{"paper_id":"2610.05196","title":"Measuring Learned Monotone Temporal Aggregation at Matched Admissibility","authors":["Yew Lee Tan"],"paper_date":"2026-10-04","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2610.05196","page_url":"https://thequant.space/flowcharts/measuring-learned-monotone-temporal-aggregation-at-matched-admissibility/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an evaluation of monotone sequence models that measures the value of learning temporal aggregation under matched admissibility, using a recurrent architecture whose state consists of classical risk statistics and is monotone by construction.","quote":"The instrument that makes these measurements possible is an architecture, and we present it as an instrument rather than as the primary contribution: the contribution is the evaluation and the boundary; the architecture is claimed only in the role that makes them measurable.","summary":"Risk regulation imposes directional constraints on scores; we adopt their strict per-input form – the score monotone non-decreasing in every exposure input – as a normative commitment. Deployed pipelines – monotone hand-crafted aggregates feeding sign-constrained gradient boosting – already satisfy…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"g1 is monotone non-decreasing and 0 < α < 1","type":"model","stated":"explicit","quote":"Assume g1 is monotone non-decreasing and 0 < α < 1."},{"assumption":"g2 is monotone non-decreasing","type":"model","stated":"explicit","quote":"Assume g2 is monotone non-decreasing."},{"assumption":"g1, g2 and F are monotone non-decreasing in each argument","type":"model","stated":"explicit","quote":"Assume g1 and g2 are monotone non-decreasing and F is monotone non-decreasing in each argument."},{"assumption":"Synthetic data generation follows a latent two‑state stress process with state‑dependent AR(1) dynamics and rare spikes","type":"data","stated":"explicit","quote":"We generate non-negative exposure sequences x1:T by modeling log-exposure yt := log(1 + xt) with (i) a latent two-state stress process and (ii) state-dependent AR(1) dynamics with rare spikes."},{"assumption":"All experiments use synthetic data to provide controlled ground‑truth monotone mechanisms","type":"data","stated":"explicit","quote":"All experiments use synthetic data to enable controlled, ground-truth monotone mechanisms and precise monotonicity diagnostics."},{"assumption":"Every dropout‑instantiated model remains monotone, preserving the per‑sample guarantee","type":"model","stated":"explicit","quote":"Corollary 1 below shows that every dropout-instantiated model remains monotone, so the per-sample guarantee is preserved."}]},"datasets":{"status":"available","items":[{"name":"synthetic exposure sequences","provider":null,"kind":"synthetic","access":"public","period":null,"universe":null,"quote":"All experiments use synthetic data to enable controlled, ground-truth monotone mechanisms and precise monotonicity diagnostics."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"A learned monotone channel reproduces the geometrically weighted separable family of hand‑crafted statistics with Spearman ρ≥0.996.","kind":"performance","quote":"a learned monotone channel reproduces the geometrically weighted separable family of hand-crafted statistics, one channel per member, to Spearman ρ≥"},{"finding":"The learned channel fails at consecutivity (ρ=0.924), time localization (ρ=0.628), and exposure floor (ρ=0.829), indicating learnability boundaries.","kind":"negative","quote":"fails at consecutivity (ρ= 0.924) and time localization (0.628), both structural, and at the exposure floor (0.829), a learnability boundary."},{"finding":"Adding one explicit admissible basis repairs each failure, achieving rank correlation 1.000.","kind":"performance","quote":"One explicit admissible basis repairs each failure (rank correlation 1.000)."},{"finding":"A committed grid pays up to 0.019 AUC in decay regions it leaves uncovered, while the learned channel stays within 0.004 of the strongest engineered consumer at every swept point.","kind":"performance","quote":"a committed grid pays up to 0.019 AUC in decay regions it leaves uncovered (the learned channel stays within 0.004 of the strongest engineered consumer at every swept point)"},{"finding":"Predictively, the learned channel is never statistically worse in‑distribution at full sample size on the core regimes at its specified capacity.","kind":"performance","quote":"Predictively, the learned channel is never statistically worse in-distribution at full sample size on the core regimes at its specified capacity"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":27,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:03:28Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}