{"record": {"aliases": [], "artifacts": [{"id": "hf:eigenformai/groundtruth-dynamic-benchmarking", "kind": "dataset", "url": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking"}], "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "Geology question sets and grading rubrics for evaluating LLMs on real-world geological reasoning, with 153 questions across four configs, each grounded in source corpora with evidence locators and a harness for generation and scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking", "source": "claire_radar", "source_url": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking", "title": "Groundtruth Dynamic Benchmarking"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:huggingface:eigenformai/groundtruth-dynamic-benchmarking", "modality": null, "name": "Groundtruth Dynamic Benchmarking", "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-candidate", "display_eligible": "false", "origin_record_id": "bm_groundtruth-dynamic-benchmarking_4f938e9e", "origin_source": "huggingface", "recognition_confidence": "0.4", "record_sha256": "d4ff9fffc36f23cc0599a412ea28dfae69a4b111b07889aed5e849296588e92c", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-26T06:15:55.708965Z", "source_url": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking"}, "publisher": null, "released": "2026-08-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:huggingface:eigenformai/groundtruth-dynamic-benchmarking", "source_url": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-huggingface-eigenformai-groundtruth-dynamic-benchmarking", "source": "claire_radar", "source_benchmark_id": "huggingface:eigenformai/groundtruth-dynamic-benchmarking", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": "EigenformAI/groundtruth-dynamic-benchmarking", "hfDatasetDownloads": 410, "hfDatasetLikes": 0, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}, "hfDatasetLikes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "stale"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Specialized domain benchmark may have limited but engaged interest from geology and LLM evaluation communities.", "score": 35}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:20:35.651311Z", "inputHash": "4c19ad07f3267ca6c1e39db5102561f70cfd4f51ae46ba053215c42d2c90e414", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "The formal benchmark name is source-grounded, but the public release does not yet meet the independent evidence or adoption threshold.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:15:55.708965Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Geology question sets and grading rubrics for evaluating LLMs on real-world geological reasoning, with 153 questions across four configs, each grounded in source corpora with evidence locators and a harness for generation and scoring.", "discoverySources": [{"id": "huggingface:eigenformai/groundtruth-dynamic-benchmarking", "type": "huggingface", "url": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["discovered via huggingface", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "Groundtruth Dynamic Benchmarking — Geology Question sets and grading rubrics for evaluating LLMs on real-world geological reasoning."}, "familyId": "bmf_d6fd851014b2", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_groundtruth-dynamic-benchmarking_4f938e9e", "indexedAt": "2026-08-23T05:46:57.857309Z", "industrySectors": [], "links": {"data": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking", "paper": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking", "report": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking"}, "metrics": [], "motivation": "Groundtruth Dynamic Benchmarking — Geology Question sets and grading rubrics for evaluating LLMs on real-world geological reasoning.", "name": "Groundtruth Dynamic Benchmarking", "oneLine": "Geology question sets and grading rubrics for evaluating LLMs on real-world geological reasoning, with 153 questions across four configs, each grounded in source corpora with evidence locators and a harness for generation and scoring.", "paperTitle": "groundtruth-dynamic-benchmarking", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T05:46:57.857309Z"}, "publications": [], "publishers": [{"name": "EigenformAI", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.3, "datasetDownloadRank": 31, "datasetRankPopulation": 85, "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": 0.6197942650957114, "value": 410}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.3, "rank": 37, "score": 54}, "method": "attention-ranking-v13", "rank": 37, "score": 54}}, "readiness": "Inspectable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-22", "source": {"authors": ["EigenformAI"], "categories": [], "id": "huggingface:eigenformai/groundtruth-dynamic-benchmarking", "title": "groundtruth-dynamic-benchmarking", "type": "huggingface", "url": "https://huggingface.co/datasets/EigenformAI/groundtruth-dynamic-benchmarking"}, "sourceUpdatedAt": "2026-08-22T10:36:21.000Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Provides an evidence-grounded evaluation for domain-specific reasoning with rubric-based scoring, enabling reproducible model comparison on geology tasks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
