HERD: Harness-Evolving Recursive Distillation for Continual Learning
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
HERD is a hybrid continual learning method that pairs an evolving harness of reusable skills and a bounded memory of hard examples with recursive distillation into model weights, under drift constraints anchored to the previous checkpoint and the base model.
Score
0.66total under rubric v2.0
- Significance0.64
- Reader interest0.71
- Audience breadth0.56
- Practical relevance0.57
- Substantiated0.79
- Technical depth0.92
- New information0.91
- Counts against: Promotional0.04
- Counts against: Overclaim0.25
Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).
| Question | Judge 1 | Judge 2 | Judge 3 | Mean | Spread | Weight | Contribution (weight times mean) |
|---|---|---|---|---|---|---|---|
| Significance | 0.65 | 0.50 | 0.78 | 0.64 | 0.28 | +0.25 | +0.161 |
| Reader interest | 0.60 | 0.60 | 0.94 | 0.71 | 0.34 | +0.20 | +0.143 |
| Audience breadth | 0.54 | 0.40 | 0.73 | 0.56 | 0.33 | +0.10 | +0.056 |
| Practical relevance | 0.56 | 0.45 | 0.72 | 0.57 | 0.27 | +0.15 | +0.086 |
| Substantiated | 0.95 | 0.60 | 0.82 | 0.79 | 0.35 | +0.10 | +0.079 |
| Technical depth | 0.98 | 0.80 | 0.98 | 0.92 | 0.18 | +0.10 | +0.092 |
| New information | 0.90 | 0.85 | 0.99 | 0.91 | 0.14 | +0.10 | +0.091 |
| Promotional | 0.05 | 0.05 | 0.02 | 0.04 | 0.03 | −0.15 | −0.006 |
| Overclaim | 0.23 | 0.35 | 0.18 | 0.25 | 0.17 | −0.15 | −0.038 |
| Sum of contributions | +0.664 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.664 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN —
Recorded for context only, checked 24 Oct 2026, 08:54 UTC. It played no part in the ranking.