Skip to content

SRC02-E01 — Scite Smart Citations

Research R0049 — Landscape Scan
Run 2026-03-31-02
Query Q003
Source SRC02
Evidence E01

Description

Scite's Smart Citations classify whether citations support or contrast the cited claim — the closest existing feature to evidence evaluation.

URL

https://scite.ai/

Extract

Smart Citations analyze and classify 1.6B+ citations across 280M+ sources. Each citation is classified as supporting, contrasting, or mentioning. The Scite Assistant synthesizes answers backed by verified citation statements. Grounding every result in evidence through over a billion verified citation statements.

Relevance to Hypotheses

Hypothesis Relevance Strength
H1 — Comprehensive frameworks Contradicts (one dimension only) Moderate
H2 — No structured features Contradicts (citation classification is structured) Strong
H3 — Partial features Supports Strong

Feature checklist: Calibrated probability: No. Bias assessment: No. Competing hypotheses: No. Search transparency: Partial (shows citations used). Self-audit: No.

Context

FACT: Scite's supporting/contrasting classification is conceptually similar to evidence weighting in ACH. JUDGMENT: However, it classifies existing citations rather than enabling the user to evaluate competing hypotheses against evidence.