DEPRECATED_Matcher (Version 2) for Automated Task Alignment in the Genomic API for Model Evaluation (GAME)
Bibliographic record
Abstract
This record provides a Matcher container that runs an automated task alignment service powered by a local LLM using Ollama, to perform semantic ontology matching. It bundles the gemma3:12b model and all necessary Python dependencies to map fuzzy, free-text user inputs to canonical terms from a controlled vocabulary. It operates as a standalone TCP server, accepting JSON-formatted requests and returning the best-matched term. Matcher V2: Recursive Tournament This version is a direct evolution of V1. It introduces a significant algorithmic and accuracy improvements for greater scalability. It retains the core architecture of V1 -- a robust framework for LLM-based entity matching in three key genomic domains: cell types, species, and binding molecules (e.g., Transcription Factors, Histone Modifications). Core Functionality and Improvements from V1 LLM-Powered Matching: Utilizes the gemma3:12b model via the Ollama framework to understand the semantic content of a user's input term. Prompting: Employs sophisticated, few-shot prompt engineering to guide the LLM's reasoning. Recursive Tournament Algorithm: The "Chunk-and-Compete" method of V1 is upgraded to a more scalable, multi-stage recursive tournament. Chunking: The extensive list of potential choices is broken down into smaller, manageable chunks (e.g. of 20 items). The LLM then finds the best candidate ("champion") within each chunk. Recursive Chunking: After the initial chunking round, the algorithm checks the number of resulting champions. If it exceeds the chunk size, it treats the champions as a new list to be chunked and runs another elimination round. This process repeats recursively, like a tournament bracket, until a small group of finalists remains for the final decision. This ensures the matcher can gracefully handle massive choice lists without failure. Enhanced Granularity Matching: The prompt for cell_type matching has been refined with new instructions and examples. V2 is now better able to discern the required level of detail. For instance, given the input mammary epithelial cell, it can correctly choose "mammary epithelial cell female" over the more specific "mammary epithelial cell female adult (23 years)" from a list of choices, and vice-versa if the input is more specific. This leads to more contextually appropriate matches. Running the container Ensure Apptainer is intalled in the system the container is intended to run. Always run the Matcher first, so it can listen for incoming connections from Predictors: apptainer run --containall --nv matcher_v2.sif MATCHER_IP MATCHER_PORT Note on Flags: --nv: This flag enables NVIDIA GPU support inside the container. It is essential for performance, as the LLM requires GPU acceleration for timely inference. --containall: This flag ensures the container is fully self-contained. It prevents the container from accessing the user's home directory or other host system files, guaranteeing that the service runs with only the software and libraries packaged within it for maximum reproducibility. Additional information about the GAME framework can be found on GitHub: Genomic API for Model Evaluation
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.003 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.119 | 0.065 |
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".