- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes FacCP, which separates local uncertainty estimation from global conformal calibration. Given a fixed predictor and a task-specific residual map , an input representation is trained using a leave-one-out energy-score objective. Kernel weights in the learned representation space are then used to estimate the conditional residual law as a weighted empirical distribution over a reference set. A geometry constructor (ellipsoid, hyperbox, KDE, or zonotope) maps the estimated law to nested residual sets, which induce a scalar nonconformity score calibrated using a single global split-conformal quantile. The theoretical analysis characterizes uncertainty-sufficient representations, studies the localization penalty induced by nuisance dimensions, and bounds conditional-coverage error in terms of score non-pivotality, which is itself controlled under a uniform geometry-approximation assumption. Experiments include a synthetic bivariate Gaussian setting, planar and 3D quadcopter reachability with trajectory-level conformal calibration, and autonomous-driving trajectory prediction on Argoverse 2, with capacity and data sweeps against resCONTRA and direct covariance prediction.
Critical strengths
- Learning the retrieval weights from an input representation trained with an energy-score objective, so that proximity reflects similarity of conditional residual laws rather than raw input proximity, is an interesting idea that could be valuable in high dimension.
- The experiments are indeed carried out on high-dimensional problems, although only one dataset is non-synthetic.
- One objection to this way of localizing the uncertainty score (here, the multivariate residuals) is that, unlike in Han et al. (Split Localized Conformal Prediction) or Plassier et al. (Rectifying conformity scores for better conditional coverage), the resulting score is not guaranteed pivotal. Under continuity and strict monotonicity of the score CDF at , those constructions allow the conditional coverage of the oracle score to be read off directly, so that conditional coverage error is quantified by the learning error of the score with respect to its oracle. Here this is no longer possible: one must additionally account for the pivotality gap of the oracle itself, analyzed through , which the authors attempt to do.
Critical weaknesses
- However, is then left uncontrolled: Thm. 4 assumes the geometry-approximation property (Assumption 3) that the energy-score objective should deliver, and Thm. 11 reduces to a triangle inequality plus DKW once , is given. Nothing connects the design choice — the energy-score objective — to or , even for the ellipsoidal constructor actually used, where equal-covariance laws with different tails already break pivotality. What is proved is standard; what is specific to FacCP is assumed. The analysis therefore names the right quantity but does not analyze it.
- The fact that the multivariate residuals are treated as a given object, produced by a black-box model, is not made sufficiently clear when the authors state that they do not learn a score. The residual T(X,Y) is itself a fixed vector-valued conformity score; the paper’s framing of “estimating the residual law rather than learning a score” conflates T with the induced scalar score . What FacCP actually does is learn an adaptive scalarization of a fixed multivariate score, which is precisely the setting addressed by recent multivariate conformal methods (Thurin et al., 2025; Klein et al., 2026; Kondratyev et al., 2026, Conrad et al., 2026) and should be positioned as such (even if they cite Thurin et al.).
- The experiments do not isolate the advantage of the proposed representation over alternative modeling choices: no ablation replaces the energy-score objective by an alternative representation objective while keeping retrieval, geometry construction and calibration fixed, and on Argoverse the pretrained encoder alone (without energy fine-tuning) is never evaluated, so the gain attributable to the method’s central component cannot be read off the results. Moreover, the comparisons are mainly against resCONTRA, direct covariance prediction and localized-quantile baselines; NLE and MVCS appear only on a single-mode. Since the method is an adaptive scalarization of a fixed multivariate residual score, the natural comparators are the other methods that learn or construct a residual geometry from such a score, e.g. OT-CP (Thurin et al., 2025), MultiDimSPCI (Xu et al.,, 2024), CopulaCP (Messoudi et al., 2021), CVQR (Kondratyev et al., 2026), GCQR/GRCP (Conrad et al., 2026); none is evaluated. Several of these can be instantiated as the constructor on the retrieved law, which would turn this missing comparison into an ablation of the authors’ own framework.
Questions for authors
-
Across the capacity and data sweeps, could you investigate the empirical relationship between the held-out energy score of the retrieved residual law, the pivotality defect , and prediction-set efficiency at comparable coverage? In particular, do improvements in residual-law estimation translate into better pivotality and tighter prediction sets?
-
For the ellipsoidal constructor used in practice, under which condition on does an energy-distance error on bound in Assumption 3? Can you state and prove such a bound for at least one constructor?
-
Since is arbitrary, can other scalarizations (like OT-CP) be instantiated as on the retrieved law, and how do they compare with the ellipsoidal constructor?
-
Clarification, not score-relevant: please unify the notation / / for the localization variable, state explicitly that enters only through the weights . More generally, the notation is heavy and partly redundant; lightening it would make the paper easier to follow.
