diff --git a/plots/box-basic/implementations/letsplot.py b/plots/box-basic/implementations/letsplot.py
index 33284d38a5..3e41ad4b53 100644
--- a/plots/box-basic/implementations/letsplot.py
+++ b/plots/box-basic/implementations/letsplot.py
@@ -1,7 +1,7 @@
 """ pyplots.ai
 box-basic: Basic Box Plot
-Library: letsplot 4.8.1 | Python 3.13.11
-Quality: 98/100 | Created: 2025-12-23
+Library: letsplot 4.8.2 | Python 3.14
+Quality: 90/100 | Created: 2025-12-23
 """
 
 import numpy as np
@@ -9,15 +9,23 @@
 from lets_plot import (
     LetsPlot,
     aes,
+    as_discrete,
+    element_blank,
+    element_line,
+    element_rect,
     element_text,
+    flavor_high_contrast_light,
     geom_boxplot,
+    geom_hline,
+    geom_text,
     ggplot,
     ggsave,
     ggsize,
     labs,
+    layer_tooltips,
     scale_fill_manual,
+    scale_y_continuous,
     theme,
-    theme_minimal,
 )
 
 
@@ -27,7 +35,6 @@
 np.random.seed(42)
 categories = ["Engineering", "Marketing", "Sales", "HR", "Finance"]
 data = []
-# Realistic salary distributions for each department
 distributions = {
     "Engineering": (85000, 15000),
     "Marketing": (65000, 12000),
@@ -40,27 +47,111 @@
     mean, std = distributions[cat]
     n = np.random.randint(50, 100)
     values = np.random.normal(mean, std, n)
-    # Add a few outliers
     outliers = np.random.choice([mean + 3.5 * std, mean - 2.5 * std], size=3)
     values = np.concatenate([values, outliers])
     data.extend([(cat, v) for v in values])
 
-df = pd.DataFrame(data, columns=["category", "value"])
+df = pd.DataFrame(data, columns=["department", "salary"])
+
+# Compute medians for annotation labels
+medians = df.groupby("department")["salary"].median().reset_index()
+medians.columns = ["department", "median_salary"]
+medians["label"] = medians["median_salary"].apply(lambda x: f"${x:,.0f}")
+
+# Insight: compare highest vs lowest median departments
+sorted_medians = medians.sort_values("median_salary")
+low_dept = sorted_medians.iloc[0]
+high_dept = sorted_medians.iloc[-1]
+pct_diff = (high_dept["median_salary"] - low_dept["median_salary"]) / low_dept["median_salary"]
+insight_text = f"+{pct_diff:.0%} vs. {low_dept['department']}"
+
+# Overall mean for reference line
+overall_mean = df["salary"].mean()
+
+# Annotation dataframes
+insight_df = pd.DataFrame(
+    {
+        "department": [high_dept["department"]],
+        "y": [high_dept["median_salary"] + 22000],
+        "lbl": [f"{high_dept['department'][:3]}. {insight_text}"],
+    }
+)
+mean_label_df = pd.DataFrame(
+    {"department": [high_dept["department"]], "y": [overall_mean + 3000], "lbl": [f"Avg: ${overall_mean:,.0f}"]}
+)
 
 # Plot
-colors = ["#306998", "#FFD43B", "#DC2626", "#16A34A", "#9333EA"]
+# Wong colorblind-safe palette (no two similar blues)
+colors = ["#0072B2", "#E69F00", "#D55E00", "#009E73", "#CC79A7"]
 
 plot = (
-    ggplot(df, aes(x="category", y="value", fill="category"))
-    + geom_boxplot(alpha=0.8, size=1.5, outlier_size=4)
+    ggplot(df, aes(x=as_discrete("department", order=1, order_by="..middle.."), y="salary", fill="department"))
+    + geom_boxplot(
+        alpha=0.85,
+        size=1.2,
+        outlier_size=5,
+        outlier_shape=21,
+        outlier_color="#333333",
+        width=0.72,
+        tooltips=layer_tooltips()
+        .title("@department")
+        .line("Median|$@{..middle..}")
+        .line("Q1|$@{..lower..}")
+        .line("Q3|$@{..upper..}")
+        .line("Min|$@{..ymin..}")
+        .line("Max|$@{..ymax..}"),
+    )
     + scale_fill_manual(values=colors)
-    + labs(x="Department", y="Salary ($)", title="box-basic · letsplot · pyplots.ai")
-    + theme_minimal()
+    # Median value labels above each box
+    + geom_text(
+        aes(x="department", y="median_salary", label="label"),
+        data=medians,
+        size=11,
+        color="#333333",
+        fontface="bold",
+        nudge_y=5000,
+        inherit_aes=False,
+    )
+    # Overall mean reference line
+    + geom_hline(yintercept=overall_mean, color="#888888", size=0.8, linetype="dashed")
+    + geom_text(
+        aes(x="department", y="y", label="lbl"),
+        data=mean_label_df,
+        size=10,
+        color="#666666",
+        fontface="italic",
+        hjust=0.5,
