# Verify ## List Verify Jobs `VerifyListPageResponse Alpha.Verify.List(VerifyListParams?parameters, CancellationTokencancellationToken = default)` **get** `/api/alpha/verify` List Verify jobs with optional filtering and pagination. Filter by `status`, specific `job_ids`, or creation date range. ### Parameters - `VerifyListParams parameters` - `DateTimeOffset? createdAtOnOrAfter` Include items created at or after this timestamp (inclusive) - `DateTimeOffset? createdAtOnOrBefore` Include items created at or before this timestamp (inclusive) - `IReadOnlyList expand` Optional fields to include (e.g. `result`). - `IReadOnlyList? jobIds` Filter by specific job IDs - `string? organizationID` - `Long? pageSize` Number of items per page - `string? pageToken` Token for pagination - `string? projectID` - `Status? status` Filter by job status - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` ### Returns - `class VerifyListPageResponse:` Response schema for paginated Verify job queries. - `required IReadOnlyList Items` The list of items. - `required string ID` Unique identifier - `required Configuration Configuration` Verify configuration used for this job - `string? TargetPages` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier Tier` 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"Agentic` - `"fast"Fast` - `required DocumentInputType DocumentInputType` Type of the document input (FILE) - `"file_id"FileID` - `"parse_job_id"ParseJobID` - `"url"Url` - `required string FileInput` ID of the input file - `required string ProjectID` Project this job belongs to - `required Status Status` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` - `required string UserID` User who created this job - `DateTimeOffset? CreatedAt` Creation datetime - `string? ErrorMessage` Error message if job failed - `Result? 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. - `required string DetectorVersion` Version of the detector that produced the result - `required Double OverallScore` Overall doctoring likelihood (0 to 1) - `required Verdict Verdict` Overall verdict for the document - `"AUTHENTIC"Authentic` - `"DOCTORED"Doctored` - `"LIKELY_DOCTORED"LikelyDoctored` - `"NO_STRONG_SIGNAL"NoStrongSignal` - `"SUSPICIOUS"Suspicious` - `CompositeScores CompositeScores` Composite scores, each answering one question about the document - `AIGenerated AIGenerated` Was this content synthesized by a generative model? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `DocumentCoherence DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `DocumentMetadata DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `KnownFraud KnownFraud` Has this asset (or its template) been seen in fraud before? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `ManuallyEdited ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `Recapture Recapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `Double Confidence` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `string? Error` Error detail when the analysis could not complete - `Long PageCount` Number of analysed pages (1 for images/docx) - `IReadOnlyList 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 - `string Reasoning` Explanation of the verdict - `IReadOnlyList SuspectRegions` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `required IReadOnlyList Bbox` Region bounding box as [x, y, w, h] in page-render pixels - `required string Explanation` Human-readable explanation of what makes this region suspect - `required string Kind` Kind of anomaly detected in this region - `required Long Page` 0-based page index (0 for standalone images) - `required Double Score` Suspicion score for this region (0 to 1) - `required string Source` Detector that flagged 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` 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 - `Double? SyntheticScore` 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 - `Double? TamperingScore` 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 - `string? TransactionID` Idempotency key - `DateTimeOffset? UpdatedAt` Update datetime - `string? NextPageToken` A token, which can be sent as page_token to retrieve the next page. If this field is omitted, there are no subsequent pages. - `Long? TotalSize` The total number of items available. This is only populated when specifically requested. The value may be an estimate and can be used for display purposes only. ### Example ```csharp VerifyListParams parameters = new(); var page = await client.Alpha.Verify.List(parameters); await foreach (var item in page.Paginate()) { Console.WriteLine(item); } ``` #### Response ```json { "items": [ { "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" } ], "next_page_token": "next_page_token", "total_size": 0 } ``` ## Create Verify Job `VerifyCreateResponse Alpha.Verify.Create(VerifyCreateParams?parameters, CancellationTokencancellationToken = default)` **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 - `VerifyCreateParams parameters` - `string? organizationID` Query param - `string? projectID` Query