## Create Verify Job

`alpha.verify.create(VerifyCreateParams**kwargs)  -> VerifyCreateResponse`

**post** `/api/alpha/verify`

Create a Verify job.

Analyzes a document for signs of doctoring (splicing, copy-move,
AI generation, metadata tampering, ...). Set `file_input` to a
file ID (`dfl-...`). Optionally provide a `configuration` object
to control the semantic agent.

The job runs asynchronously. Poll `GET /verify/{job_id}`
with `expand=result` to check status and retrieve results.

### Parameters

- `organization_id: Optional[str]`

- `project_id: Optional[str]`

- `configuration: Optional[Configuration]`

  Configuration for a Verify job.

  - `target_pages: Optional[str]`

    Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs.

  - `tier: Optional[Literal["agentic", "fast"]]`

    Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass.

    - `"agentic"`

    - `"fast"`

- `file_id: Optional[str]`

  Deprecated: use file_input instead

- `file_input: Optional[str]`

  File ID of the document to analyze

- `transaction_id: Optional[str]`

  Idempotency key scoped to the project. Reusing a key returns the original job; the new request body is ignored.

- `webhook_configuration_ids: Optional[Sequence[str]]`

  IDs of saved webhook configurations to notify for this job.

- `webhook_configurations: Optional[Iterable[WebhookConfiguration]]`

  Outbound webhook endpoints to notify on job status changes

  - `webhook_events: Optional[List[Literal["batch.cancelled", "batch.error", "batch.pending", 35 more]]]`

    Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered.

    - `"batch.cancelled"`

    - `"batch.error"`

    - `"batch.pending"`

    - `"batch.running"`

    - `"batch.success"`

    - `"classify.cancelled"`

    - `"classify.error"`

    - `"classify.partial_success"`

    - `"classify.pending"`

    - `"classify.running"`

    - `"classify.success"`

    - `"extract.cancelled"`

    - `"extract.error"`

    - `"extract.partial_success"`

    - `"extract.pending"`

    - `"extract.success"`

    - `"parse.cancelled"`

    - `"parse.error"`

    - `"parse.partial_success"`

    - `"parse.pending"`

    - `"parse.running"`

    - `"parse.success"`

    - `"sheets.cancelled"`

    - `"sheets.error"`

    - `"sheets.partial_success"`

    - `"sheets.pending"`

    - `"sheets.success"`

    - `"split.cancelled"`

    - `"split.error"`

    - `"split.pending"`

    - `"split.processing"`

    - `"split.success"`

    - `"unmapped_event"`

    - `"verify.cancelled"`

    - `"verify.error"`

    - `"verify.pending"`

    - `"verify.running"`

    - `"verify.success"`

  - `webhook_headers: Optional[Dict[str, str]]`

    Custom HTTP headers sent with each webhook request (e.g. auth tokens)

  - `webhook_output_format: Optional[str]`

    Response format sent to the webhook: 'string' (default) or 'json'

  - `webhook_signing_secret: Optional[str]`

    Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256=<hex>'). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic.

  - `webhook_url: Optional[str]`

    URL to receive webhook POST notifications

### Returns

- `class VerifyCreateResponse: …`

  Response for a Verify job.

  - `id: str`

    Unique identifier

  - `configuration: Configuration`

    Verify configuration used for this job

    - `target_pages: Optional[str]`

      Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs.

    - `tier: Optional[Literal["agentic", "fast"]]`

      Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass.

      - `"agentic"`

      - `"fast"`

  - `document_input_type: Literal["file_id", "parse_job_id", "url"]`

    Type of the document input (FILE)

    - `"file_id"`

    - `"parse_job_id"`

    - `"url"`

  - `file_input: str`

    ID of the input file

  - `project_id: str`

    Project this job belongs to

  - `status: Literal["CANCELLED", "COMPLETED", "FAILED", 2 more]`

    Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED

    - `"CANCELLED"`

    - `"COMPLETED"`

    - `"FAILED"`

    - `"PENDING"`

    - `"RUNNING"`

  - `user_id: str`

    User who created this job

  - `created_at: Optional[datetime]`

    Creation datetime

  - `error_message: Optional[str]`

    Error message if job failed

  - `result: Optional[Result]`

    Result of a Verify (doctored-document) analysis.

    Raw per-signal detail (evidence list, per-family sub-scores, raw regions,
    forensic heatmaps) is available separately via the job's details endpoint.

    - `detector_version: str`

      Version of the detector that produced the result

    - `overall_score: float`

      Overall doctoring likelihood (0 to 1)

    - `verdict: Literal["AUTHENTIC", "DOCTORED", "LIKELY_DOCTORED", 2 more]`

      Overall verdict for the document

      - `"AUTHENTIC"`

      - `"DOCTORED"`

      - `"LIKELY_DOCTORED"`

      - `"NO_STRONG_SIGNAL"`

      - `"SUSPICIOUS"`

    - `composite_scores: Optional[ResultCompositeScores]`

      Composite scores, each answering one question about the document

      - `ai_generated: Optional[ResultCompositeScoresAIGenerated]`

        Was this content synthesized by a generative model?

