A case-based reasoning approach to learning state-based behavior
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
Learning from Observation involves creating agents that observe experts performing tasks and imitate them. Case-Based Reasoning (CBR) is a tool that can be used for this purpose. Regular CBR can only learn memoryless behavior: behavior that doesn't rely on the past. Temporal Backtracking (TB) is an approach to learning state-based behavior that uses re-cency as its inductive bias, which may or may not be relevant to the agent behavior. We show how TB can be viewed as a particular case of a more generalized case-based approach to learning state-based behavior that can accommodate other inductive biases. We then propose five alternative similarity metrics to learn three different state-based behaviors in a 2D vacuum cleaner domain, and compare their performance to the TB algorithm's performance. We show that none of the proposed metrics (nor TB) is a one-size-fits all algorithm for learning state-based behavior.
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 | 0.008 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| 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