- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes Semantic Configuration Fields (SCF), a framework for analyzing how local label composition changes across network depth and neighborhood scale. At each layer and granularity, the method estimates a distance-weighted class posterior and computes its Shannon entropy, producing a layer-by-granularity field. The paper introduces descriptors (morphology) of this field, including depth organization slope, reconfiguration depth, and organization magnitude, together with an effective-neighbor validity gate and label-permutation calibration. Controlled synthetic experiments verify sensitivity to label composition at fixed geometry (Fig. 2). Experiments across five modalities illustrate that local label organization can continue changing after linear-probe accuracy largely saturates (Fig. 4). A four-seed benchmark, primarily comparing learning objectives with a shared ResNet-18 backbone on CIFAR-100, identifies different field profiles (Table 3). The permutation control further shows that some apparent morphology differences arise from geometric concentration rather than label-driven organization.
Critical strengths
A clear measurement framework for examining local label organization across depth and scale
The paper asks a well-defined question that linear-probe accuracy and representation similarity methods does not directly answer: how are labels distributed within local neighborhoods, and how does this distribution change across layers and neighborhood sizes? The field construction makes these two axes explicit rather than selecting a single layer or granularity. The audio example in Section 6, where entropy decreases at fine granularities but increases at coarse granularities, illustrates why examining multiple scales can matter. The experiments across five modalities also provide useful evidence that the construction applies beyond one architecture or data type.
The permutation-null analysis identifies an important confound in interpreting local entropy
Section 7.4 and C.3 shows that permuting the reference labels still produces systematic depth trends: deeper layers reduce the effective number of neighbors (via clustering), allowing chance label imbalances to lower entropy even with random labels. This substantially affects the morphology descriptors: 507 of 560 null descriptor vectors fall within the real regime clusters. These results demonstrate why raw entropy trends alone are insufficient evidence of label-driven organization. Subtracting the permutation-null mean provides a useful correction, and verify that every benchmarked system exhibits organization beyond its null baseline. This analysis strengthens the measurement framework by identifying a concrete confound and showing which findings persist after correcting for it.
Critical weaknesses
The additional insight provided by SCF over established multiscale neighborhood statistics remains insufficiently demonstrated
The paper explicitly acknowledges that its estimator is a Nadaraya–Watson posterior followed by Shannon entropy, so the contribution depends primarily on the field construction, descriptors, and calibration. However, Appendix C.4 reports that established local statistics separate the coarse regimes equally well, and that a multiscale kNN-entropy baseline reproduces the depth profiles of well-organized systems with correlation 1.00.
The proposed distinctions do not yet establish a clear advantage over this closest baseline. Sensitivity to minority-class composition distinguishes entropy from maximum purity, but is also available to kNN label entropy. Similarly, a joint distance–entropy signature and permutation calibration could be applied to that baseline. The synthetic composition experiments validate the estimator’s intended behavior, but the paper does not demonstrate a substantive representation-analysis conclusion that requires SCF rather than an established local statistic evaluated across layers and scales. This limits the significance of the proposed framework beyond organizing existing measurements into a common protocol.
The evidence for distinct, reproducible semantic morphologies needs to be reconciled with calibration and the reported descriptor values
The main benchmark mentions depth reversal and cross-granularity trend. However, Section 7.4 shows that the deep reversals disappear after calibration, while the calibrated cross-granularity trend becomes identical across CIFAR-100 systems. The paper acknowledges this distinction, but much of the morphology matrix and reliability analysis concerns the raw field. Consequently, it remains unclear how much of the claimed morphological diversity persists as label-driven structure beyond differences in organization magnitude.
There are also direct inconsistencies in the reconfiguration-depth evidence. Section 8 states that CE and SupCon differ sharply in reconfiguration depth, and Appendix C.5 describes SupCon as sharing an early-reconfiguration pattern. Yet Table 5 reports (L^*=0.60) for every CE and SupCon seed, as well as every SimCLR and VICReg seed. These discrepancies affect the argument that the descriptors identify complementary, system-specific organization patterns. A complete calibrated descriptor matrix and a consistent account of reconfiguration depth are needed to assess that central claim.
