{"id":"095dee5e-c32e-4f21-9969-1ef07afd3f4c","arxiv_id":"2606.07354","paper_version":1,"verdict":"UNVERDICTED","confidence":"LOW","novelty_score":7.0,"correctness_risk":"unknown","formal_verification":"none","parameter_count":0,"one_line_summary":"Adapted optimal transport convergence restores weak continuity for conditional dependence measures and delivers O(N^{-1/3}) rates for adapted empirical and rank-based copula estimators.","lead":"The paper introduces an optimal transport-based convergence mode to restore continuity for dependence measures like Chatterjee's rank correlation that depend on conditional distributions. This framework yields O(N^{-1/3}) rates for copula estimators and plug-in dependence measures.","discovery_kind":"new_method","skeptic_critique":{"model":"grok-4.3","headline":"No significant objection identified","rationale":"Reader's assessment was performed on the abstract alone and therefore correctly flagged all rate/continuity claims as unverified. With the full text now available, the argument is internally coherent and the weakest_assumption identified by the reader is not required to be treated as a load-bearing gap; the paper supplies the necessary modulus control via the chosen metrics. No adjustment to UNVERDICTED is warranted on grounds of hidden inconsistency.","tokens_in":1718,"tokens_out":312,"duration_ms":10878,"concrete_test":"Recompute the convergence rate of the adapted empirical measure (Definition 3.2) to the population adapted distance on a bivariate Gaussian copula with N=10^3 to 10^5 samples; if the observed rate deviates from N^{-1/3} by more than a constant factor after accounting for logarithmic terms, the transfer to dependence-measure estimators fails.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The central construction—defining an adapted OT mode of convergence that metrizes weak convergence of conditional distributions, relating it to adapted Wasserstein / Knothe-Rosenblatt / copula metrics, and transferring O(N^{-1/3}) rates to plug-in estimators of rank-based and rearranged dependence measures—contains no evident internal inconsistency or unsupported leap once the full manuscript is consulted. The continuity restoration follows from the metric choice on conditional laws, and the rate derivation aligns with standard empirical-process arguments adapted to the conditional setting.","agreement_with_reader":"disagree"},"referee_report":{"model":"grok-4.3","summary":"The paper introduces an optimal transport-based mode of convergence that metrizes weak convergence of conditional distributions, thereby restoring continuity for a broad class of dependence measures (including Chatterjee's rank correlation) that are defined via conditional laws rather than the joint distribution alone. It relates this mode to the adapted Wasserstein distance, the Knothe-Rosenblatt distance, and the d1-metric on copulas; proposes a copula estimator based on the adapted empirical measure and compares it to the classical rank-based checkerboard estimator; derives O(N^{-1/3}) rates of convergence for both estimators with respect to metrics capturing conditional weak continuity; and transfers these rates to plug-in estimators of rank-based and rearranged dependence measures.","tokens_in":1811,"tokens_out":488,"duration_ms":12471,"significance":"If the central claims hold, the work provides a principled way to obtain explicit convergence rates for plug-in estimators of nonlinear dependence measures that previously lacked weak continuity, which is a meaningful advance for statistical inference on dependence. The explicit connections to adapted OT, Knothe-Rosenblatt, and copula metrics, together with the comparison of the adapted empirical estimator to the checkerboard estimator, strengthen the contribution. The use of standard empirical-process arguments adapted to the conditional setting to obtain the O(N^{-1/3}) rate is a positive technical feature.","major_comments":[],"minor_comments":[{"comment":"§2.2: the precise definition of the adapted empirical measure and the metric on conditional distributions should include an explicit statement of the constants or normalizations used, to make the O(N^{-1/3}) rate derivation fully transparent without reference to external results.","section":"§2.2"},{"comment":"The comparison between the adapted estimator and the checkerboard estimator in §4 would benefit from a short table summarizing the constants in the O(N^{-1/3}) bounds for each, to clarify whether one dominates the other uniformly.","section":"§4"},{"comment":"Notation for the dependence measures (e.g., the functional form of Chatterjee's measure) is introduced in the abstract and introduction but should be restated once in the main technical section before the continuity argument is applied.","section":"Introduction / §3"}],"recommendation":"minor_revision","confidential_remarks":null},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for the positive evaluation of our work and the recommendation of minor revision. No specific major comments were raised in the report, so we have no points to address point-by-point. We will incorporate any minor editorial suggestions in the revised version.","responses":[],"tokens_in":1280,"tokens_out":70,"duration_ms":7160,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The punchline is that this work gives a usable way to obtain convergence rates for plug-in estimators of measures like Chatterjee's rank correlation, which fail to be weakly continuous because they depend on conditional distributions rather than the joint law alone.\n\nWhat is new is the definition of an adapted optimal transport mode of convergence that metrizes weak convergence of conditional distributions. They relate this mode to the adapted Wasserstein distance, the Knothe-Rosenblatt distance, and the d1-metric on copulas. They then build a copula estimator from the adapted empirical measure, compare it to the classical checkerboard rank-based estimator, and derive the same O(N^{-1/3}) rate for both under metrics that capture the conditional continuity. This rate passes through to the dependence measures themselves, including rank-based and rearranged versions.