The arithmetic for one report
Nvidia has no obvious successor to Jensen Huang — and that's a problem
81Moderate density of flagged expressions
What was read
468 words in the outlet's own voice, plus 12 in the headline. 23% of the text is in quotes, with 3 listed words inside quotes. 13 attribution markers (such as "said" or "according to") found.
Listed words inside quotes (not scored; quoting is reporting, but which quotes to use is an editorial choice): ridiculous
, massive
, very
.
Words found
- Word choice:
admitted
2 points Loaded word for "said"
the global AI economy — admitted to having an affair with avisionary
1 point Puffery
role as an innovator and visionary for the AI age. What they're - Attribution phrases:
experts say
2 points Vague attribution
an independent investigation Sunday, and experts say Huang's chances of keeping his job
Layer scores
Rates are counted points per 1,000 words of the story's own text. For a story longer than 200 words, the rate used is the average of the whole-story rate and the rate in its densest 200-word stretch, so neutral filler cannot dilute a loaded passage away. Score = 100 × (loaded end − rate used) ÷ loaded end, kept between 0 and 100. Headline words count only in the headline layer.
| Layer | Points | Words | Whole-story rate | Densest 200 words | Rate used | Scale | Score |
|---|---|---|---|---|---|---|---|
| Word choice | 3 | 468 | 6.4 | 15.0 (words 51 to 250) | 10.7 | 0 to 40 | 73 |
| Temperature | 0 | 468 | 0.0 | 0.0 (words 1 to 200) | 0.0 | 0 to 40 | 100 |
| Flagged attribution phrases | 2 | 468 | 4.3 | 10.0 (words 1 to 200) | 7.1 | 0 to 20 | 64 |
| Headline wording | 0 | 25 | 0.0 | headline only | 0.0 | 0 to 240 | 100 |
Densest stretch: Word choice, words 51 to 250 of 468, with admitted
, visionary
; Flagged attribution phrases, words 1 to 200 of 468, with experts say
.
Shown, not scored: the headline's rate minus the rate of the story's first 80 words is 0.0 points per 1,000 words. Experimental: 1 of 1 names and figures in the headline also appear in the text read.
Overall
Weighted geometric mean of the layers that are established, with 10 added to each layer first and taken away at the end: (Word choice 73 + 10)0.4 × (Temperature 100 + 10)0.3 × (Flagged attribution phrases 64 + 10)0.2 × (Headline wording 100 + 10)0.1 − 10 = 81. Adding 10 means one layer at 0 lowers the total steeply without collapsing it. A weak layer pulls the total down.
Lowered the score most: Word choice.
Name-swap test: with party, politician and institution names swapped, this report's score moves by 0.0 points.
Only the feed's headline and summary were read, so this report is listed with the headline-and-summary results and never enters the outlet ranking.
What a reader could check
| People named as sources | 4 (Charles Elson, Jeffrey Sonnenfeld, Peter Jaworski, Michael Monaghan) |
|---|---|
| Unnamed sources | 0 (0% of all sources found) |
| Links to primary records (government, court, filings, PDFs) | 0 |
| Documents cited in the text (a report, bill, ruling, filing) | 0 |
| Checkable specifics (numbers and dates) | 0 |
| Data shown (a table or chart) | no |
| Correction or clarification noted | no |
What a reader could check, counted by published patterns. Only the headline and summary were read, so most counts will be low. Shown beside the score, never part of it. How each count works
Checked against the official record
No vote count or bill number found in the text read.
Record of this measurement
Method 3.1.0, word-list fingerprint 807a17189402a416, read by text extractor version 4. Fingerprint of the text read: 6e7ccee11a898ac7. Internet Archive copy nearest the time it was read. The text read was not kept (read before method 3.1.0, or from the feed only), so a later rule change can be applied only while the report is still in the outlet's feed.