        - `applicable: Optional[bool]`

          Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it

        - `score: Optional[float]`

          Score (0 to 1); null when the composite was not applicable

      - `document_coherence: Optional[ResultCompositeScoresDocumentCoherence]`

        Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)?

        - `applicable: Optional[bool]`

          Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it

        - `score: Optional[float]`

          Score (0 to 1); null when the composite was not applicable

      - `document_metadata: Optional[ResultCompositeScoresDocumentMetadata]`

        Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals

        - `applicable: Optional[bool]`

          Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it

        - `score: Optional[float]`

          Score (0 to 1); null when the composite was not applicable

      - `known_fraud: Optional[ResultCompositeScoresKnownFraud]`

        Has this asset (or its template) been seen in fraud before?

        - `applicable: Optional[bool]`

          Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it

        - `score: Optional[float]`

          Score (0 to 1); null when the composite was not applicable

      - `manually_edited: Optional[ResultCompositeScoresManuallyEdited]`

        Was this document altered after creation (splice, retype, redact, inpaint)?

        - `applicable: Optional[bool]`

          Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it

        - `score: Optional[float]`

          Score (0 to 1); null when the composite was not applicable

      - `recapture: Optional[ResultCompositeScoresRecapture]`

        Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)?

        - `applicable: Optional[bool]`

          Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it

        - `score: Optional[float]`

          Score (0 to 1); null when the composite was not applicable

    - `confidence: Optional[float]`

      Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself

    - `error: Optional[str]`

      Error detail when the analysis could not complete

    - `page_count: Optional[int]`

      Number of analysed pages (1 for images/docx)

    - `page_dimensions: Optional[List[ResultPageDimension]]`

      Rendered pixel size per page, so region bboxes can be scaled onto the page

      - `height: int`

        Rendered page height in pixels

      - `page: int`

        0-based page index (0 for standalone images)

      - `width: int`

        Rendered page width in pixels

    - `reasoning: Optional[str]`

      Explanation of the verdict

    - `suspect_regions: Optional[List[ResultSuspectRegion]]`

      Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect

      - `bbox: List[int]`

        Region bounding box as [x, y, w, h] in page-render pixels

      - `explanation: str`

        Human-readable explanation of what makes this region suspect

      - `kind: str`

        Kind of anomaly detected in this region

      - `page: int`

        0-based page index (0 for standalone images)

      - `score: float`

        Suspicion score for this region (0 to 1)

      - `source: str`

        Detector that flagged this region

      - `primary: Optional[bool]`

        Whether this region is part of the small set of decisive evidence behind the verdict — the boxes a reviewer should look at first

      - `review: Optional[str]`

        Automated reviewer verdict for this region (confirmed, dismissed, unsure, or empty). A dismissed region can still be surfaced when it is the only place to look; this label says how to read it

    - `synthetic_score: Optional[float]`

      Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced

    - `tampering_score: Optional[float]`

      Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced

  - `transaction_id: Optional[str]`

    Idempotency key

  - `updated_at: Optional[datetime]`

    Update datetime

### Example

```python
import os
from llama_cloud import LlamaCloud

client = LlamaCloud(
    api_key=os.environ.get("LLAMA_CLOUD_API_KEY"),  # This is the default and can be omitted
)
verify = client.alpha.verify.create()
print(verify.id)
```

#### Response

```json
{
  "id": "id",
  "configuration": {
    "target_pages": "1,3,5-7",
    "tier": "agentic"
  },
  "document_input_type": "file_id",
  "file_input": "file_input",
  "project_id": "project_id",
  "status": "CANCELLED",
  "user_id": "user_id",
  "created_at": "2019-12-27T18:11:19.117Z",
  "error_message": "error_message",
  "result": {
    "detector_version": "detector_version",
    "overall_score": 0,
    "verdict": "AUTHENTIC",
    "composite_scores": {
      "ai_generated": {
        "applicable": true,
        "score": 0
      },
      "document_coherence": {
        "applicable": true,
        "score": 0
      },
      "document_metadata": {
        "applicable": true,
        "score": 0
      },
      "known_fraud": {
        "applicable": true,
        "score": 0
      },
      "manually_edited": {
        "applicable": true,
        "score": 0
      },
      "recapture": {
        "applicable": true,
        "score": 0
      }
    },
    "confidence": 0,
    "error": "error",
    "page_count": 1,
    "page_dimensions": [
      {
        "height": 0,
        "page": 0,
        "width": 0
      }
    ],
    "reasoning": "reasoning",
    "suspect_regions": [
      {
        "bbox": [
          0,
          0,
          0,
          0
        ],
        "explanation": "explanation",
        "kind": "kind",
        "page": 0,
        "score": 0,
        "source": "source",
        "primary": true,
        "review": "review"
      }
    ],
    "synthetic_score": 0,
    "tampering_score": 0
  },
  "transaction_id": "transaction_id",
  "updated_at": "2019-12-27T18:11:19.117Z"
}
```