# Alpha # Verify ## List Verify Jobs `client.Alpha.Verify.List(ctx, query) (*PaginatedCursor[AlphaVerifyListResponse], error)` **get** `/api/alpha/verify` List Verify jobs with optional filtering and pagination. Filter by `status`, specific `job_ids`, or creation date range. ### Parameters - `query AlphaVerifyListParams` - `CreatedAtOnOrAfter param.Field[Time]` Include items created at or after this timestamp (inclusive) - `CreatedAtOnOrBefore param.Field[Time]` Include items created at or before this timestamp (inclusive) - `Expand param.Field[[]string]` Optional fields to include (e.g. `result`). - `JobIDs param.Field[[]string]` Filter by specific job IDs - `OrganizationID param.Field[string]` - `PageSize param.Field[int64]` Number of items per page - `PageToken param.Field[string]` Token for pagination - `ProjectID param.Field[string]` - `Status param.Field[AlphaVerifyListParamsStatus]` Filter by job status - `const AlphaVerifyListParamsStatusCancelled AlphaVerifyListParamsStatus = "CANCELLED"` - `const AlphaVerifyListParamsStatusCompleted AlphaVerifyListParamsStatus = "COMPLETED"` - `const AlphaVerifyListParamsStatusFailed AlphaVerifyListParamsStatus = "FAILED"` - `const AlphaVerifyListParamsStatusPending AlphaVerifyListParamsStatus = "PENDING"` - `const AlphaVerifyListParamsStatusRunning AlphaVerifyListParamsStatus = "RUNNING"` ### Returns - `type AlphaVerifyListResponse struct{…}` Response for a Verify job. - `ID string` Unique identifier - `Configuration AlphaVerifyListResponseConfiguration` Verify configuration used for this job - `TargetPages string` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier string` 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. - `const AlphaVerifyListResponseConfigurationTierAgentic AlphaVerifyListResponseConfigurationTier = "agentic"` - `const AlphaVerifyListResponseConfigurationTierFast AlphaVerifyListResponseConfigurationTier = "fast"` - `DocumentInputType AlphaVerifyListResponseDocumentInputType` Type of the document input (FILE) - `const AlphaVerifyListResponseDocumentInputTypeFileID AlphaVerifyListResponseDocumentInputType = "file_id"` - `const AlphaVerifyListResponseDocumentInputTypeParseJobID AlphaVerifyListResponseDocumentInputType = "parse_job_id"` - `const AlphaVerifyListResponseDocumentInputTypeURL AlphaVerifyListResponseDocumentInputType = "url"` - `FileInput string` ID of the input file - `ProjectID string` Project this job belongs to - `Status AlphaVerifyListResponseStatus` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `const AlphaVerifyListResponseStatusCancelled AlphaVerifyListResponseStatus = "CANCELLED"` - `const AlphaVerifyListResponseStatusCompleted AlphaVerifyListResponseStatus = "COMPLETED"` - `const AlphaVerifyListResponseStatusFailed AlphaVerifyListResponseStatus = "FAILED"` - `const AlphaVerifyListResponseStatusPending AlphaVerifyListResponseStatus = "PENDING"` - `const AlphaVerifyListResponseStatusRunning AlphaVerifyListResponseStatus = "RUNNING"` - `UserID string` User who created this job - `CreatedAt Time` Creation datetime - `ErrorMessage string` Error message if job failed - `Result AlphaVerifyListResponseResult` 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. - `DetectorVersion string` Version of the detector that produced the result - `OverallScore float64` Overall doctoring likelihood (0 to 1) - `Verdict string` Overall verdict for the document - `const AlphaVerifyListResponseResultVerdictAuthentic AlphaVerifyListResponseResultVerdict = "AUTHENTIC"` - `const AlphaVerifyListResponseResultVerdictDoctored AlphaVerifyListResponseResultVerdict = "DOCTORED"` - `const AlphaVerifyListResponseResultVerdictLikelyDoctored AlphaVerifyListResponseResultVerdict = "LIKELY_DOCTORED"` - `const AlphaVerifyListResponseResultVerdictNoStrongSignal AlphaVerifyListResponseResultVerdict = "NO_STRONG_SIGNAL"` - `const AlphaVerifyListResponseResultVerdictSuspicious AlphaVerifyListResponseResultVerdict = "SUSPICIOUS"` - `CompositeScores AlphaVerifyListResponseResultCompositeScores` Composite scores, each answering one question about the document - `AIGenerated AlphaVerifyListResponseResultCompositeScoresAIGenerated` Was this content synthesized by a generative model? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `DocumentCoherence AlphaVerifyListResponseResultCompositeScoresDocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `DocumentMetadata AlphaVerifyListResponseResultCompositeScoresDocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `KnownFraud AlphaVerifyListResponseResultCompositeScoresKnownFraud` Has this asset (or its template) been seen in fraud before? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `ManuallyEdited AlphaVerifyListResponseResultCompositeScoresManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `Recapture AlphaVerifyListResponseResultCompositeScoresRecapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `Confidence float64` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `Error string` Error detail when the analysis could not complete - `PageCount int64` Number of analysed pages (1 for images/docx) - `PageDimensions []AlphaVerifyListResponseResultPageDimension` Rendered pixel size per page, so region bboxes can be scaled onto the page - `Height int64` Rendered page height in pixels - `Page int64` 0-based page index (0 for standalone images) - `Width int64` Rendered page width in pixels - `Reasoning string` Explanation of the verdict - `SuspectRegions []AlphaVerifyListResponseResultSuspectRegion` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `Bbox []int64` Region bounding box as [x, y, w, h] in page-render pixels - `Explanation string` Human-readable explanation of what makes this region suspect - `Kind string` Kind of anomaly detected in this region - `Page int64` 0-based page index (0 for standalone images) - `Score float64` Suspicion score for this region (0 to 1) - `Source string` Detector that flagged this region - `Primary 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 string` 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 - `SyntheticScore float64` 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 - `TamperingScore float64` 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 - `TransactionID string` Idempotency key - `UpdatedAt Time` Update datetime ### Example ```go package main import ( "context" "fmt" "github.com/run-llama/llama-parse-go" "github.com/run-llama/llama-parse-go/option" ) func main() { client := llamacloud.NewClient( option.WithAPIKey("My API Key"), ) page, err := client.Alpha.Verify.List(context.TODO(), llamacloud.AlphaVerifyListParams{ }) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", page) } ``` #### 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 `client.Alpha.Verify.New(ctx, params) (*AlphaVerifyNewResponse, error)` **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 - `params AlphaVerifyNewParams` - `OrganizationID param.Field[string]` Query param - `ProjectID param.Field[string]` Query param - `Configuration param.Field[AlphaVerifyNewParamsConfiguration]` Body param: Configuration for a Verify job. - `TargetPages string` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier string` 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. - `const AlphaVerifyNewParamsConfigurationTierAgentic AlphaVerifyNewParamsConfigurationTier = "agentic"` - `const AlphaVerifyNewParamsConfigurationTierFast AlphaVerifyNewParamsConfigurationTier = "fast"` - `FileID param.Field[string]` Body param: Deprecated: use file_input instead - `FileInput param.Field[string]` Body param: File ID of the document to analyze - `TransactionID param.Field[string]` Body param: Idempotency key scoped to the project. Reusing a key returns the original job; the new request body is ignored. - `WebhookConfigurationIDs param.Field[[]string]` Body param: IDs of saved webhook configurations to notify for this job. - `WebhookConfigurations param.Field[[]AlphaVerifyNewParamsWebhookConfiguration]` Body param: Outbound webhook endpoints to notify on job status changes - `WebhookEvents []string` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventBatchCancelled AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "batch.cancelled"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventBatchError AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "batch.error"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventBatchPending AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "batch.pending"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventBatchRunning AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "batch.running"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventBatchSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "batch.success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventClassifyCancelled AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "classify.cancelled"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventClassifyError AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "classify.error"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventClassifyPartialSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "classify.partial_success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventClassifyPending AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "classify.pending"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventClassifyRunning AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "classify.running"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventClassifySuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "classify.success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventExtractCancelled AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "extract.cancelled"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventExtractError AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "extract.error"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventExtractPartialSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "extract.partial_success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventExtractPending AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "extract.pending"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventExtractSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "extract.success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventParseCancelled AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "parse.cancelled"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventParseError AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "parse.error"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventParsePartialSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "parse.partial_success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventParsePending AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "parse.pending"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventParseRunning AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "parse.running"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventParseSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "parse.success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSheetsCancelled AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "sheets.cancelled"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSheetsError AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "sheets.error"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSheetsPartialSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "sheets.partial_success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSheetsPending AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "sheets.pending"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSheetsSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "sheets.success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSplitCancelled AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "split.cancelled"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSplitError AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "split.error"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSplitPending AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "split.pending"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSplitProcessing AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "split.processing"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventSplitSuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "split.success"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventUnmappedEvent AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "unmapped_event"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventVerifyCancelled AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "verify.cancelled"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventVerifyError AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "verify.error"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventVerifyPending AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "verify.pending"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventVerifyRunning AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "verify.running"` - `const AlphaVerifyNewParamsWebhookConfigurationWebhookEventVerifySuccess AlphaVerifyNewParamsWebhookConfigurationWebhookEvent = "verify.success"` - `WebhookHeaders map[string, string]` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `WebhookOutputFormat string` Response format sent to the webhook: 'string' (default) or 'json' - `WebhookSigningSecret string` 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. - `WebhookURL string` URL to receive webhook POST notifications ### Returns - `type AlphaVerifyNewResponse struct{…}` Response for a Verify job. - `ID string` Unique identifier - `Configuration AlphaVerifyNewResponseConfiguration` Verify configuration used for this job - `TargetPages string` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier string` 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. - `const AlphaVerifyNewResponseConfigurationTierAgentic AlphaVerifyNewResponseConfigurationTier = "agentic"` - `const AlphaVerifyNewResponseConfigurationTierFast AlphaVerifyNewResponseConfigurationTier = "fast"` - `DocumentInputType AlphaVerifyNewResponseDocumentInputType` Type of the document input (FILE) - `const AlphaVerifyNewResponseDocumentInputTypeFileID AlphaVerifyNewResponseDocumentInputType = "file_id"` - `const