Hybrid AI Models for Materials Discovery with Versioned Laboratory Datasets: Evidence, Failure Modes and Deployment Trade-offs

Abstract

Materials-screening datasets often mix experimental batches, computed descriptors and inconsistent processing metadata. An evaluation that overlooks these constraints may reach conclusions that cannot be reproduced. The planned investigation seeks to examine whether hybrid prediction models remain reliable when material families and laboratory batches are held out. Relevant methodological and data-quality literature informs the design of the sampling and validation strategy [3–7]. The protocol specifies a reproducibility-focused benchmark built from versioned materials datasets and documented processing histories. Comparators will include physical-descriptor baselines, purely learned models and hybrid models combining domain constraints with machine learning. Prior work on storage operations provides technical context for validation [1], while complementary systems evidence motivates service-continuity checks [2]. The evidence-mapping component examines why a successful result in one technical environment may fail elsewhere. Statistical and computational sources help define the reproducibility checks and comparison procedures [8–12]. The primary outcomes are out-of-family prediction error, calibration and stability of candidate rankings under data revisions. Potential biases include recipe duplicates, provenance gaps, leakage across related materials and sensitivity to batch-specific artefacts. Stress tests would distinguish outright failures, reduced confidence and cases where a simpler baseline is preferable. Additional research informs the prespecified stress tests and limits on interpretation [13–17]. The intended contribution is an auditable research protocol rather than an unsupported claim of effectiveness; related work frames its transferability limits [18–23].