{
  "records_identified_raw": 103011,
  "by_source": {
    "crossref": 51589,
    "semanticscholar_bulk": 37585,
    "arxiv": 13400,
    "semanticscholar_citations": 237,
    "openalex": 200
  },
  "records_after_dedup": 56727,
  "records_with_abstract": 17863,
  "records_screened_rules": 56727,
  "excluded_by_rules": 49652,
  "stage1_candidates": 7075,
  "screened_by_llm": 7083,
  "llm_excluded": 3440,
  "llm_exclusion_reasons": {
    "E8_not_housing_market": 1288,
    "E2_no_characteristics": 1040,
    "E1_no_residential_price": 429,
    "E5_not_empirical_regression": 279,
    "E3_theory_method_only": 242,
    "E4_review_or_meta": 142,
    "E6_duplicate_version": 20
  },
  "llm_unclear": 428,
  "included_hedonic_stage1": 2249,
  "included_ml_predictive_stage1": 897,
  "fulltext_sought_hedonic_or_unclear": 2667,
  "fulltext_retrieved": 501,
  "fulltext_not_retrieved": 2166,
  "retrieval_attempts": 2748,
  "retrieval_status": {
    "error": 1546,
    "ok": 530,
    "not_pdf": 511,
    "no_oa_url": 161
  },
  "fulltext_assessed_extracted": 297,
  "fulltext_eligible": 242,
  "fulltext_ineligible": 55
}