AI4S.fyi Evidence Framework

How we think about AI for Science

The hardest question is not whether AI can make a prediction. It is whether a scientific system can learn from the world.

UNDERSTANDWhat do we know?
CHOOSEWhat should we try?
TESTWhat happened when we tried?
LEARNWhat should change now?

THE LOOP

Scientific learning requires four actions

01

Understand what we know

This contains two distinct abilities. Reading existing science recovers what papers, figures and databases already say. Modeling the system predicts states that have not yet been observed.

02

Choose what to try

Candidates usually exceed the experimental budget. A useful decision system must do more than rank answers: it must justify where the next dollar, hour or experiment should go.

03

Test against reality

Simulation and proxies can filter candidates, but new evidence often appears only after synthesis, execution and measurement. Measurement itself can introduce noise, drift and failure.

04

Learn from the result

A loop closes only when a new observation changes the model or next decision. The stronger test is whether that change makes the next round better.

STRESS TESTS

Four ways a promising result can fail

It works—until the setting changes.

Generalization

Does the result survive a new material, molecule, laboratory or data distribution?

It looks convincing—but the evidence may be weak.

Trust

Do predictions correspond to reality, and can measurements be calibrated, inspected and repeated?

It works once—but not at useful scale.

Scale

Do throughput, failure rate, time and unit cost support sustained operation?

Every component works—but the system does not.

Integration

Can models, software, instruments, automation and human exceptions form a stable workflow?

EVIDENCE

Not all evidence touches reality in the same way

  1. 01

    Retrospective or simulated

    Uses existing data or simulated environments. Useful for comparison, but the dataset can be mistaken for reality.

  2. 02

    Prospective in silico

    Makes a prediction before the answer is known. This limits hindsight, but may still rely only on computational proxies.

  3. 03

    Physical validation

    Real synthesis, measurement or clinical observation places the claim in contact with the physical world.

  4. 04

    Closed-loop experimentation

    Results return to the system and change the next model or experimental choice.

  5. 05

    Field or production use

    The system enters real scientific, clinical or industrial workflows and faces long-term operation, recovery and cost.

Moving closer to reality does not automatically make a claim correct. It exposes the system to different—and usually harder—ways to fail.

AGENCY

Who actually did the work?

“AI discovered” often compresses several roles into one phrase. Separating them shows how far autonomy actually travelled.

Human

People define the problem, constraints and success criteria, and adjudicate ambiguous results.

AI

Models propose hypotheses, predict outcomes or select the next action.

Automation

Robots and software execute a predefined workflow.

Shared

People, models and automation jointly make decisions and carry them out.

CLAIMS

Scientific claims change

We do not label an entire paper “true” or “false.” Important claims are tracked separately and updated as new evidence appears.

Original claimIndependent reanalysisCorrection or disputeCurrent interpretation
Supported · Corrected · Reframed · Contested · Refuted · Untested

CANON

Canon does not mean “best paper”

A work can become Canon because the field cannot explain its current methods, validation standards, failures or controversies without it. Canon is not an honor roll; a canonical claim may later be corrected or even refuted.

THE LIBRARY

How the library evolves

Watchlist

Worth watching.

Frontier

Actively changing the field.

Canon

Impossible to route around.

Archived

No longer active, but historically preserved.

CONTEXT

Science does not happen in a vacuum

Funding, institutions, policy and infrastructure shape which questions get pursued and which systems can be built. We track that context while reading it separately from evidence that a scientific capability works.

What we are ultimately trying to see

Can AI move from understanding what is known, to choosing what to test, to learning from reality—and do so reliably enough to change how science is done?

Explore the evidence