{"record": {"aliases": ["RAD: Rule-Augmented Relational Anomaly Detection", "RAD"], "artifacts": [{"id": "arxiv:2608.23468", "kind": "paper", "url": "https://arxiv.org/abs/2608.23468v1"}, {"id": "gh:noahd15/rad_relationalanomalydetection", "kind": "repo", "url": "https://github.com/noahd15/RAD_RelationalAnomalyDetection"}], "authors": ["Noah Dahle", "Anne Tumlin", "Ngoc Tran", "Xenofon Koutsoukos", "Tyler Derr"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.23468", "source_url": "https://arxiv.org/abs/2608.23468"}, "categories": ["Cybersecurity", "Vision & 3D", "cs.LG"], "description": {"en": "The Relational Anomaly Detection Benchmark evaluates anomaly detection in multi-table relational databases, spanning three settings: LANL cybersecurity events, Amazon user churn, and H&M user churn. It provides standardized tasks and evaluation protocols for relational anomaly detection methods."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.23468v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.23468v1", "title": "Relational Anomaly Detection Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.23468", "modality": null, "name": "Relational Anomaly Detection 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_rad-rule-augmented-relational-anomaly-dete_cc65accb", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "b8c325af1bc669ed04bac0a6c858dc34c193448d42993c29ec0bfee6aa99f761", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:18:56.318436Z", "source_url": "https://arxiv.org/abs/2608.23468v1"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.23468", "source_url": "https://arxiv.org/abs/2608.23468v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-23468", "source": "claire_radar", "source_benchmark_id": "2608.23468", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["RAD: Rule-Augmented Relational Anomaly Detection", "RAD"], "annotation": "Unknown", "applicationDomains": ["Cybersecurity"], "area": "Vision & 3D", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-25T23:36:26.005677Z", "githubRepo": "https://github.com/noahd15/RAD_RelationalAnomalyDetection", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.23468", "observedAt": "2026-08-25T23:36:26.005677Z", "signalStatus": {"githubStars": {"observedAt": "2026-08-25T23:36:26.005677Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-25T23:36:26.005677Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark covers security and e-commerce applications, tapping into multiple domains and potentially attracting broad interest.", "score": 50}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:22:25.189955Z", "inputHash": "b28b8fd3c6c9ba76f278dc1ba7339b2ce556d3d85aa8e6ebc144f44c57133ae4", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "we introduce a relational anomaly detection benchmark spanning three settings", "canonicalNameSource": "abstract", "decisionReason": "The benchmark includes code and data availability, a clear task definition, and standard evaluation metrics, making it reusable by other teams.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "The Relational Anomaly Detection Benchmark evaluates anomaly detection in multi-table relational databases, spanning three settings: LANL cybersecurity events, Amazon user churn, and H&M user churn. It provides standardized tasks and evaluation protocols for relational anomaly detection methods.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To evaluate this setting, we introduce a relational anomaly detection benchmark spanning three settings: LANL cybersecurity event detection and two unexpected user-churn anomaly tasks derived from Amazon and H&M relational databases."}, "familyId": "bmf_04cbdb070b25", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_rad-rule-augmented-relational-anomaly-dete_cc65accb", "indexedAt": "2026-08-25T16:21:05.134052Z", "industrySectors": ["Cybersecurity"], "links": {"code": "https://github.com/noahd15/RAD_RelationalAnomalyDetection", "data": null, "paper": "http://arxiv.org/abs/2608.23468v1", "pdf": "https://arxiv.org/pdf/2608.23468v1", "project": null, "report": "http://arxiv.org/abs/2608.23468v1"}, "metrics": [], "motivation": "Anomaly detection is often applied to data stored in relational databases, yet most existing methods require flattening multiple tables into a single feature matrix.", "name": "Relational Anomaly Detection Benchmark", "oneLine": "The Relational Anomaly Detection Benchmark evaluates anomaly detection in multi-table relational databases, spanning three settings: LANL cybersecurity events, Amazon user churn, and H&M user churn. It provides standardized tasks and evaluation protocols for relational anomaly detection methods.", "paperTitle": "RAD: Rule-Augmented Relational Anomaly Detection", "primaryDomain": "Cybersecurity", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.23468v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-25T16:21:05.134052Z"}, "publications": [], "publishers": [{"name": "RAD Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/noahd15/RAD_RelationalAnomalyDetection"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": 0.18928571428571428, "value": 0}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 103, "score": 33}, "method": "attention-ranking-v11", "rank": 103, "score": 33}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": 0.11716621253405994, "value": 0}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 316, "score": 29}, "method": "attention-ranking-v11", "rank": 316, "score": 29}}, "readiness": "Runnable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Noah Dahle", "Anne Tumlin", "Ngoc Tran", "Xenofon Koutsoukos", "Tyler Derr"], "categories": ["cs.LG", "cs.CR", "cs.DB"], "id": "2608.23468", "title": "RAD: Rule-Augmented Relational Anomaly Detection", "type": "arxiv", "url": "http://arxiv.org/abs/2608.23468v1"}, "sourceUpdatedAt": "2026-08-24T16:36:17Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "The benchmark addresses the gap in evaluating anomaly detection that preserves relational structure, which is common in real-world databases. It provides a common ground for comparing methods and advancing research in relational learning."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
