# q-fin.GN Published articles for q-fin.GN. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## The Digital-Energy Recomposition of the Kitchin Cycle: Exploratory Evidence from U.S. IT and Irish Data-Centre Series (1995-2025) DevFeed: [The Digital-Energy Recomposition of the Kitchin Cycle: Exploratory Evidence from U.S. IT and Irish Data-Centre Series (1995-2025)]() Original publisher: [Read original article]() Author: Bartosz Ziollko, Adam Niedzialkowski, Bartosz Szyma Published: 2026-11-04T05:00:00Z Content type: article Language: en Sources: [arXiv: Artificial Intelligence]() Topics: [Sustainable Computing]() Tags: [2025](), [adjustment](), [aggregate](), [ai](), [assets](), [boundary](), [capacity](), [cloud](), [compute](), [correlation](), [cs-ai](), [data](), [data-centre](), [decoupling](), [digital](), [econ-gn](), [electricity](), [energy](), [hyperscaler](), [it](), [physics-soc-ph](), [q-fin-cp](), [q-fin-ec](), [q-fin-gn](), [recomposition](), [series]() ### AI overview The analysis reports that the U.S. IT-GDP correlation has a statistically significant break at 2014Q3, falling from +0.45 to −0.12; the break predates the imposed Cloud-AI boundary, which is not significant after adjustment. In Ireland, data-centre electricity correlates with Real GDP during the AI era (r=+0.41, N=16), but the relationship falls to about zero using Real GNP, consistent with shared multinational tax effects. Cross-correlations also indicate GDP tends to precede data-centre load, making compute capacity coincident or moderately lagging rather than a leading indicator. The authors describe the findings as exploratory given small AI-era samples and the lack of quarterly GNI* data. ### Source excerpt arXiv:2610.33122v1 Announce Type: cross Abstract: Using quarterly FRED and CSO Ireland data over 1995Q1-2025Q4, we examine whether U.S.\ IT investment and Irish data-centre electricity are recomposing the Kitchin cycle around energy- and compute-backed assets. Three findings stand out. First, a Quandt-Andrews sup-Wald test locates a significant break in the U.S.\ IT-GDP correlation at 2014Q3 (sup-W $= 9.69$; $r$ falls from $+0.45$ to $-0.12$); the Fisher $r$-to-$z$ test survives Bonferroni adjustment ($z = +3.11$, $p_{\text{Bonf}} = 0.006$), whereas the analogous test on the imposed Cloud-vs-AI boundary does not ($p_{\text{Bonf}} = 0.164$), so ``Strategic Decoupling'' pre-dates the AI Era by approximately six years. Second, in Ireland the synchronous AI-Era correlation between metered data-centre electricity and Real GDP is large ($r = +0.41$, $N = 16$) but \emph{collapses to $r \approx 0$ when Real GDP is replaced by Real GNP}, suggesting the headline is largely an artefact of the shared multinational tax-structure footprint between hyperscaler operations and Irish gross output. Third, the Irish cross-correlation profile is asymmetric in the opposite direction to a leading-indicator reading: the largest positive coefficients cluster on the $k < 0$ side (GDP precedes data-centre load), so compute capacity is better read as coincident or moderately lagging. Given the small AI-Era samples and the absence of a quarterly multinational-adjusted aggregate such as GNI*, all coefficients are exploratory; subject to these caveats, the U.S.\ Kitchin cycle is best dated to 2014Q3, and the Irish Energy-Data Nexus is dominated by multinational firm activity. ## A Financial Brain Scan of the LLM DevFeed: [A Financial Brain Scan of the LLM]() Original publisher: [Read original article]() Author: Hui Chen, Antoine Didisheim, Mo Pourmohammadi, Luciano Somoza, Hanqing Tian Published: 2026-11-04T05:00:00Z Content type: article Language: en Sources: [arXiv: Artificial Intelligence]() Topics: [Large Language Model](), [model architecture]() Tags: [autoencoders](), [causal-inference](), [concepts](), [cs-ai](), [cs-ce](), [econ-gn](), [embeddings](), [features](), [financial](), [language-models](), [lightweight](), [llm](), [mapping](), [q-fin-ec](), [q-fin-gn](), [quantitative-finance](), [reasoning](), [steering]() ### AI overview The abstract reports that sparse autoencoders (SAEs) can map LLM activations to interpretable concepts and steer selected features. Prompting models to express preferences also activates unintended concepts, making causal inference harder; SAE steering is described as smoother and more isolated. The scans find a disconnect between internal feature contributions and models' self-generated explanations, which the authors say are unreliable guides to reasoning. SAEs are also presented as a lightweight intervention for existing models that can produce interpretable embeddings and attenuate specific economic biases. ### Source excerpt arXiv:2508.21285v3 Announce Type: replace-cross Abstract: We use sparse autoencoders (SAEs) to "brain scan" large language models, mapping internal activations to interpretable concepts and enabling targeted "steering" of specific features. We show that prompting models to adopt specific preferences activates many unintended concepts, complicating causal inference. In contrast, SAEs permit smooth, more isolated steering of target concepts. Furthermore, our scans reveal a stark disconnect between the model's internal feature contributions and its self-generated explanations, showing that these explanations are unreliable guides to its reasoning. Finally, SAEs provide a lightweight intervention for existing models, producing interpretable embeddings and allowing researchers to attenuate specific economic biases. ## A Controlled Comparison of Deep Learning Architectures for Multi-Horizon Financial Forecasting: Evidence from 918 Experiments DevFeed: [A Controlled Comparison of Deep Learning Architectures for Multi-Horizon Financial Forecasting: Evidence from 918 Experiments]() Original publisher: [Read original article]() Author: Nabeel Ahmad Saidd Published: 2026-11-02T05:00:00Z