- Rating
- 2
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper introduced a method of explainable AI exploiting biological taxonomy. The method proposes to use pinball head as an interpretable hierarchical classifier, and the produced barcode as an auditable feature. Also some theoretical derivations are provided. Different downstream tasks like stacked MNIST, CIFAR generation, etc. are evaluated.
Critical strengths
This paper provides method to train pinball head as an interpretable classifier, based on top-down mold bonus and bottom-up max-dominance. Theoretical derivation is provided to guarantee strict depth monotonicity for hierarchical trait distance. Several different benchmark results are provided, including MNIST classification and CIFAR generation. In addition, the proposed method is applied to prior Concept Bottleneck Models as a backend to demonstrate its high compatibility.
Critical weaknesses
The proposed hierarchy is functionally equivalent to a classical flat Maxout classifier. Its structural contribution comes primarily from the regularization and interpretation imposed on the terminal units. The paper lacks sufficiently strong competing methods for its central auditing claims. There is no comprehensive comparison against simpler auditing alternatives, such as clustering pretrained embeddings, learned mixture models, prototype methods, or subclass discovery approaches. The experiments do not convincingly establish that barcode monitoring detects hidden intra-class shifts better than simpler alternatives. Table 2 reports an OOD test accuracy increase from 87.12% to 92.48%. However, ATCG involves additional training stages, backbone fine-tuning, extra parameters, and two regularizers. Semantic interpretability of learned traits remains insufficiently validated. The central claim is that basis traits expose meaningful intra-class factors. Yet most structural evaluations measure activation overlap, sparsity, factor purity, or barcode prevalence. Different training runs may discover equivalent prediction functions with different trait identities or hierarchies. The paper reports seed-level accuracy and barcode-category statistics but does not provide reproducibility of specific discovered traits, their semantics, or their correspondence across runs. Barcode-based error detection is not evaluated. The paper does not evaluate error-detection AUROC/AUPRC, selective-classification risk–coverage curves, or improvements over confidence-based rejection and other uncertainty measures. The CBM extension demonstrates limited improvement. The inference latency, memory overhead, monitoring throughput, and the practical tradeoff between hierarchy depth and auditing resolution are not systematically evaluated
Questions for authors
Since recursive Max-Dominance is mathematically equivalent to taking the maximum over terminal traits, what benefit does the hierarchical structure provide over a flat Maxout classifier? Could the authors compare against a parameter-matched Maxout model with similar regularization? How can the learned traits correspond to meaningful latent factors rather than arbitrary partitions of the embedding space? Are trait identities and semantic interpretations stable across different training seeds? What additional detection or localization capability does ATCG provide over conventional embedding-based clustering? Could we compare against a conventional classification head trained with the same computational budget and consistency regularization? Although barcode categories correlate with prediction errors, does barcode-based auditing outperform conventional confidence and uncertainty measures in detecting incorrect predictions? Could the authors report AUROC, AUPRC, or risk–coverage comparisons against maximum softmax probability and entropy-based baselines? The depth-monotonicity and bi-Lipschitz results characterize a weighted hierarchical distance. How do these guarantees translate into improved auditing performance? Can we empirically demonstrate that the proposed distance provides advantages over Hamming or conventional embedding distances?
7 comments
Further responses to questions and weaknesses
1. Hierarchy versus flat Maxout.
We agree that recursive Max-Dominance and a terminal maximum give the same class score. The hierarchy contributes through Molding Bonus's sibling relationships and recursively defined contexts, which are retained for inspection.
We compared parameter-matched flat Maxout heads using the same backbone, terminal capacity, consistency loss, and two-stage training protocol. The flat alternatives omit Molding Bonus or replace it with orthogonality or Information Maximization. Three-seed means on Camelyon17-WILDS are:
| Method | Dead winner (%) | OOD test accuracy (%) |
|---|---|---|
| ATCG | 8.9 | 92.48 |
| Flat + consistency | 96.9 | 88.53 |
| Flat + consistency + Orth | 96.9 | 88.49 |
| Flat + consistency + InfoMax | 60.4 | 91.53 |
A dead winner is never selected as the within-class argmax on clean training images of its own class; this measure is threshold-free. InfoMax improves utilization, while ATCG achieves substantially broader utilization with higher mean accuracy. This supports the proposed structural training relative to the tested non-hierarchical alternatives.
