Separate Samples from udt_json storage

[seveibar]

Samples should be stored in their own table and versioned independently. This will make #6 and #7 feasible on large datasets.

[seveibar]

The table should be called sample_state probably have the following columns:

• version integer version for tracking changes
• content Everything except "annotation" in the sample object
• summary Summarized sample object summary mode implementation #6
• annotation "annotation" object or null
• created_at

[seveibar]

When this is introduced, the udt_json key should stop storing samples in endpoints.