Counterfactual Explanations via Inverse Constraint Programming
Bibliographic record
Abstract
It is increasingly recognized that automated decision making systems cannot be black boxes: users require insight into the reasons that decisions are made. Explainable AI (XAI) has developed a number of approaches to this challenge, including the framework of counterfactual explanations where an explanation takes the form of the minimal change to the world required for a user’s desired decisions to be made. Building on recent work, we show that for a user query specifying an assignment to a subset of variables, a counterfactual explanation can be found using inverse optimization. Thus, we develop inverse constraint programming (CP): to our knowledge, the first definition and treatment of inverse optimization in constraint programming. We modify a cutting plane algorithm for inverse mixed-integer programming (MIP), resulting in both pure and hybrid inverse CP algorithms. We evaluate the performance of these algorithms in generating counterfactual explanations for two combinatorial optimization problems: the 0-1 knapsack problem and single machine scheduling with release dates. Our numerical experiments show that a MIP-CP hybrid approach extended with a novel early stopping criteria can substantially out-perform a MIP approach particularly when CP is the state of the art for the underlying optimization problem.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.038 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.007 | 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 source (direct Gemma or distilled Codex), 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".