{"record": {"aliases": [], "artifacts": [{"id": "gh:bagheri365/evallab", "kind": "repo", "url": "https://github.com/bagheri365/evallab"}], "categories": ["Language & Knowledge", "Software & AI Compute", "cs.AI"], "description": {"en": "Provides a frozen 120-task Python coding benchmark with paired comparisons and uncertainty analysis focused on ranking stability."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/bagheri365/evallab", "source": "claire_radar", "source_url": "https://github.com/bagheri365/evallab", "title": "EvalLab"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:bagheri365/evallab", "modality": null, "name": "EvalLab", "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_evallab_50a8738a", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "a9d152eb882bcb218d309a1c26142c0e120b7d497e0064cdcdf301c3dd67aeee", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-25T23:28:56.873215Z", "source_url": "https://github.com/bagheri365/evallab"}, "publisher": null, "released": "2026-08-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:bagheri365/evallab", "source_url": "https://github.com/bagheri365/evallab"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-bagheri365-evallab", "source": "claire_radar", "source_benchmark_id": "github:bagheri365/evallab", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["Software & AI Compute"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/bagheri365/evallab", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The meta-evaluation focus and small task set limit immediate interest, and the project currently exists only as a personal repository without formal publication.", "score": 20}, "capabilities": [], "confidence": "Medium", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-25T23:28:56.873215Z", "inputHash": "ce71816c1de976ddb9fcee59a921f31d8f9ba389963eab1cb8fca928ebba8e37", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The project presents a research-style evaluation with a clear benchmark but lacks an independent paper or external adoption; its named status as a benchmark is self-declared and early-stage.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-25T23:28:56.873215Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Provides a frozen 120-task Python coding benchmark with paired comparisons and uncertainty analysis focused on ranking stability.", "discoverySources": [{"id": "github:bagheri365/evallab", "type": "github", "url": "https://github.com/bagheri365/evallab"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "no explicit benchmark release evidence"], "snippet": "evallab Research-style evaluation of local LLMs focused on paired comparisons, uncertainty, benchmark stability, and trustworthy model-ranking conclusions."}, "familyId": "bmf_5ed793692e46", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_evallab_50a8738a", "indexedAt": "2026-08-23T05:46:57.857309Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/bagheri365/evallab"}, "metrics": [], "motivation": "evallab Research-style evaluation of local LLMs focused on paired comparisons, uncertainty, benchmark stability, and trustworthy model-ranking conclusions.", "name": "EvalLab", "oneLine": "Provides a frozen 120-task Python coding benchmark with paired comparisons and uncertainty analysis focused on ranking stability.", "paperTitle": "evallab", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/bagheri365/evallab", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T05:46:57.857309Z"}, "publications": [], "ranking": {"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": 501, "score": 23}, "method": "attention-ranking-v13", "rank": 501, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-22", "source": {"authors": ["bagheri365"], "categories": [], "id": "github:bagheri365/evallab", "title": "evallab", "type": "github", "url": "https://github.com/bagheri365/evallab"}, "sourceUpdatedAt": "2026-08-22T19:29:06Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Studies how benchmark composition and ambiguity affect model-ranking trustworthiness, informing evaluation methodology."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
