发表机构
Inovionix（Inovionix）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出并验证了在不确定性下治理人机协作优先级排序的量化方法，通过可靠性加权与依赖约束优化，显著提升估计精度并界定优化边界。
AI 中文摘要
AI原生的软件工程日益将人类判断、历史类比、参数估计和AI生成的预测整合到同一个优先级排序决策中。由此产生的问题不仅仅是如何对候选工作进行排序，而是如何治理异构估计、不确定性、战略参数、依赖关系和有限容量，同时保持可检查性和可重新校准性。我们研究了D-POAF决策实践中使用的五个定量算子：业务价值评分（BVS）、工作量与风险评分（ERS）、优先级价值评分（PVS）、集体校准评分（CCS）和最优开发路径（ODP）。受控合成实验表征了它们在已知潜在变量和显式错误过程下的行为。适度的BVS权重扰动保持了全局排名（中位数Spearman相关系数为0.986），而更广泛的战略变化将前10%的重叠率降至0.788。可靠性加权的工作量聚合实现了MAE 0.616，相对于最佳单个估计器（MAE 1.073）降低了42.6%，并优于简单平均值（MAE 0.638）。在估计器漂移下，自适应可靠性加权相对于等权重将平均RMSE降低了4.5%。模型集体分歧检测到最高误差的优先级估计，ROC-AUC为0.906。在800个依赖约束的投资组合实例中，价值-工作量比实现了平均目标比率0.962，与精确最优解的ODP距离为0.953；自举区间确认了在声明目标下价值-工作量比具有小而系统的优势。这些结果为基于证据加权的人机优先级排序建立了定量基础，并定义了最短路径ODP公式与一般发布投资组合选择之间的优化边界。
英文摘要
AI-native software engineering increasingly combines human judgment, historical analogy, parametric estimation, and AI-generated forecasts in the same prioritization decision. We study five quantitative operators used in the D-POAF decision practice and stress-test them under uncertainty, estimator dependence, drift, shared context error, dependencies, and limited capacity. Robustness extensions use 30 deterministic seeds. Moderate scoring changes preserve broad order while materially changing funded-set membership. Under independent estimator errors, inverse-MSE aggregation reaches MAE 0.615, a 42.2% reduction relative to the best individual estimator. The gain falls to 4.4% at error correlation rho = 0.6 and becomes negative at rho = 0.8, while calibration-set regression remains slightly better than the best individual and approaches a test-set oracle. Under estimator drift, four-Wave adaptive weighting reduces average RMSE by 4.64% (95% CI [4.50%, 4.78%]). Model-collective divergence achieves ROC-AUC 0.908 with independent channels and remains above 0.878 with shared noise up to 0.8. We separate budget-constrained portfolio selection from ODP's native dependency-aware sequencing role. When ODP distance is repurposed as a portfolio-selection heuristic, value-to-effort is stronger in the tested generator. For a fixed selected set, ascending ERS/BVS is optimal for an ERS-weighted completion objective without dependencies and reaches mean efficiency 0.982 versus the exact precedence-constrained optimum at dependency intensity lambda = 1.0. Scaling to 100 Feature Blocks, ODP has the highest mean early-value AUC among the transparent sequencing baselines, with a small margin over PVS ordering. These results characterize both the validity region of evidence-weighted human-AI prioritization and the boundary between selection and sequencing objectives.
Comments18 pages, 7 figures. Substantially revised version following public PREreview feedback, with 30-seed robustness analysis, correlated estimator errors, shared-noise calibration tests, exact MILP portfolio benchmarks, and explicit dependency-aware ODP sequencing
