StabilityFrontier-ModelRepo / audit /pairwise_dominance.jsonl
petra345's picture
Release stability frontier model artifacts
b23a2a5 verified
Raw
History Blame Contribute Delete
17.3 kB
{"candidate":"step_100","challenger":"step_200","quality_delta":"+0.024","risk_delta":"+0.084","floor_delta":"+0.043","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_100","challenger":"step_300","quality_delta":"+0.049","risk_delta":"+0.164","floor_delta":"+0.079","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_100","challenger":"step_400","quality_delta":"+0.070","risk_delta":"+0.232","floor_delta":"+0.110","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_100","challenger":"step_500","quality_delta":"+0.090","risk_delta":"+0.284","floor_delta":"+0.135","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_100","challenger":"step_600","quality_delta":"+0.108","risk_delta":"+0.305","floor_delta":"+0.157","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_100","challenger":"step_700","quality_delta":"+0.121","risk_delta":"+0.305","floor_delta":"+0.176","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_100","challenger":"step_800","quality_delta":"+0.130","risk_delta":"+0.305","floor_delta":"+0.197","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_100","challenger":"step_900","quality_delta":"+0.133","risk_delta":"+0.267","floor_delta":"+0.210","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_100","challenger":"step_1000","quality_delta":"+0.138","risk_delta":"+0.251","floor_delta":"+0.221","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_200","challenger":"step_100","quality_delta":"-0.024","risk_delta":"-0.084","floor_delta":"-0.043","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_200","challenger":"step_300","quality_delta":"+0.025","risk_delta":"+0.080","floor_delta":"+0.036","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_200","challenger":"step_400","quality_delta":"+0.047","risk_delta":"+0.148","floor_delta":"+0.067","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_200","challenger":"step_500","quality_delta":"+0.067","risk_delta":"+0.200","floor_delta":"+0.092","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_200","challenger":"step_600","quality_delta":"+0.084","risk_delta":"+0.221","floor_delta":"+0.114","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_200","challenger":"step_700","quality_delta":"+0.097","risk_delta":"+0.221","floor_delta":"+0.133","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_200","challenger":"step_800","quality_delta":"+0.106","risk_delta":"+0.221","floor_delta":"+0.154","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_200","challenger":"step_900","quality_delta":"+0.110","risk_delta":"+0.183","floor_delta":"+0.167","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_200","challenger":"step_1000","quality_delta":"+0.115","risk_delta":"+0.167","floor_delta":"+0.178","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_300","challenger":"step_100","quality_delta":"-0.049","risk_delta":"-0.164","floor_delta":"-0.079","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_300","challenger":"step_200","quality_delta":"-0.025","risk_delta":"-0.080","floor_delta":"-0.036","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_300","challenger":"step_400","quality_delta":"+0.021","risk_delta":"+0.068","floor_delta":"+0.031","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_300","challenger":"step_500","quality_delta":"+0.041","risk_delta":"+0.120","floor_delta":"+0.056","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_300","challenger":"step_600","quality_delta":"+0.059","risk_delta":"+0.141","floor_delta":"+0.078","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_300","challenger":"step_700","quality_delta":"+0.072","risk_delta":"+0.141","floor_delta":"+0.097","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_300","challenger":"step_800","quality_delta":"+0.081","risk_delta":"+0.141","floor_delta":"+0.118","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_300","challenger":"step_900","quality_delta":"+0.084","risk_delta":"+0.103","floor_delta":"+0.131","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_300","challenger":"step_1000","quality_delta":"+0.090","risk_delta":"+0.087","floor_delta":"+0.142","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_400","challenger":"step_100","quality_delta":"-0.070","risk_delta":"-0.232","floor_delta":"-0.110","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_400","challenger":"step_200","quality_delta":"-0.047","risk_delta":"-0.148","floor_delta":"-0.067","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_400","challenger":"step_300","quality_delta":"-0.021","risk_delta":"-0.068","floor_delta":"-0.031","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_400","