{"record": {"aliases": ["greencalculus-benchmark"], "artifacts": [{"id": "gh:greencalculus/greencalculus-benchmark", "kind": "repo", "url": "https://github.com/greencalculus/greencalculus-benchmark"}, {"kind": "dataset", "url": "https://zenodo.org/badge/DOI/10.5281/zenodo.22692277.svg"}, {"kind": "website", "url": "https://greencalculus.com/developers?ref=github-benchmark"}], "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Benchmark of 467 emission-factor questions scored for numeric accuracy and citation correctness across five models without tools."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/greencalculus/greencalculus-benchmark", "source": "claire_radar", "source_url": "https://github.com/greencalculus/greencalculus-benchmark", "title": "Emission-factor accuracy benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:greencalculus/greencalculus-benchmark", "modality": null, "name": "Emission-factor accuracy 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": "true", "origin_record_id": "bm_greencalculus-benchmark_23a8b636", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "bbd98d0ad1bc590414cf6f3223c042d55cab8efdffe302d733bf6217c708bbfe", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-11T00:48:49.405936Z", "source_url": "https://github.com/greencalculus/greencalculus-benchmark"}, "publisher": null, "released": "2026-09-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:greencalculus/greencalculus-benchmark", "source_url": "https://github.com/greencalculus/greencalculus-benchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-greencalculus-greencalculus-benchmark", "source": "claire_radar", "source_benchmark_id": "github:greencalculus/greencalculus-benchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["greencalculus-benchmark"], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/greencalculus/greencalculus-benchmark", "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": "Medium", "horizon": "7d", "reason": "Climate and sustainability relevance, public results for major models, and an archived dataset broaden the audience.", "score": 42}, "capabilities": [], "confidence": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-11T00:48:49.405936Z", "inputHash": "5cf76e1d62bd2f41a1a8c5f4269aabe589eff5c08c5ce94c712d8b477410c07b", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "# Emission-factor accuracy benchmark", "canonicalNameSource": "official_readme", "decisionReason": "Full answer key, raw model outputs, scoring code, and run instructions are public; Zenodo DOI provides archival.", "evaluationEvidence": {"reuse": "```bash python3 build_questions.py # regenerate the set python3 score.py runs.json questions.json # score a model's answers ```", "scoring": "| `within_10pct` | is the number right |", "task": "**467 questions, 45 sections, 75 publishers**, generated deterministically (seed 20260910) from data version 2026.187."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-11T00:48:49.405936Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Benchmark of 467 emission-factor questions scored for numeric accuracy and citation correctness across five models without tools.", "discoverySources": [{"id": "github:greencalculus/greencalculus-benchmark", "type": "github", "url": "https://github.com/greencalculus/greencalculus-benchmark"}], "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "greencalculus-benchmark How wrong are LLMs about emission factors — and how often do they name the wrong source for a number?"}, "familyId": "bmf_ccd2108c1967", "firstSeenAt": "2026-09-11", "heat": null, "id": "bm_greencalculus-benchmark_23a8b636", "indexedAt": "2026-09-11T00:48:20.188568Z", "industrySectors": [], "links": {"code": "https://github.com/greencalculus/greencalculus-benchmark", "data": "https://zenodo.org/badge/DOI/10.5281/zenodo.22692277.svg", "project": "https://greencalculus.com/developers?ref=github-benchmark"}, "metrics": [], "motivation": "greencalculus-benchmark How wrong are LLMs about emission factors — and how often do they name the wrong source for a number?", "name": "Emission-factor accuracy benchmark", "oneLine": "Benchmark of 467 emission-factor questions scored for numeric accuracy and citation correctness across five models without tools.", "paperTitle": "greencalculus-benchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/greencalculus/greencalculus-benchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-11T00:48:20.188568Z"}, "publications": [], "publishers": [{"name": "GreenCalculus", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/greencalculus/greencalculus-benchmark"}], "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": 30, "historyDate": "2026-09-05", "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": 188, "score": 23}, "method": "attention-ranking-v13", "rank": 188, "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": 452, "score": 23}, "method": "attention-ranking-v13", "rank": 452, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-09-10", "source": {"authors": ["greencalculus"], "categories": [], "id": "github:greencalculus/greencalculus-benchmark", "publicSignals": {"githubStars": 0}, "title": "greencalculus-benchmark", "type": "github", "url": "https://github.com/greencalculus/greencalculus-benchmark"}, "sourceUpdatedAt": "2026-09-10T14:25:13Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Quantifies a high-stakes hallucination mode where confident wrong citations undermine climate accounting trust."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
