- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
The paper studies factor-specific training-data attribution for diffusion models. It argues that existing methods summarize influence as one scalar per training example, which mixes semantic factors and hides when and how influence arises during denoising. It therefore proposes to attribute factor-induced internal response trajectories instead. The method, CADT (Concept Attribution through Dynamic Trajectories), ranks training images by their relevance to one factor (shape, colour, class, style or object) of a generated query. Each image, whether a training image or the query, is forward-noised to a set of timesteps. At each noisy state, the frozen denoiser is run twice, once with the target condition y_c and once with a matched reference y_ref(c). The difference of the intermediate activations at selected layers is called the counterfactual response (Eq. 6).
The experiments cover three settings: a synthetic shape/colour benchmark with a held-out compositional combination; CIFAR-100, with hierarchical retrieval from a model conditioned only on animal/plant and with 20% label flipping; and ArtBench-2/5 with an SD-v1.4 LoRA, for pure-style and object–style queries. All main results are reported as P@K against factor labels, in comparison with TRAK, D-TRAK, DAS and Journey-TRAK, and CADT obtains the highest precision in most settings.
Critical strengths
A gradient-free formulation of factor-specific attribution. CADT isolates a factor by contrasting the denoiser’s activations under a target condition and a matched reference condition at the same noisy state, and it needs only forward passes. Existing concept-level attribution, notably Concept-TRAK, requires a per-example parameter gradient for every training image. If validated, a forward-only alternative could make factor-level attribution cheaper and simpler to deploy. This is the main element that distinguishes CADT from prior work, and it is why I see potential in the direction. It does not change my recommendation, however. The paper does not explain why this activation-based score should reflect training influence. It reports no runtime or memory comparison, and the descriptor bank must be rebuilt for every target/reference pair. It also provides no counterfactual evidence that the retrieved examples are actually used by the model.
Critical weaknesses
Weakness 1: The claimed research gap does not exist, and the method does not answer the question it raises. The paper frames CADT as factor-specific, trajectory-level attribution, but both halves of this framing are already covered by prior work. Concept-TRAK (ICLR 2026) addresses the same task with the same mechanism: it contrasts the target condition with a condition from which the concept has been removed. It also introduced the synthetic benchmark used in §5.2. Yet the paper mentions Concept-TRAK only in passing, does not explain how CADT differs from it, and reports no comparison with it. This holds even on Concept-TRAK’s own benchmark, although the authors have an implementation (App. J). On the temporal side, Journey-TRAK already attributes individual denoising steps, and later methods (D-TRAK, DAS, K-FAC/EK-FAC influence functions, Concept-TRAK) aggregate per-timestep terms by design; the paper’s own Eq. A31 decomposes Concept-TRAK scores over timesteps. CADT also does not deliver the promised “how”. For a given factor, it still outputs one scalar per training example, summed over all layers and timesteps (Eq. 14), and every experiment measures “which”. Its trajectory is obtained by forward-noising clean images, not from the generation process. This is consequential because the paper’s contribution rests on this framing. Without it, what remains is a change of signal (activations instead of gradients) and a whitened kernel, and neither is justified or supported by the ablations: in Table A1, plain cosine outperforms K_λ.
Weakness 2: There is no evidence that the score measures training influence. Gradient-based attribution is grounded in a counterfactual, namely how a utility changes when an example is removed and the model is retrained, and the paper itself states this definition in §3.2. CADT replaces gradients with a similarity between forward activations, but it gives no argument linking this score to that counterfactual. The leave-one-descriptor-out result concerns an auxiliary regression in descriptor space, and App. D concedes that the signal is not defined through training-induced parameter updates. The experiments do not close this gap. All main results are P@K against factor labels, which measures category retrieval and would be maximized by simply looking up images with the same label, yet no similarity baseline is reported. LDS is dismissed in App. E.1, although its utility can be made factor-specific and the authors already use the official ArtBench subsets to tune DAS (l. 867–868). The deletion experiments in App. I either evaluate no ranking (I.1) or compare only against random deletion (I.2), without same-style or other-method controls. The headline comparison is also structurally biased: in Table 1, a baseline that produces a single ranking cannot exceed 50% on average, and Concept-TRAK is absent. This is consequential because the paper’s central claim is attribution. Without either a theoretical link or causal validation, the results show only that CADT retrieves images sharing the query’s factor, not that the model relies on them.
Questions for authors
Clarification requests
- For a training example x_i, which condition pair does CADT evaluate in Eq. 6: the query’s y_c / y_ref(c), or a pair derived from x_i’s own label? Does CADT use training labels anywhere? This determines how §5.4 should be read. If training descriptors do not depend on training labels, then recovering flipped animals reflects content similarity rather than label-driven influence.
