Skip to content

Get Verify Job Details

VerifyGetDetailsResponse Alpha.Verify.GetDetails(VerifyGetDetailsParamsparameters, CancellationTokencancellationToken = default)
GET/api/alpha/verify/{job_id}/details

Get the raw per-signal detail for a completed Verify job.

Forensic drill-down behind the simplified result: the full evidence list, per-family sub-scores, raw localized regions, and per-page forensic heatmap overlays (presigned image URLs).

ParametersExpand Collapse
VerifyGetDetailsParams parameters
required string jobID
string? organizationID
string? projectID
ReturnsExpand Collapse
class VerifyGetDetailsResponse:

Raw per-signal detail for a completed Verify job.

Forensic drill-down behind the simplified result: the full evidence list, per-family sub-scores, raw localized regions, and heatmap overlays.

required string JobID

ID of the Verify job

IReadOnlyList<DegradedTool> DegradedTools

Checks that could not run on this job (with the reason). A check listed here produced no findings because it could not run, not because the document is clean

required string Tool

Name of the check

string Reason

Why the check could not run

IReadOnlyList<Evidence> Evidence

Evidence items produced by detection tools

required string Code

Machine-readable evidence code

required string Detail

Human-readable evidence detail

required string Family

Signal family (e.g. metadata, splicing, compression)

required Double Score

Evidence strength score

required string Tool

Tool that produced this evidence

Boolean Hard

Whether this is hard (conclusive) evidence

IReadOnlyDictionary<string, JsonElement> MetadataTool

Raw values from the tool behind this finding; the shape varies by tool

IReadOnlyList<Heatmap> Heatmaps

Per-page forensic heatmap overlays as presigned image URLs

required DateTimeOffset ExpiresAt

The time at which the presigned URL expires

formatdate-time
required string Kind

Producing signal, e.g. double_compression, ela, noise

required Long Page

0-based page index (0 for standalone images)

required string Url

Presigned URL to the heatmap PNG (page overlay)

Double Score

Producing tool’s max score (for ranking)

IReadOnlyList<PageDimension> PageDimensions

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

required Long Height

Rendered page height in pixels

required Long Page

0-based page index (0 for standalone images)

required Long Width

Rendered page width in pixels

IReadOnlyList<Region> Regions

Suspicious regions localized on rendered pages

required IReadOnlyList<Long> Bbox

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

required string Detail

Human-readable detail about the region

required string Kind

Kind of anomaly detected in this region

required Long Page

0-based page index (0 for standalone images)

required Double Score

Region-level doctoring likelihood score

required string Source

Detector/tool that produced this region

Boolean Primary

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

string Review

Review status/verdict for this region

string ReviewNote

Free-form review note for this region

IReadOnlyDictionary<string, Double> SubScores

Per-family scores (metadata, ai_generation, splicing, copy_move, compression, noise, coherence, pdf_structure)

Get Verify Job Details

VerifyGetDetailsParams parameters = new() { JobID = "job_id" };

var response = await client.Alpha.Verify.GetDetails(parameters);

Console.WriteLine(response);
{
  "job_id": "job_id",
  "degraded_tools": [
    {
      "tool": "tool",
      "reason": "reason"
    }
  ],
  "evidence": [
    {
      "code": "code",
      "detail": "detail",
      "family": "family",
      "score": 0,
      "tool": "tool",
      "hard": true,
      "metadata_tool": {
        "foo": "bar"
      }
    }
  ],
  "heatmaps": [
    {
      "expires_at": "2019-12-27T18:11:19.117Z",
      "kind": "kind",
      "page": 0,
      "url": "url",
      "score": 0
    }
  ],
  "page_dimensions": [
    {
      "height": 0,
      "page": 0,
      "width": 0
    }
  ],
  "regions": [
    {
      "bbox": [
        0,
        0,
        0,
        0
      ],
      "detail": "detail",
      "kind": "kind",
      "page": 0,
      "score": 0,
      "source": "source",
      "primary": true,
      "review": "review",
      "review_note": "review_note"
    }
  ],
  "sub_scores": {
    "foo": 0
  }
}
Returns Examples
{
  "job_id": "job_id",
  "degraded_tools": [
    {
      "tool": "tool",
      "reason": "reason"
    }
  ],
  "evidence": [
    {
      "code": "code",
      "detail": "detail",
      "family": "family",
      "score": 0,
      "tool": "tool",
      "hard": true,
      "metadata_tool": {
        "foo": "bar"
      }
    }
  ],
  "heatmaps": [
    {
      "expires_at": "2019-12-27T18:11:19.117Z",
      "kind": "kind",
      "page": 0,
      "url": "url",
      "score": 0
    }
  ],
  "page_dimensions": [
    {
      "height": 0,
      "page": 0,
      "width": 0
    }
  ],
  "regions": [
    {
      "bbox": [
        0,
        0,
        0,
        0
      ],
      "detail": "detail",
      "kind": "kind",
      "page": 0,
      "score": 0,
      "source": "source",
      "primary": true,
      "review": "review",
      "review_note": "review_note"
    }
  ],
  "sub_scores": {
    "foo": 0
  }
}
Note for AI agents: this documentation is built for programmatic access. - Overview of all docs: https://developers.llamaindex.ai/llms.txt - Any page is available as raw Markdown by appending index.md to its URL — e.g. https://developers.llamaindex.ai/llamaparse/parse/getting_started/index.md - Agent-friendly REST search APIs live under https://developers.llamaindex.ai/api/ — search (BM25 full-text), grep (regex), read (fetch a page), and list (browse the doc tree). See https://developers.llamaindex.ai/llms.txt for parameters. - A hosted documentation MCP server is available at https://developers.llamaindex.ai/mcp. If you support MCP, you can ask the user to install it for browsing these docs directly (an alternative to the REST API). Setup: https://developers.llamaindex.ai/for-agents/mcp/ - Other LlamaIndex tooling for agents — the LlamaParse Platform MCP server, agent skills and plugins, and the n8n node — is mapped at https://developers.llamaindex.ai/for-agents/