Replication Data for: Continuous Authentication using Touch Dynamics and its Application in Personal Health Records
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
The dataset contains 20 data files for 20 participants with overall 125794 instances of touch dynamics information collected using TouchSense (available at https://play.google.com/store/apps/details?id=org.mun.navid.touchsens). The application is implemented in such a way that it prompts the user to type in 30 random words or numbers. While the user interacts with the keyboard, it captures the touch inputs corresponding to those actions and stores them in a data file. This dataset can be used exclusively for research purposes. Commercial purposes are fully excluded. Attribute information: 1- pressure (numeric), 2- size (numeric), 3- touchmajor (numeric), 4- touchminor (numeric), 5- duration (numeric), 6- flytime (numeric), 7- shake (numeric), 8- orientation (numeric), 9- type (numeric), 10- class (AndroidId, Others) Pressure: indicates the pressure applied by a touch action. Size: indicates the number of pixels affected on the screen by a touch action. Touch Major: reports the major axis of an ellipse that represents the touched area. Touch Minor: reports the minor axis of an ellipse that represents the touched area. Duration: represents the time interval from the moment a finger touches the screen until the finger loses contact with it. Fly Time: shows the time elapsed between finishing typing a character and starting to type the next one. Shake: records the amount of vibration of the smartphone while performing touch actions. Orientation: records whether the touch behavior was recorded while the device was in the landscape orientation or the portrait one. Word or Number: records whether the touch behavior involves typing in a word or a number.
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 | 0.001 | 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 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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