+        inherit_aes=False,
+    )
+    # Key insight annotation
+    + geom_text(
+        aes(x="department", y="y", label="lbl"),
+        data=insight_df,
+        size=11,
+        color="#1E4F72",
+        fontface="bold italic",
+        inherit_aes=False,
+    )
+    + scale_y_continuous(format="${,.0f}")
+    + labs(
+        x="Department",
+        y="Annual Salary (USD)",
+        title="box-basic \u00b7 letsplot \u00b7 pyplots.ai",
+        subtitle="Salary distributions across five departments, ordered by median",
+    )
+    + flavor_high_contrast_light()
     + theme(
+        plot_title=element_text(size=24, face="bold"),
+        plot_subtitle=element_text(size=16, color="#555555"),
         axis_title=element_text(size=20),
         axis_text=element_text(size=16),
-        plot_title=element_text(size=24),
+        axis_ticks=element_blank(),
+        panel_grid_major_x=element_blank(),
+        panel_grid_minor=element_blank(),
+        panel_grid_major_y=element_line(color="#DDDDDD", size=0.5),
         legend_position="none",
+        plot_background=element_rect(fill="white", color="white"),
+        plot_margin=[10, 35, 10, 10],
     )
     + ggsize(1600, 900)
 )
diff --git a/plots/box-basic/metadata/letsplot.yaml b/plots/box-basic/metadata/letsplot.yaml
index 54636675e6..e563764a8b 100644
--- a/plots/box-basic/metadata/letsplot.yaml
+++ b/plots/box-basic/metadata/letsplot.yaml
@@ -1,161 +1,184 @@
 library: letsplot
 specification_id: box-basic
 created: '2025-12-23T00:36:22Z'
-updated: '2025-12-23T00:40:11Z'
-generated_by: claude-opus-4-5-20251101
+updated: '2026-02-14T22:38:16Z'
+generated_by: claude-opus-4-6
 workflow_run: 20447786735
 issue: 0
-python_version: 3.13.11
-library_version: 4.8.1
+python_version: '3.14'
+library_version: 4.8.2
 preview_url: https://storage.googleapis.com/pyplots-images/plots/box-basic/letsplot/plot.png
 preview_thumb: https://storage.googleapis.com/pyplots-images/plots/box-basic/letsplot/plot_thumb.png
 preview_html: https://storage.googleapis.com/pyplots-images/plots/box-basic/letsplot/plot.html
-quality_score: 98
+quality_score: 90
 impl_tags:
   dependencies: []
   techniques:
-    - html-export
+  - annotations
+  - layer-composition
+  - html-export
   patterns:
-    - data-generation
-    - iteration-over-groups
+  - data-generation
+  - groupby-aggregation
+  - iteration-over-groups
   dataprep: []
-  styling: []
+  styling:
+  - alpha-blending
+  - grid-styling
 review:
   strengths:
-  - Excellent use of realistic salary data with appropriate distributions per department
-  - Outliers properly generated and clearly visible as distinct points
-  - Perfect title format following pyplots.ai convention
-  - Clean ggplot2-style grammar implementation
-  - Proper sizing for 4800x2700 output with scale=3
-  - Different colors make categories easily distinguishable
-  - Appropriate text sizes (24pt title, 20pt labels, 16pt ticks)
+  - 'Excellent use of lets-plot distinctive features: stat-based ordering via as_discrete,
+    layer_tooltips with stat variables, flavor theme'
+  - Strong data storytelling with median annotations, overall mean reference line,
+    and percentage comparison insight
+  - Wong colorblind-safe palette ensures accessibility
+  - Clean code structure with realistic salary data scenario
+  - Boxes ordered by median provides natural narrative flow
   weaknesses:
-  - Grid lines could be slightly more visible (currently very subtle with theme_minimal)
-  image_description: 'The plot displays 5 box plots showing salary distributions across
-    departments: Engineering (blue), Marketing (yellow), Sales (red), HR (green),
-    and Finance (purple). Each box clearly shows the median line, IQR (box), and whiskers
-    extending to 1.5*IQR. Outliers are displayed as large black dots - visible above
-    Engineering (~125K, ~137K), Marketing (~107K), Sales (~125K, ~131K), HR (~30K,
-    ~90K), and Finance (~120K, ~122K). The title "box-basic · letsplot · pyplots.ai"
-    appears at the top in appropriate size. X-axis labeled "Department" and Y-axis
-    labeled "Salary ($)" with values ranging from ~20,000 to 140,000. Clean minimal
-    theme with subtle grid lines. Layout is well-balanced with good proportions.'
