{"meta":{"preregistration":"docs/PROOF-PREREGISTRATION.md §7-A","axis":"hallucination","generated_at":"2026-06-29T03:32:53.756Z","bench_topk":6,"star_tolerance":0.3,"models":[{"key":"opus","id":"anthropic/claude-opus-4.8","label":"Claude Opus 4.8"},{"key":"gpt","id":"openai/gpt-5.5","label":"GPT-5.5"},{"key":"grok","id":"x-ai/grok-4.3","label":"Grok 4.3"},{"key":"glm","id":"z-ai/glm-5.2","label":"GLM 5.2"}]},"systems":[{"key":"bench","label":"vibe-bench","id":"lib/scorer.ts (real corpus)","cited_total":60,"with_path":60,"existence_rate":1,"star_accuracy_rate":0.9833,"star_median_rel_error":0},{"key":"opus","label":"Claude Opus 4.8","id":"anthropic/claude-opus-4.8","cited_total":45,"with_path":45,"existence_rate":0.9333,"star_accuracy_rate":0.5476,"star_median_rel_error":0.2732},{"key":"gpt","label":"GPT-5.5","id":"openai/gpt-5.5","cited_total":50,"with_path":50,"existence_rate":0.82,"star_accuracy_rate":0.6098,"star_median_rel_error":0.2},{"key":"grok","label":"Grok 4.3","id":"x-ai/grok-4.3","cited_total":50,"with_path":50,"existence_rate":0.58,"star_accuracy_rate":0.4483,"star_median_rel_error":0.3356},{"key":"glm","label":"GLM 5.2","id":"z-ai/glm-5.2","cited_total":45,"with_path":45,"existence_rate":0.4889,"star_accuracy_rate":0.4091,"star_median_rel_error":0.3721}],"per_plan":[{"id":"reviewmate","systems":{"bench":{"citations":[{"name":"selimozten/elek","repo":"selimozten/elek","stated_stars":19,"exists":true,"real_stars":19,"star_ok":true,"no_path":false},{"name":"yungookim/oh-my-pr","repo":"yungookim/oh-my-pr","stated_stars":42,"exists":true,"real_stars":42,"star_ok":true,"no_path":false},{"name":"aryanbrite/openrabbit","repo":"aryanbrite/openrabbit","stated_stars":38,"exists":true,"real_stars":38,"star_ok":true,"no_path":false},{"name":"agynio/gh-pr-review","repo":"agynio/gh-pr-review","stated_stars":163,"exists":true,"real_stars":163,"star_ok":true,"no_path":false},{"name":"numberly/reviewate","repo":"numberly/reviewate","stated_stars":13,"exists":true,"real_stars":13,"star_ok":true,"no_path":false},{"name":"zxkane/autonomous-dev-team","repo":"zxkane/autonomous-dev-team","stated_stars":21,"exists":true,"real_stars":21,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[{"name":"PR-Agent (Qodo Merge)","repo":"qodo-ai/pr-agent","stated_stars":8200,"exists":true,"real_stars":11870,"star_ok":false,"no_path":false},{"name":"CodeRabbit AI PR Reviewer","repo":"coderabbitai/ai-pr-reviewer","stated_stars":4400,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"AI Code Review (GitHub Action)","repo":"freeedcom/ai-codereviewer","stated_stars":1300,"exists":true,"real_stars":1030,"star_ok":true,"no_path":false},{"name":"Sweep","repo":"sweepai/sweep","stated_stars":7500,"exists":true,"real_stars":7703,"star_ok":true,"no_path":false},{"name":"CodeReview (anc95)","repo":"anc95/chatgpt-codereview","stated_stars":4500,"exists":true,"real_stars":4445,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":0.75,"star_median_rel_error":0.1442},"gpt":{"citations":[{"name":"Reviewdog","repo":"reviewdog/reviewdog","stated_stars":8500,"exists":true,"real_stars":9413,"star_ok":true,"no_path":false},{"name":"Danger JS","repo":"danger/danger-js","stated_stars":5200,"exists":true,"real_stars":5483,"star_ok":true,"no_path":false},{"name":"Danger","repo":"danger/danger","stated_stars":5400,"exists":true,"real_stars":5683,"star_ok":true,"no_path":false},{"name":"PR-Agent","repo":"qodo-ai/pr-agent","stated_stars":6800,"exists":true,"real_stars":11870,"star_ok":false,"no_path":false},{"name":"CodeRabbit AI PR Reviewer","repo":"coderabbitai/ai-pr-reviewer","stated_stars":1600,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":0.75,"star_median_rel_error":0.0743},"grok":{"citations":[{"name":"CodeRabbit","repo":"coderabbitai/coderabbit","stated_stars":5600,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Sweep","repo":"sweepai/sweep","stated_stars":7600,"exists":true,"real_stars":7703,"star_ok":true,"no_path":false},{"name":"PR-Agent","repo":"codium-ai/pr-agent","stated_stars":8300,"exists":true,"real_stars":11870,"star_ok":false,"no_path":false},{"name":"Aider","repo":"paul-gauthier/aider","stated_stars":25000,"exists":true,"real_stars":46802,"star_ok":false,"no_path":false},{"name":"OpenDevin","repo":"opendevin/opendevin","stated_stars":49000,"exists":true,"real_stars":78608,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":0.25,"star_median_rel_error":0.3387},"glm":{"citations":[{"name":"coderabbitai/ai-pr-reviewer","repo":"coderabbitai/ai-pr-reviewer","stated_stars":1400,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"mattzcarey/code-review-gpt","repo":"mattzcarey/code-review-gpt","stated_stars":700,"exists":true,"real_stars":2437,"star_ok":false,"no_path":false},{"name":"fluxninja/openai-pr-reviewer","repo":"fluxninja/openai-pr-reviewer","stated_stars":500,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