Identify and explain statistical outliers in a time series

I have a time series of {{METRIC_NAME}} data. Here is the raw series (date, value pairs):

{{RAW_DATA}}

Please do the following:

1. Calculate the mean and standard deviation of the values I provided.
2. Flag any data point that falls more than {{THRESHOLD}} standard deviations from the mean as an outlier. List each flagged point with its date, value, z-score, and direction (spike or drop).
3. For each flagged outlier, generate 3 plausible root-cause hypotheses. Draw on common operational causes (data pipeline errors, seasonality, campaign events, product changes) but do not assert which is correct.
4. Suggest one verification step for each hypothesis that an analyst could complete in under 30 minutes.
5. Note any caveats: if the series has fewer than 12 data points, flag that the standard-deviation method is less reliable. If the data shows a clear trend or seasonality, note that a rolling baseline would be more appropriate.

Format the output as: (a) an outlier summary table, then (b) a numbered list of hypotheses and verification steps per outlier.