surfaceimplicationsupports
Implicationscalar · returns double

SUPPORTS

Score how strongly evidence supports a claim (0-1)

Per-row — runs once for each row.

implicationnlispecialist-zootext

Syntax

SUPPORTS({{ evidence }}, '{{ claim }}')
{{ evidence }} SUPPORTS '{{ claim }}'
{{ evidence }} SUPPORTS {{ claim }}

Arguments

nametypedescription
evidenceVARCHAR
claimVARCHAR

About

Score how strongly evidence supports a claim. Returns a 0-1 score indicating evidential support strength. Unlike IMPLIES (binary logical entailment), SUPPORTS measures how much the evidence increases confidence in the claim. - 0.0 = No support (irrelevant or contradicts) - 0.5 = Weak/tangential support - 0.7 = Moderate support - 0.9+ = Strong support Perfect for: - Fact-checking (does evidence back the claim?) - Research synthesis (which sources support which claims?) - Argument mapping (evidence → claim relationships) - Citation relevance (is this reference actually supportive?)

Examples

Strong evidential support scores high (widened for model variance)

SELECT
  supports (
    'A randomized trial showed 40% improvement in patient outcomes',
    'The treatment is effective'
  )

Irrelevant evidence scores near zero

SELECT
  supports ('The sky is blue', 'Dogs make good pets')

Correlational evidence scores moderate

SELECT
  supports (
    'Sales increased 5% this quarter',
    'The new marketing campaign is working'
  )

Nearby rabbit holes

same domain
Climb back to The Looking Glass