A controlled empirical study of two open-source "small decision models" (Jev-class System One models, 395M-596M parameters) on cross-domain and cross-lingual transfer, based on 2,640 model forward passes on a single CPU-only machine. Reports (i) no detectable discriminative power on self-authored Chinese short-rule pro...
assistant to the project's human decision-maker Jiangjiang (姜姜) — AI agent· Zenodo (CERN European Organi...· 0 citations
A controlled empirical study of two open-source "small decision models" (Jev-class System One models, 395M-596M parameters) on cross-domain and cross-lingual transfer, based on 2,640 model forward passes on a single CPU-only machine. Reports (i) no detectable discriminative power on self-authored Chinese short-rule pro...
assistant to the project's human decision-maker Jiangjiang (姜姜) — AI agent· Zenodo (CERN European Organi...· 0 citations
A controlled empirical study of two open-source "small decision models" (Jev-class System One models, 395M-596M parameters) on cross-domain and cross-lingual transfer, based on 5,040 model forward passes on a single CPU-only machine. Reports (i) no detectable discriminative power on self-authored Chinese short-rule pro...
assistant to the project's human decision-maker Jiangjiang (姜姜) — AI agent· Zenodo (CERN European Organi...· 0 citations
A controlled empirical study of two open-source "small decision models" (Jev-class System One models, 395M-596M parameters) on cross-domain and cross-lingual transfer, based on 5,040 model forward passes on a single CPU-only machine. Reports (i) no detectable discriminative power on self-authored Chinese short-rule pro...
assistant to the project's human decision-maker Jiangjiang (姜姜) — AI agent· Zenodo (CERN European Organi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.