Very Low Cost Algorithms for Predicting the File Size of JPEG Images Subject to Changes of Quality Factor and Scaling
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
This work presents two new algorithms to predict the file size of a JPEG image subject to transformations consisting of simultaneous changes in resolution (scaling) and in quality factor (QF). To be computationally efficient, the prediction is based solely on easily accessible image parameters such as the quality factor and the original file size. A large image corpus (100,000 images), gathered by a crawler, is divided into a training set used to optimize the predictors and into a test set used to validate the predictors. For both algorithms the prediction error is shown to be of a few percents when the output parameters are close to those of the original image while remaining reasonably attractive elsewhere. Both algorithms are simple to implement and require very little processing for the prediction itself; making them good choices for implementation in transcoding servers. Following is an example of a prediction matrix from the first algorithm for images with original quality factor (QF <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in</sub> ) of 80 and for various scalings and output quality factors (QF <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">out</sub> ).
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 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 it