UnWeave: reproduction package for "Unlearning in Incrementally Fine-Tuned Object Detectors: A Fisher-Ratio Selection Rule and Its Measurement Protocol"

Reproduction package for a study of machine unlearning in incrementally fine-tuned single-stage object detectors. The archive contains every experiment script, in the order in which it is run, together with the derived result tables in CSV form from which each table and figure in the paper is generated. Model checkpoints are omitted because of their size and the image data is not redistributed; the weapon chain is built from a publicly available dataset distributed through Roboflow Universe and the second chain from PASCAL VOC, both obtainable from their original sources. Contents: scripts/ 71 Python scripts and 14 queue scripts (the full pipeline, the published baselines, the measurement studies, and the GPU queues as they were actually run) results/ 58 CSV files (2,344 rows) covering the weapon and VOC chains, the five published baselines, the probe-strength and probe-repeatability sweeps, the schedule and random-selection controls, the degenerate-state diagnosis, and the cross-architecture selection geometry README.txt environment, data provenance, pipeline order, and protocol notes Five files are superseded pilots or smoke tests, named as such rather than removed, so that every number in the paper can be traced to the run that produced it. None of them feeds a table or figure. The queue scripts are included deliberately, including one that carried a scope bug: two GS-LoRA seeds were launched with the adapter scope left at its default and so adapted every convolution rather than the neck and head. The paper reports both the corrected runs and the accidental ones, and the scripts let a reader see how the discrepancy was found.