
This preprint presents a dissociation-based attribution framework for separating two latent degradation channels in lithium-ion battery capacity trajectories under partial observability. We define two lightweight memory proxies representing rate-type stress (charge-rate history) and baseline-type stress (manufacturer batch offset), and evaluate their selective identifiability using ablation tests, permutation controls, bootstrap stability analysis, and a negative identifiability case study. Results demonstrate cross-dataset dissociation under controlled conditions and principled non-significance under structural confounding. The work is positioned as a falsifiable test of a lifecycle attribution hypothesis rather than a claim of universal validation.
machine learning, lithium-ion batteries, dissociation test, partial observability, identifiability, energy systems, battery degradation
machine learning, lithium-ion batteries, dissociation test, partial observability, identifiability, energy systems, battery degradation
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