2. Additional localization capability over clustering.
We thank the reviewer for suggesting a direct comparison with embedding clustering. We added matched-k-means and GMM baselines to evaluate how many affected and distinct changed modes can be identified within an inspection budget. We report the results on Stacked-MNIST.
Clustering is fitted to baseline training embeddings within each predicted class, with matched to the training-observed Stage 2 barcode count. The reference and target are separate held-out generated cohorts of 60,000 images each, distinct from the training population used to fit clustering and determine . All grouping methods use the paper’s Z statistic and method-specific Bonferroni correction at over groups observed in either cohort. Inspection quotas are proportional to significant positive frequency changes; within each group, images are ordered by the corresponding model's own low MSP. Exhausted candidate pools are not replenished. This additional comparison uses occupied-group correction; the original Table 3, including its stricter correction and Novel-10 Recall@3 of 0.6, remains unchanged.
Here, a mode is a Red–Green digit combination; Recall@3 measures the fraction of manipulated modes appearing among the three most frequent modes in at least one flagged group. Under this comparison protocol, both ATCG stages and both clustering baselines achieve 100% mode Recall@3 on Missing-1/2/10 and Novel-1/2. For Missing-10, Stage 1 and Stage 2 localize the changed modes through 24.3 ± 2.9 and 22.0 ± 2.6 Loss groups, respectively, compared with approximately 60 for either clustering method. For Novel-10, Stage 1 achieves 73.3 ± 11.5% mode Recall@3, versus 83.3 ± 15.3% for k-means and 70.0 ± 10.0% for GMM; Stage 2 increases the mean to 86.7 ± 15.3%. Thus, useful localization is already present in Stage 1 with the backbone weights frozen and improves on average after Stage 2 refinement.
The table reports affected images identified in Novel-10, which contains 6,042 affected images among 60,000 target images. Values are mean ± sample SD across three seeds. Parentheses indicate actual inspections when candidate pools are exhausted; otherwise, actual inspections equal the budget.
| Budget | Baseline MSP | Baseline k-means + MSP | Baseline GMM + MSP | Stage 1 Barcode + MSP | Stage 2 Barcode + MSP |
|---|---|---|---|---|---|
| 100 | 17.3 ± 4.7 | 62.3 ± 7.5 | 54.7 ± 12.9 | 53.7 ± 1.2 | 61.3 ± 6.7 |
| 300 | 60.3 ± 3.8 | 182.0 ± 20.5 | 168.3 ± 26.0 | 163.0 ± 6.9 | 181.3 ± 9.5 |
| 500 | 106.3 ± 7.2 | 291.0 ± 39.0 | 280.3 ± 39.0 | 264.7 ± 14.0 | 301.7 ± 11.0 |
| 1,000 | 223.7 ± 15.9 | 554.3 ± 69.9 | 537.3 ± 66.9 | 502.3 ± 16.6 | 592.3 ± 35.6 |
| 3,000 | 653.3 ± 41.9 | 1,284.3 ± 244.2 (2,677.3 ± 387.2) | 1,080.0 ± 274.0 (2,296.0 ± 457.8) | 1,314.7 ± 218.5 | 1,668.0 ± 93.6 |
| 5,000 | 1,035.3 ± 83.1 | 1,368.3 ± 361.1 (2,919.0 ± 747.7) | 1,080.0 ± 274.0 (2,296.0 ± 457.8) | 1,740.7 ± 508.0 (4,469.3 ± 919.1) | 2,454.7 ± 155.2 |
Stage 2 is comparable to k-means at small budgets and identifies more affected images on average at 500–1,000 actual inspections. At larger budgets, clustering exhausts its significant candidate pools, while barcode-guided inspection continues to identify affected images. The larger 5,000-budget difference therefore reflects broader coverage together with additional inspection, rather than an equal-cost advantage.
