Formatting and clarity improvements

analysis/README.md

@@ -95,17 +95,17 @@ Basic averages appear in `diagnostic_output-analysis.ods`.
 
 #### Univariate analysis
 
-First, a histogram of average values for each protocol: 
+First, a plot of average values for each protocol: 
 
-![Protocol averages histogram](img/protocol_averages.png)
+![Protocol averages plot](img/protocol_averages.png)
 
 This reveals a linear distribution of values among the protocols, aside from exponential curves only at the extremes. Perhaps the most interesting finding is a skew toward the higher end of the scale, associated with softness. Even relatively hard, technical protocols appear to have significant soft characteristics.
 
 The protocol value averages have a mean of 5.45 and a median of 5.48. In comparison to the midpoint of 5, the normalized midpoint deviation is 0.11. In comparison, the Pearson coefficient measures the skew at just -0.07, which means that the relative skew of the data is actually slightly downward. So the distribution of protocol values is very balanced but has a consistent upward deviation from the scale's baseline. (These calculations are in `diagnostic_output-analysis.odt[averages]`.)
 
-Second, a histogram of average values for each gradient:
+Second, a plot of average values for each gradient (with gaps to indicate the three groupings of gradients):
 
-![Gradient averages histogram](img/gradient_averages.png)
+![Gradient averages plot](img/gradient_averages.png)
 
 This indicates that a few of the gradients appear to have outsized responsibility for the high skew of the protocol averages.
 
@@ -142,6 +142,10 @@ Initial manual observations:
 * The correlations generally seem predictable; for example, the strongest is between `Design_static_vs_malleable` and `Experience_predictable_vs_emergent`, which is not surprising
 * The elite vs. vernacular distinction appears to be the most predictive gradient (`analysis_results/plots/feature_importances.png`)
 
+![Correlation heatmap](analysis_results/plots/correlation_heatmap_full.png)
+
+![Importance ranking](analysis_results/plots/feature_importances.png)
+
 Claude's interpretation:
 
 > 1. Two Fundamental Protocol Types (K-Means Clustering)
@@ -149,15 +153,13 @@ Claude's interpretation:
 > The data reveals two distinct protocol families (216 vs 192 protocols):
 > 
 > Cluster 1: "Vernacular/Emergent Protocols"
-> - Examples: Marronage, Songlines, Access-Centered Practices, Ethereum Proof of
+> - Examples: Marronage, Songlines, Access-Centered Practices, Ethereum Proof of Work, Sangoma Healing Practices
->  Work, Sangoma Healing Practices
 > - Characteristics:
 >   - HIGH: elite→vernacular (6.4), malleable (7.3), flocking→swarming (6.4)
 >   - LOW: self-enforcing→enforced (3.4), sovereign→subsidiary (2.9)
 > 
 > Cluster 2: "Institutional/Standardized Protocols"
-> - Examples: ISO standards, Greenwich Mean Time, Building Codes, German
+> - Examples: ISO standards, Greenwich Mean Time, Building Codes, German Bureaucratic Prose, Royal Access Protocol
-> Bureaucratic Prose, Royal Access Protocol
 > - Characteristics:
 >   - HIGH: self-enforcing (7.1), sovereign (6.0)
 >   - LOW: elite→vernacular (1.8), flocking→swarming (2.3), static (3.5)
@@ -177,19 +179,14 @@ Claude's interpretation:
 > 
 > 3. Strong Correlations (Most Significant Relationships)
 > 
-> 1. Static ↔ Predictable (r=0.61): Unchanging protocols create predictable
+>   1. Static ↔ Predictable (r=0.61): Unchanging protocols create predictable experiences
-> experiences
+>   2. Elite ↔ Self-enforcing (r=-0.58): Elite protocols need external enforcement; vernacular ones self-enforce
-> 2. Elite ↔ Self-enforcing (r=-0.58): Elite protocols need external
+>   3. Self-enforcing ↔ Flocking (r=-0.56): Self-enforcing protocols resist swarming dynamics
-> enforcement; vernacular ones self-enforce
-> 3. Self-enforcing ↔ Flocking (r=-0.56): Self-enforcing protocols resist
-> swarming dynamics
 >   4. Exclusion ↔ Kafka (r=0.52): Exclusionary protocols feel Kafka-esque
 > 
 > 4. Most Discriminative Dimension (Feature Importance)
 > 
-> Design_elite_vs_vernacular (22.7% importance) is by far the most powerful
+> Design_elite_vs_vernacular (22.7% importance) is by far the most powerful predictor of protocol type, followed by Entanglement_flocking_vs_swarming (13.8%).
-> predictor of protocol type, followed by Entanglement_flocking_vs_swarming
-> (13.8%).
 > 
 > 5. Most "Central" Protocols (Network Analysis)
 > 
@@ -200,9 +197,7 @@ Claude's interpretation:
 > 
 > 6. Outliers (DBSCAN found 281!)
 > 
-> Most protocols are actually quite unique - DBSCAN identified 281 outliers,
+> Most protocols are actually quite unique - DBSCAN identified 281 outliers, suggesting the dataset contains many distinctive protocol configurations that don't fit neat clusters. Only 10 tight sub-clusters exist.
-> suggesting the dataset contains many distinctive protocol configurations that
-> don't fit neat clusters. Only 10 tight sub-clusters exist.
 > 
 > 7. Category Prediction Power
 > 
@@ -212,10 +207,7 @@ Claude's interpretation:
 > 
 > This suggests Design and Entanglement are more fundamental than Experience.
 > 
-> The core insight: Protocols fundamentally divide between
+> The core insight: Protocols fundamentally divide between vernacular/emergent/malleable forms and institutional/standardized/static forms, with the elite↔vernacular dimension being the strongest predictor of all other characteristics.
-> vernacular/emergent/malleable forms and institutional/standardized/static
-> forms, with the elite↔vernacular dimension being the strongest predictor of
-> all other characteristics.
 
