Reproducibility package for: Material-grouped validation of machine-learning surrogates for fibre-reinforced polymer composites with implications for additive manufacturing and AI-assisted design
Identification
- Public canonical key
- radar:r-2bb59b7cfe290adae381f4aee0a79f53
- Authors
- Byron Oviedo
- Reported year
- 2026
- Reported language
- en
- Source type
- dataset
- First detected
- 2026-11-14T01:59:49.873703+00:00
- Last metadata observation
- 2026-11-14T01:59:49.873703+00:00
- Last HTTP verification
- Not checked
Institutions reported by the source
Universidad Técnica Estatal de Quevedo
Reported affiliation countries
EC
Documentary abstract — original language
This package accompanies "Material-grouped validation of machine-learning surrogates for fibre-reinforced polymer composites with implications for additive manufacturing and AI-assisted design" (B. W. Oviedo-Bayas, *Discover Composites*, revised submission). ## Contents - `supp_reproduce_all.py` is the single analysis script. It produces every number, table and figure in the manuscript and in the Supplementary Information.- `results/results.json` holds all computed metrics. The manuscript text and tables are filled from this file.- `results/run_metadata.json` records the package versions, random seeds and run settings.- `results/table_S1_configurations.csv` is Supplementary Table S1, listing the 28 material configurations.- `results/holdouts.csv` gives the metrics for each of the 150 group hold-outs.- `results/fig_*.png` are Figures 1–6. ## How to run 1. Download `data.xlsx` from https://github.com/catauggie/TPCM (Berladir et al., *Polymers* 2025, 17, 694).2. Install the packages: `pip install pandas numpy scikit-learn openpyxl matplotlib quantile-forest`. The published numbers used Python 3.13.16, NumPy 2.5.3, pandas 3.0.5, scikit-learn 1.9.1, quantile-forest 1.4.2 and Matplotlib 3.11.2.3. Run `python supp_reproduce_all.py --data data.xlsx --out results`. A full run takes about 35 minutes on two CPU cores. Add `--fast` for a quick smoke test with fewer repeats and trees. ## Determinism Every random operation is seeded (see Table 1 of the manuscript and `run_metadata.json`). The grouped partitions come from a seeded permutation of configuration labels (NumPy PCG64), not from scikit-learn's `GroupKFold`, whose fold assignment has changed between releases. The primary protocol, leave-one-configuration-out, uses no random partition at all.
Identifiers
- OPENALEX
- https://openalex.org/W7221810611
- DOI
- 10.5281/zenodo.23373191
Documentary context
- Documentary family
- dataset
- Source-reported types
- dataset
Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.
Sources
OpenAlex · Record 1
Cite this reference
Byron Oviedo. Reproducibility package for: Material-grouped validation of machine-learning surrogates for fibre-reinforced polymer composites with implications for additive manufacturing and AI-assisted design. 2026. https://doi.org/10.5281/zenodo.23373191
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.
- APA
- Byron Oviedo. (2026). Reproducibility package for: Material-grouped validation of machine-learning surrogates for fibre-reinforced polymer composites with implications for additive manufacturing and AI-assisted design. https://doi.org/10.5281/zenodo.23373191
- Chicago
- Byron Oviedo. Reproducibility package for: Material-grouped validation of machine-learning surrogates for fibre-reinforced polymer composites with implications for additive manufacturing and AI-assisted design. 2026. https://doi.org/10.5281/zenodo.23373191
- ISO 690
- Byron Oviedo. Reproducibility package for: Material-grouped validation of machine-learning surrogates for fibre-reinforced polymer composites with implications for additive manufacturing and AI-assisted design. 2026. https://doi.org/10.5281/zenodo.23373191
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR Global Rights of Nature Legal Library. Reproducibility package for: Material-grouped validation of machine-learning surrogates for fibre-reinforced polymer composites with implications for additive manufacturing and AI-assisted design. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-2bb59b7cfe290adae381f4aee0a79f53/ · Last HTTP verification: not performed
Research dossiers and documentary relations
Source roles
Bibliographic / original publication source · https://doi.org/10.5281/zenodo.23373191
An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.
Documentary status
Relevance pending
Library
This identity is not yet included in the Legal Library.