Some labels came from the pictures alone. We still have the samples, but those labels aren't tied to physical inspection results. That's irritatingly circular.

Keep the image-only labels uncertain pending physical inspection. A controlled comparison of lighting and presentation can then investigate whether the moving streaks indicate reflection effects.

That clue needs a limit: presentation can also change how a real scratch appears. Movement in the image isn't enough to reclassify the sample as acceptable.

Correct. I meant a reason to investigate the imaging, not a new defect label. Physical acceptance stays with the agreed inspection method.

Should uncertain images be treated as acceptable, or kept somewhere separate while their status is established?

Keep them explicitly undecided, with the sample link. Don't use them as confirmed examples of either class until the physical review settles them.

Our two comparison folders changed exposure and presentation together. I can't tell which change made the images look better. That comparison needs a caveat too.

I'm holding the inspection decision. Our current reference and image evidence can't establish whether the method reliably distinguishes the defects we care about.

Your reason for holding the decision is clear: the current evidence doesn't establish reliable identification of the required defects.