{"ID":2849750,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.23528","arxiv_id":"2510.23528","title":"Tracing Distribution Shifts with Causal System Maps","abstract":"Monitoring machine learning (ML) systems is hard, with standard practice focusing on detecting distribution shifts rather than their causes. Root-cause analysis often relies on manual tracing to determine whether a shift is caused by software faults, data-quality issues, or natural change. We propose ML System Maps -- causal maps that, through layered views, make explicit the propagation paths between the environment and the ML system's internals, enabling systematic attribution of distribution shifts. We outline the approach and a research agenda for its development and evaluation.","short_abstract":"Monitoring machine learning (ML) systems is hard, with standard practice focusing on detecting distribution shifts rather than their causes. Root-cause analysis often relies on manual tracing to determine whether a shift is caused by software faults, data-quality issues, or natural change. We propose ML System Maps --...","url_abs":"https://arxiv.org/abs/2510.23528","url_pdf":"https://arxiv.org/pdf/2510.23528v1","authors":"[\"Joran Leest\",\"Ilias Gerostathopoulos\",\"Patricia Lago\",\"Claudia Raibulet\"]","published":"2025-10-27T17:07:40Z","proceeding":"cs.SE","tasks":"[\"cs.SE\"]","methods":"[]","has_code":false}