{"id":"48e4f9bd-5acc-4dca-b108-e2470b577f3a","arxiv_id":"2606.18866","paper_version":1,"verdict":"UNVERDICTED","confidence":"LOW","novelty_score":6.0,"correctness_risk":"unknown","formal_verification":"none","parameter_count":0,"one_line_summary":"Proves Cramér-type moderate deviation expansion for (log q_n - n)/√n in Engel series via martingale approach, yielding full-range moderate deviation principle and uniform Berry-Esseen bound of order (log n)/√n.","lead":"The paper establishes a Cramér-type moderate deviation expansion for the normalized log-digits in random Engel series expansions using a martingale decomposition. A generalist might read it to understand how martingale tools extend classical limit theorems in number theory to intermediate deviation scales.","discovery_kind":"unclear","skeptic_critique":{"model":"grok-4.3","headline":"Martingale decomposition of (log q_n - n) requires explicit verification that Engel digits meet moment/dependence conditions of the invoked moderate-deviation theorems","rationale":"The reader's weakest_assumption identifies precisely the same point. No other internal inconsistency is visible from the abstract or claimed consequences; the concern is therefore the direct applicability of the black-box martingale theorems rather than any circularity or missing step inside the decomposition itself.","tokens_in":1647,"tokens_out":324,"duration_ms":19497,"concrete_test":"In the martingale decomposition section, extract the explicit form of the increments δ_k and verify whether sup_k E[|δ_k|^{2+δ}] < ∞ holds for some δ>0 (or the precise moment required by the referenced theorem); also check that the normalized quadratic variation converges in probability to a non-degenerate limit. If either fails, recompute the moderate-deviation expansion under the actual growth of moments.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The central claim applies standard martingale moderate-deviation and Berry-Esseen results directly to a decomposition of log q_n - n. This requires the differences to have uniformly bounded moments of order >2 and the quadratic variation to satisfy the theorem hypotheses (e.g., convergence in probability to a positive limit after normalization). The Engel process has a recursive dependence structure (each digit depends on the fractional part after the previous step), so these conditions are not automatic and must be proved; failure would mean the cited theorems cannot be applied without extra truncation or approximation arguments.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.3","summary":"The paper claims to prove a Cramér-type moderate deviation expansion for (log q_n - n)/√n, where q_n denotes the nth Engel digit of a uniform random variable x on (0,1). The argument proceeds by constructing a martingale decomposition of the centered log-digit process and invoking standard martingale moderate-deviation and Berry–Esseen theorems. As corollaries the authors obtain a moderate deviation principle on the full scale range between the CLT and the LLN (removing a lower-rate restriction present in earlier works) together with a uniform Berry–Esseen bound of order (log n)/√n.","tokens_in":1785,"tokens_out":429,"duration_ms":24216,"significance":"If the martingale conditions are verified, the result would strengthen the existing moderate-deviation theory for Engel expansions by extending the admissible range of deviation scales and improving the rate in the Berry–Esseen estimate. The martingale approach supplies a transparent way to exploit the underlying dependence structure and may be adaptable to other digit processes arising in ergodic number theory.","major_comments":[{"comment":"The central claim rests on the direct applicability of martingale moderate-deviation and Berry–Esseen theorems to the constructed decomposition of log q_n - n. The Engel digit process possesses a recursive dependence (each digit is a function of the fractional part remaining after the preceding step). Consequently, the paper must explicitly establish that the martingale differences possess moments of order greater than 2 that are uniformly bounded in n and that the normalized quadratic variation converges in probability to a positive deterministic limit. These verifications are load-bearing for the invocation of the cited limit theorems and are not automatic from the decomposition alone.","section":"Martingale decomposition and application of limit theorems (likely §3)"}],"minor_comments":[{"comment":"Clarify in the introduction the precise improvement over the lower-rate restrictions appearing in the cited earlier works on Engel moderate deviations.","section":"Introduction"}],"recommendation":"major_revision","confidential_remarks":null},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for the constructive report and the positive assessment of the significance of the martingale approach. We address the single major comment below and will revise the manuscript accordingly to strengthen the presentation.","responses":[{"response":"We agree that the recursive dependence requires explicit verification of the moment and quadratic-variation conditions before the standard martingale theorems can be invoked. While the decomposition itself appears in Section 3, the uniform (2+δ)-moment bounds and the in-probability convergence of the normalized quadratic variation are only indicated via references to the underlying ergodic properties rather than proved in full detail. In the revised manuscript we will insert a new subsection (3.2) that (i) derives the uniform moment bound from the explicit tail estimate P(q_n ≥ k) ≤ C/k (which follows directly from the uniform distribution of the remainder) and (ii) proves convergence of the quadratic variation by applying the ergodic theorem to the invariant measure of the Engel map, thereby justifying the application of the cited moderate-deviation and Berry–Esseen results for martingales.","revision_made":"yes","referee_comment":"[Martingale decomposition and application of limit theorems (likely §3)] The central claim rests on the direct applicability of martingale moderate-deviation and Berry–Esseen theorems to the constructed decomposition of log q_n - n. The Engel digit process possesses a recursive dependence (each digit is a function of the fractional part remaining after the preceding step). Consequently, the paper must explicitly establish that the martingale differences possess moments of order greater than 2 that are uniformly bounded in n and that the normalized quadratic variation converges in probability to a positive deterministic limit. These verifications are load-bearing for the invocation of the cited limit theorems and are not automatic from the decomposition alone."