Search golden sets are anything but
Comments on “Search golden sets are anything but”
3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked
A critique of standard search evaluation argues that golden sets built from BEIR-style judgment lists can mislead teams about real relevance. The author walks through NDCG using ESCI and WANDS examples, showing how a poor ideal ranking can make weak results look acceptable.
Why it ranked
No. 26 of 110 with a score of 0.59. The panel rated it highest on new information (0.91) and technical depth (0.81), lowest on significance (0.48). Placed No. 26, No. 73 by score alone: the placement terms moved other stories past it.
- AI judgeJudge 2claude-haiku-5-5
- Practical, technical discussion of search evaluation metrics (NDCG, labeling bias) useful to builders; mostly opinion with worked examples, moderate substantiation, not news-driven, and not a landmark.
- AI judgeJudge 3gpt-5.6-luna
- A technically substantive critique of golden-set and NDCG search evaluation, with concrete alternatives and formulas. It is highly actionable for search and data teams, though largely opinionated and ends with a modest course promotion.
Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.
Score
0.59total under rubric v2.3
- Significance0.48
- Reader interest0.66
- Audience breadth0.50
- Practical relevance0.76
- Substantiated0.61
- Technical depth0.81
- New information0.91
- Counts against: Promotional0.13
- Counts against: Overclaim0.21
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) |
|---|---|---|---|---|---|---|---|
| SignificanceHow much does this change what people in tech know or can do? | 0.53 | 0.30 | 0.62 | 0.48 | 0.32 | +0.24 | +0.116 |
| Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on? | 0.52 | 0.60 | 0.85 | 0.66 | 0.33 | +0.26 | +0.171 |
| Audience breadthHow many people who build technology does it concern? | 0.56 | 0.40 | 0.55 | 0.50 | 0.16 | +0.13 | +0.065 |
| Practical relevanceHow useful is it to someone who builds software or tech products? | 0.75 | 0.70 | 0.82 | 0.76 | 0.12 | +0.22 | +0.166 |
| SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations. | 0.50 | 0.60 | 0.72 | 0.61 | 0.22 | +0.05 | +0.030 |
| Technical depthHow technically substantive is it? | 0.94 | 0.70 | 0.78 | 0.81 | 0.24 | +0.05 | +0.040 |
| New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)? | 0.92 | 0.90 | 0.91 | 0.91 | 0.02 | +0.05 | +0.046 |
| PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional. | 0.08 | 0.20 | 0.12 | 0.13 | 0.12 | −0.19 | −0.025 |
| OverclaimDo the headline or conclusions claim more than the body supports? | 0.26 | 0.20 | 0.18 | 0.21 | 0.08 | −0.11 | −0.023 |
| Sum of contributions | +0.586 | ||||||
| Claim-check penalty | 0.000 | ||||||
| Total, as published | 0.586 | ||||||
Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.
The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.
<a href="https://rubric.hrih.si/editions/2026-10-29/26/"><img src="https://rubric.hrih.si/badge/2026-10-29/26.svg" alt="Ranked #26 on Rubric, 29 Oct 2026" width="245" height="28"></a>Also covered by
No other coverage was clustered with this story.
Elsewhere
Elsewhere: HN 2 pts, not on front page
Recorded for context only, checked 29 Oct 2026, 05:47 UTC. It played no part in the ranking.