DEPRECATED: Matcher (Version 1) 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 V1: Chunk and Compete This is the initial release of the GAME Matcher module. It introduces 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 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. Chunk-and-Compete Algorithm: To handle potentially thousands of choices, this version implements a two-stage, map-reduce style algorithm: Chunking: The extensive list of potential choices is broken down into smaller, manageable chunks (e.g. of 25 items). The LLM then finds the best candidate ("champion") within each chunk. Championship: All champions from the first stage are collected into a single list. The LLM then performs a final comparison on this list of champions to determine the single best overall match. 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_v1.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 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 | 0.001 |
| 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 | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".