glam/data/person/_enrichment_manifest.json
2026-01-09 20:35:19 +01:00

67 lines
No EOL
1.4 KiB
JSON

{
"enrichment_timestamp": "2026-01-09T19:18:58.038954+00:00",
"enrichment_script": "enrich_ppids.py",
"version": "1.2.0",
"rule_compliance": [
"Rule 44 (EDTF)",
"Rule 45 (Explicit Inferred Data)",
"Rule 45 Extension (List-Valued EDTF Set Notation)"
],
"statistics": {
"total_ppid_files": 7948,
"birth_decades_inferred": 2712,
"birth_decades_list_valued": 1972,
"birth_settlements_inferred": 1967,
"current_settlements_inferred": 2588
},
"coverage": {
"birth_decade": 34.1,
"birth_decade_boundary_cases": 72.7,
"birth_settlement": 24.7,
"current_settlement": 32.6
},
"improvements_this_session": {
"field_support_added": [
"years",
"year",
"school"
],
"degree_keywords_added": [
"drs",
"mr",
"ing",
"ir",
"pabo",
"meao",
"heao",
"magister",
"diplom",
"staatsexamen",
"laurea",
"postgraduate",
"post doc",
"postdoc",
"degree",
"graduate"
],
"institutions_added": 65,
"age_offset_by_degree": {
"bachelor": 18,
"master": 22,
"phd": 24,
"vocational": 16
}
},
"countries_detected": {
"NL": 1950,
"BE": 17,
"DE": 10,
"IT": 1,
"US": 1
},
"edtf_formats_used": {
"single_decade": "197X (decade unknown within century)",
"decade_set": "[196X,197X] (one of two decades)",
"unknown": "XXXX (completely unknown)"
}
}