Experiments / expC_semantic_locality
expC_semantic_locality
Cross-prompt semantic locality: do same-domain prompts reuse the same weight regions?
View benchmark implementation (benchmark.py) →
Hypothesis
documentexpC_semantic_locality/hypothesisauthorSimon-Pierre BouchercreatedMon Aug 10 2026 20:00:00 GMT-0400 (heure avancée de l’Est)statusdraft
Hypothesis — expC_semantic_locality#
Hypothesis
<what we believe and why>
Falsification criterion
<the concrete measurable outcome that would prove this wrong>
Method
<exact procedure, model(s), data, seeds, measurement points>
Baseline
<what this is compared against — no straw men>
Result
<filled after the run: numbers, with mean/median/std and run count>
Interpretation
<what the numbers mean; alternative explanations considered>
Next experiment
<the most informative follow-up given this result>Analysis
documentexpC_semantic_locality/analysisauthorSimon-Pierre BouchercreatedMon Aug 10 2026 20:00:00 GMT-0400 (heure avancée de l’Est)statusdraft
Analysis — expC_semantic_locality#
To be written after results exist. Must include the seven-field block and the evidence standard of CLAUDE.md §10.
README
documentexpC_semantic_locality/READMEauthorSimon-Pierre BouchercreatedMon Aug 10 2026 20:00:00 GMT-0400 (heure avancée de l’Est)statusdraft
expC_semantic_locality#
Cross-prompt semantic locality: do same-domain prompts reuse the same weight regions?
Status: scaffolded 2026-08-11, not yet run.