# Trained, Frozen, or Absent: Identifying What a Quantum Layer Contributes to Cross-Sectional Equity Ranking

DevFeed: [Trained, Frozen, or Absent: Identifying What a Quantum Layer Contributes to Cross-Sectional Equity Ranking](<https://devfeed.tech/articles/trained-frozen-or-absent-identifying-what-a-quantum-layer-contributes-to-cross-sectional-equity-ranking-126017.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10801>)

Author: Chi-Sheng Chen, Xinyu Zhang, En-Jui Kuo, Rong Fu, Qiuzhe Xie, Fan Zhang

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Quantum Enablement](<https://devfeed.tech/topics/quantum-enablement.md>), [Finance](<https://devfeed.tech/topics/finance.md>), [AI Models](<https://devfeed.tech/topics/ai-models.md>), [quantum mechanics](<https://devfeed.tech/topics/quantum-mechanics.md>)

Tags: [ablation](<https://devfeed.tech/tags/ablation.md>), [abstract](<https://devfeed.tech/tags/abstract.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [backtest](<https://devfeed.tech/tags/backtest.md>), [best](<https://devfeed.tech/tags/best.md>), [bootstrap](<https://devfeed.tech/tags/bootstrap.md>), [but](<https://devfeed.tech/tags/but.md>), [circuit](<https://devfeed.tech/tags/circuit.md>), [code](<https://devfeed.tech/tags/code.md>), [components](<https://devfeed.tech/tags/components.md>), [condition](<https://devfeed.tech/tags/condition.md>), [contribution](<https://devfeed.tech/tags/contribution.md>), [control](<https://devfeed.tech/tags/control.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [daily](<https://devfeed.tech/tags/daily.md>), [days](<https://devfeed.tech/tags/days.md>), [equity](<https://devfeed.tech/tags/equity.md>), [layer](<https://devfeed.tech/tags/layer.md>), [q-fin-cp](<https://devfeed.tech/tags/q-fin-cp.md>), [quant-ph](<https://devfeed.tech/tags/quant-ph.md>), [quantum](<https://devfeed.tech/tags/quantum.md>), [ranking](<https://devfeed.tech/tags/ranking.md>)

## AI overview

In this study of daily cross-sectional ranking for 2,000 Tokyo Stock Exchange equities, the trained quantum circuit performed equivalently to a frozen circuit within 0.03 annualized Sharpe on 500 out-of-sample days (p = 0.0055). The protocol compared six configurations through one code path, using four walk-forward folds, five seeds, classical baselines, statistical controls, and a locked holdout. When the circuit was the ranking head's only input, trained and frozen versions were equivalent within 0.25; comparison with a network without a circuit resolved only a 0.50 difference. No condition was distinguishable from zero (best Deflated Sharpe Ratio: 0.17). The holdout reproduced the ablation on a profitable window, while a test on 2,000 U.S. equities reproduced it in a setting where every condition lost money.

## Source excerpt

arXiv:2611.10801v1 Announce Type: cross Abstract: Hybrid quantumclassical models are increasingly proposed for nancial prediction, but reported gains are rarely separated from the classical components around them. We study a hybrid quantum temporal convolutional network for daily cross-sectional ranking of 2000 Tokyo Stock Exchange equities under a protocol built to make the quantum contribution identiable: six conditions (circuit trained, frozen or absent, a parameter-matched classical surrogate, and the circuit alone, trained or frozen) through one code path; four walk-forward folds with ve seeds; bootstrap intervals, Deated Sharpe Ratios, backtest-overtting probabilities and family-wise error control; ve classical baselines including a gradient-boosted tree; and a locked holdout. On 500 out-of-sample days two one-sided tests place the trained-versus-frozen dierence inside 0.03 annualised Sharpe (p = 0.0055, minimum detectable eect 0.02): the circuit is equivalent to a frozen one, not merely indistinguishable from it. With the circuit as the head's only input the two are equivalent inside 0.25; against the network with no circuit the design resolves only 0.50. No condition is distinguishable from zero (best De-ated Sharpe Ratio 0.17). The holdout reproduces the ablation on a protable window, and 2000 US equities reproduce it where every condition loses money.