"microsoft/code-review-gpt-action","repo":"microsoft/code-review-gpt-action","stated_stars":200,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Anciem/CodeReviewBot","repo":"anciem/codereviewbot","stated_stars":100,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.2,"star_accuracy_rate":0,"star_median_rel_error":0.7128}}},{"id":"lawsearch","systems":{"bench":{"citations":[{"name":"lemos999/korea-law-index-light","repo":"lemos999/korea-law-index-light","stated_stars":16,"exists":true,"real_stars":16,"star_ok":true,"no_path":false},{"name":"Minsu5452/korean-maritime-law-rag","repo":"minsu5452/korean-maritime-law-rag","stated_stars":0,"exists":true,"real_stars":0,"star_ok":true,"no_path":false},{"name":"hjsh200219/lyn-lawfirm","repo":"hjsh200219/lyn-lawfirm","stated_stars":2,"exists":true,"real_stars":2,"star_ok":true,"no_path":false},{"name":"seunghan91/korea-law-mcp-public","repo":"seunghan91/korea-law-mcp-public","stated_stars":2,"exists":true,"real_stars":2,"star_ok":true,"no_path":false},{"name":"skillnara/legal-basis-finder","repo":"skillnara/legal-basis-finder","stated_stars":2,"exists":true,"real_stars":2,"star_ok":true,"no_path":false},{"name":"TonyNobleHam/korean-law-web","repo":"tonynobleham/korean-law-web","stated_stars":0,"exists":true,"real_stars":0,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[],"cited_total":0,"with_path":0,"existence_rate":null,"star_accuracy_rate":null,"star_median_rel_error":null},"gpt":{"citations":[{"name":"Open Law Library","repo":"openlawlibrary/llai","stated_stars":0,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"LexPredict LexNLP","repo":"lexpredict/lexpredict-lexnlp","stated_stars":895,"exists":true,"real_stars":789,"star_ok":true,"no_path":false},{"name":"Open Legal Data","repo":"openlegaldata/openlegaldata","stated_stars":381,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Legal RAG with Mistral","repo":"zaheersunnyn/legal-rag-mistral","stated_stars":151,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Law-GPT","repo":"harshitv804/law-gpt","stated_stars":109,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.2,"star_accuracy_rate":1,"star_median_rel_error":0.1343},"grok":{"citations":[{"name":"Legal-RAG-KR","repo":"law-gov-kr/legal-rag-kr","stated_stars":1240,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"ClauseSearch","repo":"openlaw-kr/clausesearch","stated_stars":890,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"KoreanLaw-RAG","repo":"law-ai/koreanlaw-rag","stated_stars":765,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"LawBot-KR","repo":"lawbot-kr/lawbot-kr","stated_stars":610,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"StatuteRAG","repo":"statute-rag/statute-rag","stated_stars":485,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0,"star_accuracy_rate":null,"star_median_rel_error":null},"glm":{"citations":[{"name":"FakeName1","repo":"lawranks/korean-law-chatbot","stated_stars":0,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"FakeName2","repo":"korean-law-search/rag-bot","stated_stars":0,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"FakeName3","repo":"korea-legal-ai/law-search","stated_stars":0,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"FakeName4","repo":"legal-rag/korea-statutes","stated_stars":0,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"FakeName5","repo":"k-law-search/rag-chatbot","stated_stars":0,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0,"star_accuracy_rate":null,"star_median_rel_error":null}}},{"id":"radnote","systems":{"bench":{"citations":[{"name":"X-iZhang/CCD","repo":"x-izhang/ccd","stated_stars":14,"exists":true,"real_stars":14,"star_ok":true,"no_path":false},{"name":"vintasoftware/medplum-ai-concierge","repo":"vintasoftware/medplum-ai-concierge","stated_stars":26,"exists":true,"real_stars":26,"star_ok":true,"no_path":false},{"name":"Rana3112/healthguard-core","repo":"rana3112/healthguard-core","stated_stars":17,"exists":true,"real_stars":17,"star_ok":true,"no_path":false},{"name":"kyle103/medical_agent","repo":"kyle103/medical_agent","stated_stars":30,"exists":true,"real_stars":30,"star_ok":true,"no_path":false},{"name":"The-Swarm-Corporation/radiology-swarm","repo":"the-swarm-corporation/radiology-swarm","stated_stars":17,"exists":true,"real_stars":17,"star_ok":true,"no_path":false},{"name":"terilios/smartsheet-server","repo":"terilios/smartsheet-server","stated_stars":12,"exists":true,"real_stars":12,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[{"name":"OHIF