You are an expert in video understanding and explainable artificial intelligence.
Your task is to analyze video examples and discover interpretable, human-understandable
features that can differentiate between {n_classes} video categories:
{class_list}

Each video is shown to you as a sequence of frames sampled in order, possibly with a
transcript of its audio. You must reason from this evidence itself, without assuming
any predefined feature types, and describe the distinguishing properties as if
explaining them to a human researcher.

I am providing you with example videos. Each video belongs to one of the {n_classes} categories
listed above, but you are NOT told which video belongs to which category.

Do not use the category names or paraphrases of them as feature names or
values. Describe the property itself instead, in general terms rather than
names or phrases taken from the examples.

Your task is to:
  1. Examine all videos carefully and propose key features that appear to
     systematically vary across subsets of the videos and together distinguish all
     {n_classes} categories in a classification model.
  2. Give particular attention to what happens over time: the action being performed,
     how the subject moves, the order and rhythm of the movement, how the scene
     changes between the first and last frames. Static appearance and setting matter
     too, but a single frame should not be enough to answer a motion feature.
  3. Prefer properties of the subject and its action over properties of the recording.
     Camera work, on-screen graphics, or video quality are only worth proposing when
     they genuinely distinguish the categories rather than the circumstances of
     the recording.
  4. Each feature must capture a different property. Do not propose two features
     that would almost always take related values.
  5. Some categories will resemble each other much more closely than others.
     Make sure the feature set also separates the closest pairs, not only the
     obvious groupings.
  6. Express each feature as a short snake_case attribute name.
  7. For each feature, provide a brief explanation of why it could be discriminative
     across the {n_classes} hidden groups.
  8. For each feature, provide 3-6 possible values: short snake_case strings
     without filler words, mutually exclusive, together covering the realistic
     range. If a feature cannot apply to some of the categories, include an
     explicit value for that case (for example not_applicable) in the list.
     These exact values will later be used to label new videos, so choose
     values you can apply consistently.
  9. Provide at least {min_features} distinct features.
  10. Respond only with valid JSON. Do not wrap it in markdown code fences and do not include any explanation outside the JSON.

Output format:
{{
  "proposed_features": [
    {{
      "feature": "feature_name_1",
      "description": "why it separates the {n_classes} groups",
      "possible_values": ["value1", "value2", "value3"]
    }}
  ]
}}