{"record": {"aliases": ["pelican-bike-benchmark"], "artifacts": [{"id": "gh:qrzzzz/pelican-bike-benchmark", "kind": "repo", "url": "https://github.com/Qrzzzz/pelican-bike-benchmark"}, {"kind": "website", "url": "https://qrzzzz.github.io/pelican-bike-benchmark/"}], "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates AI-generated single-file HTML implementations of a pelican-riding-a-bicycle prompt using a fixed prompt and static site, with optional scoring across runnable, visual, animation, accessibility, and quality dimensions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/Qrzzzz/pelican-bike-benchmark", "source": "claire_radar", "source_url": "https://github.com/Qrzzzz/pelican-bike-benchmark", "title": "Pelican Bike Benchmark"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:qrzzzz/pelican-bike-benchmark", "modality": null, "name": "Pelican Bike 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_pelican-bike-benchmark_593593ff", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "d57f71435ec350f7d485e2825e4b055da2d5f1765bfb0e7ac726db672408a72b", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-15T09:35:32.523429Z", "source_url": "https://github.com/Qrzzzz/pelican-bike-benchmark"}, "publisher": null, "released": "2026-09-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:qrzzzz/pelican-bike-benchmark", "source_url": "https://github.com/Qrzzzz/pelican-bike-benchmark"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-qrzzzz-pelican-bike-benchmark", "source": "claire_radar", "source_benchmark_id": "github:qrzzzz/pelican-bike-benchmark", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["pelican-bike-benchmark"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-14", "attemptedAt": "2026-09-14T01:54:58.773663Z", "githubRepo": "https://github.com/Qrzzzz/pelican-bike-benchmark", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "observedAt": "2026-09-14T01:54:58.773663Z", "signalStatus": {"githubStars": {"observedAt": "2026-09-14T01:54:58.773663Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "A niche visual coding benchmark with a fixed prompt and open submission path may attract moderate interest from communities exploring AI-generated single-file HTML outputs.", "score": 20}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-15T09:37:10.086794Z", "inputHash": "ce45ec6d6b99b4c248ac0288c14cb7761bccdee1eb9e48fa996be2f5585a9baf", "model": "deepseek-v4-flash"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "# 鹈鹕骑车 · Pelican Bike Benchmark", "canonicalNameSource": "official_readme", "decisionReason": "The evidence shows a submission-based collection with scoring criteria, but the scoring appears to be optional and not clearly administered through a formal ongoing comparison mechanism. The public reuse path is unclear because submissions are manually reviewed and results are not presented as a leaderboard or standardized external submission system.", "evaluationEvidence": {"reuse": "站点收录用户提交的 DeepSeek 4.1 Flash · max 原始输出，以及相同 v1 提示词生成的 Codex 模型作品", "scoring": "scores 为 0–10 数字，notes 为对应文字依据。权重为 20%、30%、20%、20%、10%", "task": "观察 AI 生成「鹈鹕骑自行车」单文件 HTML 的差异"}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-15T09:35:32.523429Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates AI-generated single-file HTML implementations of a pelican-riding-a-bicycle prompt using a fixed prompt and static site, with optional scoring across runnable, visual, animation, accessibility, and quality dimensions.", "discoverySources": [{"id": "github:qrzzzz/pelican-bike-benchmark", "type": "github", "url": "https://github.com/Qrzzzz/pelican-bike-benchmark"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "pelican-bike-benchmark A neutral static-site benchmark for AI implementations of the pelican-riding-a-bicycle prompt."}, "familyId": "bmf_9e7601a0c723", "firstSeenAt": "2026-09-13", "heat": null, "id": "bm_pelican-bike-benchmark_593593ff", "indexedAt": "2026-09-13T06:29:18.259261Z", "industrySectors": [], "links": {"code": "https://github.com/Qrzzzz/pelican-bike-benchmark", "project": "https://qrzzzz.github.io/pelican-bike-benchmark/"}, "metrics": [], "motivation": "pelican-bike-benchmark A neutral static-site benchmark for AI implementations of the pelican-riding-a-bicycle prompt.", "name": "Pelican Bike Benchmark", "oneLine": "Evaluates AI-generated single-file HTML implementations of a pelican-riding-a-bicycle prompt using a fixed prompt and static site, with optional scoring across runnable, visual, animation, accessibility, and quality dimensions.", "paperTitle": "pelican-bike-benchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/Qrzzzz/pelican-bike-benchmark", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-13T06:29:18.259261Z"}, "publications": [], "publishers": [{"name": "Qrzzzz", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Qrzzzz/pelican-bike-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": null, "historyDate": null, "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": 136, "score": 23}, "method": "attention-ranking-v13", "rank": 136, "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": 340, "score": 23}, "method": "attention-ranking-v13", "rank": 340, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-09-12", "source": {"authors": ["Qrzzzz"], "categories": [], "id": "github:qrzzzz/pelican-bike-benchmark", "publicSignals": {"githubStars": 0}, "title": "pelican-bike-benchmark", "type": "github", "url": "https://github.com/Qrzzzz/pelican-bike-benchmark"}, "sourceUpdatedAt": "2026-09-12T15:50:41Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Provides a reproducible, fixed-input protocol for comparing model outputs on a standardized generative coding task with hash preservation and structured review options."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
