The Necessity of Imperfection:Reversing Model Collapse via Simulating Cognitive Boundedness ArXiv ID: 2512.01354 “View on arXiv” Authors: Zhongjie Jiang Abstract Although synthetic data is widely promoted as a remedy, its prevailing production paradigm – one optimizing for statistical smoothness – systematically removes the long-tail, cognitively grounded irregularities that characterize human text. Prolonged training on such statistically optimal but cognitively impoverished data accelerates model collapse. This paper proposes a paradigm shift: instead of imitating the surface properties of data, we simulate the cognitive processes that generate human text. We introduce the Prompt-driven Cognitive Computing Framework (PMCSF), whose core consists of a Cognitive State Decoder (CSD) that reverse-engineers unstructured text into structured cognitive vectors, and a Cognitive Text Encoder (CTE) that re-materializes these states into text enriched with human-typical imperfections via mathematically defined Cognitive Perturbation Operators. The framework is validated through a two-stage objective evaluation pipeline. First, in cognitive codec verification, CTE text yields a Jensen-Shannon divergence of 0.0614 from human text (vs. 0.4431 for standard LLM output), passes double-blind professional media review, and achieves an intraclass correlation coefficient ICC > 0.9 for cognitive profile alignment across heterogeneous models. Second, in functional gain evaluation, isomorphic stress tests in the A-share market show that strategies incorporating CTE-generated data reduce maximum drawdown by 47.4% during the 2015 crash and deliver 8.6% Defensive Alpha, exceeding transaction costs by a factor of 33. Our findings demonstrate that modelling human cognitive limitations – not copying surface data – enables synthetic data with genuine functional gain, offering a viable technical pathway toward resolving the AI data-collapse crisis. ...

A Hybrid Architecture for Options Wheel Strategy Decisions: LLM-Generated Bayesian Networks for Transparent Trading ArXiv ID: 2512.01123 “View on arXiv” Authors: Xiaoting Kuang, Boken Lin Abstract Large Language Models (LLMs) excel at understanding context and qualitative nuances but struggle with the rigorous and transparent reasoning required in high-stakes quantitative domains such as financial trading. We propose a model-first hybrid architecture for the options “wheel” strategy that combines the strengths of LLMs with the robustness of a Bayesian Network. Rather than using the LLM as a black-box decision-maker, we employ it as an intelligent model builder. For each trade decision, the LLM constructs a context-specific Bayesian network by interpreting current market conditions, including prices, volatility, trends, and news, and hypothesizing relationships among key variables. The LLM also selects relevant historical data from an 18.75-year, 8,919-trade dataset to populate the network’s conditional probability tables. This selection focuses on scenarios analogous to the present context. The instantiated Bayesian network then performs transparent probabilistic inference, producing explicit probability distributions and risk metrics to support decision-making. A feedback loop enables the LLM to analyze trade outcomes and iteratively refine subsequent network structures and data selection, learning from both successes and failures. Empirically, our hybrid system demonstrates effective performance on the wheel strategy. Over nearly 19 years of out-of-sample testing, it achieves a 15.3% annualized return with significantly superior risk-adjusted performance (Sharpe ratio 1.08 versus 0.62 for market benchmarks) and dramatically lower drawdown (-8.2% versus -60%) while maintaining a 0% assignment rate through strategic option rolling. Crucially, each trade decision is fully explainable, involving on average 27 recorded decision factors (e.g., volatility level, option premium, risk indicators, market context). ...

Autodeleveraging: Impossibilities and Optimization ArXiv ID: 2512.01112 “View on arXiv” Authors: Tarun Chitra Abstract Autodeleveraging (ADL) is a last-resort loss socialization mechanism for perpetual futures venues. It is triggered when solvency-preserving liquidations fail. Despite the dominance of perpetual futures in the crypto derivatives market, with over $60 trillion of volume in 2024, there has been no formal study of ADL. In this paper, we provide the first rigorous model of ADL. We prove that ADL mechanisms face a fundamental \emph{“trilemma”}: no policy can simultaneously satisfy exchange \emph{“solvency”}, \emph{“revenue”}, and \emph{“fairness”} to traders. This impossibility theorem implies that as participation scales, a novel form of \emph{“moral hazard”} grows asymptotically, rendering `zero-loss’ socialization impossible. Constructively, we show that three classes of ADL mechanisms can optimally navigate this trilemma to provide fairness, robustness to price shocks, and maximal exchange revenue. We analyze these mechanisms on the Hyperliquid dataset from October 10, 2025, when ADL was used repeatedly to close $2.1 billion of positions in 12 minutes. By comparing our ADL mechanisms to the standard approaches used in practice, we demonstrate empirically that Hyperliquid’s production queue overutilized ADL by $\approx 28\times$ relative to our optimal policy, imposing roughly $653 million of unnecessary haircuts on winning traders. This comparison also suggests that Binance overutilized ADL far more than Hyperliquid. Our results both theoretically and empirically demonstrate that optimized ADL mechanisms can dramatically reduce the loss of trader profits while maintaining exchange solvency. ...