param - `Configuration? configuration` Body param: Configuration for a Verify job. - `string? TargetPages` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier Tier` 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"Agentic` - `"fast"Fast` - `string? fileID` Body param: Deprecated: use file_input instead - `string? fileInput` Body param: File ID of the document to analyze - `string? transactionID` Body param: Idempotency key scoped to the project. Reusing a key returns the original job; the new request body is ignored. - `IReadOnlyList? webhookConfigurationIds` Body param: IDs of saved webhook configurations to notify for this job. - `IReadOnlyList? webhookConfigurations` Body param: Outbound webhook endpoints to notify on job status changes - `IReadOnlyList? WebhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"batch.cancelled"BatchCancelled` - `"batch.error"BatchError` - `"batch.pending"BatchPending` - `"batch.running"BatchRunning` - `"batch.success"BatchSuccess` - `"classify.cancelled"ClassifyCancelled` - `"classify.error"ClassifyError` - `"classify.partial_success"ClassifyPartialSuccess` - `"classify.pending"ClassifyPending` - `"classify.running"ClassifyRunning` - `"classify.success"ClassifySuccess` - `"extract.cancelled"ExtractCancelled` - `"extract.error"ExtractError` - `"extract.partial_success"ExtractPartialSuccess` - `"extract.pending"ExtractPending` - `"extract.success"ExtractSuccess` - `"parse.cancelled"ParseCancelled` - `"parse.error"ParseError` - `"parse.partial_success"ParsePartialSuccess` - `"parse.pending"ParsePending` - `"parse.running"ParseRunning` - `"parse.success"ParseSuccess` - `"sheets.cancelled"SheetsCancelled` - `"sheets.error"SheetsError` - `"sheets.partial_success"SheetsPartialSuccess` - `"sheets.pending"SheetsPending` - `"sheets.success"SheetsSuccess` - `"split.cancelled"SplitCancelled` - `"split.error"SplitError` - `"split.pending"SplitPending` - `"split.processing"SplitProcessing` - `"split.success"SplitSuccess` - `"unmapped_event"UnmappedEvent` - `"verify.cancelled"VerifyCancelled` - `"verify.error"VerifyError` - `"verify.pending"VerifyPending` - `"verify.running"VerifyRunning` - `"verify.success"VerifySuccess` - `IReadOnlyDictionary? WebhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `string? WebhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `string? WebhookSigningSecret` 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='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `string? WebhookUrl` URL to receive webhook POST notifications ### Returns - `class VerifyCreateResponse:` Response for a Verify job. - `required string ID` Unique identifier - `required Configuration Configuration` Verify configuration used for this job - `string? TargetPages` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier Tier` 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"Agentic` - `"fast"Fast` - `required DocumentInputType DocumentInputType` Type of the document input (FILE) - `"file_id"FileID` - `"parse_job_id"ParseJobID` - `"url"Url` - `required string FileInput` ID of the input file - `required string ProjectID` Project this job belongs to - `required Status Status` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` - `required string UserID` User who created this job - `DateTimeOffset? CreatedAt` Creation datetime - `string? ErrorMessage` Error message if job failed - `Result? 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. - `required string DetectorVersion` Version of the detector that produced the result - `required Double OverallScore` Overall doctoring likelihood (0 to 1) - `required Verdict Verdict` Overall verdict for the document - `"AUTHENTIC"Authentic` - `"DOCTORED"Doctored` - `"LIKELY_DOCTORED"LikelyDoctored` - `"NO_STRONG_SIGNAL"NoStrongSignal` - `"SUSPICIOUS"Suspicious` - `CompositeScores CompositeScores` Composite scores, each answering one question about the document - `AIGenerated AIGenerated` Was this content synthesized by a generative model? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `DocumentCoherence DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `DocumentMetadata DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `KnownFraud KnownFraud` Has this asset (or its template) been seen in fraud before? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `ManuallyEdited ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `Recapture Recapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `Double Confidence` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `string? Error` Error detail when the analysis could not complete - `Long PageCount` Number of analysed pages (1 for images/docx) - `IReadOnlyList 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 - `string Reasoning` Explanation of the verdict - `IReadOnlyList SuspectRegions` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `required IReadOnlyList Bbox` Region bounding box as [x, y, w, h] in page-render pixels - `required string Explanation` Human-readable explanation of what makes this region suspect - `required