# DeepVerified Results

DeepVerify provides a set of API endpoints to evaluate the factual accuracy, consistency, and reliability of information by checking against an established knowledge base and evaluating answer quality and source credibility.

## Endpoints

1. Fact Check  <mark style="color:blue;">/fact-check</mark>&#x20;

This endpoint assesses the factual accuracy and completeness of the provided information based on established knowledge.

Parameters:&#x20;

* input\_text (required): The text or information to be fact-checked.&#x20;

Evaluations:&#x20;

* Consistency with Established Knowledge: Checks if the information aligns with verified knowledge sources.&#x20;
* Fabrication: Detects if any parts of the information appear fabricated or invented.&#x20;
* Omission & Incomplete Information: Identifies missing elements that may lead to incomplete information.&#x20;

**Response Structure:**

<br>

```json
{
  "consistency_score": 0.95,
  "fabrication": "No",
  "omission_incomplete_info": "Some details are missing.",
  "fact_blocks": ["FactBlock_001", "FactBlock_002"],
  "explanation_paths": [
    {"path": ["FactBlock_001", "FactBlock_003"], "description": "Knowledge consistency path"}
  ]
}
```

***

2. Answer Check <mark style="color:blue;">/answer-check</mark>&#x20;

This endpoint evaluates the quality and accuracy of answers or responses based on logical inferences, context, and answer detail.

Parameters:&#x20;

* input\_text (required): The answer or response to evaluate.&#x20;

Evaluations:&#x20;

* False Inferences: Detects incorrect logical reasoning.&#x20;
* Parroting or Reiteration: Identifies cases where the answer merely repeats information.&#x20;
* Context Consistency: Evaluates if the answer is contextually consistent.&#x20;
* Misinterpretation of Question: Checks if the answer misinterprets the question.&#x20;
* Bias Detection: Identifies potential biases in the answer.&#x20;
* Vague or Broad Answers: Detects if the answer is too vague or overly generalized.&#x20;
* Exaggeration/Distortion&#x20;
* Overgeneralization or Simplification: Detects oversimplification or generalizations.

**Response Structure:**&#x20;

```json
{
  "false_inference": "Yes",
  "parroting": "No",
  "context_consistency": 0.87,
  "misinterpretation": "No",
  "bias_detection": "Detected",
  "vague_broad_answer": "Yes",
  "exaggeration": "No",
  "simplification": "Yes",
  "fact_blocks": ["FactBlock_005", "FactBlock_006"],
  "explanation_paths": [
    {"path": ["FactBlock_005", "FactBlock_006"], "description": "Reasoning path"}
  ]
}

```

***

3\. Reference Check <mark style="color:blue;">/reference-check</mark>&#x20;

This endpoint evaluates the credibility and completeness of sources or citations.

Parameters:&#x20;

* input\_text (required): The references or citations to be evaluated.&#x20;

Evaluations:&#x20;

* Source Reliability: Calculates the reliability score based on scores stored in cited FactBlocks.&#x20;
* Negation or Incomplete Information: Detects any unsupported negations or incomplete assertions.&#x20;
* Unverifiable Citations: Verifies if AI-cited sources are accessible and authentic. (Examples: Checks if sources are present and accessible. )&#x20;

**Response Structure:**&#x20;

```json
{
  "source_reliability": 0.92,
  "negation_incomplete_info": "No",
  "unverifiable_citations": "Yes",
  "fact_blocks": ["FactBlock_007", "FactBlock_008"],
  "explanation_paths": [
    {"path": ["FactBlock_007", "FactBlock_009"], "description": "Reliability assessment path"}
  ]
}
```

***

### Result Types

The results returned by each endpoint may include the following types:

* **Score**: A numerical score with decimal points indicating evaluation accuracy or reliability.
* **Binary Value (Yes/No)**: A binary indicator for simple evaluations.
* **Text**: Explanation or detailed notes based on the evaluation.
* **List of FactBlocks**: List of FactBlocks that served as the basis for the evaluation.
* **List of FactBlocks with Paths**: A list of FactBlocks, along with paths showing how they are connected to improve explainability.