finding
active
finding:trained-explanations-help-weak-simulators-but-hurt-strong-ones-across-five-simulatorsTrained explanations help weak simulators but hurt strong ones across five simulators
Confident wrong counterfactuals mislead.
Source paper
extracted_from(2026) · Adam Karvonen · Euan Ong · Subhash Kantamneni · Samuel Marks
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Mixed results.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- From unfiltered results.
- Core goal statement.
- One of the updates about prosaic ML simulation.
- Practical implication.
- Antra's earlier definitive statement of the tricameral model.
- Robustness controls superposition.
- Selective pressure toward convergence via task generality
- Author's interpretation of the VTAB alignment results echoing Tolstoy