CRIT-1: Stylistic extremity direction reversed — both dimensions declined
(stijl 1.875→1.744, not increased +0.097). Holistic moderation, not divergence.
CRIT-2: Masking rate corrected from 36.1% to 9.7% (S≤2, M≥4 on full dataset).
Original 36.8% was from 117-motion manual audit, not extrapolatable.
CRIT-3: Material impact values harmonized to motion-level means (2.79→2.45).
Old values (2.78→2.43) used undisclosed mean-of-yearly-means aggregation.
HIGH-1: Migration domain provenance caveat — category column is NULL,
analysis relies on title keyword matching (approximate boundaries).
HIGH-2: 2026-Q2 bounce caveat — n=44, bimodal distribution, sensitive to
composition (many consensus defense motions among CS=1.0 items).
HIGH-3: Non-right-wing control group corrected — CS rose 58%→62% (+3.5pp),
not 'flat at 49%'. Surge was disproportionate for right-wing content.
Also: fixed 6-party centrist definition (line 30) to 4-party,
removed 'did not shift rightward' phrasing, added Phase 4 synthesis
reminder to build_all_reports.py.
- Fetched 276 new motions from Tweede Kamer API (2026-04-23 to 2026-05-31)
- Fixed classify_motions.py: DROP TABLE → CREATE TABLE IF NOT EXISTS
- Restored derived columns (centrist_support_strict, category, etc.) via migration
- Scored 180 missing motions in extremity_scores_2d (now 3,049 total, 0 missing)
- Re-ran temporal trajectory with updated data (inflection: 2024-Q2)
U1: JA21 drives moderation effect (+0.203 CS shift, only party with volume+support gains)
U2: Coalition coding split at July 2024 — opposition effect confirmed (d=0.85 vs 0.87)
U3: Voting margin (ρ=0.812 with centrist support) is far superior to pass rate
U4: SVD trajectory confirms spatial divergence — centrists moved left (Δx=-0.30), right stationary
U5: Mechanism classification Cohen's κ=0.41 (moderate) — taxonomy needs revision
U6: Predictive model AUC-ROC=0.81 — submitter party and category are strongest predictors
- Project-local skill .opencode/skills/score-extremity/ for subagent dispatch
- Orchestrator extremity_rescore_2d.py with load_skill/sample/format/validate/store
- 16 TDD tests covering all orchestrator functions
- 117 motions scored by deepseek v4 flash subagents (12 parallel batches)
- Pearson r=0.45 between stylistic and material dimensions — separable
- Key finding: 36.8% of motions use restrained language for consequential policies
- 2d_extremity_correlation_report.md documents distribution, divergence patterns,
and implications for the Overton acceptance-without-conversion narrative
- Reclassified centrist to {D66, CDA, CU, NSC} — removing VVD/BBB
which are center-right coalition partners
- Added centrist_support_strict (0.251→0.507, d=+0.65), center_right_support,
and left_support_mp columns via migration script
- Figure 1 now shows center-right (VVD/BBB) support as orange dashed line
- New Figure 3: bar chart of left-party support for right-wing motions
(0.268→0.202, left opposition hardened)
- New report Section 6 covering left-wing support trends
- All analysis now uses strict centrist definition throughout
Extremity Scorer (U4 enhanced):
- Now scores BOTH original motion text AND layman explanation separately
- Schema: text_score, text_explanation, layman_score, layman_explanation
- Text scores: 1→7, 2→33, 3→5, 4→5 (mild-to-moderate)
- Layman scores: 1→12, 2→20, 3→17, 4→1 (slightly milder)
Sentiment Analysis (U5 enhanced):
- Now scores BOTH original motion text AND layman explanation separately
- Schema: text_score, text_explanation, layman_score, layman_explanation
- Text sentiment avg: 0.294 (slightly positive)
- Layman sentiment avg: 0.416 (more positive - summaries tone down hostility)
Category Derivation (new):
- Two-phase LLM approach: derive taxonomy from sample, then apply to all
- Discovered 7 categories from 30-motion sample:
veiligheid/justitie, corona/pandemie, economie/belasting, klimaat/milieu,
defensie/buitenland, asiel/vreemdelingen, overig
- Applied to 50 motions with distribution shown in DB
- Adds category + category_explanation columns to right_wing_motions
Implements U5: sentiment_analysis.py uses LLM batch calls (fallback when no
local Dutch sentiment model is available) to score motion sentiment on [-1, 1]
scale.
Design:
- Prompt asks for sentiment from -1 (hostile/aggressive) to 1 (constructive)
- JSON schema enforces numeric score + Dutch explanation
- Batch size 10, max_workers 5 for parallel API calls
- Stores results in table
- Updates with avg_sentiment, sentiment_std,
pct_strongly_negative per year
Sample validation (50 motions): good variance across [-0.9, 1.0] range.
Implements U3: temporal_analysis.py computes yearly_summary from the
right_wing_motions table (U2 output).
Metrics per year:
- total_right_wing, pct_of_total, total_motions
- avg_right_support, avg_left_opposition, centrist_support
- avg_right_keyword_matches, extremity_index (U4 placeholder)
- yoy_right_wing_delta, yoy_pct_delta
Key finding: right-wing motions grew from ~4% (2018) to ~12% (2024-2025)
of all motions, with rising centrist support over time.
sgeboers