The DOI matches its Crossref record; the references it cites are not checked yet.
The ML test score: A rubric for ML production readiness and technical debt reduction
Abstract
Creating reliable, production-level machine learning systems brings on a host of concerns not found in small toy examples or even large offline research experiments. Testing and monitoring are key considerations for ensuring the production-readiness of an ML system, and for reducing technical debt of ML systems. But it can be difficult to formulate specific tests, given that the actual prediction behavior of any given model is difficult to specify a priori. In this paper, we present 28 specific tests and monitoring needs, drawn from experience with a wide range of production ML systems to help quantify these issues and present an easy to follow road-map to improve production readiness and pay down ML technical debt.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Trust can be operationalized through measurable indicators such as detection reliability (stability of Precision, Recall, and F1) [50], diagnostic consistency (variance of root-cause ranking across executions) [51], causal validity (alignment between predicted and actual fault sources) [52], and robustness (performance degradation under noisy or incomplete telemetry) [53].”
From Anomaly detection and root-cause identification in microservices: a survey (2026) · cites this paper as [50]
In the citing paper
“Agentic systems heighten exposure risks, as such data may be incorporated into retrieval contexts, tool outputs, memory, and audit logs [155], [156].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [156]
In the citing paper
“As models may reproduce memorized content, operational agents should, by default, avoid persistent memory and treat each incident as a distinct retention boundary [154], [155], [156].”
From Large language models for agentic NetOps and AIOps: Architectures, evaluation, and safety (2027) · cites this paper as [156]
Citations
The citation lists are queued
They are fetched later and appear here then.
References 16 · Cited by 310
Research works printed but not linked: 5
- desautels, 2014, Parallelizing exploration-exploitation tradeoffs in gaussian process bandit optimization, Journal of Machine Learning Research (JMLR), 15, 40534103
- 2017, Google cloud machine learning now open to all with new professional services and education programs
- gawande, 2009, The Checklist Manifesto
- chandra, 2010, Sibyl A System for Large Scale Machine Learning, 28
- zinkevich, 1996, Rules of machine learning, Invited talk at the NIPS Reliable Machine Learning Workshop
Metadata
- Authors
- Breck, E., Cai, S., Nielsen, E., Salib, M., & Sculley, D.
- Affiliations
- Google (United States) (US)
- ORCID
- Cai, Shanqing
- Venue
- 2017 IEEE International Conference on Big Data (Big Data)
- Publisher
- IEEE
- Published
- 2017-12
- Pages
- 1123-1132
- OpenAlex
- W2782864149
- Cited by
- 310
- References
- 16
- Citations by year
- 2026: 80 · 2025: 49 · 2024: 38 · 2023: 27 · 2022: 37 · 2021: 38 · 2020: 22 · 2019: 15 · 2018: 4
- FWCI
- 8.25
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on Big Data (BigData) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Information Systems › Software Engineering Techniques and Practices
- Keywords
- assessment rubrics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: The ML test score: A rubric for ML production readiness and technical debt reduction. https://app.cochat.ai/papers/10.1109/bigdata.2017.8258038
- The paper
- Breck, E., Cai, S., Nielsen, E., Salib, M., & Sculley, D. (2017). The ML test score: A rubric for ML production readiness and technical debt reduction. 2017 IEEE International Conference on Big Data (Big Data). https://doi.org/10.1109/bigdata.2017.8258038
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.