1{2 "task_id": "F1-dev-01",3 "n_unique_firms": 400,4 "n_missing_revenue": 6,5 "n_analysed": 394,6 "mean_revenue_musd": 249.9620761421,7 "median_revenue_musd": 162.306,8 "mean_employees": 1101.435,9 "mean_revenue_raw": 30695.8823105023,10 "feasibility": "complete",11 "feasibility_reason": null,12 "data_issues": [13 {14 "issue": "45 exact duplicate rows (same firm_id and identical values); 0 conflicting duplicates",15 "handling": "kept first occurrence; one row per firm_id"16 },17 {18 "issue": "mixed revenue units: 60 distinct firms in USD_thousands, 340 in USD_millions",19 "handling": "converted all revenue to millions USD via the row-level unit column"20 },21 {22 "issue": "revenue empty on 7 raw rows = 6 distinct firms (F0048, F0121, F0129, F0269, F0348, F0399)",23 "handling": "excluded from revenue aggregates and analytic.csv; retained for n_unique_firms and mean_employees"24 }25 ],26 "n_input_rows": {27 "firms.csv": 44528 },29 "random_seed": null,30 "input_sha256": {31 "firms.csv": "78f119a92d7c11aebb8c238c69d62687a80d91031f1e8a30fb412b9e77e1625a"32 },33 "baseline_note": "mean_revenue_raw mixes USD_thousands and USD_millions and double-counts duplicates; not interpretable"34}