Early-Warning Signals of Political Risk in Stablecoin Markets: Human and Algorithmic Behavior Around the 2024 U.S. Election ArXiv ID: 2512.00893 “View on arXiv” Authors: Kundan Mukhia, Buddha Nath Sharma, Salam Rabindrajit Luwang, Md. Nurujjaman, Chittaranjan Hens, Suman Saha, Tanujit Chakraborty Abstract We study how the 2024 U.S. presidential election, viewed as a major political risk event, affected cryptocurrency markets by distinguishing human-driven peer-to-peer stablecoin transactions from automated algorithmic activity. Using structural break analysis, we find that human-driven Ethereum Request for Comment 20 (ERC-20) transactions shifted on November 3, two days before the election, while exchange trading volumes reacted only on Election Day. Automated smart-contract activity adjusted much later, with structural breaks appearing in January 2025. We validate these shifts using surrogate-based robustness tests. Complementary energy-spectrum analysis of Bitcoin and Ethereum identifies pronounced post-election turbulence, and a structural vector autoregression confirms a regime shift in stablecoin dynamics. Overall, human-driven stablecoin flows act as early-warning indicators of political stress, preceding both exchange behavior and algorithmic responses. ...

The Endogenous Constraint: Hysteresis, Stagflation, and the Structural Inhibition of Monetary Velocity in the Bitcoin Network (2016-2025) ArXiv ID: 2512.07886 “View on arXiv” Authors: Hamoon Soleimani Abstract Bitcoin operates as a macroeconomic paradox: it combines a strictly predetermined, inelastic monetary issuance schedule with a stochastic, highly elastic demand for scarce block space. This paper empirically validates the Endogenous Constraint Hypothesis, positing that protocol-level throughput limits generate a non-linear negative feedback loop between network friction and base-layer monetary velocity. Using a verified Transaction Cost Index (TCI) derived from Blockchain.com on-chain data and Hansen’s (2000) threshold regression, we identify a definitive structural break at the 90th percentile of friction (TCI ~ 1.63). The analysis reveals a bifurcation in network utility: while the network exhibits robust velocity growth of +15.44% during normal regimes, this collapses to +6.06% during shock regimes, yielding a statistically significant Net Utility Contraction of -9.39% (p = 0.012). Crucially, Instrumental Variable (IV) tests utilizing Hashrate Variation as a supply-side instrument fail to detect a significant relationship in a linear specification (p=0.196), confirming that the velocity constraint is strictly a regime-switching phenomenon rather than a continuous linear function. Furthermore, we document a “Crypto Multiplier” inversion: high friction correlates with a +8.03% increase in capital concentration per entity, suggesting that congestion forces a substitution from active velocity to speculative hoarding. ...

Convergence Rates of Turnpike Theorems for Portfolio Choice in Stochastic Factor Models ArXiv ID: 2512.00346 “View on arXiv” Authors: Hiroki Yamamichi Abstract Turnpike theorems state that if an investor’s utility is asymptotically equivalent to a power utility, then the optimal investment strategy converges to the CRRA strategy as the investment horizon tends to infinity. This paper aims to derive the convergence rates of the turnpike theorem for optimal feedback functions in stochastic factor models. In these models, optimal feedback functions can be decomposed into two terms: myopic portfolios and excess hedging demands. We obtain convergence rates for myopic portfolios in nonlinear stochastic factor models and for excess hedging demands in quadratic term structure models, where the interest rate is a quadratic function of a multivariate Ornstein-Uhlenbeck process. We show that the convergence rates are determined by (i) the decay speed of the price of a zero-coupon bond and (ii) how quickly the investor’s utility becomes power-like at high levels of wealth. As an application, we consider optimal collective investment problems and show that sharing rules for terminal wealth affect convergence rates. ...