- In Tables 1 and 5, is each baseline scored with a single ranking per query against both factors? If so, a baseline’s average P@K in Table 1 cannot exceed 50%, and D-TRAK and DAS sit at exactly 50.00. Please state this explicitly and explain why you consider the comparison fair.
- Table 3 cannot be interpreted as written. For every method, the P@1 values of the two source groups sum to more than 100% (135% for CADT), and all values are multiples of 1/185. How are the queries divided between the two columns, and which ranking and candidate pool does each column use?
- Please specify the descriptor construction for each experiment. Are queries forward-noised from the final generated image? How many probes S are used, and is one noise draw shared across timesteps within a probe (otherwise the velocity in Eq. A3 differences independently noised states)? Which layers, timesteps and reference values y_ref(c) are used, and what are the block weights w_b? §4.4 says the weights are given in App. A, but they are not there.
- In Table 6, which component accounts for the jump from “+ Multi-seed stability” (35.24) to “Full CADT” (50.59)? Since plain cosine outperforms Kλ in Table A1, why is Kλ the default, and how does cosine perform on Tables 1, 2, 4 and 5?
- Appendix J conditions the CIFAR-100 model on fine classes, whereas §5.3 states that the model is conditioned only on animal/plant. Which model is used in App. J?
- DAS and Journey-TRAK are near chance on CIFAR-100 (Table 2). On the synthetic benchmark, D-TRAK’s factor bias is the opposite of what Concept-TRAK reports for the same setup. Which timesteps, projection dimensions and damping did you use for each baseline? Did you verify the implementations, for example by reproducing published LDS values?
- For the object–style experiment, what is the base rate of cat or dog content in the ArtBench training sets, and how accurate is the Qwen3-VL judge on a labelled subset? With 11 and 30 queries, an object P@1 of 9.09% on ArtBench2 corresponds to a single query.
Requests for additional evidence (these could change my assessment)
-
Can you provide an argument for why the activation-based score K_λ measures training influence? For example, derive a link to a model-level counterfactual via representer points, a gradient factorization, or the closed-form empirical denoiser. The leave-one-descriptor-out result concerns an auxiliary regression in descriptor space, and App. D concedes that the signal is not defined through training-induced parameter updates. If no such link exists, would you reframe CADT as factor-specific similarity retrieval?
-
Please add counterfactual validation. You already use the official ArtBench 50% subsets to tune DAS (l. 867–868), so you can report CADT’s LDS on them, both with the standard utility and with a factor-level utility such as a style classifier’s probability on fixed-seed regenerations. In addition, please run leave-top-K-out retraining for every method, with random same-label deletion as a control, and measure the drop in target-factor presence. For App. I.2, please also report the deletion ratio, the number of runs, the probe set, and the quantity plotted in Fig. A7.
-
Please report Concept-TRAK in Tables 1–5. It is listed as a baseline in §5.1, the synthetic benchmark of §5.2 is its own, and you already have an implementation (App. J). Please also explain how CADT differs from it methodologically. In addition, please include baselines that receive the same factor information, such as TRAK or D-TRAK with a contrastive utility or with Concept-TRAK’s set-level protocol. Please also include feature-similarity baselines: U-Net features without the contrast, CLIP/DINO, and CSD for style.
-
Can CADT output and validate stage-wise information, i.e., when or in which layer a training example acts? One test: check whether per-stage contributions predict the timestep profile of the change in denoising error after deleting that example, as in Fig. A6. If it cannot, would you present CADT as factor-specific “which” attribution and drop the “how” claim?
-
Please ablate the core components. First, the contrast itself: H(x_t, y_c) alone vs. H(y_c) − H(y_ref(c)). Second, a trajectory vs. a single timestep with spatial resolution held fixed. Third, the choice of y_ref(c). Please also report runtime and memory relative to TRAK, D-TRAK and Concept-TRAK, given that the descriptor bank must be rebuilt for every target/reference pair.
7 comments
Response to Reviewer vR52 (2/6): W2, evidence for training influence
Link to the counterfactual. The counterfactual definition of training influence requires model-level evidence. Following R1, we derived the corresponding exact model-level link under the closed-form empirical denoiser (GR 4/6): the first-order term of the leave-one-out change of the condition-contrast energy decomposes into a kernel weight that depends on the observed training label and on the log-SNR, the inner product of the condition responses of the query and of the training example, and bounded remainders; the full energy change also contains a second-order term. This decomposition gives CADT's response-matching signal a theoretical basis in the idealized model, while training influence in actual networks is tested by the deletion-and-retraining experiments (GR 5/6).
