1. Models
  2. Meta
  3. Shift and Generalization Types Network
MetaX · Feb 3, 2023 · official

Shift and Generalization Types Network

Meta's annotated chart drew 74.5K views on X: 2.0x its median post and #445 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Network of shift and generalization types

XDataAnnotated chartMeta AI appAll Meta models
Published by Meta on X, Feb 3, 2023. Source: x.com
46/ 100

ViralChart score

Wide but thin

More views than the median post but a lower engagement rate: many saw it, few acted. Common for big accounts.

#668 of 1,162 AI chart posts we hold · #15 of 31 Meta posts. Score = views 40%, likes 30%, engagement rate 15%, save rate 15%, each as a percentile of every AI chart post we hold.

Our read

It lands in the Wide but thin quadrant, at #668 of 1,162 AI chart posts.

Its 0.36% engagement rate sits at the 14th percentile among AI chart posts, 0.49x the 0.73% median.

The post drew 74.5K views against a 36.4K company median, a 2x ratio and #12 of 31 Meta posts.

At 0.086 views per follower it trails the 0.20 median across posts with known followers, 0.43x that median.

0.09views per follower

74.5K views from an account with 865.4K followers.

bottom 14%engagement rate

0.36% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

3.3xthe median annotated chart post

Across 62 annotated chart posts we hold, the median gets 22.8K views.

2.0xMeta's median post

74.5K views, where Meta's typical post gets 36.4K.

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 31 from Meta.

Where it sits

Reach against resonance

Each dot is a post. Right is more views, up is a higher engagement rate. The lines are the medians, so the four corners are the four kinds of post.

Among 1,162 AI chart posts we hold

Score #668 of 1,162

Views74.5K#445top 38%
Likes213#634bottom 45%
Engagement rate0.36%#1,003bottom 14%
Save rate0.062%#702bottom 40%

Among 31 Meta posts

Score #15 of 31

Views74.5K#12top 37%
Likes213#13top 42%
Engagement rate0.36%#29bottom 8%
Save rate0.062%#21bottom 34%

Growth

One read so far

Views74.5K
Age at our read1347 days
Views per day of life55views divided by days since it was posted

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

Meta's posts over time

Every post from this account we hold, by date and views. This one is marked; the line is the running median of the last 10.

News · Feb 3, 2023

Meta posts Shift and Generalization Types Network chart

The annotated chart reached 74.5K views but an engagement rate of 0.36%, below the AI chart median.

What happened

Meta published an annotated chart on February 3, 2023, titled Shift and Generalization Types Network. It was the account's only post that day.

The numbers

The post reached 74.5K views, #445 of 1,162 AI chart posts and #12 of 31 Meta posts. Its score of 46 ranks #668 of 1,162 AI chart posts.

The lesson

One annotated chart with a 0.36% engagement rate and a 0.062% save rate shows that a single chart can travel to 74.5K views while drawing few saves.

What it means

At #15 of 31 Meta posts by score, this chart sits mid-pack for the account, and its 0.49x ratio to the AI median engagement rate marks the gap.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what Meta posted next

  1. Hiera Model Performance Comparison173.2K views
  2. Llama 3.1 405B Human Evaluation50.7K views
  3. Llama context window comparison10.2K views
  4. AI Model Performance Trend91.8K views
  5. LM Arena ELO score vs. cost1.5M views
  6. Net Win Rate of SAM Audio vs. SoTA36.4K views

Data and API

17 points read off this chart

Estimated from the image 30%
SeriesGroupValueRead
shift type: full100 relative index (tallest mark = 100)estimated
shift type: covariate95 relative index (tallest mark = 100)estimated
shift type: multiple shifts90 relative index (tallest mark = 100)estimated
generalisation type: across domain85 relative index (tallest mark = 100)estimated
generalisation type: across language80 relative index (tallest mark = 100)estimated
generalisation type: compositional75 relative index (tallest mark = 100)estimated
generalisation type: robustness70 relative index (tallest mark = 100)estimated
motivation: intrinsic65 relative index (tallest mark = 100)estimated
motivation: cognitive60 relative index (tallest mark = 100)estimated
motivation: structural55 relative index (tallest mark = 100)estimated
shift locus: train-test50 relative index (tallest mark = 100)estimated
shift locus: multiple train-test45 relative index (tallest mark = 100)estimated

Showing 12 of 17. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/8dd8e191a6d8.json
GET https://viral-chart.com/api/charts/8dd8e191a6d8.json
GET https://viral-chart.com/api/charts/8dd8e191a6d8.skill.md
Make one like thisOpen the post JSONChart data JSONSkill fileAPI docs

Static files in this prototype. The post JSON holds the public numbers, ranks, score, quadrant, our reads and, when checked, our copy.

API · Max

Use this chart via API

On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id 8dd8e191a6d8.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.30 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/8dd8e191a6d8Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/8dd8e191a6d8/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/8dd8e191a6d8/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/8dd8e191a6d8/data \
  -H "Authorization: Bearer $VIRALCHART_KEY"
Claude CodeMax
claude mcp add --transport http viralchart https://viral-chart.com/mcp \
  --header "Authorization: Bearer $VIRALCHART_KEY"

60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.

More charts about Meta AI app

Meta AI app: Hiera Model Performance Comparison
OfficialX · MetaJun 5, 2023
Hiera Model Performance Comparison173.2K views · 567 likes
Data
Meta AI app: SI-SDR improvement vs Number of speakers
OfficialX · MetaSep 19, 2022
SI-SDR improvement vs Number of speakers
Data

More from Meta

Meta table chart: AI model benchmark comparison
Meta·Sep 2026
AI model benchmark comparison
3.8M views19.9K likes0.6% eng.
Data
Meta line chart: SAM 3.1 vs SAM 3 Performance17x
Meta·Mar 2026
SAM 3.1 vs SAM 3 Performance
344.6K views2.2K likes0.8% eng.
Data
Meta annotated chart: APhO 2026 AI Model Results3.0x
Meta·Jul 2026
APhO 2026 AI Model Results
196.6K views404 likes0.3% eng.
Data
Llama 4: LM Arena ELO score vs. cost
OfficialX · MetaApr 5, 2025
LM Arena ELO score vs. cost1.5M views · 2.3K likes
Data
Muse Glimmer: AI Model Benchmark Comparison
OfficialX · MetaAug 10, 2026
AI Model Benchmark Comparison1.4M views · 8.2K likes
Data
Muse Spark: AI Model Benchmark Comparison
OfficialX · MetaSep 2, 2026
AI Model Benchmark Comparison435.2K views · 3.1K likes
Data
Meta speech models: Diariazation Error Rate Comparison
OfficialX · MetaSep 1, 2026
Diariazation Error Rate Comparison142.8K views · 1.5K likes
Data
Meta speech models: AA-WER Streaming Index - Final Transcription
OfficialX · MetaSep 1, 2026
AA-WER Streaming Index - Final Transcription142.8K views · 1.5K likes
Data
Muse Spark: High-dimensional ellipsoid fit threshold
OfficialX · MetaOct 2, 2026
High-dimensional ellipsoid fit threshold95.2K views · 154 likes
Data

Questions people ask

Where does this chart come from?

Meta published it on Feb 3, 2023 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. Open its data page and use Make one like this: it starts from this chart's numbers and takes yours.