The arithmetic for one report
Data center backlash fuels votes for change, stock market swing
88Few flagged expressions
What was read
546 words in the outlet's own voice, plus 10 in the headline. 40% of the text is in quotes, with 4 listed words inside quotes. 15 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): of course
, wonderful
, enormous
, very
.
Words found
- In the headline:
backlash
1 point Raises the temperature
Data center backlash fuels votes for change, stock market - Word choice:
controversial
negated, not counted Contentious label
it would no longer use controversial nondisclosure agreements with public officials and - Raises the temperature:
backlash
1 point Raises the temperature
OpenAI is responding to the backlash . On Thursday, the company laid out - Attribution phrases:
experts say
2 points Vague attribution
fueled stock market volatility that experts say is likely to continue.
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 | 0 | 546 | 0.0 | 0.0 (words 1 to 200) | 0.0 | 0 to 40 | 100 |
| Temperature | 1 | 546 | 1.8 | 5.0 (words 151 to 350) | 3.4 | 0 to 40 | 91 |
| Flagged attribution phrases | 2 | 546 | 3.7 | 10.0 (words 1 to 200) | 6.8 | 0 to 20 | 66 |
| Headline wording | 1 | 25 | 40.0 | headline only | 40.0 | 0 to 240 | 83 |
Densest stretch: Temperature, words 151 to 350 of 546, with backlash
; Flagged attribution phrases, words 1 to 200 of 546, with experts say
.
Shown, not scored: the headline's rate minus the rate of the story's first 80 words is 100.0 points per 1,000 words.
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 100 + 10)0.4 × (Temperature 91 + 10)0.3 × (Flagged attribution phrases 66 + 10)0.2 × (Headline wording 83 + 10)0.1 − 10 = 88. 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: Flagged attribution phrases.
Name-swap test: with party, politician and institution names swapped, this report's score moves by 0.0 points.
What a reader could check
| People named as sources | 5 (Keisha Lance Bottoms, Joe Maher, Nigel Green, President Trump, Jill Schlesinger) |
|---|---|
| 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) | 2 |
| Checkable specifics (numbers and dates) | 9 |
| Data shown (a table or chart) | no |
| Correction or clarification noted | no |
What a reader could check, counted by published patterns. 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: 4c4688d1ae2df088. 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.