{
  "retrieved_at_utc": "2026-09-09T02:04:20.465594+00:00",
  "source_kind": "pre-release XML export",
  "original_xml_filename": "post-processed-2026_02_28k.xml",
  "original_xml_sha256": "1268bb8b47e43df6940d4de5cd4839f77010a128d45354dba5177ffbe49ccc8e",
  "original_xml_records": 28553,
  "current_taxonomy_index_records": 5228,
  "selection": "Original XML accessions joined to current UniProt taxonomy_id:4896 index, resolved against PomBase accession mappings.",
  "original_pombe_records": 28,
  "functional_cohort_records": 20,
  "go_claims": 32,
  "function_paragraphs": 11,
  "published_pilot_pombe_records": 0,
  "source_urls": {
    "published_accessions": "https://ftp.ebi.ac.uk/pub/contrib/UniProt/ProtNLM2/List_of_UniProt_accessions_that_have_ProtNLM2_annotations.tsv",
    "uniprot_index": "https://rest.uniprot.org/uniprotkb/stream?query=taxonomy_id%3A4896&format=tsv&fields=accession%2Cid%2Corganism_id%2Corganism_name%2Cgene_names%2Clength%2Creviewed",
    "pombase_identifiers": "https://www.pombase.org/data/names_and_identifiers/gene_IDs_names_products.tsv"
  },
  "checksums": {
    "uniprot-pombe-index.tsv": "c805f6a2cc144b905ff5002953474f5c4fecf12c20b4dcfa916e5ae8be56eff3",
    "predictions.xml": "bba56596cfb51256b333fe2bb3260ab44bcce6bc16bd552ea5c5db9cfaafcc7f",
    "published-accessions.tsv": "1c198f05204ac4807a23719800b67f5415bdf3ab9615263d6b77a6c6501302b3",
    "pombase-identifiers.tsv": "14aad99f5253742e710f934f75aea52d1c48c6f93ef66b11204d88730e9736b2",
    "uniprot.jsonl.gz": "5fd9b7853870a2011d38af2449d6b25837576e181cf839c769770961650a9e44",
    "api-availability.jsonl.gz": "b3dce67d9c26560df216e7a7eedadf9e8b166ccc9b9f1ffd245beebc85673793"
  },
  "caveat": "XML sequence/taxonomy/date fields are placeholders; actual prediction-time input sequences and training membership are not established. Current sequences are fetched separately. Subset XML is reserialized, retaining all element values, attributes and evidence.",
  "current_uniprot_records": 28,
  "prediction_api_availability": {
    "200": 28
  }
}
