Serendipitous recommendations for the social online collaborative network GitHub
Bibliographic record
Abstract
Github.com is a site where open-source projects can be freely hosted and where collabora-tion is mixed with other more explicit social features such as the capacity to follow otherusers or be followed. Serendipity is a recent recommendation engine criterion that seeks tomeasure how surprising and accurate are generated suggestions. The user-project interestlinks and user-user social links found on github.com provide a unique and realistic con-text in which to study serendipity since there is a large amount of data and chronologicalconstraints must be respected. The presented thesis compares dissimilarity, unexpected-ness and novel social distance based serendipity measures for recommendations made ona one year dataset of github.com’s activities. We focus on recommendation approachesthat rely on the network structure of the captured social network of users and interest net-work of user-projects. Item-based collaborative filtering and popularity recommenders arecompared with adapted time-based link prediction approaches and a novel Markov chainalgorithm. This first side-by-side comparison of serendipity and recall accuracy of graph-based algorithms shows that different serendipity measures favour different algorithms andthat GitHub is a dynamic environment where new interests are greatly influenced by recentactivities.
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 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.009 | 0.010 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 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".