+  - 'Minor text proximity issue: Avg label and insight annotation slightly crowd the
+    Engineering box area'
+  - Some wasted whitespace on the right side of the canvas — layout could be tighter
+  - Annotation DataFrames are somewhat verbose (three separate DataFrames for text
+    layers)
+  image_description: 'The plot displays 5 box-and-whisker plots showing salary distributions
+    across departments (HR, Marketing, Sales, Finance, Engineering), ordered left-to-right
+    by ascending median salary. Each box uses a distinct color from the Wong colorblind-safe
+    palette: teal (HR), golden yellow (Marketing), orange (Sales), pink (Finance),
+    blue (Engineering). Outliers appear as large filled circles above and below whiskers.
+    A dashed gray horizontal reference line marks the overall average salary (~$71,502)
+    with a label "Avg: $71,502" near the right side. Median dollar values ($54,599
+    to $85,333) are annotated in bold above each box. A bold italic insight annotation
+    "Eng. +56% vs. HR" highlights the salary gap between highest and lowest median
+    departments. Title reads "box-basic · letsplot · pyplots.ai" with subtitle "Salary
+    distributions across five departments, ordered by median". Y-axis is "Annual Salary
+    (USD)" with dollar formatting, X-axis is "Department". Clean white background
+    with subtle horizontal gridlines.'
   criteria_checklist:
     visual_quality:
-      score: 38
-      max: 40
+      score: 26
+      max: 30
       items:
       - id: VQ-01
         name: Text Legibility
-        score: 10
-        max: 10
+        score: 8
+        max: 8
         passed: true
-        comment: Title ~24pt, axis labels ~20pt, tick labels ~16pt - all perfectly
-          readable
+        comment: 'All font sizes explicitly set: title 24pt, axis titles 20pt, axis
+          text 16pt, annotation text 10-11pt'
       - id: VQ-02
         name: No Overlap
-        score: 8
-        max: 8
+        score: 5
+        max: 6
         passed: true
-        comment: No overlapping text, category labels well spaced
+        comment: 'Minor: Avg label and insight annotation slightly crowd Engineering
+          box area'
       - id: VQ-03
         name: Element Visibility
-        score: 8
-        max: 8
+        score: 6
+        max: 6
         passed: true
-        comment: Box sizes optimal, outliers clearly visible with size=4
+        comment: Boxes well-sized (width=0.72), outliers visible (size=5), good alpha
+          (0.85)
       - id: VQ-04
         name: Color Accessibility
-        score: 5
-        max: 5
+        score: 4
+        max: 4
         passed: true
-        comment: Five distinct colors (blue, yellow, red, green, purple) with good
-          contrast
+        comment: Wong colorblind-safe palette with 5 distinct hues
       - id: VQ-05
         name: Layout Balance
-        score: 5
-        max: 5
-        passed: true
-        comment: Perfect proportions, no cut-off, good use of space
+        score: 1
+        max: 4
+        passed: false
+        comment: Some wasted whitespace on right side, boxes somewhat narrow relative
+          to canvas width
       - id: VQ-06
-        name: Axis Labels
+        name: Axis Labels & Title
         score: 2
         max: 2
         passed: true
-        comment: 'Descriptive with units: "Salary ($)", "Department"'
-      - id: VQ-07
-        name: Grid & Legend
-        score: 0
-        max: 2
-        passed: false
-        comment: Grid is subtle and good, legend correctly hidden (not needed) - but
-          grid could be slightly more visible
+        comment: Annual Salary (USD) with units, Department descriptive
+    design_excellence:
+      score: 16
+      max: 20
+      items:
+      - id: DE-01
+        name: Aesthetic Sophistication
+        score: 6
+        max: 8
+        passed: true
+        comment: 'Strong design: Wong palette, intentional hierarchy, flavor theme,
+          custom grid styling'
+      - id: DE-02
+        name: Visual Refinement
+        score: 5
+        max: 6
+        passed: true
+        comment: Ticks removed, minor grid removed, x-grid removed, subtle y-grid,
+          clean margins
+      - id: DE-03
+        name: Data Storytelling
+        score: 5
+        max: 6
+        passed: true
+        comment: Median labels, overall mean reference line, insight annotation comparing
+          highest vs lowest
     spec_compliance:
-      score: 25
-      max: 25
