anomaly_eval op• Data kinds: signal × signal → table
• Call: import fullseye as fs; fs.ledger.anomaly_image_auroc(scores, labels) (to call the implementation directly, import anomeval; anomeval.anomaly_image_auroc(scores, labels); from the registry, opsspc.get("anomaly_image_auroc"))
Image-level AUROC from one anomaly score per image and a good/defective label per image (table).
scores is a 1-D array (higher = more anomalous), labels the same length with 1 / True = defective. Exact Mann–Whitney statistic with mid-ranks for ties (Hanley & McNeil
1982): the probability that a random defective image outscores a random good one, ties counting 1/2. Returns auroc, n_pos, n_neg.
Raises ValueError on empty / mismatched / non-finite input, non-binary labels, or when all images carry the same label (AUROC undefined).
• Sample-data catalog (download URLs / licences) — 2-D uses skimage.data (BSD/public domain) plus synthetic images; 3-D lists download URLs for real data sources (Stanford, PDS, …).
• Operator provenance and references — the sources of the research/methods this op family came from.
• The canonical algorithm (author, year) and its uses are named in the family usage guide above.
• anomaly_eval_metrics — py -3.11 examples/anomaly_eval_metrics.py
• poc_good_sample_variation_model — py -3.11 examples/poc_good_sample_variation_model.py
• poc_patch_anomaly — py -3.11 examples/poc_patch_anomaly.py
table as input)msa_anova_table · msa_gauge_rr · msa_bias_linearity · msa_attribute_agreement · gum_standard_uncertainty · gum_propagate · gum_expanded · gum_monte_carlo
anomaly_eval)anomaly_pixel_auroc · anomaly_pro · anomaly_region_overlap · anomaly_pixel_f1_max · anomaly_image_f1_max · anomaly_operating_point
*Provenance: anomeval.py — SPC operator registry. This per-op note is generated by tools/opdocs.py md (do not hand-edit).*
© 2026 Kazufumi Furuse — Fullseye operator documentation. Licensed under Apache-2.0.