Position: AI for Science Should Treat Measurement-to-Dataset Pipelines as Inference Components

arXiv:2605.24558v1 Announce Type: new Abstract: AI for Science (AI4Science) workflows often treat the released dataset as a fixed interface to the underlying system. However, in domains relying on indirect observation, the learner observes a derivative representation produced by multi-stage measurement, reconstruction, and preprocessing pipelines. extbf{We argue that these measurement-to-dataset pipelines are inference components: treating their outputs as given data'' freezes an observation model and obscures uncertainty over feasible pipeline choices.} We identify three failure modes arising from this frozen lens'': extbf{(C1) hidden hypothesis space}, where the released dataset does not specify the pipeline configuration or its validity conditions; extbf{(C2) uncertified transportability}, where a pipeline may be documented but its regime of validity is untested, so failures under distribution shift cannot be adjudicated; extbf{(C3) ungoverned multiplicity}, where many defensible pipelines exist and dispersion is real but not propagated into uncertainty-aware evidence. We stress-test these claims with a large-scale neuroscience empirical audit, finding a survival rate of approx 0.0004% under a cross-dataset stability criterion. We call on the AI4Science community to make pipelines computable inference objects via domain-specific Computable Observation Frameworks. This shift enables quantifying pipeline adequacy and stability, converting implicit implementation choices into auditable, reproducible, and cumulative scientific evidence.

Source: arXiv cs.LG | 2026-05-26