5 comments
Response to Reviewer FmkN - Part 2
-
Thurin et al.'s OT-CP+. (Weakness 3, Question 3) We added OT-CP+ comparisons. On our planar quadcopter benchmark, the 100-step prediction problem has a 600-dimensional joint residual space. The evaluated finite-reference OT-CP+ construction produces unbounded prediction regions due to rank deficiency in its transport representation. A per-timestep 6D adaptation reduces this dimensionality problem but still produces unbounded regions and requires 374.83 ms/query, compared with 1.74 ms/query for FacCP (Table 20).
-
Kondratyev et al.'s CVQR. (Weakness 3, Question 3) FacCP achieves comparable normalized log-volumes while requiring less geometry-construction time and less membership-evaluation time while maintaining empirical coverage (Table 21).
-
Conrad et al.'s GRCP. (Weakness 3, Question 3) Replacing GRCP's input-space retrieval with our learned retrieval improves normalized log-volume from to while retaining coverage (Table 23).
-
Messoudi et al.'s CopulaCP (2021). (Weakness 3, Question 3) FacCP produces substantially smaller sets than CopulaCP (log-volume vs. ). Combining FacCP geometry with CopulaCP calibration further reduces log-volume to at comparable coverage, with minimal runtime overhead (Table 23).
-
Xu et al.'s MultiDimSPCI (2024). (Weakness 3, Question 3) MultiDimSPCI targets non-exchangeable multivariate time series through sequential adaptive calibration, whereas our setting assumes exchangeable trajectory samples and learns query-dependent geometry.
3. Missing representation and objective ablations
We added controlled ablations holding downstream retrieval, geometry construction, and calibration fixed.
-
Pretrained representations. (Weakness 3) On Argoverse 2, energy-score-trained retrieval produces substantially tighter uncertainty tubes than retrieval using pretrained MAE or frozen MTR features, while maintaining comparable whole-trajectory coverage. Energy-trained representations reduce footprint by 14.15% at the 95% target, compared with for pretrained MAE features and 3.74% for frozen MTR features. Corresponding coverages are 94.87%, 95.25%, and 95.20% (Table 11).
-
Alternative training objective. (Weakness 3) To show the importance of the energy score, we replace energy-score fine-tuning with a residual-neighbor KL objective. This alternative objective reduces the footprint improvement from 14.15% to 0.76%, using matched architectures, initialization, and training settings (Table 12).
-
Quadcopter ablations. (Weakness 3) Retrieval using energy-trained representations achieves normalized log-volume at the 95% target, compared with for a covariate-reconstruction autoencoder and for a residual-prediction autoencoder, with coverage near nominal (Table 6).
-
NLE and MVCS. (Weakness 3) Both methods fit a single joint ellipsoid, so we evaluate them in the single-mode setting. Extending them to six diverging trajectories would include large regions between paths. At the target, FacCP achieves a footprint of m$^2$s versus for NLE and for MVCS, all at comparable coverage (Table 20).
4. Does better held-out energy score correlate with pivotality and efficiency? (Question 1)
-
Theory and empirical validation. Theorem 14 bounds the estimation component of the pivotality defect using energy-distance retrieval error. Since the data and capacity sweeps showed little energy-score variation, we evaluated ten energy fine-tuning checkpoints after one epoch of MAE pretraining, keeping retrieval temperature, geometry, and calibration fixed (Appendix D.10).
-
Pivotality. Lower held-out energy scores correlate strongly with smaller pivotality defects across 14 scene bins, with Spearman correlations of at 97% and at 99%. This supports the theoretical connection between residual-law estimation and score pivotality (Figure 7).
-
Set efficiency. Lower energy scores also correlate with smaller prediction-set footprints, with at 97% and at 99%. Empirical coverage remains comparable across checkpoints, ranging from 96.75--97.04% and 99.16--99.25%, respectively. These results indicate that better residual-law estimation is associated with tighter prediction sets at comparable coverage (Figure 7).
Response to Reviewer FmkN - Part 3
5. Does energy-distance error control pivotality for ellipsoids? (Question 2)
-
New theoretical result. Theorem 14 establishes, under bounded support, uniformly positive definite covariance, Lipschitz Mahalanobis-score CDFs, and uniformly bounded energy-distance retrieval error, that
Here, bounds energy-distance retrieval error, is covariance regularization, and measures non-pivotality of oracle Mahalanobis scores.
-
Geometry misspecification. The term captures non-pivotality remaining even with perfect residual-law retrieval, including equal-covariance distributions with different tails. The second term quantifies estimation and regularization error. Since excess expected energy-score risk equals half the energy distance, this result connects our training objective to the downstream pivotality defect for ellipsoids. It does not require the true residual laws to be elliptical (Assumption 13, Theorem 14).