challenger":"step_500","quality_delta":"+0.020","risk_delta":"+0.052","floor_delta":"+0.025","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_400","challenger":"step_600","quality_delta":"+0.037","risk_delta":"+0.073","floor_delta":"+0.047","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_400","challenger":"step_700","quality_delta":"+0.050","risk_delta":"+0.073","floor_delta":"+0.066","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_400","challenger":"step_800","quality_delta":"+0.060","risk_delta":"+0.073","floor_delta":"+0.087","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_400","challenger":"step_900","quality_delta":"+0.063","risk_delta":"+0.035","floor_delta":"+0.100","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_400","challenger":"step_1000","quality_delta":"+0.068","risk_delta":"+0.019","floor_delta":"+0.111","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_500","challenger":"step_100","quality_delta":"-0.090","risk_delta":"-0.284","floor_delta":"-0.135","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_500","challenger":"step_200","quality_delta":"-0.067","risk_delta":"-0.200","floor_delta":"-0.092","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_500","challenger":"step_300","quality_delta":"-0.041","risk_delta":"-0.120","floor_delta":"-0.056","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_500","challenger":"step_400","quality_delta":"-0.020","risk_delta":"-0.052","floor_delta":"-0.025","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_500","challenger":"step_600","quality_delta":"+0.017","risk_delta":"+0.021","floor_delta":"+0.022","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_500","challenger":"step_700","quality_delta":"+0.030","risk_delta":"+0.021","floor_delta":"+0.041","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_500","challenger":"step_800","quality_delta":"+0.040","risk_delta":"+0.021","floor_delta":"+0.062","dominates_candidate":true,"strictly_better":["weighted_quality","risk_score","stability_floor"]}
{"candidate":"step_500","challenger":"step_900","quality_delta":"+0.043","risk_delta":"-0.017","floor_delta":"+0.075","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_500","challenger":"step_1000","quality_delta":"+0.048","risk_delta":"-0.033","floor_delta":"+0.086","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_600","challenger":"step_100","quality_delta":"-0.108","risk_delta":"-0.305","floor_delta":"-0.157","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_600","challenger":"step_200","quality_delta":"-0.084","risk_delta":"-0.221","floor_delta":"-0.114","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_600","challenger":"step_300","quality_delta":"-0.059","risk_delta":"-0.141","floor_delta":"-0.078","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_600","challenger":"step_400","quality_delta":"-0.037","risk_delta":"-0.073","floor_delta":"-0.047","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_600","challenger":"step_500","quality_delta":"-0.017","risk_delta":"-0.021","floor_delta":"-0.022","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_600","challenger":"step_700","quality_delta":"+0.013","risk_delta":"+0.000","floor_delta":"+0.019","dominates_candidate":true,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_600","challenger":"step_800","quality_delta":"+0.022","risk_delta":"+0.000","floor_delta":"+0.040","dominates_candidate":true,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_600","challenger":"step_900","quality_delta":"+0.025","risk_delta":"-0.038","floor_delta":"+0.053","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_600","challenger":"step_1000","quality_delta":"+0.031","risk_delta":"-0.054","floor_delta":"+0.064","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_700","challenger":"step_100","quality_delta":"-0.121","risk_delta":"-0.305","floor_delta":"-0.176","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_700","challenger":"step_200","quality_delta":"-0.097","risk_delta":"-0.221","floor_delta":"-0.133","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_700","challenger":"step_300","quality_delta":"-0.072","risk_delta":"-0.141","floor_delta":"-0.097","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_700","challenger":"step_400","quality_delta":"-0.050","risk_delta":"-0.073","floor_delta":"-0.066","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_700","challenger":"step_500","quality_delta":"-0.030","risk_delta":"-0.021","floor_delta":"-0.041","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_700","challenger":"step_600","quality_delta":"-0.013","risk_delta":"+0.000","floor_delta":"-0.019","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_700","challenger":"step_800","quality_delta":"+0.009","risk_delta":"+0.000","floor_delta":"+0.021","dominates_candidate":true,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_700","challenger":"step_900","quality_delta":"+0.012","risk_delta":"-0.038","floor_delta":"+0.034","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_700","challenger":"step_1000","quality_delta":"+0.018","risk_delta":"-0.054","floor_delta":"+0.045","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_800","challenger":"step_100","quality_delta":"-0.130","risk_delta":"-0.305","floor_delta":"-0.197","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_800","challenger":"step_200","quality_delta":"-0.106","risk_delta":"-0.221","floor_delta":"-0.154","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_800","challenger":"step_300","quality_delta":"-0.081","risk_delta":"-0.141","floor_delta":"-0.118","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_800","challenger":"step_400","quality_delta":"-0.060","risk_delta":"-0.073","floor_delta":"-0.087","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_800","challenger":"step_500","quality_delta":"-0.040","risk_delta":"-0.021","floor_delta":"-0.062","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_800","challenger":"step_600","quality_delta":"-0.022","risk_delta":"+0.000","floor_delta":"-0.040","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_800","challenger":"step_700","quality_delta":"-0.009","risk_delta":"+0.000","floor_delta":"-0.021","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_800","challenger":"step_900","quality_delta":"+0.003","risk_delta":"-0.038","floor_delta":"+0.013","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_800","challenger":"step_1000","quality_delta":"+0.009","risk_delta":"-0.054","floor_delta":"+0.024","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_900","challenger":"step_100","quality_delta":"-0.133","risk_delta":"-0.267","floor_delta":"-0.210","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_900","challenger":"step_200","quality_delta":"-0.110","risk_delta":"-0.183","floor_delta":"-0.167","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_900","challenger":"step_300","quality_delta":"-0.084","risk_delta":"-0.103","floor_delta":"-0.131","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_900","challenger":"step_400","quality_delta":"-0.063","risk_delta":"-0.035","floor_delta":"-0.100","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_900","challenger":"step_500","quality_delta":"-0.043","risk_delta":"+0.017","floor_delta":"-0.075","dominates_candidate":false,"strictly_better":["risk_score"]}
{"candidate":"step_900","challenger":"step_600","quality_delta":"-0.025","risk_delta":"+0.038","floor_delta":"-0.053","dominates_candidate":false,"strictly_better":["risk_score"]}
{"candidate":"step_900","challenger":"step_700","quality_delta":"-0.012","risk_delta":"+0.038","floor_delta":"-0.034","dominates_candidate":false,"strictly_better":["risk_score"]}
{"candidate":"step_900","challenger":"step_800","quality_delta":"-0.003","risk_delta":"+0.038","floor_delta":"-0.013","dominates_candidate":false,"strictly_better":["risk_score"]}
{"candidate":"step_900","challenger":"step_1000","quality_delta":"+0.005","risk_delta":"-0.016","floor_delta":"+0.011","dominates_candidate":false,"strictly_better":["weighted_quality","stability_floor"]}
{"candidate":"step_1000","challenger":"step_100","quality_delta":"-0.138","risk_delta":"-0.251","floor_delta":"-0.221","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_1000","challenger":"step_200","quality_delta":"-0.115","risk_delta":"-0.167","floor_delta":"-0.178","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_1000","challenger":"step_300","quality_delta":"-0.090","risk_delta":"-0.087","floor_delta":"-0.142","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_1000","challenger":"step_400","quality_delta":"-0.068","risk_delta":"-0.019","floor_delta":"-0.111","dominates_candidate":false,"strictly_better":[]}
{"candidate":"step_1000","challenger":"step_500","quality_delta":"-0.048","risk_delta":"+0.033","floor_delta":"-0.086","dominates_candidate":false,"strictly_better":["risk_score"]}
{"candidate":"step_1000","challenger":"step_600","quality_delta":"-0.031","risk_delta":"+0.054","floor_delta":"-0.064","dominates_candidate":false,"strictly_better":["risk_score"]}
{"candidate":"step_1000","challenger":"step_700","quality_delta":"-0.018","risk_delta":"+0.054","floor_delta":"-0.045","dominates_candidate":false,"strictly_better":["risk_score"]}
{"candidate":"step_1000","challenger":"step_800","quality_delta":"-0.009","risk_delta":"+0.054","floor_delta":"-0.024","dominates_candidate":false,"strictly_better":["risk_score"]}
{"candidate":"step_1000","challenger":"step_900","quality_delta":"-0.005","risk_delta":"+0.016","floor_delta":"-0.011","dominates_candidate":false,"strictly_better":["risk_score"]}