A combined AST-plus-embedding classifier achieves 89% accuracy assigning CogTax levels to 585 expert-annotated Linux/bash commands, outperforming either representation alone¶
Claim · All claims
Evidence · 1 study · designr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? A classifier combining syntactic AST representations with semantic embeddings achieves 89% accuracy on 585 expert-annotated Linux/bash commands, outperforming either representation alone and demonstrating cross-language extensibility. → Alonso-Carracedo 2026
Evidence¶
Alonso-Carracedo 2026¶
Alonso-Carracedo, M., Fernandez-Boullon, R., Celard, P., Rodríguez-Martínez, F. J., & Otero-Cerdeira, L. (2026). CogTax: A Four-Level Cognitive Taxonomy for Command-Line Computing Education. arXiv. https://arxiv.org/abs/2607.00140 doi:10.48550/arxiv.2607.00140
q2 · i? · design · r2
Evaluation of the combined classification approach on the 585-command expert-annotated Linux/bash dataset, reported in the article's abstract as achieving "89% accuracy, outperforming either representation alone". The detailed results section was not available in the supplied text.
"this combined approach achieves 89% accuracy, outperforming either representation alone, and demonstrates cross-language extensibility through structural equivalences across command languages."
Discussion¶
Related Claims¶
- An AST-only structural classifier substantially exceeds random baseline accuracy in predicting CogTax levels, with L1–L3 mutually confused and L4 perfectly precise — related
- Taxonomy level is defined as the maximum of cognitive complexity and operational impact, ensuring monotone coverage of both dimensions — related
- Combining semantic and process features yields the best difficulty prediction; semantic embeddings alone trail the full model by 7.4–12.1 macro-F1 points on SAT Math — a broader claim this one bears on
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
combined-ast-embedding-classifier-89-accuracy |
title |
A combined AST-plus-embedding classifier achieves 89% accuracy assigning CogTax levels to 585 expert-annotated Linux/bash commands, outperforming either representation alone |
description |
A combined AST-plus-embedding classifier achieves 89% accuracy assigning CogTax levels to 585 expert-annotated Linux/bash commands, outperforming either representation alone |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
recheck_by |
2029 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — alonso-carracedo-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.