← Cosmin Badea Research · the papers
§ Research

The papers, with somewhere to put them.

A working selection of my published work on moral reasoning in AI, good decision-making, interpretability, and value alignment. Not sorted by citation count. The first three are the core of the research programme; the rest extend or apply it. Each card carries my own short note, a star line for what kind of paper it is, and links to read it.

Citations
141
Total times my papers have been cited (Google Scholar).
h-index
8
The largest h such that I have h papers each cited at least h times.
i10-index
7
Number of my papers with at least 10 citations each.
As of
May 2026
Updated by hand. AI safety and ethics cites more slowly than ML proper. Sadness :(
The core research programme The first three papers below sit at the centre of what I am doing. The interpretation problem is the conceptual core, MARS is the formal system, and meta-decision-making is the architecture that holds them together.
An invitation

Thinking with these papers?

If something here sparked an objection, a question, a related result, a correction, or an idea you want to push further, I would like to hear it. Reactions from researchers, clinicians, students, and curious readers are all welcome. The shorter and sharper the better; long is also fine.

Replies come from a human, slowly. I read everything but cannot promise a response to all of it. If you would prefer to leave a note on a specific paper, each card above has a small “respond to this paper” link tucked at the foot.

A public discussion space, with moderated comments per paper, is something I would like to add later.

Sent privately to my research inbox.
Timeline · circle area approximates citation count · the three accent-rimmed circles are the core programme