calibration_analysis

34 rows

✎ View and edit SQL

This data as json, CSV (advanced)

Suggested facets: skill_code, dimension, level_pair, events_analyzed, human_events, human_agreement, deepseek_agreement, weighted_agreement, avg_margin_score, dominant_feature, health_score, analyzed_at (date)

id ▼ skill_code dimension level_pair events_analyzed human_events deepseek_events human_agreement deepseek_agreement weighted_agreement avg_response_time_ms avg_margin_score dominant_feature health_score revision_recommended analyzed_at
1 RL-EVIDENCE autonomy L1v2 1 0 1   1.0 1.0 11713.0 0.75 independence_level 86.0 0 2026-05-26 02:37:26
2 RL-EVIDENCE autonomy L2v3 2 1 1 0.0 1.0 0.3333333333333333 9332.5 0.625 original_thinking 48.0 0 2026-05-26 02:37:26
3 RL-EVIDENCE autonomy L3v4 2 1 1 0.0 1.0 0.3333333333333333 19508.0 0.75 original_thinking 44.0 0 2026-05-26 02:37:26
4 RL-CHARACTER autonomy L2v3 2 1 1 1.0 1.0 1.0 18293.0 0.75 original_thinking 82.0 0 2026-05-26 02:37:26
5 RL-CHARACTER performance L3v4 2 1 1 1.0 1.0 1.0 19204.0 0.75 depth_of_thinking 81.0 0 2026-05-26 02:37:26
6 RL-EVIDENCE performance L1v2 1 0 1   1.0 1.0 14903.0 1.0 evidence_quality 90.0 0 2026-05-26 02:37:26
7 RL-EVIDENCE performance L2v3 1 0 1   0.0 0.0 23468.0 0.5   17.0 0 2026-05-26 02:37:26
8 RL-EVIDENCE performance L3v4 1 0 1   1.0 1.0 22540.0 0.75 depth_of_thinking 79.0 0 2026-05-26 02:37:26
9 RL-CHARACTER autonomy L1v2 1 0 1   1.0 1.0 17918.0 0.75 self_awareness 82.0 0 2026-05-26 02:37:26
10 RL-CHARACTER autonomy L3v4 1 0 1   1.0 1.0 13235.0 0.75 original_thinking 85.0 0 2026-05-26 02:37:26
11 RL-CHARACTER performance L1v2 1 0 1   1.0 1.0 10939.0 0.75 depth_of_thinking 86.0 0 2026-05-26 02:37:26
12 RL-CHARACTER performance L2v3 1 0 1   1.0 1.0 13411.0 0.75 depth_of_thinking 85.0 0 2026-05-26 02:37:26
13 RL-POV autonomy L1v2 1 0 1   1.0 1.0 22131.0 0.75 independence_level 79.0 0 2026-05-26 02:37:26
14 RL-POV autonomy L2v3 1 0 1   1.0 1.0 23114.0 0.75 independence_level 78.0 0 2026-05-26 02:37:26
15 RL-POV autonomy L3v4 1 0 1   1.0 1.0 17791.0 0.75 original_thinking 82.0 0 2026-05-26 02:37:26
16 RL-POV performance L1v2 1 0 1   1.0 1.0 8966.0 0.75 depth_of_thinking 88.0 0 2026-05-26 02:37:26
17 RL-POV performance L2v3 1 0 1   1.0 1.0 16112.0 0.75 depth_of_thinking 83.0 0 2026-05-26 02:37:26
18 RL-POV performance L3v4 1 0 1   1.0 1.0 15534.0 0.75 depth_of_thinking 83.0 0 2026-05-26 02:37:26
19 RI-EVIDENCE autonomy L1v2 1 0 1   1.0 1.0 13746.0 0.75 independence_level 85.0 0 2026-05-26 02:37:26
20 RI-EVIDENCE autonomy L2v3 1 0 1   1.0 1.0 23298.0 0.75 independence_level 78.0 0 2026-05-26 02:37:26
21 RI-EVIDENCE autonomy L3v4 1 0 1   1.0 1.0 21690.0 0.75 self_awareness 79.0 0 2026-05-26 02:37:26
22 RI-EVIDENCE performance L1v2 1 0 1   1.0 1.0 13493.0 0.75 evidence_quality 85.0 0 2026-05-26 02:37:26
23 RI-EVIDENCE performance L2v3 1 0 1   1.0 1.0 11979.0 1.0 depth_of_thinking 92.0 0 2026-05-26 02:37:26
24 RI-EVIDENCE performance L3v4 1 0 1   1.0 1.0 19434.0 0.75 evidence_quality 81.0 0 2026-05-26 02:37:26
25 W-CLAIMS autonomy L1v2 1 0 1   1.0 1.0 20644.0 0.5 self_awareness 74.0 0 2026-05-26 02:37:26
26 W-CLAIMS autonomy L2v3 1 0 1   1.0 1.0 19709.0 0.75 original_thinking 81.0 0 2026-05-26 02:37:26
27 W-CLAIMS autonomy L3v4 1 0 1   1.0 1.0 18402.0 0.75 self_awareness 81.0 0 2026-05-26 02:37:26
28 W-CLAIMS performance L1v2 1 0 1   1.0 1.0 13723.0 1.0 clarity_of_reasoning 91.0 0 2026-05-26 02:37:26
29 W-CLAIMS performance L2v3 1 0 1   1.0 1.0 20237.0 0.75 depth_of_thinking 80.0 0 2026-05-26 02:37:26
30 W-CLAIMS performance L3v4 1 0 1   1.0 1.0 21272.0 0.75 depth_of_thinking 80.0 0 2026-05-26 02:37:26
31 W-ARGUMENT autonomy L1v2 1 0 1   1.0 1.0 19081.0 0.75 independence_level 81.0 0 2026-05-26 02:37:26
32 W-ARGUMENT autonomy L2v3 1 0 1   1.0 1.0 17805.0 0.75 original_thinking 82.0 0 2026-05-26 02:37:26
33 W-ARGUMENT autonomy L3v4 1 0 1   1.0 1.0 22128.0 0.75 self_awareness 79.0 0 2026-05-26 02:37:26
34 W-ARGUMENT performance L1v2 1 0 1   1.0 1.0 11771.0 0.75 evidence_quality 86.0 0 2026-05-26 02:37:26

Advanced export

JSON shape: default, array, newline-delimited, object

CSV options: 

CREATE TABLE calibration_analysis (
    id INTEGER PRIMARY KEY,
    skill_code TEXT NOT NULL,
    dimension TEXT NOT NULL,
    level_pair TEXT NOT NULL,
    events_analyzed INTEGER NOT NULL,
    human_events INTEGER DEFAULT 0,
    deepseek_events INTEGER DEFAULT 0,
    human_agreement REAL,
    deepseek_agreement REAL,
    weighted_agreement REAL,
    avg_response_time_ms REAL,
    avg_margin_score REAL,
    dominant_feature TEXT,
    health_score REAL,
    revision_recommended INTEGER DEFAULT 0,
    analyzed_at TEXT DEFAULT (datetime('now')),
    UNIQUE(skill_code, dimension, level_pair)
  );
CREATE INDEX idx_analysis_skill ON calibration_analysis(skill_code);
CREATE INDEX idx_analysis_revision ON calibration_analysis(revision_recommended);