Scalable and energy efficient software architecture for human behavioral measurement
Bibliographic record
Abstract
Understanding human behavior is central to many professions in engineering, health and the social sciences, and has typically been measured through surveys, direct observation and interviews. However, these methods are known to have drawbacks, including bias, problems with recall accuracy, and low temporal fidelity. Recently, a new tool has been employed to great effect: the smartphone. Modern mobile phones have a variety of sensors that can be used to find activity patterns and infer the underlying human behaviors, placing a heavy load on the phone's battery. Social science researchers hoping to leverage this new technology must carefully balance the fidelity of the data with the cost in phone performance. Crucially, many of the data collected are of limited utility because they are redundant or unnecessary for a particular study question. Previous researchers have attempted to address this problem by modifying the measurement schedule based on sensed context, but a complete solution remains elusive. In the approach described here, measurement is made contingent on sensed context and measurement objectives through extensions to a configuration language, allowing significant improvement to flexibility and reliability. Empirical studies indicate a significant improvement in energy efficiency with acceptable losses in data fidelity.
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 | 0.008 | 0.027 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.006 |
| Open science | 0.007 | 0.006 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.006 | 0.004 |
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".