Explain WHY two scientific papers reach different conclusions. Extracts each study design (species, model, intervention, assay, dose, timing, endpoint, sample size, statistic, finding, limitations), verifies every extracted value against the source text with deterministic grounding, then lists the design differences that could drive the disagreement (unranked, plus the dimensions that are identical in both and so ruled out) and suggests what evidence would resolve it. Every claim is traced to a verbatim quote; unsupported fields are returned as "not reported" rather than guessed. Never picks a winner. Each paper is given as {id} (PMID or DOI) or {text}. Requires ANTHROPIC_API_KEY – use compare_example for a no-key demonstration.

Run one of StudyDiff's built-in worked examples – real, famous contradictions with verbatim abstracts. Runs fully offline against cached papers: no API key and no network needed, so it is the quickest way to see the grounded output. Options: "mouse-inflammation" (Seok 2013 vs Takao 2015 – same datasets, opposite conclusions), "resveratrol-sirt1" (Howitz 2003 vs Beher 2009 – an assay artifact), "treg-stability" (Zhou 2009 vs Rubtsov 2010 – stable vs unstable Treg lineage, driven by the fate-mapping method).

List StudyDiff's cached worked examples (real published contradictions) that can be run with compare_example without an API key.