graph TD
    %% Data Sources
    PG[(PostgreSQL<br/>countydata)]
    DMV[("DMV Data<br/>~18M records<br/>2011-2024")]
    INSP[("Inspection Data<br/>~19.3M records<br/>2010-2026")]

    PG --- DMV
    PG --- INSP

    %% Extraction
    PG -->|"export_history_sample.py<br/>(VIN hashing, page sampling)"| CSV["history_sample_10000.csv.gz<br/>+ manifest"]

    %% Feature Mart Build
    CSV -->|"build_feature_mart.py"| DUCKDB

    subgraph DuckDB["DuckDB Local Warehouse"]
        direction TB
        SQL20["20_stage_events.sql<br/>Normalize & validate"]
        SQL21["21_build_episodes.sql<br/>Group episodes (30-day gap)"]
        SQL22["22_build_features.sql<br/>Point-in-time feature windows"]
        SQL20 --> SQL21 --> SQL22
    end

    DUCKDB --> MART["inspection_feature_mart.parquet<br/>(episode × features, temporal partitions)"]

    %% Temporal Partitions
    subgraph Partitions["Temporal Splits"]
        TRAIN["Train: 2016–2022"]
        TUNE["Tune: 2023"]
        CAL["Calibrate: 2024"]
        TEST["Locked Test: 2025"]
        DRIFT["Shadow Drift: 2026"]
    end
    MART -.- Partitions

    %% Model Training
    MART -->|"train_baselines.py"| BL["artifacts/baselines/baseline_v1/<br/>Logistic Regression +<br/>Prevalence & Prior-Outcome"]
    MART -->|"train_tree_model.py"| TREE["artifacts/tree/hist_gradient_boosting_v1/<br/>Histogram Gradient Boosting"]

    %% Model Outputs
    BL --> ARTIFACTS["Model Artifacts<br/>manifest.json, metrics.json,<br/>model.joblib, calibration_bins.csv"]
    TREE --> ARTIFACTS

    %% Dashboard Export
    MART -->|"export_dashboard_data.py<br/>(privacy suppression, aggregation)"| JSON

    subgraph JSON["dashboard/public/data/"]
        direction TB
        DM["data_manifest.json"]
        OV["overview_period_county.json"]
        CS["cohort_scorecard.json"]
        ARC["age_risk_curve.json"]
        CQ["coverage_quality.json"]
        FC["filter_catalog.json"]
        MD["model_diagnostics.json"]
    end

    ARTIFACTS -.->|metrics & manifest| JSON

    %% Dashboard Frontend
    JSON --> SERVER["server.mjs<br/>Node.js HTTP server"]

    subgraph Dashboard["Browser SPA"]
        direction TB
        APP["app.js<br/>Routing & pages"]
        CHARTS["charts.js<br/>D3 visualizations"]
        DATA["data.js<br/>Data loading & filters"]
        APP --- CHARTS
        APP --- DATA
    end

    SERVER --> Dashboard

    subgraph Pages["Dashboard Pages"]
        P1["Overview<br/>KPIs, trends, county map"]
        P2["Reliability Explorer<br/>Make/model comparison"]
        P3["Next-Test Estimator<br/>Risk prediction"]
        P4["Data & Methods<br/>Coverage, limitations"]
    end

    Dashboard --> Pages

    %% Privacy Controls
    subgraph Privacy["Privacy Controls"]
        direction LR
        S1["≥100 inspections per cell"]
        S2["≥100 distinct vehicles"]
        S3["≥10 outcome records"]
        S4["No VINs/plates/ZIPs"]
    end

    JSON -.- Privacy

    %% Testing
    subgraph Tests["Test Suite"]
        direction LR
        PT["Python unittest<br/>(feature mart, models,<br/>export, baselines)"]
        CT["Node.js contract tests<br/>(dashboard JSON schemas)"]
    end

    MART -.- PT
    JSON -.- CT

    %% Styling
    classDef source fill:#e1f5fe,stroke:#0288d1
    classDef process fill:#fff3e0,stroke:#f57c00
    classDef storage fill:#e8f5e9,stroke:#388e3c
    classDef dashboard fill:#fce4ec,stroke:#c62828
    classDef test fill:#f3e5f5,stroke:#7b1fa2

    class PG,DMV,INSP source
    class CSV,MART,ARTIFACTS,DUCKDB storage
    class BL,TREE process
    class SERVER,Dashboard,Pages,JSON dashboard
    class Tests test