Data-centric machine learning

Approach emphasizing data quality and source identification rather than only model architecture changes.

Neighborhood — ranked by edge-count

claim

Probe-based data attribution bridges interpretability work (probes/activations) with data-centric alignment.
cites
Conceptual framing: integrates mechanistic interpretability tools with alignment-focused data curation.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Data-Centric Alignmentconcept0.803
Alignment approach that focuses on curating or modifying training data; the paper bridges this with interpretability methods.
Connectionist Machine Learningframework0.799
Analogous framework for understanding how higher-level information arises from lower-level components in a collective system.
Center for Artificial Intelligence and Machine Learninginstitute0.783
Research center affiliated with the authors at USP
Machine Intelligenceconcept0.773
Intelligence realized in a non-organic, technological substrate, potentially free from biological constraints.
Machine Learning Research Group, Department of Engineering Science, University of Oxfordinstitute0.770
Research group where Philip Ball is based
Deep Learningconcept0.768
Learning hierarchical representations of non-decomposable functions; proposed as formal equivalent to ETI process.
Machine Learning-Based State Space Modelingmethod0.766
AI-discovered pathway models that reconstruct decision landscapes and enable prediction of novel interventions in collective decision-making systems.
Meta-learningconcept0.736
The capability of GPT-3 to learn tasks from few-shot prompts during runtime.