The arithmetic for one report
Prosecutors: 3 Crooks Used AI Voice-Cloning Scheme to Steal $129 Million from Companies
82Moderate density of flagged expressions
What was read
599 words in the outlet's own voice, plus 13 in the headline. 0% of the text is in quotes. 0 attribution markers (such as "said" or "according to") found.
Scare quotes (a phrase of one to three words in quotation marks with no speaker in the same sentence): Lawyer Call,
, Rocky Balboa
, Superman Cash
, Fat Boy,
. Since method 3.1.0 their words count as the outlet's own.
Insults found but not counted: 1 (crooks
). Insult words are experimental until the reader panel rates them, so they are shown and not scored.
Words found
- In the headline:
crooks
experimental, shown but not counted Insult or name-calling
Prosecutors: 3 Crooks Used AI Voice-Cloning Scheme to Steal - Word choice:
supposedly
2 points Expression of doubt
manager, would receive an email supposedly from a company executive. In onebragged
2 points Loaded word for "said"
alongside other activities; Hazan allegedly bragged about laundering more than $400 millionleftists
3 points Contentious label
of our nation to the leftists of Silicon Valley or allowing the
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 | 7 | 599 | 11.7 | 15.0 (words 400 to 599) | 13.3 | 0 to 40 | 67 |
| Temperature | 0 | 599 | 0.0 | 0.0 (words 1 to 200) | 0.0 | 0 to 40 | 100 |
| Flagged attribution phrases | 0 | 599 | 0.0 | 0.0 (words 1 to 200) | 0.0 | 0 to 20 | not established |
| Headline wording | 0 | 25 | 0.0 | headline only | 0.0 | 0 to 240 | 100 |
Densest stretch: Word choice, words 400 to 599 of 599, with leftists
.
Attribution is not established: the story's own text has no attribution and no flagged sourcing phrase, so this layer is left out instead of scoring 100.
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 3 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 67 + 10)0.4 × (Temperature 100 + 10)0.3 × (Flagged attribution phrases left out)0.2 × (Headline wording 100 + 10)0.1 − 10 = 82. 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.
What a reader could check
| People named as sources | 0 |
|---|---|
| Unnamed sources | 0 |
| 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) | 15 |
| 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: f038cead227dac9f. 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.