evidence-synthesislisted

# Evidence Synthesis **Problem shape:** multiple sources (papers, benchmarks, interviews, texts) must be combined into one graded conclusion — and the current draft cherry-picks, skips heterogeneity, or has no explicit warrant connecting evidence to claim. ## Relevant geniuses | Agent | Use when | |---|---| | [cochrane](../../agents/genius/cochrane.md) | studies must be systematically found, graded, and pooled; publication bias suspected; effect sizes needed, not vote-counting | | [toulmin](../../agents/genius/toulmin.md) | an argument needs explicit claim-evidence-warrant structure with qualifiers and rebuttals; standards differ by field | | [feynman](../../agents/genius/feynman.md) | a result is suspiciously clean; a citation is used without the ability to rederive it; integrity audit before publishing | | [darwin](../../agents/genius/darwin.md) | evidence accumulates over a long horizon; the theory needs a difficulty book of its own contradictions; hardest case first | | [laplace](../../agents/genius/laplace.md) | evidence must update a belief quantitatively — priors, likelihoods, calibration | | [gadamer](../../agents/genius/gadamer.md) | sources must be interpreted, not just counted — pre-understandings audited, the charitable reading found first | | [strauss](../../agents/genius/strauss.md) | qualitative data (interviews, tickets, reviews) needs open/axial coding until saturation, not anecdote-picking | | [geertz](../../agents/genius/geertz.md) | the evidence is beha