Two studies from published papers. Each separates the question, method, reported result and limits. These studies do not evaluate an agent trading in cryptocurrency markets.
We compare a Wavelet–Transformer model with persistence for Bitcoin price forecasting. In the reported one-day test, the more complex model does not outperform the last observed price. The result concerns this model and this test.
The study evaluates forecasting errors. It does not evaluate agents, trades or trading costs. A complete reproduction has not been verified.
Read the studyWe study verbatim extraction of causal spans from financial texts in English and Spanish. VERSA combines specialised agents, question rephrasing and iterative aggregation. Development results improve on a single-pass baseline; some component tests remain preliminary estimates.
Small development samples and preliminary estimates for some component tests limit the comparison. This is information extraction, with no evidence of market forecasting or trading performance.
Read the study