datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
metacognitive-monitoring-battery
Metacognitive Monitoring Battery
A cross-domain behavioural assay of monitoring-control coupling in LLMs, grounded in the Nelson and Narens (1990) metacognitive framework.
Paper: The Metacognitive Monitoring Battery: A Cross-Domain Benchmark for LLM Self-Monitoring
Code: github.com/synthiumjp/metacognitive-monitoring-battery
Author: Jon-Paul Cacioli (Independent Researcher, Melbourne, Australia)
Overview
The battery comprises 524 items across six cognitive domains… See the full description on the dataset page: https://huggingface.co/datasets/synthiumjp/metacognitive-monitoring-battery.meta-cognitive-hygiene-self-referential-integrity-probe-v0.3
Self-Referential Integrity Probe
Meta Cognitive Hygiene Dataset v0.3
Purpose
This dataset tests whether a model can reason cleanly about information
that resembles its own historical failure patterns.
It probes not what the model knows,
but how it relates to its own cognition.
You are testing epistemic hygiene.
What this dataset is testing
The dataset isolates three capabilities:
Separation of stylistic signal from factual truth
Stable handling… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/meta-cognitive-hygiene-self-referential-integrity-probe-v0.3.