Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.10742 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913174606839808 |
|---|---|
| author | Roth, Simon |
| author_facet | Roth, Simon |
| contents | Data leakage has been identified in 648 published papers across 30 scientific fields. The knowledge to prevent it has existed for over a decade; the problem persists because the tools do not enforce what the textbooks teach. This paper presents a grammar (eight typed primitives connected by a directed acyclic graph with four hard constraints) that makes the most damaging leakage types structurally unrepresentable within the grammar's scope. The core mechanism is a terminal assessment gate: the first call-time-enforced evaluate/assess boundary documented in the peer-reviewed ML methodology literature (to my knowledge, as of May 2026), backed by a specification precise enough for independent reimplementation. A companion landscape study across 2,047 datasets grounds the constraints in measured effect sizes. Two reference implementations (Python, R) are available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10742 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Grammar of Machine Learning Workflows: Rejecting Data Leakage at Call Time Roth, Simon Machine Learning I.2.6; D.2.4 Data leakage has been identified in 648 published papers across 30 scientific fields. The knowledge to prevent it has existed for over a decade; the problem persists because the tools do not enforce what the textbooks teach. This paper presents a grammar (eight typed primitives connected by a directed acyclic graph with four hard constraints) that makes the most damaging leakage types structurally unrepresentable within the grammar's scope. The core mechanism is a terminal assessment gate: the first call-time-enforced evaluate/assess boundary documented in the peer-reviewed ML methodology literature (to my knowledge, as of May 2026), backed by a specification precise enough for independent reimplementation. A companion landscape study across 2,047 datasets grounds the constraints in measured effect sizes. Two reference implementations (Python, R) are available. |
| title | A Grammar of Machine Learning Workflows: Rejecting Data Leakage at Call Time |
| topic | Machine Learning I.2.6; D.2.4 |
| url | https://arxiv.org/abs/2603.10742 |