{"record": {"aliases": [], "artifacts": [{"id": "hf:bryel-labs/musp-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench"}], "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "490-question benchmark for musical score understanding, performance listening, and combined score-performance reasoning, with multiple input modalities and accepted ground-truth answers."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://huggingface.co/datasets/bryel-labs/MuSP-Bench", "source": "claire_radar", "source_url": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench", "title": "MuSP-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:huggingface:bryel-labs/musp-bench", "modality": null, "name": "MuSP-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-candidate", "display_eligible": "false", "origin_record_id": "bm_musp-bench_8c379446", "origin_source": "huggingface", "recognition_confidence": "0.4", "record_sha256": "3eba2abf2d751ee19d4e549c7aa53bd80a9a5785a3aeb0e7df0a523931f0d9ad", "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/bryel-labs/MuSP-Bench"}, "publisher": null, "released": "2026-08-20", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:huggingface:bryel-labs/musp-bench", "source_url": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-huggingface-bryel-labs-musp-bench", "source": "claire_radar", "source_benchmark_id": "huggingface:bryel-labs/musp-bench", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "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": "bryel-labs/MuSP-Bench", "hfDatasetDownloads": 113, "hfDatasetLikes": 1, "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": {"additionalProperties": false, "confidence": "Medium", "horizon": "7d", "reason": "The dataset is publicly accessible with detailed documentation and baseline results, but the domain is niche and the publisher is not widely known.", "score": 45}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:15:55.708965Z", "inputHash": "af2ad0ef979628a45c2421f1346b1244148acffcea5ee6facce4d54b5ee0665a", "model": "deepseek-v4-pro"}, "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": "490-question benchmark for musical score understanding, performance listening, and combined score-performance reasoning, with multiple input modalities and accepted ground-truth answers.", "discoverySources": [{"id": "huggingface:bryel-labs/musp-bench", "type": "huggingface", "url": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via huggingface", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "MuSP-Bench MuSP-Bench is a 490-question benchmark for musical score understanding, performance listening, and combined score-performance reasoning."}, "familyId": "bmf_45c04f063445", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_musp-bench_8c379446", "indexedAt": "2026-08-23T06:55:51.988821Z", "industrySectors": [], "links": {"data": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench", "paper": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench", "report": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench"}, "metrics": [], "motivation": "MuSP-Bench MuSP-Bench is a 490-question benchmark for musical score understanding, performance listening, and combined score-performance reasoning.", "name": "MuSP-Bench", "oneLine": "490-question benchmark for musical score understanding, performance listening, and combined score-performance reasoning, with multiple input modalities and accepted ground-truth answers.", "paperTitle": "MuSP-Bench", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T06:55:51.988821Z"}, "publications": [], "publishers": [{"name": "bryel-labs", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.3, "datasetDownloadRank": 56, "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": 0.48773335097640735, "value": 113}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.3, "rank": 69, "score": 50}, "method": "attention-ranking-v13", "rank": 69, "score": 50}}, "readiness": "Inspectable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-20", "source": {"authors": ["bryel-labs"], "categories": [], "id": "huggingface:bryel-labs/musp-bench", "title": "MuSP-Bench", "type": "huggingface", "url": "https://huggingface.co/datasets/bryel-labs/MuSP-Bench"}, "sourceUpdatedAt": "2026-08-21T22:38:42.000Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Provides a structured way to compare multimodal models on musical score and performance understanding, enabling systematic evaluation across different input representations and task horizons."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