 Comments:
 
@@ -223,8 +215,6 @@ Comments:
 * Strange that "Ethereum Proof of Work" appears in the "Vernacular/Emergent" family
 
 
-
-
 ## Conclusions
 
 ### Improvements to the bicorder
@@ -256,8 +246,7 @@ Claude report on possible improvements:
 > Tier 3 - Supplementary (<5%):
 > - All remaining 17 dimensions
 > 
-> Recommendation: Reorganize the tool to present Tier 1 dimensions first, or
+> Recommendation: Reorganize the tool to present Tier 1 dimensions first, or mark them as "core diagnostics" vs. "supplementary diagnostics."
-> mark them as "core diagnostics" vs. "supplementary diagnostics."
 > 
 > 2. Consider Reducing Low-Value Dimensions
 > 
@@ -269,27 +258,22 @@ Claude report on possible improvements:
 > - Design_durable_vs_ephemeral (1.2% importance, σ=2.41)
 > - Entanglement_defensible_vs_exposed (1.1% importance, σ=2.41)
 > 
-> Recommendation: Either remove these or combine into composite measures. Going
+> Recommendation: Either remove these or combine into composite measures. Going from 23→18 dimensions would reduce analyst burden by ~20% with minimal information loss.
-> from 23→18 dimensions would reduce analyst burden by ~20% with minimal
-> information loss.
 > 
 > 3. Add Composite Scores 📊
 > 
 > Since PC1 explains the main variance, create derived metrics:
 > 
 > "Protocol Type Score" (based on PC1 loadings):
-> Score = elite_vs_vernacular(0.36) + static_vs_malleable(0.33) +
+> Score = elite_vs_vernacular(0.36) + static_vs_malleable(0.33) + flocking_vs_swarming(0.31) - self-enforcing_vs_enforced(0.29)
->         flocking_vs_swarming(0.31) - self-enforcing_vs_enforced(0.29)
 > - High score = Institutional/Standardized
 > - Low score = Vernacular/Emergent
 > 
 > "Protocol Completeness Score" (based on PC2):
-> Score = sufficient_vs_insufficient(0.43) + crystallized_vs_contested(0.38) -
+> Score = sufficient_vs_insufficient(0.43) + crystallized_vs_contested(0.38) - Kafka_vs_Whitehead(0.36)
->         Kafka_vs_Whitehead(0.36)
 > - Measures how "finished" vs. "kafkaesque" a protocol feels
 > 
-> Recommendation: Display these composite scores alongside individual dimensions
+> Recommendation: Display these composite scores alongside individual dimensions to provide quick high-level insights.
->  to provide quick high-level insights.
 > 
 > 4. Highlight Key Correlations 🔗
 > 
@@ -311,12 +295,10 @@ Claude report on possible improvements:
 > 
 > Two dimension pairs show moderate correlation within the same category:
 > 
-> 1. Entanglement_abstract_vs_embodied ↔ Entanglement_flocking_vs_swarming
+> 1. Entanglement_abstract_vs_embodied ↔ Entanglement_flocking_vs_swarming (r=-0.56)
-> (r=-0.56)
 > 2. Design_documenting_vs_enabling ↔ Design_static_vs_malleable (r=0.53)
 > 
-> Recommendation: Consider merging these or making one primary and the other
+> Recommendation: Consider merging these or making one primary and the other optional.
-> optional.
 > 
 > 6. Rebalance Categories ⚖️
 > 
@@ -340,8 +322,7 @@ Claude report on possible improvements:
 > - Entanglement_exclusive_vs_non-exclusive: 93% of protocols rate 7-9
 > - Design_technical_vs_social: Mean=7.6, heavily skewed toward "social"
 > 
-> Recommendation: Consider revising these gradient definitions or endpoints to
+> Recommendation: Consider revising these gradient definitions or endpoints to achieve better distribution.
-> achieve better distribution.
 > 
 > 8. Create Shortened Version 🎯
 > 
@@ -360,14 +341,12 @@ Claude report on possible improvements:
 > 
 > 9. Add Comparison Features
 > 
-> The network analysis shows some protocols are highly "central" (similar to
+> The network analysis shows some protocols are highly "central" (similar to many others):
-> many others):
 > - VPN Usage (Circumvention Protocol)
 > - Access Check-in
 > - Quadratic Voting
 > 
-> Recommendation: After rating a protocol, show: "This protocol is most similar 
+> Recommendation: After rating a protocol, show: "This protocol is most similar to: [X, Y, Z]" based on dimensional proximity.
-> to: [X, Y, Z]" based on dimensional proximity.
 
 > Summary of Recommendations
 
@@ -381,8 +360,7 @@ Claude report on possible improvements:
 > 5. 💡 Add contextual tooltips about correlations
 > 6. 📊 Show similar protocols after assessment
 
-> This would make the tool ~20% faster to use while maintaining 95%+ of its 
+> This would make the tool ~20% faster to use while maintaining 95%+ of its discriminative power.
-> discriminative power.
 
 Questions: