{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.00918", "kind": "paper", "url": "https://arxiv.org/abs/2609.00918"}, {"id": "gh:zhongruchen/rpcbench", "kind": "repo", "url": "https://github.com/ZhongruChen/RPCBench"}], "authors": ["Zhongru Chen", "Yuan Wu", "Yi Chang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.00918", "source_url": "https://arxiv.org/abs/2609.00918"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates LLM-based recommendation assistants on detecting, localizing, and handling faulty premises in natural-language recommendation requests."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.00918", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.00918", "title": "RPCBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Jilin University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.00918", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.00918", "source_url": "https://openalex.org/W7206182156"}, "key": "claire-radar:2609.00918", "modality": null, "name": "RPCBench", "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": "true", "origin_record_id": "bm_rpcbench_c42d6a6c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f331fc9c059fa87a23426e0a2321f4ccbb34921ec89ad7f29b1b77a9d48296c4", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-03T00:59:34.317835Z", "source_url": "https://arxiv.org/abs/2609.00918"}, "publisher": null, "released": "2026-09-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.00918", "source_url": "https://arxiv.org/abs/2609.00918"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-00918", "source": "claire_radar", "source_benchmark_id": "2609.00918", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-02", "attemptedAt": "2026-09-02T06:30:32.214812Z", "githubRepo": "https://github.com/ZhongruChen/RPCBench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.00918", "observedAt": "2026-09-02T06:30:32.214812Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-02T06:30:32.214812Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-02T06:30:32.214812Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark has a large dataset (4,623 instances), multiple models, and a clear task relevant to recommendation systems.", "score": 65}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-03T00:59:34.317835Z", "inputHash": "fdd5d68e097d834f2dcc6f2b5fd9f75f3278abb3ba60329669e325ec3dd533c9", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark is formally named, has a complete dataset, clear scoring rules, and a public code repository for reproducible evaluation.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-03T00:59:34.317835Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLM-based recommendation assistants on detecting, localizing, and handling faulty premises in natural-language recommendation requests.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce RPCBench, a benchmark for evaluating Recommender-Premise Critique: the ability to detect, diagnose, and properly handle faulty premises in natural-language recommendation requests."}, "familyId": "bmf_7d77649330d3", "firstSeenAt": "2026-09-02", "heat": null, "id": "bm_rpcbench_c42d6a6c", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": "https://github.com/ZhongruChen/RPCBench", "data": null, "paper": "https://arxiv.org/abs/2609.00918", "pdf": "https://arxiv.org/pdf/2609.00918", "project": null, "report": "https://arxiv.org/abs/2609.00918"}, "metrics": [], "motivation": "Large language models are increasingly used as interactive recommender assistants.", "name": "RPCBench", "oneLine": "Evaluates LLM-based recommendation assistants on detecting, localizing, and handling faulty premises in natural-language recommendation requests.", "paperTitle": "RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.00918", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "publishers": [{"name": "Zhongru Chen", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/ZhongruChen/RPCBench"}], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 119, "score": 23}, "method": "attention-ranking-v13", "rank": 119, "score": 23}, "90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 312, "score": 23}, "method": "attention-ranking-v13", "rank": 312, "score": 23}, "today": {"confidence": "Low", "coverage": 0.25, "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": 2, "historyDate": "2026-08-31", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"normalization": "percentile", "normalized": 0.3333333333333333, "percentile": 0.3333333333333333, "value": 0}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.62, "role": "bonus", "value": 62}}, "confidence": "Low", "coverage": 0.25, "rank": 4, "score": 49}, "method": "attention-ranking-v13", "rank": 4, "score": 49}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-01", "source": {"authors": ["Zhongru Chen", "Yuan Wu", "and Yi Chang"], "categories": ["cs.AI", "cs.CL"], "id": "2609.00918", "title": "RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation", "type": "arxiv", "url": "https://arxiv.org/abs/2609.00918"}, "sourceUpdatedAt": "2026-09-01T08:44:56Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Addresses a gap in evaluating models' proactive critique of faulty premises, which is critical for reliable and safe recommendation systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
