{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.23893", "kind": "paper", "url": "https://arxiv.org/abs/2608.23893"}], "authors": ["Ismail Lamaakal"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.23893", "source_url": "https://arxiv.org/abs/2608.23893"}, "categories": ["Cybersecurity", "Finance", "Language & Knowledge", "cs.AI"], "description": {"en": "RuleShift-Bench is a benchmark for evaluating concept drift under evolving concept definitions, spanning multiple data types and revision types. It assesses the ability of learning systems to adapt to rule-induced concept shifts with high accuracy while minimizing reprocessing."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.23893", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.23893", "title": "RuleShift-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.23893", "modality": null, "name": "RuleShift-Bench", "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_ruleshift-bench_b86e99e6", "origin_source": "arxiv", "recognition_confidence": "0.65", "record_sha256": "23458e02bb1ca19c14b1cbbb6804859268dd28d0201db036a28466651fdbe03a", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:10:57.123445Z", "source_url": "https://arxiv.org/abs/2608.23893"}, "publisher": null, "released": "2026-08-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.23893", "source_url": "https://arxiv.org/abs/2608.23893"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-23893", "source": "claire_radar", "source_benchmark_id": "2608.23893", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Cybersecurity", "Finance"], "area": "Language & Knowledge", "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/2608.23893", "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 addresses a relevant problem in machine learning and data management, with broad applicability across domains.", "score": 45}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:22:25.189955Z", "inputHash": "8561521e6bf7c183e317ac03c589db12807ca62a2ad495f34d78af269afc3eca", "model": "deepseek-v4-flash"}, "curation": {"canonicalNameEvidence": "We also introduce RuleShift-Bench, spanning financial, demographic, cybersecurity, and graph-structured data with threshold, predicate, logical, relational, recurring, and mixed concept revisions.", "canonicalNameSource": "abstract", "decisionReason": "The paper introduces a named benchmark with specified domains and revision types, and indicates release, meeting the benchmark criteria.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:10:57.123445Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "RuleShift-Bench is a benchmark for evaluating concept drift under evolving concept definitions, spanning multiple data types and revision types. It assesses the ability of learning systems to adapt to rule-induced concept shifts with high accuracy while minimizing reprocessing.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "evaluation protocol evidence"], "snippet": "We also introduce RuleShift-Bench, spanning financial, demographic, cybersecurity, and graph-structured data with threshold, predicate, logical, relational, recurring, and mixed concept revisions."}, "familyId": "bmf_a4b2fc88cb45", "firstSeenAt": "2026-08-26", "heat": null, "id": "bm_ruleshift-bench_b86e99e6", "indexedAt": "2026-08-26T06:08:22.244942Z", "industrySectors": ["Cybersecurity", "Financial Services"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.23893", "pdf": "https://arxiv.org/pdf/2608.23893", "project": null, "report": "https://arxiv.org/abs/2608.23893"}, "metrics": [], "motivation": "Learning systems deployed over long periods must adapt not only to statistical changes in incoming data, but also to revisions of the definitions that generate their prediction targets.", "name": "RuleShift-Bench", "oneLine": "RuleShift-Bench is a benchmark for evaluating concept drift under evolving concept definitions, spanning multiple data types and revision types. It assesses the ability of learning systems to adapt to rule-induced concept shifts with high accuracy while minimizing reprocessing.", "paperTitle": "Provenance Guided Incremental Learning Under Evolving Concept Definitions", "primaryDomain": "Cybersecurity", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.23893", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-26T06:08:22.244942Z"}, "publications": [], "publishers": [{"name": "RuleShift-Bench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.23893"}], "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": 0.65, "relation": "introduces", "releasedAt": "2026-08-24", "source": {"authors": ["Ismail Lamaakal"], "categories": ["cs.AI", "cs.LG"], "id": "2608.23893", "title": "Provenance Guided Incremental Learning Under Evolving Concept Definitions", "type": "arxiv", "url": "https://arxiv.org/abs/2608.23893"}, "sourceUpdatedAt": "2026-08-24T23:03:10Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "The benchmark addresses the challenge of adapting learning systems to explicit concept revisions, which is common in real-world deployed systems. It provides a standardized evaluation to compare methods for incremental learning and data maintenance."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