AlphaVerifyNewResponseDocumentInputTypeParseJobID AlphaVerifyNewResponseDocumentInputType = "parse_job_id"` - `const AlphaVerifyNewResponseDocumentInputTypeURL AlphaVerifyNewResponseDocumentInputType = "url"` - `FileInput string` ID of the input file - `ProjectID string` Project this job belongs to - `Status AlphaVerifyNewResponseStatus` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `const AlphaVerifyNewResponseStatusCancelled AlphaVerifyNewResponseStatus = "CANCELLED"` - `const AlphaVerifyNewResponseStatusCompleted AlphaVerifyNewResponseStatus = "COMPLETED"` - `const AlphaVerifyNewResponseStatusFailed AlphaVerifyNewResponseStatus = "FAILED"` - `const AlphaVerifyNewResponseStatusPending AlphaVerifyNewResponseStatus = "PENDING"` - `const AlphaVerifyNewResponseStatusRunning AlphaVerifyNewResponseStatus = "RUNNING"` - `UserID string` User who created this job - `CreatedAt Time` Creation datetime - `ErrorMessage string` Error message if job failed - `Result AlphaVerifyNewResponseResult` 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. - `DetectorVersion string` Version of the detector that produced the result - `OverallScore float64` Overall doctoring likelihood (0 to 1) - `Verdict string` Overall verdict for the document - `const AlphaVerifyNewResponseResultVerdictAuthentic AlphaVerifyNewResponseResultVerdict = "AUTHENTIC"` - `const AlphaVerifyNewResponseResultVerdictDoctored AlphaVerifyNewResponseResultVerdict = "DOCTORED"` - `const AlphaVerifyNewResponseResultVerdictLikelyDoctored AlphaVerifyNewResponseResultVerdict = "LIKELY_DOCTORED"` - `const AlphaVerifyNewResponseResultVerdictNoStrongSignal AlphaVerifyNewResponseResultVerdict = "NO_STRONG_SIGNAL"` - `const AlphaVerifyNewResponseResultVerdictSuspicious AlphaVerifyNewResponseResultVerdict = "SUSPICIOUS"` - `CompositeScores AlphaVerifyNewResponseResultCompositeScores` Composite scores, each answering one question about the document - `AIGenerated AlphaVerifyNewResponseResultCompositeScoresAIGenerated` Was this content synthesized by a generative model? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `DocumentCoherence AlphaVerifyNewResponseResultCompositeScoresDocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `DocumentMetadata AlphaVerifyNewResponseResultCompositeScoresDocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `KnownFraud AlphaVerifyNewResponseResultCompositeScoresKnownFraud` Has this asset (or its template) been seen in fraud before? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `ManuallyEdited AlphaVerifyNewResponseResultCompositeScoresManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `Recapture AlphaVerifyNewResponseResultCompositeScoresRecapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `Confidence float64` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `Error string` Error detail when the analysis could not complete - `PageCount int64` Number of analysed pages (1 for images/docx) - `PageDimensions []AlphaVerifyNewResponseResultPageDimension` Rendered pixel size per page, so region bboxes can be scaled onto the page - `Height int64` Rendered page height in pixels - `Page int64` 0-based page index (0 for standalone images) - `Width int64` Rendered page width in pixels - `Reasoning string` Explanation of the verdict - `SuspectRegions []AlphaVerifyNewResponseResultSuspectRegion` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `Bbox []int64` Region bounding box as [x, y, w, h] in page-render pixels - `Explanation string` Human-readable explanation of what makes this region suspect - `Kind string` Kind of anomaly detected in this region - `Page int64` 0-based page index (0 for standalone images) - `Score float64` Suspicion score for this region (0 to 1) - `Source string` Detector that flagged this region - `Primary 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 string` 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 - `SyntheticScore float64` 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 - `TamperingScore float64` 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 - `TransactionID string` Idempotency key - `UpdatedAt Time` Update datetime ### Example ```go package main import ( "context" "fmt" "github.com/run-llama/llama-parse-go" "github.com/run-llama/llama-parse-go/option" ) func main() { client := llamacloud.NewClient( option.WithAPIKey("My API Key"), ) verify, err := client.Alpha.Verify.New(context.TODO(), llamacloud.AlphaVerifyNewParams{ }) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", 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" } ``` ## Get Verify Job `client.Alpha.Verify.Get(ctx, jobID, query) (*AlphaVerifyGetResponse, error)` **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 - `jobID string` - `query AlphaVerifyGetParams` - `Expand param.Field[[]string]` Optional fields to include (e.g. `result`). - `OrganizationID param.Field[string]` - `ProjectID param.Field[string]` ### Returns - `type AlphaVerifyGetResponse struct{…}` Response for a Verify job. - `ID string` Unique identifier - `Configuration AlphaVerifyGetResponseConfiguration` Verify configuration used for this job - `TargetPages string` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier string` 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. - `const AlphaVerifyGetResponseConfigurationTierAgentic AlphaVerifyGetResponseConfigurationTier = "agentic"` - `const AlphaVerifyGetResponseConfigurationTierFast AlphaVerifyGetResponseConfigurationTier = "fast"` - `DocumentInputType AlphaVerifyGetResponseDocumentInputType` Type of the document input (FILE) - `const AlphaVerifyGetResponseDocumentInputTypeFileID AlphaVerifyGetResponseDocumentInputType = "file_id"` - `const AlphaVerifyGetResponseDocumentInputTypeParseJobID AlphaVerifyGetResponseDocumentInputType = "parse_job_id"` - `const AlphaVerifyGetResponseDocumentInputTypeURL AlphaVerifyGetResponseDocumentInputType = "url"` - `FileInput string` ID of the input file - `ProjectID string` Project this job belongs to - `Status AlphaVerifyGetResponseStatus` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `const AlphaVerifyGetResponseStatusCancelled AlphaVerifyGetResponseStatus = "CANCELLED"` - `const AlphaVerifyGetResponseStatusCompleted AlphaVerifyGetResponseStatus = "COMPLETED"` - `const AlphaVerifyGetResponseStatusFailed AlphaVerifyGetResponseStatus = "FAILED"` - `const AlphaVerifyGetResponseStatusPending AlphaVerifyGetResponseStatus = "PENDING"` - `const AlphaVerifyGetResponseStatusRunning AlphaVerifyGetResponseStatus = "RUNNING"` - `UserID string` User who created this job - `CreatedAt Time` Creation datetime - `ErrorMessage string` Error message if job failed - `Result AlphaVerifyGetResponseResult` 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. - `DetectorVersion string` Version of the detector that produced the result - `OverallScore float64` Overall doctoring likelihood (0 to 1) - `Verdict string` Overall verdict for the document - `const AlphaVerifyGetResponseResultVerdictAuthentic AlphaVerifyGetResponseResultVerdict = "AUTHENTIC"` - `const AlphaVerifyGetResponseResultVerdictDoctored AlphaVerifyGetResponseResultVerdict = "DOCTORED"` - `const AlphaVerifyGetResponseResultVerdictLikelyDoctored AlphaVerifyGetResponseResultVerdict = "LIKELY_DOCTORED"` - `const AlphaVerifyGetResponseResultVerdictNoStrongSignal AlphaVerifyGetResponseResultVerdict = "NO_STRONG_SIGNAL"` - `const AlphaVerifyGetResponseResultVerdictSuspicious AlphaVerifyGetResponseResultVerdict = "SUSPICIOUS"` - `CompositeScores AlphaVerifyGetResponseResultCompositeScores` Composite scores, each answering one question about the document - `AIGenerated AlphaVerifyGetResponseResultCompositeScoresAIGenerated` Was this content synthesized by a generative model? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `DocumentCoherence AlphaVerifyGetResponseResultCompositeScoresDocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `DocumentMetadata AlphaVerifyGetResponseResultCompositeScoresDocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `KnownFraud AlphaVerifyGetResponseResultCompositeScoresKnownFraud` Has this asset (or its template) been seen in fraud before? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `ManuallyEdited AlphaVerifyGetResponseResultCompositeScoresManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `Recapture AlphaVerifyGetResponseResultCompositeScoresRecapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `Confidence float64` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `Error string` Error detail when the analysis could not complete - `PageCount int64` Number of analysed pages (1 for images/docx) - `PageDimensions []AlphaVerifyGetResponseResultPageDimension` Rendered pixel size per page, so region bboxes can be scaled onto the page - `Height int64` Rendered page height in pixels - `Page int64` 0-based page index (0 for standalone images) - `Width int64` Rendered page width in pixels - `Reasoning string` Explanation of the verdict - `SuspectRegions []AlphaVerifyGetResponseResultSuspectRegion` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `Bbox []int64` Region bounding box as [x, y, w, h] in page-render pixels - `Explanation string` Human-readable explanation of what makes this region suspect - `Kind string` Kind of anomaly detected in this region - `Page int64` 0-based page index (0 for standalone images) - `Score float64` Suspicion score for this region (0 to 1) - `Source string` Detector that flagged this region - `Primary 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 string` 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 - `SyntheticScore float64` 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 - `TamperingScore float64` 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 - `TransactionID string` Idempotency key - `UpdatedAt Time` Update datetime ### Example ```go package main import ( "context" "fmt" "github.com/run-llama/llama-parse-go" "github.com/run-llama/llama-parse-go/option" ) func main() { client := llamacloud.NewClient( option.WithAPIKey("My API Key"), ) verify, err := client.Alpha.Verify.Get( context.TODO(), "job_id", llamacloud.AlphaVerifyGetParams{ }, ) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", 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" } ``` ## Cancel Verify Job `client.Alpha.Verify.Cancel(ctx, jobID, body) (*AlphaVerifyCancelResponse, error)` **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 - `jobID string` - `body AlphaVerifyCancelParams` - `OrganizationID param.Field[string]` - `ProjectID param.Field[string]` ### Returns - `type AlphaVerifyCancelResponse struct{…}` Response for a Verify job. - `ID string` Unique identifier - `Configuration AlphaVerifyCancelResponseConfiguration` Verify configuration used for this job - `TargetPages string` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Tier string` 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. - `const AlphaVerifyCancelResponseConfigurationTierAgentic AlphaVerifyCancelResponseConfigurationTier = "agentic"` - `const AlphaVerifyCancelResponseConfigurationTierFast AlphaVerifyCancelResponseConfigurationTier = "fast"` - `DocumentInputType AlphaVerifyCancelResponseDocumentInputType` Type of the document input (FILE) - `const AlphaVerifyCancelResponseDocumentInputTypeFileID AlphaVerifyCancelResponseDocumentInputType = "file_id"` - `const AlphaVerifyCancelResponseDocumentInputTypeParseJobID AlphaVerifyCancelResponseDocumentInputType = "parse_job_id"` - `const AlphaVerifyCancelResponseDocumentInputTypeURL AlphaVerifyCancelResponseDocumentInputType = "url"` - `FileInput string` ID of the input file - `ProjectID string` Project this job belongs to - `Status AlphaVerifyCancelResponseStatus` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `const AlphaVerifyCancelResponseStatusCancelled AlphaVerifyCancelResponseStatus = "CANCELLED"` - `const AlphaVerifyCancelResponseStatusCompleted AlphaVerifyCancelResponseStatus = "COMPLETED"` - `const AlphaVerifyCancelResponseStatusFailed AlphaVerifyCancelResponseStatus = "FAILED"` - `const AlphaVerifyCancelResponseStatusPending AlphaVerifyCancelResponseStatus = "PENDING"` - `const AlphaVerifyCancelResponseStatusRunning AlphaVerifyCancelResponseStatus = "RUNNING"` - `UserID string` User who created this job - `CreatedAt Time` Creation datetime - `ErrorMessage string` Error message if job failed - `Result AlphaVerifyCancelResponseResult` 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. - `DetectorVersion string` Version of the detector that produced the result - `OverallScore float64` Overall doctoring likelihood (0 to 1) - `Verdict string` Overall verdict for the document - `const AlphaVerifyCancelResponseResultVerdictAuthentic AlphaVerifyCancelResponseResultVerdict = "AUTHENTIC"` - `const AlphaVerifyCancelResponseResultVerdictDoctored AlphaVerifyCancelResponseResultVerdict = "DOCTORED"` - `const AlphaVerifyCancelResponseResultVerdictLikelyDoctored AlphaVerifyCancelResponseResultVerdict = "LIKELY_DOCTORED"` - `const AlphaVerifyCancelResponseResultVerdictNoStrongSignal AlphaVerifyCancelResponseResultVerdict = "NO_STRONG_SIGNAL"` - `const AlphaVerifyCancelResponseResultVerdictSuspicious AlphaVerifyCancelResponseResultVerdict = "SUSPICIOUS"` - `CompositeScores AlphaVerifyCancelResponseResultCompositeScores` Composite scores, each answering one question about the document - `AIGenerated AlphaVerifyCancelResponseResultCompositeScoresAIGenerated` Was this content synthesized by a generative model? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `DocumentCoherence AlphaVerifyCancelResponseResultCompositeScoresDocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `DocumentMetadata AlphaVerifyCancelResponseResultCompositeScoresDocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `KnownFraud AlphaVerifyCancelResponseResultCompositeScoresKnownFraud` Has this asset (or its template) been seen in fraud before? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `ManuallyEdited AlphaVerifyCancelResponseResultCompositeScoresManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `Recapture AlphaVerifyCancelResponseResultCompositeScoresRecapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Applicable 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 float64` Score (0 to 1); null when the composite was not applicable - `Confidence float64` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `Error string` Error detail when the analysis could not complete - `PageCount int64` Number of analysed pages (1 for images/docx) - `PageDimensions []AlphaVerifyCancelResponseResultPageDimension` Rendered pixel size per page, so region bboxes can be scaled onto the page - `Height int64` Rendered page height in pixels - `Page int64` 0-based page index (0 for standalone images) - `Width int64` Rendered page width in pixels - `Reasoning string` Explanation of the verdict - `SuspectRegions []AlphaVerifyCancelResponseResultSuspectRegion` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `Bbox []int64` Region bounding box as [x, y, w, h] in page-render pixels - `Explanation string` Human-readable explanation of what makes this region suspect - `Kind string` Kind of anomaly detected in this region - `Page int64` 0-based page index (0 for standalone images) - `Score float64` Suspicion score for this region (0 to 1) - `Source string` Detector that flagged this region - `Primary 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 string` 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 - `SyntheticScore float64` 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 - `TamperingScore float64` 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 - `TransactionID string` Idempotency key - `UpdatedAt Time` Update datetime ### Example ```go package main import ( "context" "fmt" "github.com/run-llama/llama-parse-go" "github.com/run-llama/llama-parse-go/option" ) func main() { client := llamacloud.NewClient( option.WithAPIKey("My API Key"), ) response, err := client.Alpha.Verify.Cancel( context.TODO(), "job_id", llamacloud.AlphaVerifyCancelParams{ }, ) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", response.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" } ``` ## Get Verify Job Details `client.Alpha.Verify.GetDetails(ctx, jobID, query) (*AlphaVerifyGetDetailsResponse, error)` **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 - `jobID string` - `query AlphaVerifyGetDetailsParams` - `OrganizationID param.Field[string]` - `ProjectID param.Field[string]` ### Returns - `type AlphaVerifyGetDetailsResponse struct{…}` 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. - `JobID string` ID of the Verify job - `DegradedTools []AlphaVerifyGetDetailsResponseDegradedTool` 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 - `Tool string` Name of the check - `Reason string` Why the check could not run - `Evidence []AlphaVerifyGetDetailsResponseEvidence` Evidence items produced by detection tools - `Code string` Machine-readable evidence code - `Detail string` Human-readable evidence detail - `Family string` Signal family (e.g. metadata, splicing, compression) - `Score float64` Evidence strength score - `Tool string` Tool that produced this evidence - `Hard bool` Whether this is hard (conclusive) evidence - `MetadataTool map[string, any]` Raw values from the tool behind this finding; the shape varies by tool - `Heatmaps []AlphaVerifyGetDetailsResponseHeatmap` Per-page forensic heatmap overlays as presigned image URLs - `ExpiresAt Time` The time at which the presigned URL expires - `Kind string` Producing signal, e.g. double_compression, ela, noise - `Page int64` 0-based page index (0 for standalone images) - `URL string` Presigned URL to the heatmap PNG (page overlay) - `Score float64` Producing tool's max score (for ranking) - `PageDimensions []AlphaVerifyGetDetailsResponsePageDimension` Rendered pixel size per page, so region bboxes can be scaled onto the page - `Height int64` Rendered page height in pixels - `Page int64` 0-based page index (0 for standalone images) - `Width int64` Rendered page width in pixels - `Regions []AlphaVerifyGetDetailsResponseRegion` Suspicious regions localized on rendered pages - `Bbox []int64` Region bounding box as [x, y, w, h] in page-render pixels - `Detail string` Human-readable detail about the region - `Kind string` Kind of anomaly detected in this region - `Page int64` 0-based page index (0 for standalone images) - `Score float64` Region-level doctoring likelihood score - `Source string` Detector/tool that produced this region - `Primary 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 string` Review status/verdict for this region - `ReviewNote string` Free-form review note for this region - `SubScores map[string, float64]` Per-family scores (metadata, ai_generation, splicing, copy_move, compression, noise, coherence, pdf_structure) ### Example ```go package main import ( "context" "fmt" "github.com/run-llama/llama-parse-go" "github.com/run-llama/llama-parse-go/option" ) func main() { client := llamacloud.NewClient( option.WithAPIKey("My API Key"), ) response, err := client.Alpha.Verify.GetDetails( context.TODO(), "job_id", llamacloud.AlphaVerifyGetDetailsParams{ }, ) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", response.JobID) } ``` #### 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 } } ```