PROXAI: Interactive Provenance-Aware Debugging of Machine Learning Pipelines
Summary: PROXAI connects XAI-identified influential data to multi-granular provenance, tracing anomalous model behavior through preprocessing to root causes. Its interactive workflow lets users inspect transformations and validate fixes end to end. (summarized by gpt-5.6-luna on Aug 28 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Pasquale Leonardo Lazzaro (Roma Tre University)
- 2. Elia Guglielmi (Roma Tre University)
- 3. Paolo Missier (University of Birmingham)
- 4. Riccardo Torlone (Roma Tre University)
BibTeX Citation
@article{lazzaro_vldb26,
title = {{PROXAI: Interactive Provenance-Aware Debugging of Machine Learning Pipelines}},
author = {Lazzaro, Pasquale Leonardo and Guglielmi, Elia and Missier, Paolo and Torlone, Riccardo},
journal = {PVLDB},
series = {{VLDB} '26},
volume = {19},
number = {12},
pages = {4706--4709},
doi = {10.14778/3827998.3828102},
url = {https://doi.org/10.14778/3827998.3828102},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 0 of 0 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 4,195 | PrIU: A Provenance-Based Approach for Incrementally Updating Regression Models | 2020 | SIGMOD |
| 2 | 5,178 | Explainable AI: Foundations, Applications, Opportunities for Data Management Research | 2022 | SIGMOD |
| 3 | 7,626 | BugDoc: Algorithms to Debug Computational Processes | 2020 | SIGMOD |
| 4 | 11,335 | Enabling Efficient Attack Investigation via Human-in-the-Loop Security Analysis | 2025 | VLDB |
| 5 | 11,821 | Towards Observability for Machine Learning Pipelines | 2022 | CIDR |
| 6 | 11,902 | DPDS: Assisting Data Science with Data Provenance | 2022 | VLDB |
| 7 | 9,599 | BugDoc: A System for Debugging Computational Pipelines | 2020 | SIGMOD |
| 8 | 4,801 | Improving Reproducibility of Data Science Pipelines through Transparent Provenance Capture | 2020 | VLDB |
| 9 | 7,212 | Capturing and Querying Fine-grained Provenance of Preprocessing Pipelines in Data Science | 2021 | VLDB |
| 10 | 8,076 | Provenance-Enabled Explainable AI | 2024 | SIGMOD |