Fake Door Landing Page Validation Setup

Caller independently verified audience/measurement/consent/nondeceptive follow-up fake-door experiment requirements, no instruction to collect payments for nonexistent fulfillment. Independently declared positive requirements, overlapping/unknown classes retained. Caller independently verifies policy, evidence, dates and applicability; not legal/compliance advice or causal business-success prediction.

Description

A fake-door test measures response to a proposed offering before full delivery.

A fake-door test measures response to a proposed offering before full delivery.^[1]

A caller setup rubric does not build a landing page or establish that participant disclosures and measurement are adequate. Use this tool to compare independently annotated features with the stated candidate rules.

When to use Fake Door Landing Page Validation Setup

Use this tool to compare independently annotated features with the stated candidate rules. Establish the business period, event definitions, jurisdiction or agreement edition, and independently documented evidence or comparison rubric.

How to use Fake Door Landing Page Validation Setup and understand its results

Establish the business period, event definitions, jurisdiction or agreement edition, and independently documented evidence or comparison rubric.
Enter callerFakeDoorExperimentClassIds, callerFakeDoorExperimentRequirements, observedFakeDoorExperimentEvidence, knownFakeDoorExperimentFlags, using the field meanings and rules below, then run the tool.
Read compatibleCallerClasses, fullyWitnessedCallerClasses. Interpret the fields using their units, signs and evidence conventions below.
If input validation fails, correct the reported field and run again. Before applying the result, check reference scope, model assumptions and any missing evidence or placeholder values.

Input field	Meaning	Value type	Requirement
callerFakeDoorExperimentClassIds	Caller fake door experiment class ids	list of string	Required
callerFakeDoorExperimentRequirements	Caller fake door experiment requirements	list of list of number	Required
observedFakeDoorExperimentEvidence	Observed fake door experiment evidence	list of number	Required
knownFakeDoorExperimentFlags	Known fake door experiment flags; binary 1=known, 0=unknown, in the order described below	list of number	Required

Supply nonempty unique class IDs and a rectangular binary requirement matrix with one row per class and one column per observed feature. Every class must require at least one positive feature. Supply aligned binary observation and known-flag lists. A requirement 0 ignores its column; a requirement 1 permits a class only if the feature is unknown or observed present. Fully witnessed classes require every required feature to be known present. Return all compatible and fully witnessed caller classes in caller order; unknown evidence can leave several candidates, and known absent required evidence excludes a class. The rubric is supplied rather than installed.

compatible={class:each required column is unknown or present}; witnessed={class:each required column is known present}

Use the exact units, boundary rules, ordering and missing-evidence conventions above.

Output field	Meaning	Value type
compatibleCallerClasses	Every supplied class whose required features are unknown or known present	list of string
fullyWitnessedCallerClasses	Every supplied class with all required features known present	list of string

json

{
  "input": {
    "callerFakeDoorExperimentClassIds": [
      "a",
      "b"
    ],
    "callerFakeDoorExperimentRequirements": [
      [
        1,
        0
      ],
      [
        0,
        1
      ]
    ],
    "observedFakeDoorExperimentEvidence": [
      1,
      0
    ],
    "knownFakeDoorExperimentFlags": [
      1,
      0
    ]
  },
  "output": {
    "compatibleCallerClasses": [
      "a",
      "b"
    ],
    "fullyWitnessedCallerClasses": [
      "a"
    ]
  }
}

Limitations and assumptions

Features and criteria are independent annotations. Compatible candidates and retained unknown evidence do not establish an identity, interpretation, overall pass or permission.

All listed fields require explicit values. Unexpected fields, incorrect types, nonfinite numbers and sparse evidence arrays fail validation; the specific bounds and alignment requirements are stated above. Extremely large inputs or outputs can also be rejected. An input error is distinct from a successful result reporting false, no matches or missing evidence.

Alternative or Complementary methods

Use Concierge Mvp vs Wizard of Oz Classifier for this related task: Concierge and Wizard-of-Oz experiments differ in how service delivery is presented and performed.

Use Pivot Or Persevere Decision Checklist when its separate inputs and assumptions fit the question: Pivot-versus-persevere reviews compare independently established observations with a decision rubric.

References

Fake Door Landing Page Validation Setup — tool.io

Similar or alternative tools

Concierge Mvp vs Wizard of Oz Classifier
Concierge and Wizard-of-Oz experiments differ in how service delivery is presented and performed.
Pivot Or Persevere Decision Checklist
Pivot-versus-persevere reviews compare independently established observations with a decision rubric.