Abstract Priorities, Concrete Rewards: How Stated Preferences Relate to What People Reward in AI Responses
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
This working paper examines whether the priorities people state about AI responses match what they actually reward when rating them, using the public PRISM dataset of 1,396 participants rating 29,347 responses from 21 models.
Score
0.65total under rubric v2.0
- Significance0.54
- Reader interest0.65
- Audience breadth0.63
- Practical relevance0.63
- Substantiated0.86
- Technical depth0.85
- New information0.86
- Counts against: Promotional0.03
- Counts against: Overclaim0.18
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 | 0.64 | 0.35 | 0.63 | 0.54 | 0.29 | +0.25 | +0.135 |
| Reader interest | 0.60 | 0.50 | 0.86 | 0.65 | 0.36 | +0.20 | +0.131 |
| Audience breadth | 0.72 | 0.50 | 0.68 | 0.63 | 0.22 | +0.10 | +0.063 |
| Practical relevance | 0.70 | 0.50 | 0.68 | 0.63 | 0.20 | +0.15 | +0.094 |
| Substantiated | 0.98 | 0.80 | 0.80 | 0.86 | 0.18 | +0.10 | +0.086 |
| Technical depth | 0.98 | 0.70 | 0.88 | 0.85 | 0.28 | +0.10 | +0.085 |
| New information | 0.88 | 0.70 | 0.99 | 0.86 | 0.29 | +0.10 | +0.086 |
| Promotional | 0.04 | 0.05 | 0.01 | 0.03 | 0.04 | −0.15 | −0.005 |
| Overclaim | 0.23 | 0.20 | 0.12 | 0.18 | 0.11 | −0.15 | −0.027 |
| Sum of contributions | +0.648 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.648 | ||||||
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.