.org/abs/2609.09849"}, "sourceUpdatedAt": "2026-09-09T07:58:24Z", "topics": ["cs.NI"], "venueAttempts": [], "whyItMatters": "It provides a measurable way to assess artifact integrity, an under-addressed requirement for trustworthy AI operation in network systems, and exposes the difficulty of propagating repairs across interdependent artifacts."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
