{
  "sample_id": "-iRBcNs9oI8/8",
  "selection": "manually selected example with valid audio and vision query maps",
  "duration_s": 8.093000411987305,
  "word_count": 21,
  "words": [
    "I've",
    "drawn",
    "this",
    "man",
    "here,",
    "and",
    "if",
    "you",
    "can",
    "tell,",
    "he",
    "has",
    "a",
    "lot",
    "of",
    "big",
    "muscles,",
    "he",
    "looks",
    "very",
    "strong"
  ],
  "audio_query_shape": [
    21,
    803
  ],
  "audio_query_nnz": 495,
  "audio_query_mapped_words": 21,
  "vision_query_shape": [
    21,
    241
  ],
  "vision_query_nnz": 160,
  "vision_query_mapped_words": 21,
  "audio_query_feature_validity_channel": "log_energy (audio feature dimension 66)",
  "vision_query_feature_validity_channel": "OpenFace AU12 intensity (vision feature dimension 10)",
  "alignment_semantics": "per-word normalized overlap between stored CTC word intervals and native source intervals; no learned content similarity",
  "coordinate_axes_shown": false,
  "color_scale": "shared square-root intensity transform for visibility; original overlap weights retained",
  "word_label_positions": "actual transcript labels placed at their CTC word-interval centers on the source-time axis",
  "image": "alignment_query_example.png"
}