EgoHand: Monocular 3D Hand Reconstruction from Egocentric Video
2 judges. Scored by two of the three judges. The third reads only the day’s strongest candidates. How far stories are checked
EgoHand is a monocular model that reconstructs 3D hand poses from egocentric video, trained on a 14-million-image corpus mixing synthetic data, in-the-wild video, and multi-camera motion capture.
Score
0.55total under rubric v2.0
- Significance0.52
- Reader interest0.56
- Audience breadth0.35
- Practical relevance0.67
- Substantiated0.74
- Technical depth0.71
- New information0.92
- Counts against: Promotional0.14
- Counts against: Overclaim0.28
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 | 0.40 | — | 0.52 | 0.24 | +0.25 | +0.131 |
| Reader interest | 0.62 | 0.50 | — | 0.56 | 0.12 | +0.20 | +0.112 |
| Audience breadth | 0.40 | 0.30 | — | 0.35 | 0.10 | +0.10 | +0.035 |
| Practical relevance | 0.79 | 0.55 | — | 0.67 | 0.23 | +0.15 | +0.100 |
| Substantiated | 0.82 | 0.65 | — | 0.74 | 0.17 | +0.10 | +0.074 |
| Technical depth | 0.73 | 0.70 | — | 0.71 | 0.03 | +0.10 | +0.071 |
| New information | 0.93 | 0.90 | — | 0.92 | 0.03 | +0.10 | +0.092 |
| Promotional | 0.12 | 0.15 | — | 0.14 | 0.03 | −0.15 | −0.020 |
| Overclaim | 0.27 | 0.30 | — | 0.28 | 0.03 | −0.15 | −0.043 |
| Sum of contributions | +0.551 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.551 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested. Judge 3 did not score this story; its mean uses the other two.
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.