hypothesis
active
hypothesis:suppressing-the-j-space-entirely-should-impair-flexible-reasoning-while-leaving-automatic-processing-intactSuppressing the J-space entirely should impair flexible reasoning while leaving automatic processing intact.
Tested via ablation battery.
Source paper
extracted_fromAuthors
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (2)
finding
- Heavy J-space ablation leaves MMLU, SQuAD, sentiment, CoLA near baseline but drops Caesar cipher, analogy, summarization, TriviaQA, multi-hop, translation, sonnet writing below unablated Haiku 4.5.associated_withsupportsCapabilities.
- Positive control.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Information in J-space should be required for report/flexible computation tasks but not routine automatic processing.hypothesis0.852GWT-derived prediction.
- Selectivity.
- The J-space can hold more concepts when they have coherent relationships than unrelated ones.hypothesis0.804Tested with lists.
- Probe decomposition.
- Experience reports.
- The model attends to the J-space on the user prompt when determining its introspective answer, so concepts there are reportable.hypothesis0.784Motivated by elephant observation.
- Ablation flattens experiential language.
- Structural signature.