发表机构
University of Trento; Argonne National Laboratory; Oak Ridge National Laboratory（特伦托大学; 阿贡国家实验室; 橡树岭国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出工作流卡片，将工作流执行的溯源数据转化为可读的结构化摘要，填补了现有模型、数据卡片缺失执行级信息的空白，使LLM回答质量较传统查询提升近一倍。
AI 中文摘要
模型卡片（Model Cards）与数据卡片（Data Cards）已证明结构化、人类可读的文档对机器学习制品具有重要价值，可记录其上下文、参数、局限性及预期用途。然而，这些实践仍聚焦于静态制品（数据集与训练模型本身），忽略了生成、转换与评估这些制品的工作流执行过程。此类执行过程包含数据准备、参数选择、运行时行为、资源使用及中间转换等关键细节，而偏差、性能波动与可复现性差距往往就源于这些环节。为填补这一空白，本文提出工作流卡片（Workflow Cards）：一种结构化摘要，可将工作流执行的机器可读溯源数据浓缩为人类与大型语言模型（LLMs）均可读取和分析的形式。本文包含两个主要部分：第一，基于模型卡片与数据卡片缺失的执行级数据所引发的代表性溯源问题，定义了工作流卡片的模板；第二，对比通过基于模式的接口查询溯源数据库的方式，评估LLM利用工作流卡片理解工作流执行的有效性。结果表明，工作流卡片提供了现有卡片类型（如模型卡片与数据卡片）所缺失的执行级信息，填补了重要的文档空白；且在LLM作为评判者与人工评估中，工作流卡片的回答质量较基于模式的查询提升近一倍。
英文摘要
Model Cards and Data Cards have demonstrated the value of structured, human-readable documentation for machine learning artifacts, capturing their context, parameters, limitations, and intended use. However, these practices remain focused on static artifacts (the datasets and trained models themselves) while overlooking the workflow executions that produce, transform, and evaluate them. Such executions hold critical details about data preparation, parameter choice, runtime behavior, resource use, and intermediate transformations, precisely where bias, performance variation, and reproducibility gaps tend to originate. To close this gap, we introduce Workflow Cards: structured summaries that condense the machine-readable provenance data of a workflow execution into a form both humans and large language models (LLMs) can read and analyze. This paper has two main parts. First, it defines a Workflow Card template informed by a representative set of provenance questions that surface from the execution-level data missing from Model and Data Cards. Second, it evaluates how effectively LLMs use Workflow Cards to understand workflow executions compared with querying provenance databases through a schema-based interface. Results show that Workflow Cards provide execution-level information absent from existing card types, such as Model Cards and Data Cards, thereby filling an important documentation gap; and that Workflow Cards nearly double answer quality compared with schema-based querying, consistently across LLM-as-a-Judge and human assessments.
CommentsAccepted at eScience2026
