Benjamini-Hochberg (BH) correction

Applied within concept/endpoint families to control false discovery rate across parallel tests

Neighborhood — ranked by edge-count

framework

Quantitative Introspection Framework
implements
The paper's central contribution: treating LLM numeric self-report as a quantitative signal validated against probe-defined internal states with causal confirmation via steering

method

Benjamini-Hochberg FDR correction
related_to
Multiple testing correction applied to significance tests of emotion persistence and self-evaluation word associations

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.

Holm Correctionmethod0.717
Multiple comparisons correction applied to Wilcoxon p-values for the Strange Stories task with three score categories.
Implication (A → B)concept0.680
Backpropagation of Errormethod0.662
Primary training method for neural networks; cited as surprisingly effective even to its inventors, illustrating resistance to full reductionist understanding
Self-Correcting Searchmethod0.658
Technique using internal model representations as feedback loops to steer diffusion-based materials generation toward target properties.
Synthetic Self-Correction Fine-Tuningmethod0.657
Fine-tuning on Claude-generated self-correction examples with loss masking to induce ESR-like behavior
Latched Hyperprior Hypothesis (LHH)hypothesis0.654
Sustained vascular contractions engage latch-bridge mechanism, durably freezing neural circuits and isolating them from conscious experience; creates durable hyperprior commitments.
Feedback and Correctionconcept0.653
The adaptive, incremental nature of living process, allowing small steps with continuous evaluation and adjustment.