Viewer","repo":"ohif/viewers","stated_stars":3500,"exists":true,"real_stars":4223,"star_ok":true,"no_path":false},{"name":"Orthanc","repo":"jodogne/orthancmirror","stated_stars":700,"exists":true,"real_stars":40,"star_ok":false,"no_path":false},{"name":"Slicer","repo":"slicer/slicer","stated_stars":1800,"exists":true,"real_stars":2515,"star_ok":true,"no_path":false},{"name":"dwv","repo":"ivmartel/dwv","stated_stars":1800,"exists":true,"real_stars":1823,"star_ok":true,"no_path":false},{"name":"Cornerstone3D","repo":"cornerstonejs/cornerstone3d","stated_stars":700,"exists":true,"real_stars":1091,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.6,"star_median_rel_error":0.2843},"gpt":{"citations":[{"name":"3D Slicer","repo":"slicer/slicer","stated_stars":4500,"exists":true,"real_stars":2515,"star_ok":false,"no_path":false},{"name":"OHIF Viewer","repo":"ohif/viewers","stated_stars":3200,"exists":true,"real_stars":4223,"star_ok":true,"no_path":false},{"name":"Horos","repo":"horosproject/horos","stated_stars":1200,"exists":true,"real_stars":608,"star_ok":false,"no_path":false},{"name":"Weasis","repo":"nroduit/weasis","stated_stars":850,"exists":true,"real_stars":1276,"star_ok":false,"no_path":false},{"name":"Cornerstone3D","repo":"cornerstonejs/cornerstone3d","stated_stars":600,"exists":true,"real_stars":1091,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.2,"star_median_rel_error":0.45},"grok":{"citations":[{"name":"OHIF Viewer","repo":"ohif/viewers","stated_stars":3100,"exists":true,"real_stars":4223,"star_ok":true,"no_path":false},{"name":"Orthanc","repo":"jodogne/orthanc","stated_stars":1200,"exists":true,"real_stars":89,"star_ok":false,"no_path":false},{"name":"Weasis","repo":"nroduit/weasis","stated_stars":950,"exists":true,"real_stars":1276,"star_ok":true,"no_path":false},{"name":"Horos","repo":"horosproject/horos","stated_stars":1400,"exists":true,"real_stars":608,"star_ok":false,"no_path":false},{"name":"Cornerstone.js","repo":"cornerstonejs/cornerstone","stated_stars":1800,"exists":true,"real_stars":2109,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.6,"star_median_rel_error":0.2659},"glm":{"citations":[{"name":"OHIF Viewer","repo":"ohif/viewers","stated_stars":3200,"exists":true,"real_stars":4223,"star_ok":true,"no_path":false},{"name":"dicompyler","repo":"dicompyler/dicompyler","stated_stars":350,"exists":true,"real_stars":287,"star_ok":true,"no_path":false},{"name":"Invesalius","repo":"invesalius/invesalius3","stated_stars":650,"exists":true,"real_stars":795,"star_ok":true,"no_path":false},{"name":"Cornerstone.js","repo":"cornerstonejs/cornerstone","stated_stars":2200,"exists":true,"real_stars":2109,"star_ok":true,"no_path":false},{"name":"dwv","repo":"ivmartel/dwv","stated_stars":650,"exists":true,"real_stars":1823,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.8,"star_median_rel_error":0.2195}}},{"id":"dangolbot","systems":{"bench":{"citations":[{"name":"Tiledesk/tiledesk-chatbot","repo":"tiledesk/tiledesk-chatbot","stated_stars":75,"exists":true,"real_stars":3,"star_ok":false,"no_path":false},{"name":"10xshivam/Cenra","repo":"10xshivam/cenra","stated_stars":34,"exists":true,"real_stars":34,"star_ok":true,"no_path":false},{"name":"huabeitech/agent-desk","repo":"huabeitech/agent-desk","stated_stars":153,"exists":true,"real_stars":153,"star_ok":true,"no_path":false},{"name":"Hesper-Labs/owly","repo":"hesper-labs/owly","stated_stars":102,"exists":true,"real_stars":102,"star_ok":true,"no_path":false},{"name":"nuaazs/AskLLM","repo":"nuaazs/askllm","stated_stars":11,"exists":true,"real_stars":11,"star_ok":true,"no_path":false},{"name":"tgoai/tgo","repo":"tgoai/tgo","stated_stars":508,"exists":true,"real_stars":508,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":0.8333,"star_median_rel_error":0},"opus":{"citations":[{"name":"Chatwoot","repo":"chatwoot/chatwoot","stated_stars":21000,"exists":true,"real_stars":33688,"star_ok":false,"no_path":false},{"name":"Botpress","repo":"botpress/botpress","stated_stars":12500,"exists":true,"real_stars":14765,"star_ok":true,"no_path":false},{"name":"Rasa","repo":"rasahq/rasa","stated_stars":18500,"exists":true,"real_stars":21224,"star_ok":true,"no_path":false},{"name":"Typebot","repo":"baptistearno/typebot.io","stated_stars":7500,"exists":true,"real_stars":10084,"star_ok":true,"no_path":false},{"name":"Tiledesk","repo":"tiledesk/tiledesk-dashboard","stated_stars":280,"exists":true,"real_stars":5,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.6,"star_median_rel_error":0.2562},"gpt":{"citations":[{"name":"Chatwoot","repo":"chatwoot/chatwoot","stated_stars":24100,"exists":true,"real_stars":33688,"star_ok":true,"no_path":false},{"name":"Botpress","repo":"botpress/botpress","stated_stars":13000,"exists":true,"real_stars":14765,"star_ok":true,"no_path":false},{"name":"Rasa","repo":"rasahq/rasa","stated_stars":21000,"exists":true,"real_stars":21224,"star_ok":true,"no_path":false},{"name":"Typebot","repo":"baptistearno/typebot.io","stated_stars":8500,"exists":true,"real_stars":10084,"star_ok":true,"no_path":false},{"name":"Papercups","repo":"papercups-io/papercups","stated_stars":6200,"exists":true,"real_stars":6071,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0.1195},"grok":