{"id":"145abeac-611c-4442-9163-6dff95ae3d12","arxiv_id":"2605.27340","paper_version":1,"verdict":"UNVERDICTED","confidence":"LOW","novelty_score":6.0,"correctness_risk":"unknown","formal_verification":"none","parameter_count":1,"one_line_summary":"Presents an eight-parameter closed-form SiPM charge spectrum model using characteristic functions, Lambert W for cross-talk progeny, and negative binomial for recursive afterpulsing.","lead":"The paper derives a unified closed-form analytical expression for the full charge response spectrum of silicon photomultipliers that incorporates pedestal noise, single-electron response, optical cross-talk via Galton-Watson branching, and afterpulsing via negative binomial statistics. A smart generalist might read it because improved analytical models could speed up event reconstruction in large-scale neutrino detectors without numerical convolution.","discovery_kind":"new_method","skeptic_critique":{"model":"grok-4.3","headline":"The closed-form eight-parameter likelihood rests on afterpulsing exactly following the max-entropy geometric per-avalanche law; any deviation breaks the negative-binomial closure and independent factorization.","rationale":"The reader's weakest_assumption correctly isolates the single assumption whose failure would invalidate the closed-form property and the explicit likelihood. All other elements (Lambert-W cross-talk, characteristic-function factorization) are standard once the afterpulsing statistics are granted; the max-entropy step is the non-obvious modeling choice whose correctness is not demonstrated by the abstract alone. Hence the verdict remains CONDITIONAL pending either a first-principles derivation or direct validation against measured or simulated afterpulsing statistics.","tokens_in":1870,"tokens_out":447,"duration_ms":29229,"concrete_test":"Generate 10^6 Monte-Carlo realizations of the SiPM response using the paper's cross-talk branching process but with afterpulsing drawn from an exponential delay distribution at the same mean probability; bin the total charge and compare the resulting histogram to the analytical Negative-Binomial prediction at the same parameters. If the Kolmogorov-Smirnov distance exceeds 0.02 or the tail probabilities differ by >5% in any bin above 10 photoelectrons, the max-entropy assumption does not reproduce the underlying process.","verdict_should_be":"CONDITIONAL","load_bearing_attack":"The abstract states afterpulsing is modelled as a per-avalanche geometric chain obtained from the maximum-entropy Poisson-Gamma mixture, whose N-avalanche sum is Negative Binomial. This supplies the analytical handle that lets the full characteristic function factor into independent pedestal/SER/avalanche components and yields an explicit charge-time likelihood without convolution. The derivation is presented as following directly from the max-entropy principle with fixed mean, but the physical afterpulsing mechanism (trap release, delayed avalanche probability) is not shown to produce exactly this distribution. If the true per-avalanche statistics differ (e.g., time-dependent or non-geometric), both the closed-form PGF and the claimed factorization fail, so the central claim that an eight-parameter expression suffices for event-level reconstruction does not hold.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.3","summary":"The manuscript claims to derive a unified closed-form analytical expression for the full charge response spectrum of silicon photomultipliers, factorizing the characteristic function into independent pedestal, single-electron-response, and avalanche-count components. Prompt cross-talk is treated as a Galton-Watson branching process with Poisson offspring, yielding a Lambert-W closed form for the total-progeny PGF via Lagrange-Bürmann inversion. Afterpulsing is modeled as a per-avalanche geometric distribution obtained from the maximum-entropy Poisson-Gamma mixture, whose sum over N avalanches is negative binomial; the resulting eight-parameter model supplies an explicit per-channel charge-time likelihood for event-level reconstruction without numerical convolution.","tokens_in":2029,"tokens_out":655,"duration_ms":41453,"significance":"A validated closed-form likelihood free of truncation or convolution would enable faster and more precise event reconstruction in high-statistics neutrino detectors that rely on SiPM arrays. The factorization into physically motivated components and the explicit handling of recursive correlated avalanches represent a technical advance over existing numerical or truncated models, provided the maximum-entropy afterpulsing assumption and the branching-process inversion are shown to be both mathematically consistent and physically realistic.","major_comments":[{"comment":"Afterpulsing section: the manuscript states that the geometric per-avalanche distribution follows directly from the maximum-entropy Poisson-Gamma mixture with fixed mean, yet provides no derivation or comparison showing that the physical trap-release mechanism produces exactly this distribution (rather than a time-dependent or non-geometric form). Because this assumption supplies the negative-binomial closure and the independent factorization of the characteristic function, its justification is load-bearing for the central claim of an eight-parameter closed-form likelihood.","section":"Afterpulsing model"},{"comment":"Cross-talk derivation, Lagrange-Bürmann step: the claim of a Lambert-W closed form for the total-progeny PGF rests on the application of the inversion theorem to the Galton-Watson process with Poisson offspring; the manuscript must exhibit the explicit functional equation and the resulting expression to confirm that no hidden truncation or auxiliary approximation is introduced beyond Vinogradov’s generalised Poisson statistics.","section":"Cross-talk model"},{"comment":"Parameter count and identifiability: the abstract asserts an eight-parameter expression, but the manuscript does not list the eight parameters explicitly or demonstrate that they