}],"tokens_in":1292,"tokens_out":388,"duration_ms":11142,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The main takeaway is that the paper establishes a Cramér-type moderate deviation expansion for (log q_n - n)/√n that works over the entire scale range between the CLT and LLN, without the extra lower bound on the deviation rate that earlier papers imposed. They also obtain a uniform Berry-Esseen bound of order (log n)/√n. The proof route is a martingale decomposition of the quantity followed by off-the-shelf martingale moderate-deviation and Berry-Esseen theorems.\n\nWhat the work does cleanly is identify a decomposition that appears to sidestep the restriction. If the differences satisfy the moment and dependence hypotheses of the cited martingale results, the argument is direct and avoids extra truncation layers. That is a modest but concrete improvement inside the existing program on probabilistic number theory for digit expansions.\n\nThe soft spot is whether the Engel process actually supplies those hypotheses. The digits are defined recursively through successive fractional parts, so the martingale increments are not independent and their higher moments are not obviously uniform. The quadratic variation after normalization must converge in probability to a positive limit for the standard theorems to apply directly. The abstract does not display the bounds, and the stress-test concern is on point: without those checks the decomposition cannot be fed straight into the martingale results. If the full paper supplies the moment estimates and the convergence, the claim stands; otherwise an extra approximation argument would be needed.\n\nThis is for readers already working on limit theorems for dependent sequences or Engel-type expansions. Someone following the moderate-deviation literature in probabilistic number theory would find the removal of the rate restriction useful for later applications. It is incremental rather than foundational, but the target is specific and the method is standard.\n\nThe paper deserves a serious referee. The central claim is falsifiable once the decomposition details are checked, and the citation pattern to prior Engel results looks appropriate. I would send it to review to confirm the martingale conditions hold.","headline":"They get the full-range moderate deviation principle for Engel series by martingale decomposition, removing the prior lower-rate restriction, but the conditions on moments and quadratic variation need explicit verification.","tokens_in":2216,"tokens_out":474,"would_cite":false,"duration_ms":14764,"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":"A martingale decomposition gives Cramér-type moderate deviation expansions for Engel series without rate restrictions.","keywords":["Engel series","moderate deviations","martingale decomposition","Cramér-type expansion","Berry-Esseen bound","Engel digits","probability theory"],"falsifier":"Compute the empirical distribution of (log q_n - n)/sqrt n for large n and check if the tail probabilities align with the predicted Cramér-type expansion, such as the Gaussian tail adjusted by moderate deviation factors.","tokens_in":2552,"feed_emoji":"","tokens_out":472,"duration_ms":29495,"temperature":0.7,"pith_summary":"The authors show that for a uniform random x in (0,1), the Engel digits q_n satisfy a moderate deviation expansion for (log q_n - n) scaled by sqrt n. This is proved via a martingale decomposition to which standard asymptotic results apply. As a result, the moderate deviation principle holds over the entire range of scales from the central limit theorem to the law of large numbers. The paper also obtains a uniform Berry-Esseen bound of order (log n)/sqrt n. A reader would care because this removes the lower rate restriction that limited earlier results on such expansions.","feed_headline":"Martingale removes rate limits for Engel series deviations","feed_subtitle":"Cramér-type expansions now cover all scales from CLT to LLN, plus uniform bound of order log n over sqrt n.","key_machinery":"Martingale decomposition of the sequence (log q_n - n) allowing direct application of martingale moderate-deviation and Berry-Esseen asymptotics.","core_discovery":"Let x be uniformly distributed on (0,1), and let (q_n) be the digits of its Engel series expansion. We establish a Cramér-type moderate deviation expansion for (log q_n - n)/sqrt n. The proof is based on a martingale decomposition and asymptotic results for martingales. As consequences, we obtain a moderate deviation principle over the full range of scales between the central limit theorem and the law of large numbers, without the additional lower rate restriction required in several earlier works. We also derive a uniform Berry--Esseen bound of order (log n)/sqrt n.","pith_inferences":[],"forward_implications":[],"fun_headline_variants":["Martingale gives full moderate deviations for Engel series without restrictions","Full-scale Cramer deviations for Engel series proven with martingales","Uniform bound of order log n over sqrt n for Engel series Berry-Esseen","Moderate deviation principle for Engel series holds without rate restrictions"],"cache_read_input_tokens":2112,"weakest_assumption_plain":"The Engel digit process allows a martingale decomposition that meets the moment and dependence conditions needed for the standard martingale moderate deviation theorems to apply.","fun_headline_variants_meta":{"raw":{"variants":["Martingale gives full moderate deviations for Engel series without restrictions","Full-scale Cramer deviations for Engel series proven with martingales","Uniform bound of order log n over sqrt n for Engel series Berry-Esseen","Moderate deviation principle for Engel series holds without rate restrictions"]},"model":"grok-4.3","cost_usd":0.00546,"raw_usage":{"total_tokens":2594,"prompt_tokens":605,"num_sources_used":0,"completion_tokens":70,"cost_in_usd_ticks":54599500,"prompt_tokens_details":{"text_tokens":605,"audio_tokens":0,"image_tokens":0,"cached_tokens":256},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":1919,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":605,"tokens_out":70,"duration_ms":10638,"temperature":1.0,"reasoning_tokens":1919,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-06-26T20:08:25.702808+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"Compute the empirical distribution of (log q_n - n)/sqrt n for large n and check if the tail probabilities align with the predicted Cramér-type expansion, such as the Gaussian tail adjusted by moderate deviation factors.","supporting_citations":[],"review_version":1}