6. Can other scalarizations use the retrieved law? (Question 3)
- Yes. The constructor is independent of representation learning. We evaluate FacCP with OT-CP+, GRCP, and CopulaCP. Learned retrieval improves GRCP efficiency at unchanged coverage, while CopulaCP calibration further reduces FacCP set volume at comparable coverage. OT-CP+ retains its finite-reference limitations (Appendix E.1, Tables 20, 22, 23).
7. Notation clarification (Question 4)
We simplified Sections 3 and 4, using for learned retrieval coordinates and for the induced scalar score, while reserving for latent uncertainty-generating variables in controlled experiments. The representation enters residual-law estimation only through the retrieval weights .
8. Additional Results
We added real-world evaluations on world models, New York taxi data, and river flow data from Dheur et al. (2025) (Appendix E.2, Figures 9--10, Tables 25--26).
Response to Reviewer FmkN - Part 1
We thank the reviewer for the detailed feedback. We have revised the paper to clarify its central theoretical contribution, added a new constructor-specific pivotality result, and expanded the experimental comparisons. For this reviewer, we provide
Highlights\_FmkN.pdfwith relevant revisions highlighted for a targeted re-read.1. Theoretical novelty, motivation, and pivotality
Novelty. (Weakness 1) We disagree that our theoretical contribution is standard. Our central result establishes a connection between local geometry approximation and score pivotality. Theorem 3 proves that approximating query-dependent oracle geometries with invariant conditional probability mass yields approximately pivotal scores, with Δpiv≤2ϵgeom. Unlike prior analyses based on score-distribution correction (Laplante, 2026; Plassier et al. 2025a) or conditional-law estimation error (Plassier et al., 2025b), Theorem 3 directly bounds score non-pivotality in terms of the conditional probability mass where the learned and true geometric sublevel sets disagree. Corollary 7 and Theorem 8 translate this into local coverage guarantees under global calibration, while Corollary 9 bounds coverage loss under covariate shift without score reweighting. This is important because correcting scalar thresholds cannot recover misspecified geometry. Figure 2 shows that even oracle local quantile calibration of a fixed geometry produces sets with 1.99× oracle area.
Energy-score retrieval is a practical implementation of the theory. (Weakness 1) FacCP provides a practical realization of Theorem 3 by constructing query-dependent residual geometries from energy-score-trained residual law retrieval and aiming to make the resulting nonconformity scores approximately pivotal, doing so in a principled, scalable, and efficient manner. Theorem 3 applies to any nested geometry satisfying Assumption 2, regardless of how the geometries are constructed. Rather than directly estimating high-dimensional geometry parameters, FacCP learns a compact uncertainty-relevant representation using a strictly proper energy score that targets the full conditional residual law. Proposition 4 characterizes uncertainty sufficiency through excess energy-score risk, while Proposition 12 establishes the statistical benefit of suppressing uncertainty-irrelevant dimensions. Figure 3 and Appendix C.3 further support this design choice, demonstrating data and parameter efficiency against direct covariance and flow-based models, especially with limited training data or capacity.
Controlling pivotality. (Weakness 1, Question 2) We added Theorem 14, which bounds pivotality for the ellipsoidal constructor using energy-distance retrieval error. The bound separates non-pivotality inherent to the geometry class from error due to imperfect retrieval and covariance regularization. Crucially, it accounts for the reviewer's example of equal-covariance distributions with different tails. Even perfect residual-law estimation need not yield pivotal ellipsoidal scores when the chosen geometry cannot represent differences in conditional tail behavior. Empirically, the full-CDF pivotality defect decreases from 0.361 for global geometry to 0.117 with FacCP (Figure 2, Table 2).
2. Adaptive scalarization and requested multivariate conformal comparisons
Score definition. (Weakness 2) We agree that T(X,Y) is a fixed vector-valued residual score and that FacCP learns its adaptive scalarization. We now explicitly distinguish this fixed residual map from the induced scalar nonconformity score S(X,Y), which measures the inflation required for the residual to enter the query-dependent geometry. See Sec. 3, 4.1, and 4.3 for the specific discussion.
Positioning relative to prior methods. (Weakness 2) We clarified FacCP's relationship to recent multivariate conformal methods (Thurin et al., 2025; Klein et al., 2026; Kondratyev et al., 2026; Conrad et al., 2026). Unlike methods focused on specific score geometries, FacCP establishes a general geometry-to-pivotality connection and learns residual-law retrieval independently of the geometry constructor (Section 2, Appendix B). Our choice of local residual-law modeling is motivated by its scalability, demonstrated empirically against direct geometry models (Figure 3). Theorem 3 applies to any nested geometry satisfying Assumption 2, and Appendix E.1 shows that learned retrieval also improves alternative constructors such as GRCP and CopulaCP.