OER·harvester

Competency catalogue

The 104 active T2.3 competencies: the vocabulary the harvester searches with, the descriptor the alignment reads, and what the alignment found. Compose a harvest →

What the alignment foundHow often each was searched

How many resources the alignment reads as contributing to each competency or developing it: decided at level 2 or 3, or not decided yet and more likely than not to reach 2. 54 competencies have none, 24 one or two. Every figure is a lower bound: on a sample graded on every competency, the map counts 33% of what was graded 2 or 3, and almost nothing of the 5 competencies underlined with dots.

How many times a harvest has searched for each competency, once for each source it asked. 101 competencies have never been searched. A search is not material found: the aligned view says what came of it.

none 1–2 3–9 10–29 30+
never 1–2 3–5 6–11 12+
DDigital 94212203420012149086012303134 GGreen 0000000102000010000100010 RResilience & Entrepreneurial 004000000000000010000120000 TDeep Tech 72643202372825212335201140010

T18 Deep Tech · Skill · Advanced

Explainable AI (XAI)

Implement techniques making AI decisions interpretable

Alignment

5 resources likely to contribute to it or develop it

0 decided at level 2 or 3 · 5 not decided yet, more likely than not

On a graded sample, 1 pair was graded 2 or 3 for it, and the map counts 1.

Retrieval

0 resources harvested by searching its terms

Never searched yet.

Search vocabulary

Domain group
explainable AIXAImodel interpretabilitySHAPLIMEfeature attributioncounterfactual explanationinterpretable machine learning

Zenodo and arXiv take the whole group in one query. GitHub takes one phrase at a time and works left to right, stopping once the competency is satisfied — so on that lane this order decides which terms actually run.

The compiled queries
zenodo ("artificial intelligence" OR "machine learning" OR "generative AI" OR "deep learning" OR "reinforcement learning" OR "large language model" OR "AI") AND ("explainable AI" OR "XAI" OR "model interpretability" OR "SHAP" OR "LIME" OR "feature attribution" OR "counterfactual explanation" OR "interpretable machine learning")
arxiv (all:"artificial intelligence" OR all:"machine learning" OR all:"generative AI" OR all:"deep learning" OR all:"reinforcement learning" OR all:"large language model") AND (all:"explainable AI" OR all:"XAI" OR all:"model interpretability" OR all:"SHAP" OR all:"LIME" OR all:"feature attribution" OR all:"counterfactual explanation" OR all:"interpretable machine learning")
github · term 1 AI "explainable AI" in:name,description,readme fork:false archived:false
github · term 2 AI "XAI" in:name,description,readme fork:false archived:false
github · term 3 AI "model interpretability" in:name,description,readme fork:false archived:false
github · term 4 AI "SHAP" in:name,description,readme fork:false archived:false
github · term 5 AI "LIME" in:name,description,readme fork:false archived:false
github · term 6 AI "feature attribution" in:name,description,readme fork:false archived:false
github · term 7 AI "counterfactual explanation" in:name,description,readme fork:false archived:false
github · term 8 AI "interpretable machine learning" in:name,description,readme fork:false archived:false

Profile 8b95a744335d1a21

Alignment descriptor draft

Outcomes
  • Can apply explanation techniques such as SHAP, LIME or feature attribution to a model.
  • Can interpret explanations and their limits.
  • Can choose an explanation method for a model and audience.
Develops it

Hands-on material on explainable AI, where the learner applies explanation techniques to a model and interprets the results.

Only mentions it

A feature importance chart shown without explanation.

Alignment terms
shaplimefeature importanceexplainable aiinterpretabilitysaliency mapcounterfactual explanations

Read in a resource's text beside the domain group. They are never compiled into a search.

Neighbours

Descriptor aaebc96c4ba0

How a vocabulary becomes a search

Every candidate must match both concept groups in its title, description or keywords before any content is downloaded. Precision warnings are recorded for audit; they never silently cancel positive evidence.

  1. Official name and description
  2. AI/ML terms and domain terms
  3. Zenodo, arXiv and GitHub syntax
  4. Metadata relevance gate
Mandatory AI/ML group
artificial intelligencemachine learninggenerative AIdeep learningreinforcement learninglarge language modelAI

GitHub's repository search takes one phrase at a time. Measured against the live endpoint, a parenthesised OR group returns nothing at all where each term alone returns thousands, and the 256-character limit rejects a long group outright — so that lane issues one query per term and stops as soon as the competency is satisfied.

coverage-vocabulary-1.3.0+sha256:08ad2cd19868 · catalogue sha256:04970bfc77255b1f

What a descriptor is

A descriptor is how the alignment reads a competency: what a learner who has it can do, what a resource has to do to develop it, what only mentions it, the phrases its subject is written in, its false friends, and how to tell it from the competencies that share its words. The definition above it stays the authority.

Every descriptor is a draft until a partner approves it; 0 of 104 are approved. Read the alignment rubric →

competency-descriptors-1.0.0+sha256:3cc741a61ced