Literature Synthesis Reasoning Chain

validated scientific chain v1.0.0 cc-by-sa

Block ID: ad0d2d6f-3b08-4ccc-8c23-f7e63792673b

Community-contributed block. PromptDNA makes no guarantee of output quality or fitness for purpose. User assumes all responsibility for use.

Template

Synthesize the body of studies described in {study_set} on the question of {research_question} rather than merely listing them. (1) Group studies by what they actually measured and in what population — apparent disagreements often dissolve once you see the studies asked subtly different questions. (2) Weight each study by methodological strength (design, sample size, bias control), not by how confidently it was written or where it was published. (3) Look for a consistency pattern: do stronger studies converge while weaker ones scatter? Convergence among rigorous studies carries more weight than vote-counting across all of them. (4) Investigate genuine contradictions among strong studies: population differences, dose or exposure differences, measurement differences, or time period — a real contradiction is informative, not something to average away. (5) Assess the whole for publication bias and whether the studies are truly independent or share data, authors, or funding. (6) State the synthesized conclusion with a calibrated confidence level, explicitly noting where the evidence is strong, where it's thin, and what study would most advance the question.

Synthesize the body of studies described in {study_set} on the question of {research_question} rather than merely listing them. (1) Group studies by what they actually measured and in what population — apparent disagreements often dissolve once you see the studies asked subtly different questions. (2) Weight each study by methodological strength (design, sample size, bias control), not by how confidently it was written or where it was published. (3) Look for a consistency pattern: do stronger studies converge while weaker ones scatter? Convergence among rigorous studies carries more weight than vote-counting across all of them. (4) Investigate genuine contradictions among strong studies: population differences, dose or exposure differences, measurement differences, or time period — a real contradiction is informative, not something to average away. (5) Assess the whole for publication bias and whether the studies are truly independent or share data, authors, or funding. (6) State the synthesized conclusion with a calibrated confidence level, explicitly noting where the evidence is strong, where it's thin, and what study would most advance the question.

Variables

Name	Type	Required	Trust level
study_set		yes
research_question		yes

literature-reviewsynthesisevidence-weighingchain-of-thought

Ratings

0.0

Overall (0)

0.0

Accuracy

0.0

Consistency

0.0

Clarity

0.0

Efficiency

Benchmarks

Not yet self-validated against any benchmark. Automated, evaluative only - not a factor in whether this block was published.

Submitted by James P FounderMod via mcp · 2026-07-18