{"citations":[{"name":"Chatwoot","repo":"chatwoot/chatwoot","stated_stars":21600,"exists":true,"real_stars":33688,"star_ok":false,"no_path":false},{"name":"Rocket.Chat","repo":"rocketchat/rocket.chat","stated_stars":41500,"exists":true,"real_stars":45728,"star_ok":true,"no_path":false},{"name":"Botpress","repo":"botpress/botpress","stated_stars":13100,"exists":true,"real_stars":14765,"star_ok":true,"no_path":false},{"name":"Typebot","repo":"baptistearno/typebot.io","stated_stars":6700,"exists":true,"real_stars":10084,"star_ok":false,"no_path":false},{"name":"Flowise","repo":"flowiseai/flowise","stated_stars":31000,"exists":true,"real_stars":54092,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.4,"star_median_rel_error":0.3356},"glm":{"citations":[{"name":"naver-talktalk-api","repo":"jongpak/naver-talktalk","stated_stars":18,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"kakao-chatbot","repo":"hyunse/jeongbot","stated_stars":24,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"kakao-i-openbuilder","repo":"kimgeonung/kakao-i-openbuilder","stated_stars":16,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"kakaobot-py","repo":"jelaminlo/kakaobot-py","stated_stars":12,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"naver-talktalk-node","repo":"seunggabi/naver-talktalk-node","stated_stars":5,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0,"star_accuracy_rate":null,"star_median_rel_error":null}}},{"id":"browserqa","systems":{"bench":{"citations":[{"name":"alexandriashai/cbrowser","repo":"alexandriashai/cbrowser","stated_stars":17,"exists":true,"real_stars":17,"star_ok":true,"no_path":false},{"name":"rjsx197047/AI-Automation-QA-Engineer","repo":"rjsx197047/ai-automation-qa-engineer","stated_stars":10,"exists":true,"real_stars":10,"star_ok":true,"no_path":false},{"name":"heal-dev/heal-playwright-tracer","repo":"heal-dev/heal-playwright-tracer","stated_stars":40,"exists":true,"real_stars":40,"star_ok":true,"no_path":false},{"name":"bug0inc/passmark","repo":"bug0inc/passmark","stated_stars":1069,"exists":true,"real_stars":1070,"star_ok":true,"no_path":false},{"name":"DebugBase/glance","repo":"debugbase/glance","stated_stars":152,"exists":true,"real_stars":152,"star_ok":true,"no_path":false},{"name":"oursky/skytest-agent","repo":"oursky/skytest-agent","stated_stars":29,"exists":true,"real_stars":29,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[{"name":"browser-use","repo":"browser-use/browser-use","stated_stars":50000,"exists":true,"real_stars":101207,"star_ok":false,"no_path":false},{"name":"Skyvern","repo":"skyvern-ai/skyvern","stated_stars":11000,"exists":true,"real_stars":22025,"star_ok":false,"no_path":false},{"name":"LaVague","repo":"lavague-ai/lavague","stated_stars":5500,"exists":true,"real_stars":6375,"star_ok":true,"no_path":false},{"name":"Midscene","repo":"web-infra-dev/midscene","stated_stars":6000,"exists":true,"real_stars":13869,"star_ok":false,"no_path":false},{"name":"Stagehand","repo":"browserbase/stagehand","stated_stars":10000,"exists":true,"real_stars":23269,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.2,"star_median_rel_error":0.506},"gpt":{"citations":[{"name":"browser-use","repo":"browser-use/browser-use","stated_stars":56000,"exists":true,"real_stars":101207,"star_ok":false,"no_path":false},{"name":"Stagehand","repo":"browserbase/stagehand","stated_stars":13000,"exists":true,"real_stars":23269,"star_ok":false,"no_path":false},{"name":"ADED","repo":"servicenow/browsergym","stated_stars":2500,"exists":true,"real_stars":1260,"star_ok":false,"no_path":false},{"name":"ZeroStep","repo":"zerostep-ai/zerostep","stated_stars":1000,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"ADED","repo":"microsoft/playwright-mcp","stated_stars":19000,"exists":true,"real_stars":34475,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":0,"star_median_rel_error":0.4478},"grok":{"citations":[{"name":"Browserbase","repo":"browserbase/stagehand","stated_stars":4200,"exists":true,"real_stars":23269,"star_ok":false,"no_path":false},{"name":"MultiOn","repo":"multion-org/multion","stated_stars":1800,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"OpenAI Computer-Using Agent","repo":"openai/openai-cua","stated_stars":950,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Adept Fuyu","repo":"adept-ai/fuyu-browser","stated_stars":720,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Skyvern","repo":"skyvern-ai/skyvern","stated_stars":3100,"exists":true,"real_stars":22025,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.4,"star_accuracy_rate":0,"star_median_rel_error":0.8394},"glm":{"citations":[{"name":"AutoPlaywright","repo":"lucgagan/auto-playwright","stated_stars":532,"exists":true,"real_stars":842,"star_ok":false,"no_path":false},{"name":"ZeroStep","repo":"zerostep-ai/zerostep","stated_stars":432,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Magenest