Benjamini-Hochberg FDR correction

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

Neighborhood — ranked by edge-count

finding

method

Benjamini-Hochberg (BH) correction
related_to
Applied within concept/endpoint families to control false discovery rate across parallel tests
Causal Contrast Z-Score
uses
Per-(emotion, token) z-score computed as injected emotion activation minus mean of 170 other probes, contrasted against no-steering baseline
One-Sided Permutation Test for Emotion Word Mention
uses
Tests whether SAE features whose self-evaluation transcripts mention a specific emotion word have higher cosine similarity to that emotion probe

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 Correctionmethod0.679
Multiple comparisons correction applied to Wilcoxon p-values for the Strange Stories task with three score categories.
Feedback and Correctionconcept0.661
The adaptive, incremental nature of living process, allowing small steps with continuous evaluation and adjustment.
Synthetic Self-Correction Fine-Tuningmethod0.659
Fine-tuning on Claude-generated self-correction examples with loss masking to induce ESR-like behavior
Hypothesis: Fine-tuning reduces mismatch dr between prior and targethypothesis0.658
UCCT's theoretical prediction about how fine-tuning maps onto the anchoring score