Michael Burkhart, Luke Solo, Inhyeok Lee, Khaja Charles, Zewei Whiskey, " Liao, Kaveri Chhikara, Dema Therese, Wan-Ting Liao, Catherine Gao, William Parker, Brett Beaulieu-Jones
We lifted 6 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| bbj-lab/coreopsis | canonical | 4 of 6 |
| Function | Status | Where it lives |
|---|---|---|
| get_weights | Ran | bbj-lab/coreopsis/src/coreopsis/task.py code served (permissive licence) · get_code("ae8dd1052ccd2327") |
| load_cis | Ran | bbj-lab/coreopsis/recipes/plotting.py code served (permissive licence) · get_code("b7dbc0a1a6178a61") |
| re_fmt_ci | Ran | bbj-lab/coreopsis/recipes/baselines.py code served (permissive licence) · get_code("e4981ff27bed70c7") |
| rgba | Ran | bbj-lab/coreopsis/recipes/plotting.py code served (permissive licence) · get_code("1594174ea0ff58d6") |
| get_ci | Not yet run | bbj-lab/coreopsis/recipes/plotting.py code served (permissive licence) · get_code("a07f015da72cfc2c") |
| load_vocab | Not yet run | bbj-lab/coreopsis/recipes/analyze-site-data.py code served (permissive licence) · get_code("d2c193ef453aefa3") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Electronic health record foundation models are limited by institutionally siloed data and substantial performance degradation under cross-site transfer. We evaluated federated training of tokenized generative event models (GEMs) across 122,251 intensive care hospitalizations from three independent health systems harmonized to the Common Longitudinal ICU Data Format. Models were assessed on 12 post-24-hour clinical prediction tasks using within-site, cross-site, centralized, and federated training configurations. GEMs achieved the highest mean within-site and cross-site ROC-AUC and were substantially more transportable than conventional supervised models: their average cross-site penalties were 0.025 ROC-AUC and 0.027 PR-AUC, compared with 0.079 and 0.089 for LightGBM. Federated Learning (FedAvg and FedAvgM) approached the performance of centralized GEM training, with most gains obtained within 5-10 communication rounds. However, centralized multi-site training provided only modest improvements over complete local training. Multi-site models were most useful when local training data were limited, with their advantage narrowing as institutional data accumulated. These findings show that federated GEM training is technically feasible and preserves most centralized performance, but that the main open challenge is learning transportable representations to translate larger, but heterogeneous data from multiple health systems into a reliable target-site benefit.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2608.02939")
get_code_for_paper("2608.02939")
have("2608.02939")
Connect an agent — have() is free.