At 500 inspections, the selected images represent 9.7 ± 0.6 of the 10 novel modes for Stage 2, compared with 9.3 ± 0.6 for k-means and 7.7 ± 0.6 for GMM, counting a mode as represented when at least one image is selected. At 1,000 inspections, Stage 2 and k-means both represent 9.7 ± 0.6 modes. This measures breadth of coverage, not balanced recovery across modes.
3. Semantic meaning and stability across seeds.
We thank the reviewer for requesting semantic evidence on real-world data and across training runs. We added Waterbirds experiments with a SigLIP2 vision–language backbone, using depth-4 hierarchies throughout. We examine the training population to characterize the organization learned by ATCG, using semantic descriptions assigned afterward by the unchanged pretrained image–text encoder. These descriptions do not supervise the traits.
Across three seeds, Stage 2 achieves 94.67% test accuracy and 85.41% worst-group accuracy, compared with 93.76% and 79.60% for the 10-epoch fully fine-tuned baseline. ATCG starts separately from the original pretrained encoder, with five frozen-backbone epochs followed by five joint fine-tuning epochs. Worst-group accuracy uses the four bird-class × background groups.
Semantic organization is already present in Stage 1. Eight of the nine examined background and appearance descriptions have significantly enriched landbird groups in both stages across all three seeds. These associations are assessed within the same true bird class using two-sided Fisher exact tests, with Holm correction over the full trait–concept family.
We additionally test whether sibling branches have different semantic distributions, rather than only testing individual traits against their surroundings. We compare images activating only one sibling, report jointly activated images separately, and use permutation tests of the complete semantic distribution. Holm correction covers all 540 planned comparisons across both class trees, three semantic families, both stages, and three seeds.
The table gives the number of significant sibling contrasts among all 15 sibling pairs in the landbird tree. Each entry is Stage 1 → Stage 2.
| Semantic family | Seed 123 | Seed 456 | Seed 789 |
|---|---|---|---|
| Background | 7 → 7 | 7 → 7 | 8 → 4 |
| Belly colour | 10 → 13 | 7 → 11 | 9 → 12 |
| Wing pattern | 10 → 13 | 7 → 9 | 8 → 11 |
Thus, sibling-level semantic differentiation occurs in every run before backbone fine-tuning. Stage 2 yields more significant appearance contrasts in all three runs, although background contrasts do not consistently increase.
A concrete example illustrates shared background association with contrasting appearance associations. In seed 123, two child branches predominantly contain broadleaf-labelled images but differ in wing pattern:
| Stage | Left-only images | Spotted / solid | Right-only images | Spotted / solid |
|---|---|---|---|---|
| 1 | 77 | 42.9% / 33.8% | 233 | 9.0% / 79.0% |
| 2 | 151 | 65.6% / 23.2% | 343 | 2.9% / 92.1% |
The complete wing-pattern distributions differ in both stages (Holm-adjusted Monte Carlo ); Cramér's V increases from 0.446 to 0.752 in this example. At Stage 2, broadleaf labels account for 93.4% and 88.9% of the two exclusive groups. Joint activation remains possible: 216 and 48 shared images in Stages 1 and 2 are reported separately.
Elsewhere in the same tree, upper branches exhibit bamboo versus broadleaf associations, while deeper siblings exhibit brown-belly/striped-wing versus yellow-belly/solid-wing associations. This provides an inspectable account of shared and differentiated descriptions within the class-score hierarchy. The waterbird tree shows weaker wing-pattern differentiation, which we retain in the complete results.
4. Hierarchical barcode distance
In response to the question “Can we empirically demonstrate that the proposed distance provides advantages over Hamming distance?”, we additionally examined the learned organization on CIFAR-100 Superclass across three runs initialized from the same pretrained checkpoint. We assessed whether distances distinguish images from the same versus different fine classes within each superclass. We distinguish the empty barcode (no basis trait meets the activation threshold, ≥5.5) from nonempty barcodes (one or more basis traits meet this threshold). An empty barcode indicates absent above-threshold trait evidence, rather than a shared semantic identity.
Excluding empty barcodes, our hierarchical barcode distance performs better than terminal Hamming in all three runs of both stages, on both the training and test sets:
| Fine-class separation AUROC | Training: Stage 1 | Training: Stage 2 | Test: Stage 1 | Test: Stage 2 |
|---|---|---|---|---|
| Terminal Hamming | 0.815 ± 0.001 | 0.798 ± 0.0005 | 0.833 ± 0.001 | 0.822 ± 0.002 |
| HBD | 0.832 ± 0.003 | 0.826 ± 0.004 | 0.855 ± 0.003 | 0.850 ± 0.004 |
AUROC is first computed within each superclass and macro-averaged across superclasses; values are mean ± sample SD over three runs. Within each stage and split, both distances use identical image pairs from the common cohort whose true-superclass barcodes are nonempty in all three runs. These results support fine-class organization in the decision hierarchy among images with activated trait evidence.
Response to Reviewer 6VfE
We thank the reviewer for recognizing our purpose of using the Pinball head as an interpretable hierarchical classifier and the produced barcode as an auditable feature, as well as for pointing out our key strengths: providing theoretical derivations to guarantee strict depth-monotonicity for hierarchical trait distance; providing several benchmark results including synthetic MNIST and CIFAR generation; and demonstrating high compatibility through application to Concept Bottleneck Models (as a backend).
Before addressing the weaknesses and responding to specific questions, we would like to clarify three points in our manuscript that may have contributed to the reviewer's criticism regarding presentation:
First, there appears to be some confusion about whether the Pinball head is designed to compete with post-hoc auditing tools for auditing a standard deep classifier. The answer is no. Because the standard class-label decision step from the feature layer to the logit layer compresses intra-class heterogeneity too tightly, our goal is to introduce a new classification head that surfaces intra-class heterogeneity relevant to class prediction directly from the feature layer. Our approach inserts multiple structured layers of representation between the feature layer and the logit layer.
Through this construct, we make the decision logic at the classification head, how trait scores are aggregated into class scores, explicit for auditing. We use the term combinatorial auditing to highlight the diagnostic richness of these resulting barcode patterns.
Second, we clarify how our hierarchical trait distance and heatmap visualization directly operationalize our Diagnostic Utility claim—namely, using barcodes as auditing signals at both the sample and cohort levels to flag predictions lacking consistent evidence and to localize intra-class distribution shifts through changes in barcode prevalence. Clustered heatmaps are a standard diagnostic tool in genomics. In ATCG, their rows represent trait-activation patterns, and their columns follow the hierarchy used for class-score computation. By pairing ATCG's discrete multi-level trait representations with our proposed hierarchical trait distance, heatmaps become a powerful visual diagnostic aid: (1) At the sample level: A heatmap row makes a single prediction's decision logic immediately inspectable across trait layers, allowing an auditor to visually spot missing or conflicting trait activations (inconsistent evidence) without digging into black-box embeddings; (2) At the cohort level: Using our hierarchical trait distance to drive row clustering (as shown in Figure 3 for Camelyon17-WILDS and Figure 12 for generative structure fidelity) by shared decision pathways, visually exposing shifts in barcode prevalence across subpopulations or domains.
In responding to the reviewer’s last question concerning Hamming and embedding distances, terminal Hamming compares leaf-level activation patterns, while Euclidean embedding distance measures proximity in the encoder representation. HBD explicitly weights disagreements across trait layers. Its depth-monotonicity and conditional bi-Lipschitz guarantees characterize this hierarchical geometry, which we use to organize heatmaps for medical imaging (Figure 3) and generative models (Figure 12). The empirical comparison with terminal Hamming is reported below.
Third, we clarify the criticism regarding a "lack of sufficiently strong competing methods for its central auditing claim" and the absence of comparisons against "simpler alternative approaches." Because ATCG is an architectural classification head rather than a standalone post-hoc diagnostic, it does not replace existing auditing tools—instead, it provides a structured, multi-level representation space upon which those very tools can operate. Various existing auditing methods (such as clustering, distance-based outlier detection, or confidence calibration) can be directly applied to the basis traits and intermediate layers of ATCG to audit different types of distribution shift. While applying simpler post-hoc alternatives directly to a standard flat-head classifier requires auditing either a compressed logit layer or an entangled penultimate feature layer, ATCG exposes intermediate trait representations that are explicitly aligned with the decision logic, making downstream auditing with existing tools more informative.