Keeping the “glass box” transparent: Comparing expert and AI-generated ratings and feedback in stealth assessment for judgement-focused negotiation simulations
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Negotiation is a hard-to-measure competency, involving a dynamic balance of relational and outcome-oriented dimensions. Generative AI has opened avenues for delivering real-time assessment and feedback after a negotiation simulation. However, there is a tension between the “black box” architecture of GenAI and the “glass box” approach of stealth assessment. This case study uses a mixed-method approach to compare ratings and feedback given by GenAI and a human expert on seven negotiation transcripts. The results illustrate that with predetermined criteria, GenAI provides more formulaic feedback across various simulations, while the human expert’s feedback is more contextually sensitive and adapted to the uniqueness of each negotiation exchange. Implications for stealth assessment and negotiation feedback are discussed.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it