QA Agent","repo":"magenest/qachain","stated_stars":3,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Midscene","repo":"web-infra-dev/midscene","stated_stars":5100,"exists":true,"real_stars":13869,"star_ok":false,"no_path":false},{"name":"Skyvern","repo":"skyvern-ai/skyvern","stated_stars":7600,"exists":true,"real_stars":22025,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.6,"star_accuracy_rate":0,"star_median_rel_error":0.6323}}},{"id":"meetnote","systems":{"bench":{"citations":[{"name":"joinly-ai/joinly","repo":"joinly-ai/joinly","stated_stars":527,"exists":true,"real_stars":527,"star_ok":true,"no_path":false},{"name":"pattern-ai-labs/agentcall","repo":"pattern-ai-labs/agentcall","stated_stars":102,"exists":true,"real_stars":102,"star_ok":true,"no_path":false},{"name":"videosdk-community/videosdk-deepgram-voice-agent","repo":"videosdk-community/videosdk-deepgram-voice-agent","stated_stars":11,"exists":true,"real_stars":11,"star_ok":true,"no_path":false},{"name":"renatoromao/voice-ai-agent","repo":"renatoromao/voice-ai-agent","stated_stars":12,"exists":true,"real_stars":12,"star_ok":true,"no_path":false},{"name":"postcoitum/meeting_log","repo":"postcoitum/meeting_log","stated_stars":1,"exists":true,"real_stars":1,"star_ok":true,"no_path":false},{"name":"videosdk-community/ai-agent","repo":"videosdk-community/ai-agent","stated_stars":24,"exists":true,"real_stars":24,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[{"name":"Whisper (OpenAI)","repo":"openai/whisper","stated_stars":0,"exists":true,"real_stars":103803,"star_ok":false,"no_path":false},{"name":"WhisperX (speaker diarization)","repo":"m-bain/whisperx","stated_stars":0,"exists":true,"real_stars":22761,"star_ok":false,"no_path":false},{"name":"Bert Extractive Summarizer","repo":"dmmiller612/bert-extractive-summarizer","stated_stars":0,"exists":true,"real_stars":1452,"star_ok":false,"no_path":false},{"name":"pyannote-audio (speaker diarization)","repo":"pyannote/pyannote-audio","stated_stars":0,"exists":true,"real_stars":10197,"star_ok":false,"no_path":false},{"name":"Vocode (voice AI agents)","repo":"vocodedev/vocode-core","stated_stars":0,"exists":true,"real_stars":3767,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0,"star_median_rel_error":1},"gpt":{"citations":[{"name":"OpenHands","repo":"all-hands-ai/openhands","stated_stars":58900,"exists":true,"real_stars":78608,"star_ok":true,"no_path":false},{"name":"Khoj","repo":"khoj-ai/khoj","stated_stars":31000,"exists":true,"real_stars":35382,"star_ok":true,"no_path":false},{"name":"Vocode","repo":"vocodedev/vocode-python","stated_stars":8700,"exists":true,"real_stars":3767,"star_ok":false,"no_path":false},{"name":"OpenAdapt","repo":"openadaptai/openadapt","stated_stars":5500,"exists":true,"real_stars":1628,"star_ok":false,"no_path":false},{"name":"Meeting Bot Starter Kit","repo":"recallnet/meeting-bot-starter-kit","stated_stars":600,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":0.5,"star_median_rel_error":0.7801},"grok":{"citations":[{"name":"tl;dv","repo":"tldv-io/tldv","stated_stars":1240,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Fireflies.ai","repo":"firefliesai/fireflies","stated_stars":890,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Fathom","repo":"fathomlabs/fathom","stated_stars":650,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Otter.ai","repo":"otterapi/otter","stated_stars":520,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Grain","repo":"grainhq/grain","stated_stars":410,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0,"star_accuracy_rate":null,"star_median_rel_error":null},"glm":{"citations":[{"name":"meetnote","repo":"meetnote-ai/meetnote","stated_stars":528,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"actionbot","repo":"yongkanglu/actionbot","stated_stars":142,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"slack-meeting-summarizer","repo":"harperreed/slack-meeting-summarizer","stated_stars":89,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"meeting-summary-bot","repo":"kx-huang/meeting-summary-bot","stated_stars":76,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"zoom-recording-summarizer","repo":"microsoft/zoom-recording-summarizer","stated_stars":45,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0,"star_accuracy_rate":null,"star_median_rel_error":null}}},{"id":"codesearch","systems":{"bench":{"citations":[{"name":"vitali87/code-graph-rag","repo":"vitali87/code-graph-rag","stated_stars":2275,"exists":true,"real_stars":2274,"star_ok":true,"no_path":false},{"name":"Davidyz/VectorCode","repo":"davidyz/vectorcode","stated_stars":869,"exists":true,"real_stars":869,"star_ok":true,"no_path":false},{"name":"Brainwires/project-rag","repo":"brainwires/project-rag","stated_stars":19,"exists":true,"real_stars":19,"star_ok":true,"no_path":false},{"name":"bluewings1211/codebase-RAG","repo":"bluewings1211/codebase-rag","stated_stars":15,"exists":true,"real_stars":15,"star_ok":true,"no_path":false},{"name":"anrgct/autodev-codebase","repo":"anrgct/autodev-codebase","stated_stars":119,"exists":true,"real_stars":119,"star_ok":true,"no_path":false},{"name":"proofofwork-agency/reporecall","repo":"proofofwork-agency/reporecall","stated_stars":33,"exists":true,"real_stars":33,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[{"name":"Sourcegraph (Cody)","repo":"sourcegraph/cody","stated_stars":3000,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Continue","repo":"continuedev/continue","stated_stars":27000,"exists":true,"real_stars":34554,"star_ok":true,"no_path":false},{"name":"Tabby","repo":"tabbyml/tabby","stated_stars":31000,"exists":true,"real_stars":33653,"star_ok":true,"no_path":false},{"name":"Bloop","repo":"bloopai/bloop","stated_stars":9700,"exists":true,"real_stars":9506,"star_ok":true,"no_path":false},{"name":"Aider","repo":"aider-ai/aider","stated_stars":35000,"exists":true,"real_stars":46802,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":1,"star_median_rel_error":0.1487},"gpt":{"citations":[{"name":"Continue","repo":"continuedev/continue","stated_stars":26700,"exists":true,"real_stars":34554,"star_ok":true,"no_path":false},{"name":"Tabby","repo":"tabbyml/tabby","stated_stars":31300,"exists":true,"real_stars":33653,"star_ok":true,"no_path":false},{"name":"Sourcegraph Cody","repo":"sourcegraph/cody","stated_stars":1400,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Aider","repo":"aider-ai/aider","stated_stars":26300,"exists":true,"real_stars":46802,"star_ok":false,"no_path":false},{"name":"Bloop","repo":"bloopai/bloop","stated_stars":9200,"exists":true,"real_stars":9506,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":0.75,"star_median_rel_error":0.1486},"grok":{"citations":[{"name":"Continue","repo":"continuedev/continue","stated_stars":21000,"exists":true,"real_stars":34554,"star_ok":false,"no_path":false},{"name":"Cody","repo":"sourcegraph/cody","stated_stars":2700,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Aider","repo":"paul-gauthier/aider","stated_stars":19000,"exists":true,"real_stars":46802,"star_ok":false,"no_path":false},{"name":"Bloop","repo":"bloopai/bloop","stated_stars":9000,"exists":true,"real_stars":9506,"star_ok":true,"no_path":false},{"name":"AskCodebase","repo":"whitead/askcodebase","stated_stars":650,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.6,"star_accuracy_rate":0.3333,"star_median_rel_error":0.3923},"glm":{"citations":[{"name":"bloop","repo":"bloopai/bloop","stated_stars":8900,"exists":true,"real_stars":9506,"star_ok":true,"no_path":false},{"name":"Tabby","repo":"tabbyml/tabby","stated_stars":21000,"exists":true,"real_stars":33653,"star_ok":false,"no_path":false},{"name":"Continue","repo":"continuedev/continue","stated_stars":21000,"exists":true,"real_stars":34554,"star_ok":false,"no_path":false},{"name":"Aider","repo":"paul-gauthier/aider","stated_stars":18000,"exists":true,"real_stars":46802,"star_ok":false,"no_path":false},{"name":"Sourcegraph Cody","repo":"sourcegraph/cody","stated_stars":2400,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":0.25,"star_median_rel_error":0.3841}}},{"id":"promptops","systems":{"bench":{"citations":[{"name":"promptdesk/promptdesk","repo":"promptdesk/promptdesk","stated_stars":98,"exists":true,"real_stars":98,"star_ok":true,"no_path":false},{"name":"langwatch/langwatch","repo":"langwatch/langwatch","stated_stars":3314,"exists":true,"real_stars":3315,"star_ok":true,"no_path":false},{"name":"future-agi/future-agi","repo":"future-agi/future-agi","stated_stars":1251,"exists":true,"real_stars":1253,"star_ok":true,"no_path":false},{"name":"ToolBrain/TraceBrain","repo":"toolbrain/tracebrain","stated_stars":69,"exists":true,"real_stars":69,"star_ok":true,"no_path":false},{"name":"wwwazzz/senior-pm-prompt","repo":"wwwazzz/senior-pm-prompt","stated_stars":87,"exists":true,"real_stars":87,"star_ok":true,"no_path":false},{"name":"remorses/opencode-injection-guard","repo":"remorses/opencode-injection-guard","stated_stars":12,"exists":true,"real_stars":12,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[{"name":"Langfuse","repo":"langfuse/langfuse","stated_stars":7500,"exists":true,"real_stars":29983,"star_ok":false,"no_path":false},{"name":"Promptfoo","repo":"promptfoo/promptfoo","stated_stars":5000,"exists":true,"real_stars":22701,"star_ok":false,"no_path":false},{"name":"Helicone","repo":"helicone/helicone","stated_stars":3000,"exists":true,"real_stars":5873,"star_ok":false,"no_path":false},{"name":"Phoenix (Arize)","repo":"arize-ai/phoenix","stated_stars":4000,"exists":true,"real_stars":10312,"star_ok":false,"no_path":false},{"name":"OpenLLMetry (Traceloop)","repo":"traceloop/openllmetry","stated_stars":5000,"exists":true,"real_stars":7244,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0,"star_median_rel_error":0.6121},"gpt":{"citations":[{"name":"Promptfoo","repo":"promptfoo/promptfoo","stated_stars":5200,"exists":true,"real_stars":22701,"star_ok":false,"no_path":false},{"name":"LangSmith SDK","repo":"langchain-ai/langsmith-sdk","stated_stars":1900,"exists":true,"real_stars":947,"star_ok":false,"no_path":false},{"name":"Langfuse","repo":"langfuse/langfuse","stated_stars":9800,"exists":true,"real_stars":29983,"star_ok":false,"no_path":false},{"name":"Helicone","repo":"helicone/helicone","stated_stars":3700,"exists":true,"real_stars":5873,"star_ok":false,"no_path":false},{"name":"OpenPrompt","repo":"thunlp/openprompt","stated_stars":4400,"exists":true,"real_stars":4879,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.2,"star_median_rel_error":0.6731},"grok":{"citations":[{"name":"PromptLayer","repo":"promptlayer/promptlayer","stated_stars":1200,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"LangSmith","repo":"langchain-ai/langsmith-sdk","stated_stars":850,"exists":true,"real_stars":947,"star_ok":true,"no_path":false},{"name":"Helicone","repo":"helicone/helicone","stated_stars":2400,"exists":true,"real_stars":5873,"star_ok":false,"no_path":false},{"name":"Promptfoo","repo":"promptfoo/promptfoo","stated_stars":3100,"exists":true,"real_stars":22701,"star_ok":false,"no_path":false},{"name":"Humanloop","repo":"humanloop/humanloop","stated_stars":650,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.6,"star_accuracy_rate":0.3333,"star_median_rel_error":0.5914},"glm":{"citations":[{"name":"Promptfoo","repo":"promptfoo/promptfoo","stated_stars":4500,"exists":true,"real_stars":22701,"star_ok":false,"no_path":false},{"name":"Dify","repo":"langgenius/dify","stated_stars":51000,"exists":true,"real_stars":146891,"star_ok":false,"no_path":false},{"name":"Langfuse","repo":"langfuse/langfuse","stated_stars":6500,"exists":true,"real_stars":29983,"star_ok":false,"no_path":false},{"name":"Pezzo","repo":"pezzolabs/pezzo","stated_stars":3000,"exists":true,"real_stars":3249,"star_ok":true,"no_path":false},{"name":"Agenta","repo":"agenta-ai/agenta","stated_stars":1500,"exists":true,"real_stars":4248,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.2,"star_median_rel_error":0.6528}}},{"id":"design2code","systems":{"bench":{"citations":[{"name":"kwakseongjae/oh-my-design","repo":"kwakseongjae/oh-my-design","stated_stars":280,"exists":true,"real_stars":280,"star_ok":true,"no_path":false},{"name":"mikesheehan54/Claude-Code-Design-AI","repo":"mikesheehan54/claude-code-design-ai","stated_stars":77,"exists":true,"real_stars":77,"star_ok":true,"no_path":false},{"name":"uselayout/app","repo":"uselayout/app","stated_stars":10,"exists":true,"real_stars":10,"star_ok":true,"no_path":false},{"name":"f0d010c/stark","repo":"f0d010c/stark","stated_stars":13,"exists":true,"real_stars":13,"star_ok":true,"no_path":false},{"name":"Kacep91/figma-ai-bridge","repo":"kacep91/figma-ai-bridge","stated_stars":15,"exists":true,"real_stars":15,"star_ok":true,"no_path":false},{"name":"marvkr/better-design","repo":"marvkr/better-design","stated_stars":157,"exists":true,"real_stars":157,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[{"name":"AnimaApp","repo":"animaapp/anima","stated_stars":null,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Builder.io","repo":"builderio/builder","stated_stars":7600,"exists":true,"real_stars":8742,"star_ok":true,"no_path":false},{"name":"OpenV0","repo":"raidendotai/openv0","stated_stars":4100,"exists":true,"real_stars":3945,"star_ok":true,"no_path":false},{"name":"Plasmic","repo":"plasmicapp/plasmic","stated_stars":4900,"exists":true,"real_stars":6882,"star_ok":true,"no_path":false},{"name":"tldraw make-real","repo":"tldraw/make-real","stated_stars":4400,"exists":true,"real_stars":5444,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":1,"star_median_rel_error":0.1612},"gpt":{"citations":[{"name":"Builder.io Mitosis","repo":"builderio/mitosis","stated_stars":12700,"exists":true,"real_stars":13872,"star_ok":true,"no_path":false},{"name":"Locofy Lightning","repo":"locofyai/locofy-lightning","stated_stars":2100,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Figma to Code","repo":"bernaferrari/figmatocode","stated_stars":5800,"exists":true,"real_stars":5029,"star_ok":true,"no_path":false},{"name":"TeleportHQ","repo":"teleporthq/teleport-code-generators","stated_stars":900,"exists":true,"real_stars":1112,"star_ok":true,"no_path":false},{"name":"Onlook","repo":"onlook-dev/onlook","stated_stars":21800,"exists":true,"real_stars":26062,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":1,"star_median_rel_error":0.1584},"grok":{"citations":[{"name":"Anima","repo":"animaapp/anima","stated_stars":3200,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Locofy","repo":"locofyai/locofy-docs","stated_stars":1800,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"Builder.io","repo":"builderio/builder","stated_stars":6800,"exists":true,"real_stars":8742,"star_ok":true,"no_path":false},{"name":"TeleportHQ","repo":"teleporthq/teleport-code-generators","stated_stars":1400,"exists":true,"real_stars":1112,"star_ok":true,"no_path":false},{"name":"DhiWise","repo":"dhiwise/dhiwise-code-generator","stated_stars":950,"exists":false,"real_stars":null,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.4,"star_accuracy_rate":1,"star_median_rel_error":0.2406},"glm":{"citations":[{"name":"Builder.io