{"record": {"aliases": ["benchmark-llms-landuse-relevance", "Land-use relevance: small-LLM benchmark results"], "artifacts": [{"id": "hf:noeflandre/benchmark-llms-landuse-relevance", "kind": "dataset", "url": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance"}], "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "This entry is a dataset of predictions and scores for small LLMs on a land-use relevance classification task, not an original standalone benchmark with a stable evaluation contract."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance", "source": "claire_radar", "source_url": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance", "title": "Land-use relevance benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:huggingface:noeflandre/benchmark-llms-landuse-relevance", "modality": null, "name": "Land-use relevance benchmark", "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-candidate", "display_eligible": "false", "origin_record_id": "bm_benchmark-llms-landuse-relevance_7050e5ea", "origin_source": "huggingface", "recognition_confidence": "0.4", "record_sha256": "2b39694641850c85d7c3e04550590927c815581d2659c7e0c9712455417a6c45", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-16T01:08:00.372065Z", "source_url": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance"}, "publisher": null, "released": "2026-09-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:huggingface:noeflandre/benchmark-llms-landuse-relevance", "source_url": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-huggingface-noeflandre-benchmark-llms-landuse-relevance", "source": "claire_radar", "source_benchmark_id": "huggingface:noeflandre/benchmark-llms-landuse-relevance", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["benchmark-llms-landuse-relevance", "Land-use relevance: small-LLM benchmark results"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-14", "attemptedAt": "2026-09-14T01:54:58.773663Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": "NoeFlandre/benchmark-llms-landuse-relevance", "hfDatasetDownloads": 0, "hfDatasetLikes": 0, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-09-14T01:54:58.773663Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"observedAt": "2026-09-14T01:54:58.773663Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-09-14T01:54:58.773663Z", "state": "fresh"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Forecast omitted for excluded records.", "score": 0}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-16T01:08:00.372065Z", "inputHash": "0c59c77872f5142a7885d33c4ab45d0f1c284b0140418537b3a6a7acaef233de", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "# Land-use relevance benchmark", "canonicalNameSource": "official_readme", "decisionReason": "The artifact is a result dataset for an existing sentence classification task; it does not declare a formal benchmark name or provide a repeatable scoring protocol beyond the stored predictions.", "evaluationEvidence": {"reuse": "Code: https://github.com/NoeFlandre/benchmark-llms-landuse-relevance", "scoring": "Scores are recomputed from the published predictions.", "task": "`benchmark.csv`; 154 labelled sentences; greedy decoding; `max_new_tokens=4096`; seed 0."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-16T01:08:00.372065Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "This entry is a dataset of predictions and scores for small LLMs on a land-use relevance classification task, not an original standalone benchmark with a stable evaluation contract.", "discoverySources": [{"id": "huggingface:noeflandre/benchmark-llms-landuse-relevance", "type": "huggingface", "url": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["discovered via huggingface", "benchmark term in abstract", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "Land-use relevance: small-LLM benchmark results Predictions and scores for small open-weight LLMs asked to judge whether a sentence about a place carries land-use, land-cover, or geographic-environment signal that could be observed by remote sensing."}, "familyId": "bmf_71ba26e3b6a4", "firstSeenAt": "2026-09-14", "heat": null, "id": "bm_benchmark-llms-landuse-relevance_7050e5ea", "indexedAt": "2026-09-14T00:39:58.047193Z", "industrySectors": [], "links": {"data": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance", "paper": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance", "report": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance"}, "metrics": [], "motivation": "Land-use relevance: small-LLM benchmark results Predictions and scores for small open-weight LLMs asked to judge whether a sentence about a place carries land-use, land-cover, or geographic-environment signal that could be observed by remote sensing.", "name": "Land-use relevance benchmark", "oneLine": "This entry is a dataset of predictions and scores for small LLMs on a land-use relevance classification task, not an original standalone benchmark with a stable evaluation contract.", "paperTitle": "benchmark-llms-landuse-relevance", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-14T00:39:58.047193Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.15, "datasetDownloadRank": 44, "datasetRankPopulation": 44, "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": 0.0, "value": 0}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.15, "rank": 48, "score": 43}, "method": "attention-ranking-v13", "rank": 48, "score": 43}, "90d": {"confidence": "Low", "coverage": 0.3, "datasetDownloadRank": 78, "datasetRankPopulation": 78, "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": 0.0, "value": 0}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.3, "rank": 188, "score": 35}, "method": "attention-ranking-v13", "rank": 188, "score": 35}, "today": {"confidence": "Low", "coverage": 0.05, "datasetDownloadRank": 1, "datasetRankPopulation": 1, "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": "2026-09-13", "rank": null, "score": null, "windowDays": 1}, "level": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": 0.5, "percentile": 0.5, "value": 0}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.3, "role": "bonus", "value": 30}}, "confidence": "Low", "coverage": 0.05, "rank": 1, "score": 45}, "method": "attention-ranking-v13", "rank": 1, "score": 45}}, "readiness": "Inspectable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-09-13", "source": {"authors": ["NoeFlandre"], "categories": [], "id": "huggingface:noeflandre/benchmark-llms-landuse-relevance", "publicSignals": {"hfDatasetDownloads": 0, "hfDatasetLikes": 0}, "title": "benchmark-llms-landuse-relevance", "type": "huggingface", "url": "https://huggingface.co/datasets/NoeFlandre/benchmark-llms-landuse-relevance"}, "sourceUpdatedAt": "2026-09-13T18:00:54.000Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "It does not define a new reusable benchmark or evaluation protocol; it reports results on an existing task without establishing a distinct public comparison path."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
