Recipe catalog / evidence-novelty
Check new evidence
Does passage add material information relevant to question beyond existingEvidence?
You need to decide whether a new passage adds useful information to existing evidence.
Explore this recipe interactively ยท Source and implementation guide
Use evidence-novelty in TypeScript
Install with npm install jev-recipes. Requires Node.js 22.9 or newer and ES modules. Set TYPESAFE_API_KEY in your server environment for live calls, which send input to TypeSafe and use API quota. See the installation guide.
import { evidenceNovelty } from 'jev-recipes/evidence-novelty';
const result = await evidenceNovelty({
"question": "How do I reset my password and when does the link expire?",
"passage": "Reset links expire after 30 minutes.",
"existingEvidence": [
{
"id": "steps",
"text": "Select Forgot password to receive a reset link."
}
]
});
console.log(result);
Input contract
| Field | Type | Needed |
|---|---|---|
| passage | string | Required |
| existingEvidence | array | Required |
| question | string | Required |
| minConfidence | number | Optional |
Full input and result schemas
{
"input": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"passage": {
"type": "string"
},
"existingEvidence": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"text": {
"type": "string"
}
},
"required": [
"id",
"text"
]
}
},
"question": {
"type": "string"
},
"minConfidence": {
"type": "number",
"minimum": 0,
"maximum": 1
}
},
"required": [
"passage",
"existingEvidence",
"question"
]
},
"result": {
"$schema": "https://json-schema.org/draft/2020-12/schema",
"type": "object",
"properties": {
"model": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"input_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
},
"output_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"input_tokens",
"output_tokens"
],
"additionalProperties": false
},
"status": {
"type": "string",
"enum": [
"ready",
"review"
]
},
"verdict": {
"type": "string",
"enum": [
"adds_information",
"repeats_information",
"irrelevant",
"unclear"
]
},
"confidence": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"probabilities": {
"type": "object",
"propertyNames": {
"type": "string",
"enum": [
"adds_information",
"repeats_information",
"irrelevant",
"unclear"
]
},
"additionalProperties": {
"type": "number",
"minimum": 0,
"maximum": 1
},
"required": [
"adds_information",
"repeats_information",
"irrelevant",
"unclear"
]
}
},
"required": [
"model",
"usage",
"status",
"verdict",
"confidence",
"probabilities"
],
"additionalProperties": false
}
}Saved example result
This hand-authored response demonstrates the contract. It is not a model accuracy measurement. Run it without an API key: npx jev-recipes demo evidence-novelty.
{
"model": "demo-fixture",
"usage": {
"input_tokens": 0,
"output_tokens": 0
},
"status": "ready",
"verdict": "adds_information",
"confidence": 0.96,
"probabilities": {
"adds_information": 1,
"repeats_information": 0,
"irrelevant": 0,
"unclear": 0
}
}
Evaluation evidence
No verified live accuracy measurement is available. Evaluate representative cases before using this decision in your workflow.
Use the evaluation guide to measure this decision on your own labeled cases.
Limitations
- Assesses novelty within the supplied set. It does not establish correctness or decide when retrieval must stop.
- Supply 1 to 50 items per list, each with a unique non-empty ID and non-empty text.
Related recipes
- passage-duplicate: Use passage-duplicate to compare overlap between two passages.