surface↓classification↓authenticity
Classificationdimension · returns varchar

AUTHENTICITY

Assess authenticity of content via zero-shot NLI

Per-row classifier — stable across GROUP BY.

classificationnlispecialist-zootext

Arguments

nametypedescription
textVARCHAR—
focusVARCHAR—

About

Authenticity dimension — buckets text by how genuine vs artificial it appears. Used for filtering bot/spam/AI-generated content. Backend: specialist zoo zero-shot NLI via /classify_batch. When no `focus` is given, uses a general 5-level authenticity scale. When `focus` is given (bot / astroturf / spam / ai_generated), the label set shifts to focus-specific buckets. For LLM-style assessment with nuanced pattern detection, use AUTHENTICITY_LLM — see authenticity_dimension_llm.cascade.yaml.

Examples

Authenticity assessed

SELECT
  authenticity ('This post seems genuine and authentic')

Nearby rabbit holes

same domain
dimension

AUDIENCE

Identify target audience via zero-shot NLI

classificationnlispecialist-zootext+1
dimension

AUDIENCE_LLM

LLM-backed audience identification (escape hatch for AUDIENCE)

classificationllmllm-escape-hatchtext
dimension

AUTHENTICITY_LLM

LLM-backed authenticity assessment (escape hatch for AUTHENTICITY)

classificationllmllm-escape-hatchtext
dimension

BUCKET

Classify text into user-specified buckets via zero-shot NLI

classificationnlispecialist-zootext
dimension

BUCKET_LLM

LLM-backed bucketing (escape hatch for BUCKET)

classificationllmllm-escape-hatchtext
scalar

CASE

Multi-branch semantic classification via specialist zoo NLI

classificationnlispecialist-zootext
Climb back to The Looking Glass