| Term | Definition | Section | |
|---|---|---|---|
3-second video plays | Times the video played for at least 3 seconds. | Engagement | |
Amount spent | Dollars spent on the flight. A delivery condition, shown beside the score and never inside it. | Delivery | |
Average frequency | Impressions divided by reach: how many times the average person saw it. | Delivery | |
Average watch time | Seconds the average viewer watched. | Engagement | |
Boost | The reader's public push: stronger than a like, short of a share. A boost counts on the video's button, moves the video up the For you ranking for every reader (log of one plus its count, added to the ranking score), and weights the reader's own feed toward more like it. Each reader holds at most 10 boosts at once, and every press is logged as a reader action, the rows the Feed Ranker trains on. | Engagement | |
Content neighborhood | A cluster of shorts the embedding model reads as similar in content, from k-means over the serving index. The vector graph draws one dot per short and one circle per neighborhood. | Graph | |
Cost per 1,000 impressions | Spend divided by impressions, times 1,000. | Delivery | |
e² (end to end) | The stricter of the two lab tiers: a video carried through every measurement on the platform, end to end — its file fetched and measured (cuts, loudness, on-screen text, speech timing), its transcript, its embedding (its place among similar shorts), its comments and its headline score. Lab Tested, the looser tier, needs only the file's measurements. Four videos carry e²: Fix American Politics and Closed Primaries Cause Gridlock (Unite America), Taxation Without Representation? and When Political Parties See Independent Voters (Voter Freedom). The dashboard's e² (end to end) block lists them. | Graph | |
Explicit ask | What the viewer is told to do at the end. In Swayable's 617 control-tested political ads, an explicit ask ran +0.59 points of persuasion (0.2 to 1.0) over ads without one. | Script | |
Feature lift formula | How PAX2 measures whether a trait helps videos break out. Within each channel, the share of videos with the trait that broke out is compared with the share of those without it; each channel counts in proportion to how many videos it has on both sides; the channels are pooled into one difference in points; and a 90% range comes from redrawing the channels a thousand times. | Campaigns | |
Forecast | What PAX2 expects a video to score before its results come in, given as a likely range, the way a weather forecast gives a chance of rain. When the results arrive they are set beside the forecast as the actuals, and the gap between the two is how the forecasting improves. | Score | |
Hits and Misses | Every short PAX2 tracks, as a dot: publish date across, and views over the channel's usual (its median) up, on a log scale. Green dots broke out well above their channel's usual, red ones fell well below it, grey landed near it. Each dot opens its video. | Campaigns | |
Hook | The opening words of a script — what a viewer hears before deciding to stay or scroll. PAX2 asks for a hook under 12 words: on the headline model trained on Upworthy's 10,452 tested pairs (held-out accuracy 0.672), short, concrete first lines rank high. | Script | |
Impressions | How many times the video was shown in a feed. | Delivery | |
Internal wins above replacement | A video's views divided by its own channel's median views. It takes channel size out, so a small channel's hit counts as much as a big one's: 3× or more is a hit, half or less a miss. A channel growing fast understates its new videos, because its median lags behind it. | Campaigns | |
Lab Tested | The flask on a video marks that PAX2 measured the video file itself in the lab: composition extracted from the media — cuts, loudness, on-screen text — not just public counts. 5,080 videos carry it as of 2026-10-22. | Graph | |
Lift, in percentage points | For a content neighborhood: each short's over-3× result minus its own channel's usual over-3× rate, averaged, in percentage points. Measured against each channel's own baseline so one hot channel cannot read as a content finding. | Graph | |
Measured and predicted Resonance | Resonance reads as the word and the number at the head of a clip's test panel. A clip with the RCT badge carries the Resonance its own test measured; a clip without it carries a predicted Resonance, which the completion hook replaces with the measurement the moment the clip's test closes. | Score | |
Median video length | The middle length across a channel's recent shorts. | Campaigns | |
Multi-Modal Biometric Frequency | The human-measurement analogy that named the viometric version: vitals measured across modes — pressure, rate, rhythm — identify a person without describing their whole body. PAX measures videos, never people; the term survives only as the analogy. | Graph | |
Multi-Modal Viometric Frequency | A PAX term: one video's measured signature across every mode it carries — visual, sound, speech, title, embedding — rendered as a single deterministic visual unique to that video. Drawn only from measured variables, so similar videos draw similar signatures and a video's signature never changes unless its measurements do. | Graph | |
Outperformer (5–10×) | A PAX working term: a short whose views run five to ten times its channel's median — past the 3× threshold and into the range where distribution has clearly shifted beyond the channel's usual audience. The band, not the word, is the definition. | Graph | |
Paid run | The numbers from a video's paid run, as the ad platform exports them: what was spent, how many saw it, how far they watched (3 seconds, 25%, 50%, 75%, to the end), and what they did after (shares, saves, comments, reactions, clicks), with the cost of each. | Campaigns | |
People reached | How many different people saw the video at least once. | Delivery | |
Resonance band | The top tenth of content neighborhoods by lift, counting only neighborhoods spanning five or more channels — content that outruns its channels' own baselines no matter who posts it. | Graph | |
Resonance score | The percentile, 0 to 100, of a video's primary-outcome lift against the placebo among every measured lift on file for that outcome, ties counted half. 50 is the middle lift on file; 90 beats nine in ten. A tested video's Resonance comes from its own randomized test in the results register, and the score shows once the pool holds at least five lifts. | Score | |
Share at or over 3× channel median | Of a group of shorts, the share whose views reached at least three times their own channel's median. The 3× line is the threshold the tracking pages use throughout. | Graph | |
Swayable persuasion tests | Swayable showed 617 political ads from 2018 and 2020 to one randomly chosen group of people and not to another, then asked both groups how they would vote. The difference is how much the ad changed minds. Each ad was also coded on a checklist of traits, so the effect of a trait is the shift for ads with it against ads without it (Hewitt, Broockman, Coppock and others, APSR 2024). | Campaigns | |
ThruPlays | Plays to the end, or to 15 seconds for longer videos (Meta's definition). | Engagement | |
Upworthy Research Archive | From 2013 to 2015 Upworthy ran 32,487 tests showing the same story under different headlines to readers at random, and recorded which headline drew more clicks. It measures packaging: what a title does to whether people open the story. Released by Matias and Munger, 2021. | Campaigns | |
Views per day since posting | Public YouTube views divided by the days since the video was posted. Organic, not paid, and not comparable to Resonance. | Campaigns | |
Wesleyan Media Project | Wesleyan tracks and codes nearly every political ad that runs: on TV since 2006, and on Meta and Google since 2018. For 2022 it labels each Meta ad's goal (persuade voters, raise money, or both), its tone and the party it favors, beside what Meta reports it spent and how often it was shown. It shows what every other campaign ran, not whether any of it worked. | Campaigns | |
Wins above replacement | A video's views divided by the median views of every short across all 65 followed channels together. It measures raw reach in the whole field, so big channels lead it simply by being big. | Campaigns |