Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2507.20364 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911079382122496 |
|---|---|
| author | Miyaguchi, Kohei Joko, Masao Sheraw, Rebekah Idé, Tsuyoshi |
| author_facet | Miyaguchi, Kohei Joko, Masao Sheraw, Rebekah Idé, Tsuyoshi |
| contents | How can we identify problematic upstream processes when a certain type of wafer defect starts appearing at a quality checkpoint? Given the complexity of modern semiconductor manufacturing, which involves thousands of process steps, cross-process root cause analysis for wafer defects has been considered highly challenging. This paper proposes a novel framework called Trajectory Shapley Attribution (TSA), an extension of Shapley values (SV), a widely used attribution algorithm in explainable artificial intelligence research. TSA overcomes key limitations of standard SV, including its disregard for the sequential nature of manufacturing processes and its reliance on an arbitrarily chosen reference point. We applied TSA to a good-bad wafer diagnosis task in experimental front-end-of-line processes at the NY CREATES Albany NanoTech fab, aiming to identify measurement items (serving as proxies for process parameters) most relevant to abnormal defect occurrence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sequence-Aware Inline Measurement Attribution for Good-Bad Wafer Diagnosis Miyaguchi, Kohei Joko, Masao Sheraw, Rebekah Idé, Tsuyoshi Machine Learning How can we identify problematic upstream processes when a certain type of wafer defect starts appearing at a quality checkpoint? Given the complexity of modern semiconductor manufacturing, which involves thousands of process steps, cross-process root cause analysis for wafer defects has been considered highly challenging. This paper proposes a novel framework called Trajectory Shapley Attribution (TSA), an extension of Shapley values (SV), a widely used attribution algorithm in explainable artificial intelligence research. TSA overcomes key limitations of standard SV, including its disregard for the sequential nature of manufacturing processes and its reliance on an arbitrarily chosen reference point. We applied TSA to a good-bad wafer diagnosis task in experimental front-end-of-line processes at the NY CREATES Albany NanoTech fab, aiming to identify measurement items (serving as proxies for process parameters) most relevant to abnormal defect occurrence. |
| title | Sequence-Aware Inline Measurement Attribution for Good-Bad Wafer Diagnosis |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.20364 |