Overview

Machine learning models for automated analysis of quantum device data. Models power the analysis step of Control’s calibration loop, replacing hours of manual interpretation with structured, automated results. Use them during device tune-up and characterization to quickly extract key device parameters from your measurement data.

Regardless of the specific model, the SDK always wraps the response in a ModelResultInfo object:

FieldTypeDescription
idstrUnique identifier for the execution
modelstrName of the executed model
created_atdatetimeTimestamp (UTC) when the execution was created
input_file_namestrName of the uploaded input file
input_file_sizeintSize of the input file in bytes
outputDictModel‑specific output (boolean or dictionary)

Model Versioning

Our models use a versioning scheme (v0, v1, etc.) where higher numbers generally indicate improved accuracy and performance. When selecting a model version, consider:

  • Newer versions typically offer better accuracy and robustness
  • Specialized versions for specific data types or conditions
  • Performance variations based on your measurement characteristics

We recommend testing multiple versions to find the optimal one for your quantum device data.

Charge Stability Diagram Analysis

ModelDescriptionInput ShapeOutput KeysEndpoints
charge-stability-diagram-segmenter-v0Segments a charge stability diagram into different regions(128, 128)segmentationExecute
charge-stability-diagram-binary-classifier-v0-16x16Classifies a charge stability diagram as no dot, single, or double dot(16, 16)classificationExecute
charge-stability-diagram-binary-classifier-v1-16x16Classifies a charge stability diagram as no dot, single, or double dot(16, 16)classificationExecute
charge-stability-diagram-binary-classifier-v2-16x16Classifies a charge stability diagram as no dot, single, or double dot(16, 16)classificationExecute
charge-stability-diagram-binary-classifier-v3-16x16Classifies a charge stability diagram as no dot, single, or double dot(16, 16)classification, scoreExecute
charge-stability-diagram-binary-classifier-v0-48x48Classifies a charge stability diagram as no dot, single, or double dot(48, 48)classification, scoreExecute
charge-stability-diagram-binary-classifier-v1-48x48Classifies a charge stability diagram as no dot, single, or double dot(48, 48)classification, scoreExecute
charge-stability-diagram-transition-detector-v0Detects the locations of charge transition lines in a charge stability diagram(n, m)transition_linesExecute
charge-stability-diagram-transition-detector-v1Detects the locations of charge transition lines in a charge stability diagram(n, m)transition_linesExecute
charge-stability-diagram-transition-detector-v2Detects the locations of charge transition lines in a charge stability diagram(n, m)transition_linesExecute
charge-stability-diagram-transition-detector-v3Detects the locations of charge transition lines in a charge stability diagram(n, m)transition_linesExecute

You can see how to use the charge stability diagram models on the Charge Stability Diagram Models page.

Coulomb Blockade Analysis

ModelDescriptionInput ShapeOutput KeysEndpoints
coulomb-blockade-classifier-v0Determines if a current measurement exhibits Coulomb blockade characteristics(n, )classificationExecute
coulomb-blockade-classifier-v1Determines if a current measurement exhibits Coulomb blockade characteristics(n, )classificationExecute
coulomb-blockade-classifier-v2Determines if a current measurement exhibits Coulomb blockade characteristics(128, )classification, scoreExecute
coulomb-blockade-classifier-v3Determines if a current measurement exhibits Coulomb blockade characteristics(128, )classification, scoreExecute
coulomb-blockade-peak-detector-v0Detects the locations of Coulomb blockade peaks in current measurement(n, )peak_indicesExecute
coulomb-blockade-peak-detector-v1Detects the locations of Coulomb blockade peaks in current measurement(n, )peak_indicesExecute
coulomb-blockade-peak-detector-v1-miniDetects the locations of Coulomb blockade peaks in current measurement(n, )peak_indicesExecute
coulomb-blockade-peak-detector-v2Detects the locations of Coulomb blockade peaks in current measurement(n, )peak_indicesExecute

You can see how to use the Coulomb Blockade models on the Coulomb Blockade Models page.

Note: coulomb-blockade-peak-detector-v1-mini is a quicker version of coulomb-blockade-peak-detector-v1 that gives a good trade-off between accuracy and speed.

Coulomb Diamond Analysis

ModelDescriptionInput ShapeOutput KeysEndpoints
coulomb-diamond-segmenter-v0Segments a Coulomb diamond conductance grid to Coulomb diamond regions(n, m)segmentationExecute
coulomb-diamond-detector-v0Detects the vertices of Coulomb diamond structures from a binary mask(n, m)diamond_verticesExecute
coulomb-diamond-detector-v1Detects the vertices of Coulomb diamond structures directly from conductance data(n, n)diamond_verticesExecute
coulomb-diamond-detector-v2Detects the vertices of Coulomb diamond structures directly from conductance data(n, n)diamond_verticesExecute

You can see how to use the Coulomb Diamond models on the Coulomb Diamond Models page.

Pinch-off Analysis

ModelDescriptionInput ShapeOutput KeysEndpoints
pinch-off-classifier-v0Determines if a current measurement exhibits pinch-off characteristics(n, )classificationExecute
pinch-off-parameter-extractor-v0Extracts key parameters from pinch-off measurements (cut_off_voltage, transition_voltage, saturation_voltage)(n, )cut_off_index, transition_index, saturation_indexExecute

You can see how to use the Pinch-off models on the Pinch-off Models page.

Turn-on Analysis

ModelDescriptionInput ShapeOutput KeysEndpoints
turn-on-classifier-v0Determines if a current measurement exhibits turn-on characteristics(n, )classificationExecute
turn-on-parameter-extractor-v0Extracts the threshold voltage from turn-on measurements(n, )threshold_indexExecute

You can see how to use the Turn-on models on the Turn-on Models page.

Resonator Spectroscopy Analysis

ModelDescriptionInput ShapeOutput KeysEndpoints
resonator-dip-finder-v0Detects resonator dips in spectroscopy magnitude traces(n,)dip_indicesExecute

You can see how to use the Resonator Dip Finder model on the Resonator Dip Finder page.