HUB-DT: A tool for unsupervised behavioural discovery and analysis
Bibliographic record
Abstract
Abstract There has been an expansion in the diversity of tools used to measure various aspects of brain function in behaving animals. While these tools have great potential to transform our understanding of brain function, they are of little value if the behavior of interest is poorly defined or quantified. Traditional methods of behavioural labelling focus on easily quantified gross measure, such as velocity, gate crossing, nosepokes, etc. While these measures are specific and reproducible, they are crude descriptions of behaviour at best. Manually defined behaviours, while providing increased granularity and descriptive power over specific gross measures, suffer from being inexact and somewhat arbitrary. Consistent labelling between human observers is often difficult, and even if manually defined behaviours are subsequently labelled in an automated fashion (via a supervised learning algorithm) these behaviours need to be defined ahead of time, possibly biasing the range of behaviours of interest for a given task. Here we present HUB-DT, a behavioural discovery pipeline built on the frameworks of several existing tools and methods in the space of behavioural categorisation, the specifics of which will be highlighted in this report, and designed to address the requirements of behavioral discovery.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.011 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.004 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.013 | 0.009 |
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 source (direct Gemma or distilled Codex), 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".