remain independent once the maximum-entropy and branching-process constraints are imposed; this affects whether the model is truly parameter-efficient for likelihood-based reconstruction.","section":"Overall model"}],"minor_comments":[{"comment":"Notation for the characteristic function should be introduced once with a clear definition of its argument (charge or charge-time) to avoid ambiguity when the time component is later adjoined.","section":"Introduction"},{"comment":"The abstract refers to “recursive correlated avalanches” but the body should explicitly map this phrase to the combination of the branching-process cross-talk and the geometric afterpulsing chains.","section":"Abstract vs. body"}],"recommendation":"major_revision","confidential_remarks":null},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for the thorough review and for highlighting the load-bearing aspects of the afterpulsing and cross-talk derivations as well as the parameter enumeration. We address each major comment below with clarifications and commit to targeted revisions that strengthen the manuscript without altering its core claims.","responses":[{"response":"We will insert a dedicated subsection deriving the geometric distribution step-by-step from the maximum-entropy principle applied to a Poisson-Gamma mixture with fixed mean (exponential prior on yield, marginalisation over Poisson count). This supplies the required mathematical closure. On the physical side, the maximum-entropy choice is presented as a principled approximation consistent with the observed afterpulsing statistics in the literature; we will add a short paragraph noting that a full microscopic trap-release simulation lies outside the present scope while the resulting negative-binomial form reproduces the measured spectra shown in the manuscript.","revision_made":"yes","referee_comment":"[Afterpulsing model] Afterpulsing section: the manuscript states that the geometric per-avalanche distribution follows directly from the maximum-entropy Poisson-Gamma mixture with fixed mean, yet provides no derivation or comparison showing that the physical trap-release mechanism produces exactly this distribution (rather than a time-dependent or non-geometric form). Because this assumption supplies the negative-binomial closure and the independent factorization of the characteristic function, its justification is load-bearing for the central claim of an eight-parameter closed-form likelihood."},{"response":"We will expand the cross-talk section to state the probability-generating-function functional equation for the Galton-Watson branching process with Poisson offspring, followed by the explicit application of the Lagrange-Bürmann inversion formula that yields the Lambert-W expression. This will make clear that the closed form is exact under the stated Poisson-offspring assumption and introduces no truncation beyond the Vinogradov generalised-Poisson framework already cited.","revision_made":"yes","referee_comment":"[Cross-talk model] Cross-talk derivation, Lagrange-Bürmann step: the claim of a Lambert-W closed form for the total-progeny PGF rests on the application of the inversion theorem to the Galton-Watson process with Poisson offspring; the manuscript must exhibit the explicit functional equation and the resulting expression to confirm that no hidden truncation or auxiliary approximation is introduced beyond Vinogradov’s generalised Poisson statistics."},{"response":"We will add an explicit table or enumerated list of the eight parameters together with their physical interpretations (pedestal offset and width, SER gain and width, prompt cross-talk probability, afterpulsing probability per avalanche, negative-binomial dispersion parameter, and overall scaling). A short paragraph will argue that the characteristic-function factorisation keeps the parameters independent because each controls a distinct physical component; the constraints from maximum-entropy and branching-process derivations do not introduce additional functional relations among them.","revision_made":"yes","referee_comment":"[Overall model] Parameter count and identifiability: the abstract asserts an eight-parameter expression, but the manuscript does not list the eight parameters explicitly or demonstrate that they remain independent once the maximum-entropy and branching-process constraints are imposed; this affects whether the model is truly parameter-efficient for likelihood-based reconstruction."}],"tokens_in":1619,"tokens_out":683,"duration_ms":33735,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The main takeaway is that this work supplies an eight-parameter analytical expression for the full SiPM charge response that factors cleanly and avoids convolution at reconstruction time. That is the practical hook for neutrino-detector groups that need fast per-channel likelihoods.\n\nWhat is actually new is the combination of the Lambert-W closed form for the Galton-Watson total progeny (building on Vinogradov) with the negative-binomial sum that follows from treating afterpulsing as a maximum-entropy Poisson-Gamma mixture. The characteristic-function factorization into three independent pieces is a clean way to keep everything analytical.\n\nThe paper does well at showing how these pieces fit together without truncation or numerical integration, which removes a real bottleneck for event-level energy reconstruction. If the derivations are correct, the resulting likelihood is directly usable at scale.\n\nThe soft spot is the afterpulsing model. The geometric per-avalanche distribution is taken as the maximum-entropy outcome with fixed mean, and the N-avalanche total is then negative binomial. That supplies the closure, but the physical mechanism (trap release timing and probability) is not shown to produce exactly that distribution. If real afterpulsing deviates, both the factorization and the closed form stop holding. The abstract gives no fits or Monte-Carlo comparisons, so it is hard to judge how much the model buys in practice versus how much it approximates.