Bibliographic record
Abstract
The success of P2P file sharing applications prompted new efforts to explore the applicability of using P2P overlays in other applications, for example, to build computing clusters. These new genres of P2P applications necessitate mechanisms for discovering resources (not contents) in P2P systems. Existing solutions address this issue by converting the resource descriptions into contents and then use content discovery overlays to store and retrieve these descriptions. They use structured P2P overlays that provides the best search efficiency for content discovery. Even though this approach works well, it suffers from a number of drawbacks. For example, structured overlays are designed for discovering specific contents and querying to find a range of content makes the system inefficient. Unfortunately, it is highly likely for resources queries to include range specification like "memory ≥ 3GB." Further, these research efforts discover resources based on their attributes, but neglect connectivity metrics, latency and bandwidth. These issues warrant another look at resource discovery in distributed systems. I introduce a new resource discovery scheme called resource addressable network (RAN) to address these issues. The inability to support range queries in structured overlays is a result from assigning the nodes with random node IDs. The mechanisms introduced in this thesis produce non-random node IDs such that, while they provide a structured search space, they also retain the characteristics of the unstructured metric space where the resources are naturally located, for example, the attribute–value space; the proximity between two resources in terms of their attributes is reflected also in their node IDs. Producing such a mapping from a unstructured metric space to a structured search space and designing supporting architecture is the key contribution of this thesis. RAN is multi-tier discovery substr
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.022 | 0.007 |
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".