P@K is maximized by label lookup; no similarity baseline. This holds when labels are reliable, and it is why we added CLIP, DINOv2, CSD and text-retrieval baselines (GR 3/6). In label flip, looking up the corrupted training label does not help: flipped animals and genuine plants carry the same observed label. CLIP text retrieval scores 0.00% on flipped sources, CLIP image similarity 8.11%, Concept-TRAK 12.43%, CADT 37.84%. How this result should be read, given that CADT uses training labels, is discussed under Q1 (3/6).
LDS. We agree that both standard and factor-level LDS are valuable counterfactual tests. The utility of standard LDS is the whole-image denoising loss, which does not answer the same question as CADT's factor-specific score; factor-level LDS responds in a threshold-like rather than linear way when the target factor is common (consistent with the argument of Concept-TRAK), and it requires retraining many subset models, beyond our compute budget for this round (GR 6/6). We therefore added the leave-top-K-out retraining that you also suggested (GR 5/6).
Deletion experiments. We ran the test you propose in R2: leave-top-K-out retraining with random same-label deletion as control (GR 5/6). CADT-guided deletion gives the largest increase in target-class denoising error, is the only deletion whose 95% interval excludes 0, and is significantly above deletions guided by CLIP and Concept-TRAK; only 8–24% of the examples it selects belong to the target fine class, yet the effect is comparable to deleting 200 same-class images. The missing details of App. I.2 are given in GR 5/6, and its random group is a same-style control; I.1 indeed evaluates no ranking, which the text already states.
Structural bias of Table 1. This is explained under Q2 (3/6); Concept-TRAK results in the setting of Table 1 are in GR 2/6.
In sum. Around W2, we added three kinds of direct evidence: a model-level theoretical link (GR 4/6), feature-similarity baselines (GR 3/6), and deletion-and-retraining experiments with a same-label random control (GR 5/6).
Response to Reviewer vR52 (3/6): Clarifications Q1–Q4
Q1. Which condition pair for a training example? Are training labels used? A pair derived from the example's own observed label; CADT does use training labels. CIFAR-100: is the observed (possibly flipped) class and the other class. Synthetic: the example's own shape/color with only the target factor flipped. ArtBench pure style: its own caption "a {style} painting" vs. the empty prompt. The only exception is the object head of object–style, where all training images use the query's object word vs. the empty prompt.
Sec. 5.4 should be read as follows: flipped animals and genuine plants have the same observed label (plant), so the label cannot separate them; among identically labeled examples, CADT separates them by the model's condition-contrast response (flipped sources 37.84 / 38.27 / 37.51 / 34.42, chance ≈ 5.9%; genuine plants 97.30 / 95.46 / 95.51 / 94.53). We tested your alternative directly with a label-free variant in which every training example gets the query's condition pair:
| CADT (own label) | Label-free | |
|---|---|---|
| Hierarchy P@5 (mid / fine) | 50.59 / 21.68 | 39.62 / 16.00 |
| Label flip, average P@1 | 67.57 | 45.41 |
| – flipped animal P@1 | 37.84 | 5.95 |
| – genuine plant P@1 | 97.30 | 84.86 |
| Synthetic OOD P@1 (shape / color) | 91.20 / 90.80 | 89.30 / 23.50 |
Without labels, the share of flipped sources in the top-10 of flipped-animal queries falls from 37% to 6% and that of ordinary animals rises from 2% to 60%: pure response similarity retrieves "animal content", not "animals learned as plants". This matches the derivation in GR 4/6, where the observed label enters only through the gate : the label decides in which condition an example took part in training, and the response separates examples within that condition. So you are right that recovering flipped animals is not label-free; but it is not label lookup either.
Q2. Single ranking and the 50% bound in Table 1. Yes. Each whole-image baseline scores both factors with the same single ranking, and since the query's factor combination is held out, a training example shares at most one factor with it; shape and color precision sum to at most 100%. Concept-TRAK results in the setting of Table 1 are in GR 2/6, and the contrastive TRAK/D-TRAK are in our response to GQFn, 1 (cont.).
Q3. Table 3. The table contains 370 queries, all generated under the plant condition and split by a frozen classifier trained on clean labels into 185 visually-animal queries (relevant set: the 1,574 animals relabeled as plant) and 185 visually-plant queries (relevant set: the 6,298 genuine plants). Each column is computed only on its own 185 queries, hence multiples of 1/185; the two columns are independent results on two disjoint query groups, not a split of one ranking, so they need not sum to 100%. Each column uses the method's ranking for that query (the whole-image ranking for whole-image methods, the plant-vs-animal factor ranking for CADT and Concept-TRAK) over all 26,500 training candidates.
