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

T12 Deep Tech · Knowledge · Advanced

Generative AI Architecture

Understand transformers, diffusion models, generative approaches

Alignment

25 resources likely to contribute to it or develop it

2 decided at level 2 or 3 (2 develop it) · 23 not decided yet, more likely than not

On a graded sample, 8 pairs were graded 2 or 3 for it, and the map counts 4.

Retrieval

0 resources harvested by searching its terms

Never searched yet.

Search vocabulary

Domain group
generative AI architecturedeep generative methodsgenerative methodstransformer architecturediffusion modelgenerative adversarial networkvariational autoencoderfoundation model architectureattention mechanismretrieval augmented generationRAG architecturehybrid RAGmultimodal RAGembedding retrievalvector storevector databasequery transformationhypothetical document embeddingHyDEcontext augmented generationGraphRAGRAPTORsentence window RAGself-query RAG

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 ("generative AI architecture" OR "deep generative methods" OR "generative methods" OR "transformer architecture" OR "diffusion model" OR "generative adversarial network" OR "variational autoencoder" OR "foundation model architecture" OR "attention mechanism" OR "retrieval augmented generation" OR "RAG architecture" OR "hybrid RAG" OR "multimodal RAG" OR "embedding retrieval" OR "vector store" OR "vector database" OR "query transformation" OR "hypothetical document embedding" OR "HyDE" OR "context augmented generation" OR "GraphRAG" OR "RAPTOR" OR "sentence window RAG" OR "self-query RAG")
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:"generative AI architecture" OR all:"deep generative methods" OR all:"generative methods" OR all:"transformer architecture" OR all:"diffusion model" OR all:"generative adversarial network" OR all:"variational autoencoder" OR all:"foundation model architecture" OR all:"attention mechanism" OR all:"retrieval augmented generation" OR all:"RAG architecture" OR all:"hybrid RAG" OR all:"multimodal RAG" OR all:"embedding retrieval" OR all:"vector store" OR all:"vector database" OR all:"query transformation" OR all:"hypothetical document embedding" OR all:"HyDE" OR all:"context augmented generation" OR all:"GraphRAG" OR all:"RAPTOR" OR all:"sentence window RAG" OR all:"self-query RAG")
github · term 1 AI "generative AI architecture" in:name,description,readme fork:false archived:false
github · term 2 AI "deep generative methods" in:name,description,readme fork:false archived:false
github · term 3 AI "generative methods" in:name,description,readme fork:false archived:false
github · term 4 AI "transformer architecture" in:name,description,readme fork:false archived:false
github · term 5 AI "diffusion model" in:name,description,readme fork:false archived:false
github · term 6 AI "generative adversarial network" in:name,description,readme fork:false archived:false
github · term 7 AI "variational autoencoder" in:name,description,readme fork:false archived:false
github · term 8 AI "foundation model architecture" in:name,description,readme fork:false archived:false
github · term 9 AI "attention mechanism" in:name,description,readme fork:false archived:false
github · term 10 AI "retrieval augmented generation" in:name,description,readme fork:false archived:false
github · term 11 AI "RAG architecture" in:name,description,readme fork:false archived:false
github · term 12 AI "hybrid RAG" in:name,description,readme fork:false archived:false
github · term 13 AI "multimodal RAG" in:name,description,readme fork:false archived:false
github · term 14 AI "embedding retrieval" in:name,description,readme fork:false archived:false
github · term 15 AI "vector store" in:name,description,readme fork:false archived:false
github · term 16 AI "vector database" in:name,description,readme fork:false archived:false
github · term 17 AI "query transformation" in:name,description,readme fork:false archived:false
github · term 18 AI "hypothetical document embedding" in:name,description,readme fork:false archived:false
github · term 19 AI "HyDE" in:name,description,readme fork:false archived:false
github · term 20 AI "context augmented generation" in:name,description,readme fork:false archived:false
github · term 21 AI "GraphRAG" in:name,description,readme fork:false archived:false
github · term 22 AI "RAPTOR" in:name,description,readme fork:false archived:false
github · term 23 AI "sentence window RAG" in:name,description,readme fork:false archived:false
github · term 24 AI "self-query RAG" in:name,description,readme fork:false archived:false

Profile 7bb49a1ae8d8dd29

Alignment descriptor draft

Outcomes
  • Can explain transformers, attention, diffusion models and other generative approaches.
  • Can explain retrieval-augmented generation and its components.
  • Can compare generative architectures and their trade-offs.
Develops it

Material that explains how generative models are built — attention, transformers, diffusion, GANs, RAG architecture — with diagrams and code.

Only mentions it

A generative model used through an API, with no explanation of how it works.

Alignment terms
transformerattention mechanismself-attentiondiffusion modelganvariational autoencoderretrieval-augmented generationrag

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

Neighbours

Descriptor f90b348135d5

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