Personalized Neural State Segmentation: Validating the Greedy State Boundary Search Algorithm for Individual-level Functional Magnetic Resonance Imaging Data
Bibliographic record
Abstract
Humans segment experience into a nested series of discrete events, separated by neural state transitions that can be identified in fMRI data collected during passive movie viewing. Current neural state segmentation techniques manage the noisiness of fMRI data by modeling groups of participants at once. However, the perception of event boundaries is itself idiosyncratic. As such, we developed a denoising pipeline to separate meaningful signal from noise and validated the Greedy State Boundary Search algorithm for use in individual participants. We applied the Greedy State Boundary Search to publicly available (1) young adult and (2) developmental fMRI data sets. After extensive denoising, we confirmed that personalized young adult neural state transitions exhibited a canonical temporal cortical hierarchy and were related to normative behavioral boundaries across time in key regions such as posterior parietal cortex. Furthermore, we used machine learning to show that the strongest neural transitions from across cortex could be used to predict the timing of normative boundary judgments. Results from the developmental data set also demonstrated important boundary conditions for estimating personalized neural state transitions. Nonetheless, some brain-behavior relations were still apparent in individually modeled developmental data. Finally, we ran two individual differences analyses demonstrating the utility of our method. These validations pave the way for applying personalized fMRI modeling to the study of event segmentation; what meaningful insights could we be missing when we average away what makes each of us unique?
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.
How this classification was reachedexpand
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 | 0.002 | 0.017 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".