Score how strongly evidence supports a claim (0-1)
Per-row — runs once for each row.
SUPPORTS({{ evidence }}, '{{ claim }}'){{ evidence }} SUPPORTS '{{ claim }}'{{ evidence }} SUPPORTS {{ claim }}| name | type | description |
|---|---|---|
| evidence | VARCHAR | — |
| claim | VARCHAR | — |
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'
)Extract hidden assumptions from an argument or claim
Returns TRUE if text_a contradicts text_b (3-class NLI)
LLM-backed contradiction check (escape hatch for CONTRADICTS)
Returns TRUE if premise entails conclusion (zero-shot NLI)
LLM-backed logical implication (escape hatch for IMPLIES)
Score how strongly evidence supports a claim (0-1)
Per-row — runs once for each row.
SUPPORTS({{ evidence }}, '{{ claim }}'){{ evidence }} SUPPORTS '{{ claim }}'{{ evidence }} SUPPORTS {{ claim }}| name | type | description |
|---|---|---|
| evidence | VARCHAR | — |
| claim | VARCHAR | — |
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'
)Extract hidden assumptions from an argument or claim
Returns TRUE if text_a contradicts text_b (3-class NLI)
LLM-backed contradiction check (escape hatch for CONTRADICTS)
Returns TRUE if premise entails conclusion (zero-shot NLI)
LLM-backed logical implication (escape hatch for IMPLIES)