让元分析的决策过程可执行、可验证，提升结果一致性。
Constructing Executable Analytical Knowledge Representations for Meta-Analysis Synthesis Using an Agentic Harness
- 用EAKR结构化表示元分析中的证据与决策逻辑，支持机器处理。
- 58个合成单元中57个成功执行统计分析，98.2%置信区间重叠。
- 相比直接生成，该方法在结构一致性和公式准确性上显著提升。
元分析合成面临的核心挑战是：结构化证据本身并不包含可执行计算所需的分析知识。在进行统计运算前，必须明确定义证据分配、分析对比、结局与时间点对齐、效应量构建及方法学可接受性等决策。现有自动化方法常将这些决策嵌入模型输出、生成代码或工作流痕迹中，而非作为独立可验证的知识表示。本文提出可执行分析知识表示（EAKR），一种可被机器操作的元分析知识表示形式，涵盖证据、关系、数值输入、约束、溯源信息及未决问题。我们通过MetaSynDec实现EAKR，该系统由大语言模型提出结构化更新，确定性服务负责基于模式与契约的验证与执行。在58个合成单元中，所有单位均完成EAKR构建，其中57个进入统计执行。在56个具备足够信息定义参考分析对象的单元中，38个（67.9%）达到完全对象保真度，42个（75.0%）实现精确证据集一致，平均杰卡德相似度为0.909。生成并发布的置信区间在55个单位中有54个重叠（98.2%）。相比直接使用大模型生成，MetaSynDec在参考合成结构一致性上表现更优（57/58 对比 23/58；p<0.001），在23个共同完成的单元中，参考公式一致性也显著更高（23/23 对比 1/23；p<0.001）。结果表明，EAKR能有效支持形式化验证、可追溯性、统计执行，并优于直接大模型生成的方法。
原文摘要 · Abstract (English)
Meta-analysis synthesis highlights a fundamental challenge in knowledge-based scientific analysis: structured evidence does not by itself represent the analytical knowledge required for executable computation. Decisions about evidence assignment, analytical contrasts, outcome and time-point alignment, effect-size formulation, and methodological admissibility must be explicit before statistical execution. Existing automated approaches often embed these decisions in model outputs, generated code, or workflow traces rather than representing them as independently verifiable knowledge. We introduce the Executable Analytical Knowledge Representation (EAKR), a machine-actionable representation of the knowledge required to transform structured evidence into executable meta-analysis. An EAKR represents evidence, relations, numerical inputs, constraints, provenance, and unresolved issues. We operationalise EAKR in MetaSynDec, an agentic harness in which large language models propose structured updates and deterministic services govern schema- and contract-based validation and execution. Across 58 synthesis units, MetaSynDec constructed all EAKRs, with 57 proceeding to statistical execution. Of 56 units with sufficient information to define a reference analysis object, 38 (67.9%) achieved complete object fidelity and 42 (75.0%) exact evidence-set agreement, with a mean Jaccard similarity of 0.909. Generated and published confidence intervals overlapped in 54 of 55 units (98.2%). MetaSynDec outperformed direct LLM generation in reference synthesis-structure agreement (57/58 versus 23/58; p<0.001) and among 23 jointly completed units, exact reference-formulation agreement (23/23 versus 1/23; p<0.001). These findings provide feasibility evidence that EAKR supports formal validation, traceability, statistical execution, and improved methodological agreement relative to direct LLM generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。