Newshot

When Passing Checks Do Not Establish Completion: Evidence Interpretation in Coding Agents

Summary

arXiv:2611.22835v1 Announce Type: new Abstract: Verification procedures in coding agents must preserve execution facts, interpret their scope and discharge checking obligations. We study these responsibilities through qualified repository checks, controlled evidence consumers and executable workflows. A prospective thirteen-task factorial study finds that correct reported facts need not yield the requested finite verdict. Conversely, all 122 delivered labels in a held-out receipt-supply study are correct, while sixteen responses misreport facts and eleven others exceed authorized scope. Production repair supplies successful controls and finite-supported preservation failures. Across 118 repair episodes on 31 tasks, source interventions separate startup reachability from repair and witness production from the claimed operation. Lifetime and resource controls delimit what passing validation establishes. Generated-note comparisons yield local repair differences but can state false explana…

Original text(via arXiv cs.CL)

Computer Science > Computation and Language

Title:When Passing Checks Do Not Establish Completion: Evidence Interpretation in Coding Agents

Abstract:Verification procedures in coding agents must preserve execution facts, interpret their scope and discharge checking obligations. We study these responsibilities through qualified repository checks, controlled evidence consumers and executable workflows. A prospective thirteen-task factorial study finds that correct reported facts need not yield the requested finite verdict. Conversely, all 122 delivered labels in a held-out receipt-supply study are correct, while sixteen responses misreport facts and eleven others exceed authorized scope. Production repair supplies successful controls and finite-supported preservation failures. Across 118 repair episodes on 31 tasks, source interventions separate startup reachability from repair and witness production from the claimed operation. Lifetime and resource controls delimit what passing validation establishes. Generated-note comparisons yield local repair differences but can state false explanations; strong ordinary baselines, new tasks and Skill-transfer studies supply no consistent overall advantage. These results characterize evidence interpretation, applicability and fulfilled actions while limiting claims of general diagnostic superiority, Skill deterioration or deployed folding effects.
Comments:12 pages; supplementary material included as ancillary files
Subjects:Computation and Language (cs.CL) ; Software Engineering (cs.SE)
Cite as:arXiv:2611.22835 [cs.CL]
(or arXiv:2611.22835v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2611.22835 arXiv-issued DOI via DataCite (pending registration)

Submission history

Access Paper:

  • HTML (experimental)

Ancillary files (details):

  • Supplementary-Material.pdf
  • supplement-source/benefit-scope-supplement.tex
  • supplement-source/evidence-guide.tex
  • supplement-source/figures/action-allocation.pdf
  • supplement-source/figures/shutdown-order.pdf
  • supplement-source/focused-supplement.tex
  • supplement-source/native-update255.tex
  • supplement-source/prospective-update253.tex
  • supplement-source/relocated-boundary-detail253.tex
  • supplement-source/relocated-guidance-detail253.tex
  • (5 additional files not shown)

Additional Features

  • Audio Summary

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv cs.CL
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