string Kind` Kind of anomaly detected in this region - `required Long Page` 0-based page index (0 for standalone images) - `required Double Score` Suspicion score for this region (0 to 1) - `required string Source` Detector that flagged 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` 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 - `Double? SyntheticScore` 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 - `Double? TamperingScore` 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 - `string? TransactionID` Idempotency key - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp VerifyCreateParams parameters = new(); var verify = await client.Alpha.Verify.Create(parameters); Console.WriteLine(verify); ``` #### 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" } ``` ## Get Verify Job `VerifyGetResponse Alpha.Verify.Get(VerifyGetParamsparameters, CancellationTokencancellationToken = default)` **get** `/api/alpha/verify/{job_id}` Get a Verify job by ID. Returns the job status and configuration. Pass `expand=result` to include the Verify result (overall score, verdict, confidence, composite scores, and suspect regions) when the job is complete. Raw per-signal detail is available via `GET /verify/{job_id}/details`. ### Parameters - `VerifyGetParams parameters` - `required string jobID` - `IReadOnlyList expand` Optional fields to include (e.g. `result`). - `string? organizationID` - `string? projectID` ### Returns - `class VerifyGetResponse:` Response for a Verify job. - `required string ID` Unique identifier - `required Configuration Configuration` Verify configuration used for this job - `string? TargetPages` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier Tier` 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"Agentic` - `"fast"Fast` - `required DocumentInputType DocumentInputType` Type of the document input (FILE) - `"file_id"FileID` - `"parse_job_id"ParseJobID` - `"url"Url` - `required string FileInput` ID of the input file - `required string ProjectID` Project this job belongs to - `required Status Status` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` - `required string UserID` User who created this job - `DateTimeOffset? CreatedAt` Creation datetime - `string? ErrorMessage` Error message if job failed - `Result? 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. - `required string DetectorVersion` Version of the detector that produced the result - `required Double OverallScore` Overall doctoring likelihood (0 to 1) - `required Verdict Verdict` Overall verdict for the document - `"AUTHENTIC"Authentic` - `"DOCTORED"Doctored` - `"LIKELY_DOCTORED"LikelyDoctored` - `"NO_STRONG_SIGNAL"NoStrongSignal` - `"SUSPICIOUS"Suspicious` - `CompositeScores CompositeScores` Composite scores, each answering one question about the document - `AIGenerated AIGenerated` Was this content synthesized by a generative model? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `DocumentCoherence DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `DocumentMetadata DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `KnownFraud KnownFraud` Has this asset (or its template) been seen in fraud before? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `ManuallyEdited ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `Recapture Recapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `Double Confidence` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `string? Error` Error detail when the analysis could not complete - `Long PageCount` Number of analysed pages (1 for images/docx) - `IReadOnlyList 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 - `string Reasoning` Explanation of the verdict - `IReadOnlyList SuspectRegions` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `required IReadOnlyList Bbox` Region bounding box as [x, y, w, h] in page-render pixels - `required string Explanation` Human-readable explanation of what makes this region suspect - `required string Kind` Kind of anomaly detected in this region - `required Long Page` 0-based page index (0 for standalone images) - `required Double Score` Suspicion score for this region (0 to 1) - `required string Source` Detector that flagged 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` 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 - `Double? SyntheticScore` 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 - `Double? TamperingScore` 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 - `string? TransactionID` Idempotency key - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp VerifyGetParams parameters = new() { JobID = "job_id" }; var verify = await client.Alpha.Verify.Get(parameters); Console.WriteLine(verify); ``` #### 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" } ``` ## Cancel Verify Job `VerifyCancelResponse Alpha.Verify.Cancel(VerifyCancelParamsparameters, CancellationTokencancellationToken = default)` **post** `/api/alpha/verify/{job_id}/cancel` Cancel a running Verify job. Stops processing and marks the job as CANCELLED. Returns the updated