ai4mat-lab/GPT_MOF_Project: MOF Data Extractor - v1.0.0
Bibliographic record
Abstract
GPT-MOF-Project In this project, we used GPT-4o-mini (LLM) to extract key elements from scientific literature regarding metal-organic frameworks features and their CO2 capture properties. Using the MOFDataExtractor.py, you can extract MOF key characteristics from literature. These characteristics include MOF Type, Secondary building block formation, Linker, Solvent, Reaction Temperature, Reaction Time, Physical state, Metal, Oxidation number, pore diameter, pore volume, ligand, multidentate, synthesis method, carboxylate ligands, imidazolate, specific surface area, BET, CO₂ selectivity, CO₂ selectivity percentage, CO₂ adsorption amount, CO₂ adsorption capacity, adsorption temperature, and adsorption pressure. You can edit the characteristics inside the code by editing the GPT prompt. To run the code: 1- Install the requirements 2-Insert your OpenAI API key in the outlined section. 3-Make a directory with the name "Directory for Literature" and put the literature in PDF format in the folder. 4-Rename the documents in numeric format to track the documents for further analysis (optional). MOF_database_cleaned. csv contains the CSV output of data extracted from 434 articles. The data has been cleaned and is machine-readable.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.004 | 0.002 |
| Meta-epidemiology (broad) | 0.002 | 0.004 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.005 | 0.003 |
| Research integrity | 0.002 | 0.004 |
| Insufficient payload (model declined to judge) | 0.238 | 0.204 |
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".