Content type: comparison Language: en Sources: [arXiv: Machine Learning]() Topics: [Predictive AI](), [Time Series](), [Hyperparameter optimization](), [Deep learning](), [Machine learning]() Tags: [architectures](), [bayesian](), [benchmark](), [comparison](), [cryptocurrency](), [cs-lg](), [deep-learning](), [error](), [evaluation](), [experiments](), [financial](), [financial-forecasting](), [forecasting](), [horizon](), [hyperparameter-optimization](), [linear](), [metric](), [prediction](), [q-fin-gn](), [q-fin-st](), [rank](), [ranking](), [time-series]() ### AI overview In a controlled benchmark of 918 runs across nine architectures, 12 assets, and 4- and 24-hour forecast horizons, ModernTCN ranked first overall (mean rank 1.333) and had the lowest RMSE at 18 of 24 asset-horizon points; PatchTST ranked second. The five-stage procedure used equal-budget Bayesian optimization, frozen category configurations, three-seed training, held-out aggregation, and rank-based validation. Ranking differences were statistically strong, while rankings remained consistent across horizons and errors rose at 24 hours. Architecture accounted for much more error variance than random seed under the reported analyses. Mean directional accuracy was 50.08%, so the results establish relative performance under these benchmark conditions, not strong directional prediction. ### Source excerpt arXiv:2603.16886v2 Announce Type: replace-cross Abstract: Reliable comparison of deep learning architectures for financial forecasting requires controlled evaluation that separates architectural effects from hyperparameter tuning, random initialization, forecast horizon, and asset characteristics. We present a five-stage benchmark using equal-budget Bayesian hyperparameter optimization, category-level configuration freezing, three-seed final training, held-out metric aggregation, and rank-based statistical validation. Nine architectures from Transformer, MLP/linear, convolutional, and recurrent families are evaluated with direct multi-step prediction from five OHLCV features across 12 assets (four cryptocurrency, four foreign exchange, four equity-index instruments), using chronological 70/15/15 splits of 30,000 hourly windows per asset at 4- and 24-hour horizons. The benchmark includes 918 runs (270 optimization trials, 648 final training runs). Across 24 asset-horizon points, ModernTCN has mean rank 1.333 and the lowest RMSE in 18 points (75.0%), followed by PatchTST (mean rank 2.000). Global ranking differences are strongly supported by an Iman-Davenport test (F(8,184)=101.36, p<1e-15), with 33 of 36 Holm-adjusted pairwise comparisons significant. Rankings are consistent across horizons for all 12 assets (rho>=0.683; Stouffer p=3.47e-10), while errors increase at the longer horizon. Architecture explains 99.90% of raw error variance and 68.33% after within-slot normalization excluding LSTM; seed variance contributes at most 0.04% (0.02% without LSTM). Mean directional accuracy is 50.08%. These findings provide a statistically validated comparison of nine architectures, identify ModernTCN and PatchTST as leading performers under the evaluated conditions, and offer a reproducible benchmark for multi-asset financial time-series forecasting. ## Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries DevFeed: [Right Numbers, Wrong Questions: Evaluating LLMs on Underspecified Financial Queries]() Original publisher: [Read original article]() Author: Radha Yadav, Prasanna Devadiga, Peeyush Mishra, Apoorv Singh Published: 2026-10-30T04:00:00Z Content type: article Language: en Sources: [arXiv: Artificial Intelligence]() Topics: [AI Chat](), [Finance]() Tags: [ai](), [cs-ai](), [cs-cl](), [financial](), [funds](), [llms](), [models](), [q-fin-gn](), [queries](), [question](), [tax]() ### AI overview In Indian mutual fund queries, assistants can return a valid figure while answering a different interpretation of the user's question--a failure the authors call "frame collapse." In separate tests, models adopted ambiguously labelled figures, and when alternatives were labelled, their ordering depended on presentation layout. When investor details were missing, weaker agents assumed defaults or outdated tax rules; requiring the missing detail did not ensure they used it. Data checks missed these errors because the answers matched the underlying data. An AI judge identified mislabelled figures only when given field definitions and still accepted answers that silently selected another interpretation. The study shows how these failures arise, not how often, and proposes controls for financial assistants. ### Source excerpt arXiv:2610.38631v1 Announce Type: new Abstract: Financial assistants answer questions that sound factual but depend on what the user leaves unsaid: what a data figure measures, which product variant is meant, and the investor's situation and the rules that apply. An assistant that ignores these can still answer with a real number from its data, one that answers a different question. We call this frame collapse. We study it in Indian mutual funds, where product variants and tax rules are formally defined, so the correct answer can be computed for every reading. One study tests each challenge. Given an ambiguously labelled figure, models used it, often under the user's label. Given every alternative labelled, they listed them all, but the layout decided which came first. Missing a fact about the investor, weaker agents assumed a default or an outdated tax rule; requiring the fact did not guarantee its use. Because such answers match their data, checks against the data pass them. An AI judge caught mislabelled figures only when told what each field means, and still passed answers that silently chose another reading. We show how these failures arise, not how often, and propose controls for financial assistants.