Q4. Descriptor construction.
| Synthetic | CIFAR-100 | ArtBench | |
|---|---|---|---|
| Query states | forward-noised final generated image | same | VAE latent of the generated image, forward-noised |
| Probes | 1 (training), 5 (query) | same | same |
| Noise within a probe | one draw shared across timesteps | same | same |
| Layers (resnets.0) | 10: down0–3, mid0–1, up0–3 | 6: down0–2, mid, up1–2 | 7: down0–2, mid, up1–3 |
| Timesteps | 13-point grid 900→100, refined at low noise; 200→100 selected on the 500 selection queries | 900→100, step 100; last third | 900→100, step 100; last third |
| Reference | flip only the target factor | the other class | style: empty prompt; object–style: object prompt (style head), "in the style of {style}" (object head) |
| Block weights | 0.5 energy family, 0.5 velocity family, uniform over layers | same | same |
Since one noise draw is shared across timesteps within a probe, the velocity of Eq. A3 differences responses under the same noise. The block weights were missing from App. A; this was our omission, and they are given in the table above.
Response to Reviewer vR52 (1/6): W1, research gap and positioning
Thank you for the exceptionally detailed review. We carried out the work closely following your requests R1–R5; questions shared by several reviewers are answered in the General Response (GR) 2–6.
Factor-specific attribution and Concept-TRAK. Concept-TRAK and CADT both isolate the target factor through a condition contrast. They differ in where the contrast is applied and in the signal that is compared: Concept-TRAK writes the contrast into a scalar utility and compares projected parameter gradients, whereas CADT builds the condition contrast on the internal activations of the frozen denoiser and compares how the response is distributed over layers and evolves over noise levels. The quantitative comparison in all settings of Tables 1–5 and the implementation are in GR 2/6. One further clarification: the benchmark of Sec. 5.2 was built by us following the design of Concept-TRAK, whose original data are not public, so the numbers in the two papers cannot be compared directly.
Temporal side. Journey-TRAK computes attributions for individual sampling steps, and D-TRAK, DAS and Concept-TRAK aggregate per-timestep scalar terms. CADT keeps an ordered, layer-resolved sequence of condition responses together with their change between adjacent noise levels; a simple sum cannot retain these structures. In Table 6, adding the temporal direction to response energy raises mid-level P@5 from 13.73 to 31.57. The new single-timestep control shows that the full trajectory is better than the best single timestep on fine-class retrieval (P@5 21.68 vs. 19.89); the best timestep also depends on the target factor, e.g. t=900 for shape, t=600 for color and t=100 on CIFAR-100 (see R5 in 6/6).
The "how" claim (also R4). By "how" we mean how the internal response to the target factor is distributed over network layers and how it evolves along the denoising timesteps; CADT does provide this structural information. The attribution score of Eq. 14 is a sum of block interactions indexed by layer and timestep, so every attribution comes with a layer–timestep decomposition. The paper analyzes this structure: Figs. 4–5 and Table A2 show that shape and color depend on different network layers (d1 and d0) and share a late interval (t=300→100); App. J shows that two training examples with nearly identical Concept-TRAK scores have different layer–time response patterns; Fig. A6 shows that the effect of deleting training data also varies over timesteps. The new ablations further show that the stage structure matters for attribution: restricting the descriptor to the late interval raises mid-level P@5 from 35.24 to 50.59 (Table 6; component-wise decomposition in our response to ubCe, 4(b)), and the most informative stage differs across factors. The per-example deletion-and-retraining profile test suggested in R4 requires larger-scale experiments and could not be completed in this round; we regard it as a complementary validation of the existing layer–timestep analysis (see 5/6).
Trajectory from forward-noising, not from generation. This is a deliberate design. The response trajectory is defined as the ordered responses of the trained denoiser over a sequence of noise levels; queries and training examples are forward-noised in the same way, so that every stage is compared at a matched noise level. A training image has no corresponding generation path, so the sampling path of a query could not be aligned with the training examples. The settings are given in Q4 (3/6).
Signal and kernel. The conclusion of Table A1 is confirmed on label flip and on the synthetic model (cosine better) and reversed on ArtBench style (style head of ArtBench5 object–style: Kλ 90.00 vs. cosine 46.67). No scoring function dominates; results of all three on every main task are in GR 3/6, and we agree that the descriptor matters more than the kernel. Whether activations are a justified signal is addressed in GR 4/6 and GR 5/6.