DeepDive like watson is a system to extract value from dark data. Like dark matter, dark data is the great mass of data buried in text, tables, figures, and images, which lacks structure and so is essentially unprocessable .DeepDive is used to extract sophisticated relationships between entities and make inferences about facts involving those entities.I believe that the scientific knowledge to prove, explain or disprove lenr is available on the web (patents,forums,papers sometimes unrelated to the field) and accessible but not readable because the information is scattered sometimes trolled in never ending debates or interpretations.DeepDive is a trained system that uses machine learning to cope with various forms of noise and imprecision. it might help this community to solve some of the hard problems in lenr (finding a theory/recipes/ applications ) i understand that not everyone here is capable experimenting for various reasons i know that a lot of people are impatiently waiting for recipes but i think that everyone both sceptics and believers can collaborate to set up teams to feed a DeepDive system and perhaps find answers . My opinion is that excess heat is not the only answer if we could use a cheap tool to understand the phenomena it my open many doors .
i don't know if it will help answer to all the questions but i think machine learning will help narrow down the variables. a knowledge base build from deepdive can than be feed into other predictive algorithms to build models .
you can find deedive here http://deepdive.stanford.edu/
Examples of DeepDive applications :
MEMEX - Supporting the fight against human trafficking, which was recently featured on Forbes and is now actively used by law enforcement agencies.
PaleoDeepDive - A knowledge base for Paleobiologists with quality higher than human volunteers.
GeoDeepDive - Extracting dark data from geology journal articles.
Wisci - Enriching Wikipedia with structured data.