Puppet Master: designing reactive character behavior by demonstration
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
Puppet Master is a system that enables designers to rapidly create interactive and autonomous animated charac-ter behaviors that react to a main character controlled by an end-user. The behavior is designed by demonstration, allowing non-technical artists to intuitively design the style, personality, and emotion of the character, traits which are very difficult to design using conventional programming. During training, designers demonstrate paired be-havior between the main and reacting characters. During run time, the end user controls the main character and the system synthesizes the motion of the reacting character using the given training data. The algorithm is an extension of Image Analogies [HJO∗01], modified to synthesize dynamic character behavior instead of an image. We introduce non-trivial extensions to the algorithm such as our selection of features, dynamic balancing between similarity metrics, and separate treatment of path trajectory and high-frequency motion texture. We implemented a prototype system using physical pucks tracked by a motion-capture system and conducted a user study demon-strating that novice users can easily and successfully design character personality and emotion using our system and that the resulting behaviors are meaningful and engaging.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.002 | 0.001 |
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