Observed since 20 Oct, 19:47 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
TRIM (Transfer Refined Iterative Modeling) builds an accurate predictive model from a small dataset by iteratively sampling a Discovery Space.
ado-trim is an operator plugin for the
Accelerated Discovery Orchestrator (ADO),
providing the Transfer Refined Iterative Modeling (TRIM) characterization
operator.
TRIM is designed to efficiently build a surrogate model of a complex system. It is ideal for scenarios where exploring a parameter space is time-consuming or expensive. TRIM intelligently samples just enough points to create a stable and accurate predictive model, saving significant time and resources.
The TRIM operator works in two main phases:
No-Priors Characterization: If the system has not been measured before, TRIM starts by sampling a small, representative set of points using a space-filling algorithm to get a baseline understanding of the parameter space.
Iterative Modeling: This phase begins by using all currently available data to train a single preliminary surrogate model. The feature importance from this model is used to order for all remaining unmeasured points. TRIM then enters a loop where it:
This loop continues until the improvement falls below the configured thresholds
or the sampling budget is exhausted. TRIM then trains one high-quality final
model on all collected data and saves it to {outputDirectory}_finalized/
(defaults to trim_models_finalized/ in the directory you run
ado create operation from), alongside a model_card.json file.
The stopping_criteria_satisfied field in model_card.json is true when
TRIM stopped because the convergence thresholds were met, and false when the
sampling budget was exhausted first.
It also outputs a file containing the measured values and predictions for all
points in your space.
You can install the TRIM operator and its dependencies (including ado-core)
directly from PyPI:
pip install ado-trim
To learn more about TRIM and explore the full capabilities of ADO, including detailed documentation, configuration guides, and additional examples, visit the official ADO website:
Download counts and popularity will appear here as the collector receives them.
| Version | Published | Direct dependencies | Open version |
|---|---|---|---|
| 2.2.4 | 14 Oct 2026 | 6 |
This describes our collected data; it is not a security assessment.
Observed since 20 Oct, 19:47 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package:12508a780b9dea79b2f45a7ac0619ca1a150a4ed6520074f7361d7b60dfa5359