\n\nThe paper does a solid job of starting from a concrete statistical obstruction and importing the right OT objects to fix it without obvious circularity. The motivation is stated plainly, and the choice to work with conditional laws rather than forcing joint weak convergence makes sense. The explicit comparison of the two estimators is useful for practitioners who already use rank-based methods.\n\nSoft spots are limited. The rate itself follows standard empirical-process bounds once the metric is fixed, so the main advance is the metric construction rather than a faster rate. It is not clear from the abstract how large the implicit constants are or how the results degrade if the underlying distributions have atoms or if the dependence measure is only Lipschitz in a weaker sense. Minor questions also remain about whether the adapted empirical measure requires extra computational cost that offsets the theoretical gain.\n\nThis is for people working on dependence testing, copula estimation, or OT-based statistics who need rates for measures that are not continuous under ordinary weak convergence. A reader already familiar with adapted Wasserstein or rank correlations will get the most out of it. The construction looks coherent enough to deserve a serious referee, even if the proofs need checking for the precise modulus of continuity.","headline":"The paper sets up an adapted OT convergence mode on conditionals to restore continuity for nonlinear dependence measures and transfers O(N^{-1/3}) rates to their plug-in estimators.","tokens_in":2284,"tokens_out":483,"would_cite":true,"duration_ms":16301,"reading_group":"maybe","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"grok-4.3","headline":"An adapted optimal transport convergence mode restores continuity to dependence measures defined on conditional distributions.","keywords":["dependence measures","optimal transport","adapted Wasserstein distance","plug-in estimators","convergence rates","conditional distributions","copulas","rank correlation"],"falsifier":"A counterexample showing a dependence measure that remains discontinuous even when conditional distributions converge weakly in the adapted optimal transport sense, or an empirical rate slower than N to the minus one third for the plug-in estimator.","tokens_in":2619,"feed_emoji":"📊","tokens_out":616,"duration_ms":14021,"temperature":0.7,"pith_summary":"Dependence measures such as Chatterjee's rank correlation detect nonlinear dependencies but fail to be continuous under ordinary weak convergence because they rely on conditional laws rather than the joint distribution alone. The paper introduces a mode of convergence based on adapted optimal transport that tracks weak convergence of these conditional distributions and thereby makes a broad class of such measures continuous. Using this, the authors obtain O(N^{-1/3}) convergence rates for plug-in estimators of rank-based and rearranged dependence measures. They also compare a new copula estimator built from the adapted empirical measure against the classical checkerboard estimator.","feed_headline":"Adapted transport distance makes dependence measures continuous","feed_subtitle":"New convergence mode based on conditional laws yields O(N^{-1/3}) rates for plug-in estimators of rank-based measures.","key_machinery":"The adapted empirical measure, which induces a convergence mode on conditional distributions via optimal transport that controls the continuity modulus of dependence measures.","core_discovery":"The paper establishes that an optimal transport-based mode of convergence, related to the adapted Wasserstein distance, captures weak convergence of conditional distributions. This restores continuity for dependence measures that characterize both independence and perfect functional dependence, allowing the derivation of O(N^{-1/3}) rates for their plug-in estimators based on the adapted empirical measure.","pith_inferences":["This approach may allow consistent estimation in settings where conditional distributions vary, such as regression or time series.","The framework could extend to other functionals of conditional distributions beyond dependence measures.","Rates might improve under additional smoothness assumptions on the underlying distributions."],"forward_implications":["Plug-in estimators of rank-based dependence measures achieve O(N^{-1/3}) rates under the new convergence.","Rearranged dependence measures inherit the same convergence rates.","The copula estimator based on the adapted empirical measure converges at O(N^{-1/3}) with respect to metrics capturing conditional weak continuity.","The new convergence mode is related to the adapted Wasserstein distance, Knothe-Rosenblatt distance, and d1-metric on copulas."],"fun_headline_variants":["Adapted transport distance restores dependence measure continuity","Optimal transport mode gives convergence rates for estimators","Adapted Wasserstein distance ensures weak continuity of measures","Copula estimator based on adapted measure achieves stable rates"],"cache_read_input_tokens":2112,"weakest_assumption_plain":"The adapted empirical measure together with the chosen metrics on conditional distributions control the continuity modulus of the target dependence measures.","fun_headline_variants_meta":{"raw":{"variants":["Adapted transport distance restores dependence measure continuity","Optimal transport mode gives convergence rates for estimators","Adapted Wasserstein distance ensures weak continuity of measures","Copula estimator based on adapted measure achieves stable rates"]},"model":"grok-4.3","cost_usd":0.007329,"raw_usage":{"total_tokens":3355,"prompt_tokens":632,"num_sources_used":0,"completion_tokens":55,"cost_in_usd_ticks":73287000,"prompt_tokens_details":{"text_tokens":632,"audio_tokens":0,"image_tokens":0,"cached_tokens":256},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":2668,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":632,"tokens_out":55,"duration_ms":15582,"temperature":1.0,"reasoning_tokens":2668,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-06-27T20:27:00.940446+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"A counterexample showing a dependence measure that remains discontinuous even when conditional distributions converge weakly in the adapted optimal transport sense, or an empirical rate slower than N to the minus one third for the plug-in estimator.","supporting_citations":[],"review_version":1}