job. Jobs already in a terminal state (COMPLETED, FAILED, CANCELLED) cannot be cancelled. ### Parameters - `VerifyCancelParams parameters` - `required string jobID` - `string? organizationID` - `string? projectID` ### Returns - `class VerifyCancelResponse:` Response for a Verify job. - `required string ID` Unique identifier - `required Configuration Configuration` Verify configuration used for this job - `string? TargetPages` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier Tier` 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"Agentic` - `"fast"Fast` - `required DocumentInputType DocumentInputType` Type of the document input (FILE) - `"file_id"FileID` - `"parse_job_id"ParseJobID` - `"url"Url` - `required string FileInput` ID of the input file - `required string ProjectID` Project this job belongs to - `required Status Status` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"Cancelled` - `"COMPLETED"Completed` - `"FAILED"Failed` - `"PENDING"Pending` - `"RUNNING"Running` - `required string UserID` User who created this job - `DateTimeOffset? CreatedAt` Creation datetime - `string? ErrorMessage` Error message if job failed - `Result? 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. - `required string DetectorVersion` Version of the detector that produced the result - `required Double OverallScore` Overall doctoring likelihood (0 to 1) - `required Verdict Verdict` Overall verdict for the document - `"AUTHENTIC"Authentic` - `"DOCTORED"Doctored` - `"LIKELY_DOCTORED"LikelyDoctored` - `"NO_STRONG_SIGNAL"NoStrongSignal` - `"SUSPICIOUS"Suspicious` - `CompositeScores CompositeScores` Composite scores, each answering one question about the document - `AIGenerated AIGenerated` Was this content synthesized by a generative model? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `DocumentCoherence DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `DocumentMetadata DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `KnownFraud KnownFraud` Has this asset (or its template) been seen in fraud before? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `ManuallyEdited ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `Recapture Recapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Boolean Applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Double? Score` Score (0 to 1); null when the composite was not applicable - `Double Confidence` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `string? Error` Error detail when the analysis could not complete - `Long PageCount` Number of analysed pages (1 for images/docx) - `IReadOnlyList 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 - `string Reasoning` Explanation of the verdict - `IReadOnlyList SuspectRegions` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `required IReadOnlyList Bbox` Region bounding box as [x, y, w, h] in page-render pixels - `required string Explanation` Human-readable explanation of what makes this region suspect - `required string Kind` Kind of anomaly detected in this region - `required Long Page` 0-based page index (0 for standalone images) - `required Double Score` Suspicion score for this region (0 to 1) - `required string Source` Detector that flagged 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` 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 - `Double? SyntheticScore` 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 - `Double? TamperingScore` 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 - `string? TransactionID` Idempotency key - `DateTimeOffset? UpdatedAt` Update datetime ### Example ```csharp VerifyCancelParams parameters = new() { JobID = "job_id" }; var response = await client.Alpha.Verify.Cancel(parameters); Console.WriteLine(response); ``` #### 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" } ``` ## 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). ### Parameters - `VerifyGetDetailsParams parameters` - `required string jobID` - `string? organizationID` - `string? projectID` ### Returns - `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 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 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 MetadataTool` Raw values from the tool behind this finding; the shape varies by tool - `IReadOnlyList Heatmaps` Per-page forensic heatmap overlays as presigned image URLs - `required DateTimeOffset ExpiresAt` The time at which the presigned URL expires - `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 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 Regions` Suspicious regions localized on rendered pages - `required IReadOnlyList 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 SubScores` Per-family scores (metadata, ai_generation, splicing, copy_move, compression, noise, coherence, pdf_structure) ### Example ```csharp VerifyGetDetailsParams parameters = new() { JobID = "job_id" }; var response = await client.Alpha.Verify.GetDetails(parameters); Console.WriteLine(response); ``` #### Response ```json { "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 } } ```