Unverified50% confidenceFactExact time
Keera was fine-tuned on the self-oss-instruct-sc2-exec-filter-50k dataset, which contains 50k Python instructions and answers, and all answer code was actually run and passed the tests.
1
Sources
50%
Confidence
Long-term
Relevance
10/18/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在测试中向智能体输入「计算 6 乘 7」的请求，模型自动调用 ai_python_executable 工具并返回结果 42，整个推理过程在 MLflow 中完整记录72% similarUnverifiedThe test designed 50 automatically verifiable tasks, divided into five categories: multi-step math computation, extracting JSON from order notes, classifying support tickets, conditional filtering and sorting, and strict-format writing, with 10 questions per category, each with a standard answer.67% similarUnverifiedThe sampler implementation given in the article is about forty lines of code, a proposal based on run_id hashing, reading SALT from environment variables, and covering three storage modes, and has not been benchmarked against production traffic.65% similarUnverifiedIndependent evaluator Anass Kartit tested all decision models available on OpenRouter using 82 manually annotated questions, and additionally tested 4 models locally on a Mac.65% similarUnverifiedKeera was pretrained on the 2B-token codeparrot-clean dataset, following the Chinchilla rule of about 20 tokens/parameter.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1057718API
curl https://kongchang.com/api/v1/knowledge/claims/1057718MCP
get_claim(id=1057718)