{"i":2,"slug":"blind-review-head-to-head","chart":{"id":"blind-review-dimension-scores","title":"What the critics scored higher","subtitle":"Mean 1-5 score per dimension, latest attempt of 12 tasks","kind":"grouped-bar","unit":"score","yLabel":"Mean score (1-5)","series":[{"name":"AI change","points":{"$k":["label","value","n","highlight"],"$r":[["Correctness",4.4,12,true],["Root cause",4.46,12,true],["Edge cases",3.95,12,true],["Tests",4.51,12,true],["Completeness",4.22,12,true],["Compatibility",4.39,12,true],["Security",4.38,12,true],["Maintainability",4.19,12,true],["Simplicity",4.19,12,true],["Conventions",4.36,12,true],["Docs",4.04,12,true],["Communication",4.59,12,true],["Production readiness",4.03,12,true],["Overall",4.14,12,true]]}},{"name":"Merged human change","points":{"$k":["label","value","n"],"$r":[["Correctness",3.86,12],["Root cause",3.97,12],["Edge cases",3.49,12],["Tests",3.29,12],["Completeness",3.34,12],["Compatibility",3.74,12],["Security",4.14,12],["Maintainability",3.64,12],["Simplicity",3.85,12],["Conventions",3.52,12],["Docs",3.2,12],["Communication",3.58,12],["Production readiness",3.21,12],["Overall",3.2,12]]}}],"note":"Unweighted mean over tasks of each pair’s mean critic score. Critics were not told which change came from a person.","sourceIds":["agent-blind-review"]}}