+      score: 15
+      max: 15
       items:
       - id: SC-01
         name: Plot Type
-        score: 8
-        max: 8
-        passed: true
-        comment: Correct box-and-whisker plot
-      - id: SC-02
-        name: Data Mapping
         score: 5
         max: 5
         passed: true
-        comment: Categories on X, values on Y correctly assigned
-      - id: SC-03
+        comment: Correct box plot with all components
+      - id: SC-02
         name: Required Features
-        score: 5
-        max: 5
+        score: 4
+        max: 4
         passed: true
-        comment: Median line ✓, outliers as points ✓, whiskers at 1.5*IQR ✓, different
-          colors
-      - id: SC-04
-        name: Data Range
+        comment: 'All spec features present: median line, outliers, whiskers at 1.5*IQR,
+          different colors'
+      - id: SC-03
+        name: Data Mapping
         score: 3
         max: 3
         passed: true
-        comment: All data visible including outliers
-      - id: SC-05
-        name: Legend Accuracy
-        score: 2
-        max: 2
-        passed: true
-        comment: Legend hidden appropriately (colors explained by x-axis)
-      - id: SC-06
+        comment: Categories on X-axis, values on Y-axis correctly assigned
+      - id: SC-04
         name: Title Format
-        score: 2
-        max: 2
+        score: 3
+        max: 3
         passed: true
-        comment: 'Correct format: "box-basic · letsplot · pyplots.ai"'
+        comment: Title box-basic · letsplot · pyplots.ai correct, legend appropriately
+          hidden
     data_quality:
-      score: 20
-      max: 20
+      score: 14
+      max: 15
       items:
       - id: DQ-01
         name: Feature Coverage
-        score: 8
-        max: 8
+        score: 5
+        max: 6
         passed: true
-        comment: Shows outliers, different spreads (Sales widest, HR narrowest), different
-          medians
+        comment: Different distributions with varying spreads, outliers present, meaningful
+          median differences
       - id: DQ-02
         name: Realistic Context
-        score: 7
-        max: 7
+        score: 5
+        max: 5
         passed: true
-        comment: Salary by department is a real, comprehensible scenario
+        comment: Salary distributions across departments — real, neutral business
+          scenario
       - id: DQ-03
         name: Appropriate Scale
-        score: 5
-        max: 5
+        score: 4
+        max: 4
         passed: true
-        comment: Realistic salary values ($20K-$140K range appropriate for US salaries)
+        comment: Realistic salary values in $20K-$140K range
     code_quality:
-      score: 10
+      score: 9
       max: 10
       items:
       - id: CQ-01
@@ -163,11 +186,11 @@ review:
         score: 3
         max: 3
         passed: true
-        comment: Simple imports → data → plot → save structure
+        comment: Clean Imports → Data → Plot → Save flow
       - id: CQ-02
         name: Reproducibility
-        score: 3
-        max: 3
+        score: 2
+        max: 2
         passed: true
         comment: np.random.seed(42) set
       - id: CQ-03
@@ -175,21 +198,35 @@ review:
         score: 2
         max: 2
         passed: true
-        comment: All imports used
+        comment: All imports are used
       - id: CQ-04
-        name: No Deprecated API
+        name: Code Elegance
         score: 1
-        max: 1
+        max: 2
         passed: true
-        comment: Current lets-plot API
+        comment: Slightly verbose with three annotation DataFrames but serves storytelling
       - id: CQ-05
-        name: Output Correct
+        name: Output & API
         score: 1
         max: 1
         passed: true
-        comment: Saves as plot.png and plot.html
-    library_features:
-      score: 5
-      max: 5
-      items: []
+        comment: Saves as plot.png with scale=3, current API
+    library_mastery:
+      score: 10
+      max: 10
+      items:
+      - id: LM-01
+        name: Idiomatic Usage
+        score: 5
+        max: 5
+        passed: true
+        comment: 'Expert grammar of graphics: as_discrete ordering, layer_tooltips,
+          flavor themes, ggsave'
+      - id: LM-02
+        name: Distinctive Features
+        score: 5
+        max: 5
+        passed: true
+        comment: as_discrete stat-based ordering, layer_tooltips with stat variables,
+          flavor_high_contrast_light
   verdict: APPROVED