{"paper":{"title":"DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chengyu Shen, Hao Liang, Runming He, Wentao Zhang, Xiaochen Ma, Zhen Hao Wong, Zimo Meng","submitted_at":"2026-07-18T03:30:19Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the \\textit{NL2Pipeline gap}. To bridge it, we introduce \\textsc{DataFlow-Harness}, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines \\textsc{DataFlow-Skills} for procedural guidance, a Model Context Protocol (MCP) layer t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16617","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.16617/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}