\n\nThis is for instrumentation people who already model SiPMs in reconstruction code and want an analytical alternative. A reader who needs the likelihood to be accurate to a few percent will still want to see validation against data.\n\nI would send it to peer review. The math is worth checking even if the physical justification for the afterpulsing piece needs more work.","headline":"The paper derives a closed-form SiPM charge spectrum by factoring the characteristic function into pedestal, SER, Lambert-W cross-talk, and negative-binomial afterpulsing terms, but the max-entropy geometric assumption for afterpulsing is the load-bearing step.","tokens_in":2566,"tokens_out":455,"would_cite":false,"duration_ms":24346,"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 characteristic-function model yields a closed-form eight-parameter expression for the full charge response of silicon photomultipliers including recursive cross-talk and afterpulsing.","keywords":["silicon photomultiplier","SiPM","charge response","closed-form","afterpulsing","optical cross-talk","characteristic function","negative binomial"],"falsifier":"Measurement of the charge spectrum from a SiPM illuminated by a pulsed light source at intensities where multiple avalanches and afterpulses occur; systematic deviation from the predicted eight-parameter distribution would falsify the closed-form model.","tokens_in":2731,"feed_emoji":"⚡","tokens_out":717,"duration_ms":24402,"temperature":0.7,"pith_summary":"The paper derives a unified closed-form analytical expression for the charge response spectrum of silicon photomultipliers. This expression accounts for pedestal noise, single-electron response, optical cross-talk modeled as a Galton-Watson branching process, and afterpulsing modeled as a negative binomial distribution from a maximum-entropy mixture. The characteristic function factors these components independently, leading to a Lambert W function for cross-talk and avoiding numerical convolutions. Such a model matters because it enables direct computation of likelihoods for energy reconstruction in neutrino experiments without simulation overhead. If correct, it unifies treatment of correlated avalanche effects absent in standard photomultiplier tubes.","feed_headline":"Closed-form charge model unifies SiPM cross-talk and afterpulsing","feed_subtitle":"Eight-parameter expression gives explicit likelihood for energy reconstruction without numerical convolution.","key_machinery":"The characteristic-function factorisation of the charge spectrum together with the Lambert W closed form for the Galton-Watson total-progeny PGF and the negative-binomial representation of recursive afterpulsing.","core_discovery":"Within the characteristic-function framework the full charge spectrum factorises into pedestal, single-electron-response, and avalanche-count statistics. Prompt internal optical cross-talk is a Galton-Watson branching process with Poisson offspring whose total-progeny probability-generating function admits a Lambert W closed form via Lagrange-Bürmann inversion. Afterpulsing is a per-avalanche geometric chain obtained as the maximum-entropy Poisson-Gamma mixture, whose sum over N avalanches is negative binomial. The resulting eight-parameter expression supplies an explicit per-channel charge-time likelihood for event-level energy reconstruction.","pith_inferences":["If the closed-form holds, detector simulations in large neutrino experiments could replace convolution steps with direct evaluation, reducing computational cost.","The maximum-entropy derivation of the geometric afterpulse distribution suggests a way to test whether real SiPM data obey the same entropy-maximising statistics.","The branching-process treatment of cross-talk may extend to other photodetectors that exhibit similar internal optical coupling."],"forward_implications":["The model captures correlated cross-talk and afterpulsing on equal footing with pedestal and SER.","It provides analytical closure that encompasses both the Poisson afterpulsing limit and recursive chains.","An explicit likelihood for charge-time data is obtained without numerical convolution at inference time.","The eight-parameter form can be applied directly to event-level energy reconstruction."],"fun_headline_variants":["Closed-form SiPM model factors charge spectrum into pedestal SER avalanche stats","Lambert W form models SiPM optical cross-talk as Galton-Watson process","Negative binomial models SiPM afterpulsing chains in closed-form expression","SiPM eight-parameter model yields explicit charge-time likelihood"],"cache_read_input_tokens":2112,"weakest_assumption_plain":"The afterpulsing process is correctly described by the maximum-entropy Poisson-Gamma mixture that yields a geometric distribution for each avalanche.","fun_headline_variants_meta":{"raw":{"variants":["Closed-form SiPM model factors charge spectrum into pedestal SER avalanche stats","Lambert W form models SiPM optical cross-talk as Galton-Watson process","Negative binomial models SiPM afterpulsing chains in closed-form expression","SiPM eight-parameter model yields explicit charge-time likelihood"]},"model":"grok-4.3","cost_usd":0.013265,"raw_usage":{"total_tokens":5810,"prompt_tokens":793,"num_sources_used":0,"completion_tokens":74,"cost_in_usd_ticks":132649500,"prompt_tokens_details":{"text_tokens":793,"audio_tokens":0,"image_tokens":0,"cached_tokens":256},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":4943,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":793,"tokens_out":74,"duration_ms":39274,"temperature":1.0,"reasoning_tokens":4943,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-06-29T14:44:23.738541+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"Measurement of the charge spectrum from a SiPM illuminated by a pulsed light source at intensities where multiple avalanches and afterpulses occur; systematic deviation from the predicted eight-parameter distribution would falsify the closed-form model.","supporting_citations":[],"review_version":1}