Risk-driven Online Testing and Test Case Diversity Analysis for ML-enabled Critical Systems (Replication Package)
Bibliographic record
Abstract
This repository contains the replication package as well as obtained results for the study titled "Risk-driven Online Testing and Test Case Diversity Analysis for ML-enabled Critical Systems". These include simulation control script, simulation file, test output and evaluation scripts. <strong>Hint:</strong> [search algorithm] refers to ES, GA, SA or RS. For instance, <em>cais_zmq_[search algorithm].py</em> could be <em>cais_zmq_ES.py </em>or <em>cais_zmq_GA.py </em>etc. <em>cais_scenario.ttt </em>is the actual simulation file and is loaded into CoppeliaSim <em>cais_zmq_[search algorithm].py </em>is the control script for each search algorithm and connected via the ZMQ <em>zmqRemoteApi</em> package file <em>clusterdata[search algorithm].csv</em> contains the output from clustering all test evaluations for the respective algorithm <em>result_evaluation.py</em> is the evaluation script <em>Distribution.pdf</em> is related only to distribution of failed evaluations <em>evaluation results.zip</em> contains outcomes from test data analysis (<em>grouped[0,1,2].pdf</em> are boxplots for failed, false "positives" and passed evaluations respectively) <em>README.md</em> instructions to run replication package <em>result_[search algorithm].txt </em>all test evaluations per algorithm <em>run_details_[search algorithm].csv </em>objective function output and time taken for each test evaluation per algorithm <em>vargha_delaney.py</em> python module for Vargha Delaney effect size determination <strong>Note:</strong> Instructions to run the package can be found in <em>README.md</em>
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".