Open Dots: Securely Connecting Like-Minded People Using Machine Learning
Bibliographic record
Abstract
Often, in today’s world, it is difficult to make new acquaintances if we discuss in our social group, and even for individuals, finding someone who has common interests can be challenging. Additionally, by utilizing web3, WebRTC, and machine learning, this project facilitates safe connections between individuals with shared interests located all over the world. Every person in this world has unique interests, preferences, and dislikes. Everyone wants to get in touch with someone who shares their interests so that they can communicate more effectively. We support the connection of all types of people in this project because some people need mentoring, others want to practice interviews, others enjoy listening to stories, and still, others want to perform stand-up comedy. People who enjoy learning about new cultures from various nations and languages can also connect.The entire user’s interest data, including age, favourite subject, learned programming languages, consulting interest, interview interest, current employment history, favourite Netflix shows, favourite movies, favourite hero, and favourite song playlist, will be collected for this project. We use all the data from the various individuals to match people using a machine learning algorithm, and then, based on the outcomes, we connect the people using WebRTC so that they can communicate face-to-face while sharing real-time audio and video. More user interest information will increase the precision of finding the ideal match. Our algorithm matches you with various people who can observe, suggest to you, and help you eliminate loneliness by talking to other people while people share their screens and work on tasks like studying and coding.
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 | 0.005 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.003 | 0.009 |
| Open science | 0.003 | 0.013 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.029 | 0.018 |
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".