Vanity or Vice
Skip to content
Northern Lantern House Labs (opens in a new tab)
Makeup Intelligence

Score a profile · leave with a list

The Edit

0 of 29 fields personalised · risk 43 · skin-like 57 · 3 films · 8 min applying

The answer

Build performance minimal — 6 objects, 3 films, about 8 minutes.

Why

Sebum movement is doing the most model work (+7). The model raises wear pressure because sebum is in the profile and you do not want midday intervention.

Caveat

Education only — never a diagnosis, toxin score, safety ranking or calibrated probability. Verify the unit in your hand.

Next

Read the order, then open the kit, pick one house example, and take your list to the counter.

Pancake index 43 out of 100. Skin-like index 57 out of 100. These are heuristic model scores, not measured probabilities.

Your pancake index

43

Conditional · Balanced architecture

Skin-like index 57·model baseline 30

Products

6 / 6

Layers

3

Minutes applying

8

Tension

20

Wear & longevity · Edit pathway

The model sees moderate wear pressure; a blot-first maintenance test is worth logging.

The day-brief pancake index is a planning heuristic from today's hours, climate context and pathway. It is not the same as the profile pancake index, and neither is a probability or a wear test of a named bottle.

Day-brief pancake 49

Figure · the day, forecast against record

What this desk expects your base to do over the day. There is nothing of yours on it yet — write one wear log and the marks appear.An integrity-over-time chart for the day's wear, with the forecast drawn as a line and the reader's own logged outcomes drawn as discrete marks.050100on3h7h10hgoes first — hour 6integrity
  • Forecast
What this desk expects your base to do over the day. There is nothing of yours on it yet — write one wear log and the marks appear.Modelled from your profile, kit and stated hours. Not evidence — a forecast.

  1. Hour 0

    100

    Modelled integrity remains high at this checkpoint.

  2. Hour 2

    90

    Modelled integrity remains high at this checkpoint.

  3. Hour 4

    80

    Modelled integrity remains high at this checkpoint.

  4. Hour 6

    70

    The model flags a first wear-pressure zone; log what actually appears rather than assuming the mode.

  5. Hour 8

    61

    The model flags a first wear-pressure zone; log what actually appears rather than assuming the mode.

  6. Hour 10

    51

    The model expects more visible movement here. Blot-first is the low-film maintenance test.

  • 43·Transfer / sweat

    Sweat/contact exposure and film load raise the model pressure; actual transfer depends on the specific formula, amount and day.

  • 39·Cake / settle

    Model pressure combines opacity, film load and dryness/exposure context. Prep, placement and fewer films are variables to test; this score is not a probability.

  • 28·Colour fade

    This is a catalogue/use-context pressure score. Actual fade belongs in the wear log for the named product.

  • 27·Slide / sebum break

    The model raises pressure when sebum/humidity and low maintenance coincide. Blot-first versus repowder is the useful A/B test.

Log what actually held past hour six →

Contextual finding intelligence

The finding should tell you what to look at next.

Each panel ties the current desk context to a measurement procedure, one-variable test, explanatory plate, worked case and source trail. It is a decision aid, not a diagnosis.

audited baked fallback

catalog 2026-09-13-baked

Why this is here now

Use the forecast to decide what to observe, then let logged wear correct the model.

This brief asks for about 10 hours on face, so first-failure timing matters more than a single end-of-day verdict.

Wear timeline and first failureA horizontal timeline marks application, observation checkpoints, first visible failure and maintenance so the user can distinguish model forecast from observed wear.0h2h4h6h8h10hFIRST VISIBLE CHANGEMAINTENANCELOG ZONE · FAILURE TYPE · HOUR · WHAT HAPPENED BEFORE IT
Explanatory plate, not a measurement. The measurement procedure is listed beside it.

Measure this

Log the first visible change, exact zone and hour. Also log comparable days when the predicted failure never appears.

Smallest useful test

Change only one maintenance or film-load variable on the next comparable wear.

Closest worked case

Flash photography + finish uncertainty

The base looks good in room light but the event includes direct flash and phone cameras.

Worked-case outcome reading
If betterIf sameIf worse
A consistent improvement supports that finishing choice for this setup.The suspect product may not be controlling the effect; test exposure/white balance or another finishing layer.Restore the prior version and test a smaller change.

Next · Save the successful setup as a repeatable event configuration.

Prefills hypothesis, constants and the one variable to change. Saved locally only.

Sources for this finding