fma_semantic_bucket_template.json 1.29 KB
{
  "notes": {
    "purpose": "Template for semantic/style-aware bucket benchmarking on local FMA-like trees.",
    "how_to_use": "Replace placeholder glob patterns with your own curated track groups before running ab_smoke_bucketed.py.",
    "warning": "Do not treat filename prefixes as product semantics; this file is for manually curated semantic buckets."
  },
  "buckets": [
    {
      "name": "energy_dominant",
      "patterns": [
        "fma_small/*/REPLACE_WITH_HIGH_ENERGY_TRACKS_*.mp3"
      ],
      "subset_size": 16,
      "label_hint": "chorus-heavy or consistently high-energy songs"
    },
    {
      "name": "repeated_section_rich",
      "patterns": [
        "fma_small/*/REPLACE_WITH_REPEATED_SECTION_TRACKS_*.mp3"
      ],
      "subset_size": 16,
      "label_hint": "clear repeating hook/chorus structure"
    },
    {
      "name": "steady_beat_regular_meter",
      "patterns": [
        "fma_small/*/REPLACE_WITH_STEADY_BEAT_TRACKS_*.mp3"
      ],
      "subset_size": 16,
      "label_hint": "stable beat, strong downbeat, regular meter"
    },
    {
      "name": "hard_negative_confusable",
      "patterns": [
        "fma_small/*/REPLACE_WITH_CONFUSABLE_TRACKS_*.mp3"
      ],
      "subset_size": 16,
      "label_hint": "sonically similar tracks likely to trigger confusion"
    }
  ]
}