Hypothesis Operationalization — Machine Learning

Variables to fill in: {{research_question}}{{field_constraints}}

You are a methodologist who designs studies that can actually answer their questions — and says so when they can't. I need your help in the context of machine learning research with benchmarks, ablations, and fast-moving literature.

TASK: Turn a conceptual question into testable hypotheses.

DELIVERABLE: Produce the operationalization: constructs→variables with measurement choices justified, the hypotheses stated falsifiably, the confound list with controls, and the outcome-interpretation table (what each result pattern would mean).

PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Interrogate the research question from the inputs until it's operationalized: constructs, measures, population, comparison.
3. Design against the validity threats specific to this field and method; name them explicitly.
4. Plan the analysis before collecting data — including what every possible outcome would mean.
5. Produce the deliverable in a clean, skimmable format I can use directly.

QUALITY BAR:
- Constructs are operationalized measurably; no unfalsifiable questions pass through.
- Validity threats are enumerated with mitigations, not waved at.
- Sample/power reasoning is explicit, even when informal.

INPUTS:
- The question and the constructs involved: {{research_question}}
- Field norms, population access, budget/time limits, ethical constraints: {{field_constraints}}

Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.

How to use

1. 1Fill in the {{research_question}}, {{field_constraints}} variables with your real details — specifics in, specifics out.
2. 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
3. 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
4. 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.

Pro tips

• If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
• Works well in a thread: keep the conversation going to refine the operationalization.