Efficient Calibration in the rough Bergomi model by Wasserstein distance ArXiv ID: 2512.00448 “View on arXiv” Authors: Changqing Teng, Guanglian Li Abstract Despite the empirical success in modeling volatility of the rough Bergomi (rBergomi) model, it suffers from pricing and calibration difficulties stemming from its non-Markovian structure. To address this, we propose a comprehensive computational framework that enhances both simulation and calibration. First, we develop a modified Sum-of-Exponentials (mSOE) Monte Carlo scheme which hybridizes an exact simulation of the singular kernel near the origin with a multi-factor approximation for the remainder. This method achieves high accuracy, particularly for out-of-the-money options, with an $\mathcal{“O”}(n)$ computational cost. Second, based on this efficient pricing engine, we then propose a distribution-matching calibration scheme by using Wasserstein distance as the optimization objective. This leverages a minimax formulation against Lipschitz payoffs, which effectively distributes pricing errors and improving robustness. Our numerical results confirm the mSOE scheme’s convergence and demonstrate that the calibration algorithm reliably identifies model parameters and generalizes well to path-dependent options, which offers a powerful and generic tool for practical model fitting. ...

Financial Text Classification Based On rLoRA Finetuning On Qwen3-8B model ArXiv ID: 2512.00630 “View on arXiv” Authors: Zhiming Lian Abstract Financial text classification has increasingly become an important aspect in quantitative trading systems and related tasks, such as financial sentiment analysis and the classification of financial news. In this paper, we assess the performance of the large language model Qwen3-8B on both tasks. Qwen3-8B is a state-of-the-art model that exhibits strong instruction-following and multilingual capabilities, and is distinct from standard models, primarily because it is specifically optimized for efficient fine tuning and high performance on reasoning-based benchmarks, making it suitable for financial applications. To adapt this model, we apply Noisy Embedding Instruction Finetuning and based on our previous work, this method increases robustness by injecting controlled noise into the embedding layers during supervised adaptation. We improve efficiency further with Rank-stabilized Low-Rank Adaptation low-rank optimization approach, and FlashAttention, which allow for faster training with lower GPU memory. For both tasks, we benchmark Qwen3-8B against standard classical transformer models, such as T5, BERT, and RoBERTa, and large models at scale, such as LLaMA1-7B, LLaMA2-7B, and Baichuan2-7B. The findings reveal that Qwen3-8B consistently surpasses these baselines by obtaining better classification accuracy and needing fewer training epochs. The synergy of instruction-based fine-tuning and memory-efficient optimization methods suggests Qwen3-8B can potentially serve as a scalable, economical option for real-time financial NLP applications. Qwen3-8B provides a very promising base for advancing dynamic quantitative trading systems in the future. ...

Stochastic Dominance Constrained Optimization with S-shaped Utilities: Poor-Performance-Region Algorithm and Neural Network ArXiv ID: 2512.00299 “View on arXiv” Authors: Zeyun Hu, Yang Liu Abstract We investigate the static portfolio selection problem of S-shaped and non-concave utility maximization under first-order and second-order stochastic dominance (SD) constraints. In many S-shaped utility optimization problems, one should require a liquidation boundary to guarantee the existence of a finite concave envelope function. A first-order SD (FSD) constraint can replace this requirement and provide an alternative for risk management. We explicitly solve the optimal solution under a general S-shaped utility function with a first-order stochastic dominance constraint. However, the second-order SD (SSD) constrained problem under non-concave utilities is difficult to solve analytically due to the invalidity of Sion’s maxmin theorem. For this sake, we propose a numerical algorithm to obtain a plausible and sub-optimal solution for general non-concave utilities. The key idea is to detect the poor performance region with respect to the SSD constraints, characterize its structure and modify the distribution on that region to obtain (sub-)optimality. A key financial insight is that the decision maker should follow the SD constraint on the poor performance scenario while conducting the unconstrained optimal strategy otherwise. We provide numerical experiments to show that our algorithm effectively finds a sub-optimal solution in many cases. Finally, we develop an algorithm-guided piecewise-neural-network framework to learn the solution of the SSD problem, which demonstrates accelerated convergence compared to standard neural network approaches. ...

DeFi TrustBoost: Blockchain and AI for Trustworthy Decentralized Financial Decisions ArXiv ID: 2512.00142 “View on arXiv” Authors: Swati Sachan, Dale S. Fickett Abstract This research introduces the Decentralized Finance (DeFi) TrustBoost Framework, which combines blockchain technology and Explainable AI to address challenges faced by lenders underwriting small business loan applications from low-wealth households. The framework is designed with a strong emphasis on fulfilling four crucial requirements of blockchain and AI systems: confidentiality, compliance with data protection laws, resistance to adversarial attacks, and compliance with regulatory audits. It presents a technique for tamper-proof auditing of automated AI decisions and a strategy for on-chain (inside-blockchain) and off-chain data storage to facilitate collaboration within and across financial organizations. ...