{
  "artifact_type": "empirical_public_advanced_disease_fragment_extraction",
  "clinical_claim": false,
  "dataset": "FinaleMe Zenodo 7779198 ULP-WGS processed coordinates",
  "sample_records": 77,
  "patient_id_groups": 42,
  "manifest": "real_data/manifests/finaleme_samples.csv",
  "manifest_sha256": "661c52fa89ab57d77c23e9cd0c6a5d53b00c476914a8a107c0a2c50f944337d7",
  "sources": "real_data/manifests/finaleme_sources.json",
  "sources_sha256": "5494710ced0cec2f47c65d2e348ef32a29f9b09850534fd1b054c9574492642c",
  "archive": {
    "name": "ulp_wgs_frag.tar",
    "bytes": 1894809600,
    "md5": "a98744886e648d8b02d1c914dd4548b0",
    "sha256": "d06852eb556822c1c7653972c312c18d151eeced236920ce4e9ed2f6c6c0e6dc"
  },
  "feature_contract": {
    "bins": "real_data/assets/human_g1k_v37.autosomes.5mb_bins.tsv",
    "bins_sha256": "53e5b08377b6dec52f54311d5d6b70fc9dd9a8296cb2d46c633ec80a60b76213",
    "bin_count": 589,
    "canonical_contigs": [
      "chr1",
      "chr2",
      "chr3",
      "chr4",
      "chr5",
      "chr6",
      "chr7",
      "chr8",
      "chr9",
      "chr10",
      "chr11",
      "chr12",
      "chr13",
      "chr14",
      "chr15",
      "chr16",
      "chr17",
      "chr18",
      "chr19",
      "chr20",
      "chr21",
      "chr22"
    ],
    "min_mapq": 30,
    "min_fragment_length": 50,
    "max_fragment_length": 1000,
    "short_fragment_definition": [
      100,
      150
    ],
    "long_fragment_definition": [
      151,
      220
    ],
    "gc_mappability_annotation": "neutral placeholders; not reference-corrected"
  },
  "filter_accounting": {
    "input_records": 250308232,
    "mapq_pass_records": 232039075,
    "mapq_filtered_records": 18269157,
    "length_filtered_records_after_mapq": 349371,
    "outside_canonical_autosome_bins_after_mapq_and_length": 9897689,
    "canonical_autosome_usable_coordinate_records": 221792015
  },
  "deduplication": "Unknown: processed BED6 has no duplicate flag or unique fragment ID; duplicate removal was not claimed or reproduced.",
  "record_semantics": "Counts are processed coordinate records passing filters, not guaranteed unique fragments or molecules because duplicate status is unknown.",
  "canonical_autosome_filter": "Only records located in the 589 chr1-chr22 bins contribute to features; sex chromosomes, MT, GL contigs, NC_007605, and out-of-range coordinates are counted as outside_bin_records after MAPQ and length filtering.",
  "analysis_boundary": "The cohort contains advanced prostate and metastatic breast cancer. These features support a bounded engineering/confounding stress test only, not MCED, early-stage, screening, sensitivity, or specificity claims."
}