Franklin
Aggregate metrics
Based on 6 episode(s). FFC: 0.251
| Metric | Mean | Median | Std dev |
|---|
| Formal-Feature Composite (FFC) | 0.251 | 0.251 | 0.017 |
| Cuts per minute | 13.3 | 12.7 | 1.7 |
| Color saturation | 0.473 | 0.514 | 0.095 |
| Color contrast | 0.205 | 0.204 | 0.015 |
| Motion | 0.0653 | 0.0645 | 0.0047 |
| Flashing events / min | 5.4 | 5.0 | 0.9 |
| Audio RMS | 0.0417 | 0.0259 | 0.0347 |
Unlike black-box tools, CMAT measures its own error rate against human coding. That validation is currently a small, single-coder pilot, so treat the figures as indicative, not settled. Detection accuracy (preliminary): transition-BOUNDARY detection across all coded transition types — i.e. whether a transition was found there, not whether it was labelled correctly — agreed with human coding at F1 0.85 (±2s match, 2 comparison run(s), single coder; larger sample and inter-rater reliability in progress). This is the figure the pacing RATE depends on; type classification is scored separately and is lower. Accuracy is content-dependent. Dissolve/scene-change detection experimental. Colour, motion and audio are deterministic measurements; FLASHING is unvalidated and is not a safety assessment. See Methodology.
Episodes
| Episode | Air date | FFC | Cuts/min | Saturation | Motion | Flash/min |
|---|
| Back to School with Franklin (2003 VHS) | | 0.276 | 12.6 | 0.286 | 0.0619 | 4.5 |
| Franklin 1 | | 0.265 | 17.0 | 0.425 | 0.0732 | 6.3 |
| Franklin 2 | | 0.247 | 12.9 | 0.498 | 0.0688 | 4.7 |
| Franklin 3 | | 0.235 | 12.1 | 0.530 | 0.0637 | 5.3 |
| Franklin 4 | | 0.227 | 11.9 | 0.566 | 0.0589 | 4.7 |
| Franklin 5 | | 0.255 | 13.2 | 0.536 | 0.0652 | 7.1 |