Questions for authors
-
Additional value over multiscale kNN entropy. Under the same validity and permutation-calibration protocol, which substantive findings does SCF reveal that multiscale kNN label entropy does not? Can the authors compare the calibrated descriptors and the joint distance–signature analysis directly?
-
Morphology after calibration. Which system differences in reconfiguration depth, curvature, and cross-granularity behavior remain reproducible after null correction? A calibrated counterpart to Table 3 would help distinguish semantic morphology from the raw-field concentration effects.
-
Reconfiguration-depth discrepancies. How should the claims about early reconfiguration in SupCon and several self-supervised systems be reconciled with Table 5, where these systems consistently have ()? Do the text and table refer to different fields or descriptor definitions?
W1 / Q1. Direct comparison with multiscale kNN
Thank you for requesting a direct comparison of the calibrated descriptors and the joint distance–signature analysis against multiscale kNN.
We added this experiment using identical four-quadrant data, splits, classifiers, and paired resamples (App. E.1). The standalone SCF signature achieves 0.884 accuracy, compared with 0.485 for multiscale kNN and 0.850 for support-matched kNN.
Importantly, SCF retains its advantage after geometric distance is included:
(d,ΓSCF): 0.913
(d,ΓkNN): 0.906
(d,ΓSM): 0.909
The paired gains are +0.0072 (95% CI [0.0049,0.0093]) over multiscale kNN and +0.0035 ([0.0013,0.0057]) over support-matched kNN.
The estimator analysis explains these differences. Support matching recovers much of the calibrated field structure (r=0.987), while continuous weighting contributes additional composition resolution. At identical per-query support, Gaussian and Epanechnikov weighting improve posterior KL relative to uniform voting by 0.138 and 0.127 nats in the primary synthetic comparison. SCF also achieves lower geometric leakage and posterior error in the factorial experiment (App. E.9–E.10).
These results demonstrate additional analytical information at the signature, joint-analysis, and calibrated-field levels.
W2 / Q2. What morphology survives calibration?
Thank you for requesting a complete evaluation of morphology after removing the geometric null baseline.
We now report all eight systems' calibrated descriptors in Tables 2 and 18. The strongest differences concern final-layer organization, depth accumulation, and curvature.
Across CIFAR-100 systems, Olast ranges from 0.091 for DINO-lite to 0.355 for CE-LS, while ΔZcal ranges from 0.023 to 0.286. Curvature also separates systems with similar directional trends: CE has 0.698±0.005, SupCon 0.492±0.041, and VICReg 0.294±0.039.
Calibration additionally changes system comparisons: the raw depth change is larger for VICReg than SimCLR, while their calibrated ordering is reversed (Fig. 2). The calibrated CIFAR fields exhibit predominantly shared directional trends but distinct organization magnitudes and trajectories. ESC-50 provides a complementary cross-modal result, with a significant opposing fine/coarse interaction after calibration (T=0.591 nats, family-wise p=0.0025).
Together, these findings establish reproducible differences in the strength, accumulation, and shape of target-associated organization.
W2 / Q3. Reconfiguration-depth discrepancy
Thank you for pointing out the discrepancy between the qualitative reconfiguration description and the reported L∗ values.
We have corrected the interpretation. The hard reconfiguration locator gives L∗=0.60 for CE and SupCon in every seed (Table 6), indicating a shared strongest transition location. Their calibrated fields nevertheless differ in final-layer organization (0.330 vs 0.285), depth change (0.261 vs 0.214), and curvature (0.698 vs 0.492). These measurements describe different aspects of the same depth trajectory.
We also introduced a continuous localization readout (App. C.4). On synthetic fields with known transition locations, its localization MAE decreases from 0.103 for hard argmax to 0.072–0.074 for the soft alternatives. This provides finer localization while retaining the calibrated magnitude and curvature descriptors as the principal comparisons.