Mitosis","repo":"builderio/mitosis","stated_stars":12000,"exists":true,"real_stars":13872,"star_ok":true,"no_path":false},{"name":"Locofy.ai Lightning AI","repo":"locofy-ai/lightning","stated_stars":2500,"exists":false,"real_stars":null,"star_ok":false,"no_path":false},{"name":"TeleportHQ","repo":"teleporthq/teleport-code-generators","stated_stars":1400,"exists":true,"real_stars":1112,"star_ok":true,"no_path":false},{"name":"Figma to Code (Builder.io)","repo":"builderio/figma-html","stated_stars":2800,"exists":true,"real_stars":3635,"star_ok":true,"no_path":false},{"name":"Plasmic","repo":"plasmicapp/plasmic","stated_stars":4700,"exists":true,"real_stars":6882,"star_ok":false,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":0.8,"star_accuracy_rate":0.75,"star_median_rel_error":0.2444}}},{"id":"apidocs","systems":{"bench":{"citations":[{"name":"FreePeak/ktme","repo":"freepeak/ktme","stated_stars":15,"exists":true,"real_stars":15,"star_ok":true,"no_path":false},{"name":"dochia-dev/dochia-cli","repo":"dochia-dev/dochia-cli","stated_stars":146,"exists":true,"real_stars":146,"star_ok":true,"no_path":false},{"name":"raccioly/docguard","repo":"raccioly/docguard","stated_stars":18,"exists":true,"real_stars":19,"star_ok":true,"no_path":false},{"name":"shotgun-sh/shotgun","repo":"shotgun-sh/shotgun","stated_stars":681,"exists":true,"real_stars":681,"star_ok":true,"no_path":false},{"name":"Dicklesworthstone/automated_plan_reviser_pro","repo":"dicklesworthstone/automated_plan_reviser_pro","stated_stars":60,"exists":true,"real_stars":60,"star_ok":true,"no_path":false},{"name":"raye-deng/open-code-review","repo":"raye-deng/open-code-review","stated_stars":27,"exists":true,"real_stars":27,"star_ok":true,"no_path":false}],"cited_total":6,"with_path":6,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0},"opus":{"citations":[{"name":"Redocly / Redoc","repo":"redocly/redoc","stated_stars":23000,"exists":true,"real_stars":25784,"star_ok":true,"no_path":false},{"name":"Stoplight Spectral","repo":"stoplightio/spectral","stated_stars":2400,"exists":true,"real_stars":3137,"star_ok":true,"no_path":false},{"name":"OpenAPI Diff (Tufin)","repo":"tufin/oasdiff","stated_stars":1500,"exists":true,"real_stars":1250,"star_ok":true,"no_path":false},{"name":"Swagger UI","repo":"swagger-api/swagger-ui","stated_stars":27000,"exists":true,"real_stars":28859,"star_ok":true,"no_path":false},{"name":"Optic","repo":"opticdev/optic","stated_stars":1900,"exists":true,"real_stars":1534,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0.2},"gpt":{"citations":[{"name":"OpenAPI Generator","repo":"openapitools/openapi-generator","stated_stars":23600,"exists":true,"real_stars":26464,"star_ok":true,"no_path":false},{"name":"Swagger UI","repo":"swagger-api/swagger-ui","stated_stars":26700,"exists":true,"real_stars":28859,"star_ok":true,"no_path":false},{"name":"Redoc","repo":"redocly/redoc","stated_stars":24000,"exists":true,"real_stars":25784,"star_ok":true,"no_path":false},{"name":"OpenAPI Diff","repo":"openapitools/openapi-diff","stated_stars":900,"exists":true,"real_stars":1087,"star_ok":true,"no_path":false},{"name":"oasdiff","repo":"tufin/oasdiff","stated_stars":1000,"exists":true,"real_stars":1250,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":1,"star_median_rel_error":0.1082},"grok":{"citations":[{"name":"Spectral","repo":"stoplightio/spectral","stated_stars":2223,"exists":true,"real_stars":3137,"star_ok":true,"no_path":false},{"name":"Redocly CLI","repo":"redocly/redocly-cli","stated_stars":452,"exists":true,"real_stars":1477,"star_ok":false,"no_path":false},{"name":"OpenAPI Diff","repo":"openapitools/openapi-diff","stated_stars":801,"exists":true,"real_stars":1087,"star_ok":true,"no_path":false},{"name":"oasdiff","repo":"tufin/oasdiff","stated_stars":312,"exists":true,"real_stars":1250,"star_ok":false,"no_path":false},{"name":"Optic","repo":"opticdev/optic","stated_stars":1284,"exists":true,"real_stars":1534,"star_ok":true,"no_path":false}],"cited_total":5,"with_path":5,"existence_rate":1,"star_accuracy_rate":0.6,"star_median_rel_error":0.2914},"glm":{"citations":[],"cited_total":0,"with_path":0,"existence_rate":null,"star_accuracy_rate":null,"star_median_rel_error":null}}}],"summary":{"bench_existence":1,"model_mean_existence":0.7056,"fabricators":3,"models":4,"claimHolds":true}}