# Alpha # Verify ## List Verify Jobs `client.alpha.verify.list(VerifyListParamsquery?, RequestOptionsoptions?): PaginatedCursor` **get** `/api/alpha/verify` List Verify jobs with optional filtering and pagination. Filter by `status`, specific `job_ids`, or creation date range. ### Parameters - `query: VerifyListParams` - `created_at_on_or_after?: string | null` Include items created at or after this timestamp (inclusive) - `created_at_on_or_before?: string | null` Include items created at or before this timestamp (inclusive) - `expand?: Array` Optional fields to include (e.g. `result`). - `job_ids?: Array | null` Filter by specific job IDs - `organization_id?: string | null` - `page_size?: number | null` Number of items per page - `page_token?: string | null` Token for pagination - `project_id?: string | null` - `status?: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more | null` Filter by job status - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` ### Returns - `VerifyListResponse` Response for a Verify job. - `id: string` Unique identifier - `configuration: Configuration` Verify configuration used for this job - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `document_input_type: "file_id" | "parse_job_id" | "url"` Type of the document input (FILE) - `"file_id"` - `"parse_job_id"` - `"url"` - `file_input: string` ID of the input file - `project_id: string` Project this job belongs to - `status: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` - `user_id: string` User who created this job - `created_at?: string | null` Creation datetime - `error_message?: string | null` Error message if job failed - `result?: Result | null` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `detector_version: string` Version of the detector that produced the result - `overall_score: number` Overall doctoring likelihood (0 to 1) - `verdict: "AUTHENTIC" | "DOCTORED" | "LIKELY_DOCTORED" | 2 more` Overall verdict for the document - `"AUTHENTIC"` - `"DOCTORED"` - `"LIKELY_DOCTORED"` - `"NO_STRONG_SIGNAL"` - `"SUSPICIOUS"` - `composite_scores?: CompositeScores` Composite scores, each answering one question about the document - `ai_generated?: AIGenerated` Was this content synthesized by a generative model? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_coherence?: DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_metadata?: DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `known_fraud?: KnownFraud` Has this asset (or its template) been seen in fraud before? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `manually_edited?: ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` 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)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `confidence?: number` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `error?: string | null` Error detail when the analysis could not complete - `page_count?: number` Number of analysed pages (1 for images/docx) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `reasoning?: string` Explanation of the verdict - `suspect_regions?: Array` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Suspicion score for this region (0 to 1) - `source: string` Detector that flagged this region - `primary?: boolean` 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 - `synthetic_score?: number | null` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `tampering_score?: number | null` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `transaction_id?: string | null` Idempotency key - `updated_at?: string | null` Update datetime ### Example ```typescript import LlamaCloud from '@llamaindex/llama-cloud'; const client = new LlamaCloud({ apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted }); // Automatically fetches more pages as needed. for await (const verifyListResponse of client.alpha.verify.list()) { console.log(verifyListResponse.id); } ``` #### 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.create(VerifyCreateParamsparams, RequestOptionsoptions?): VerifyCreateResponse` **post** `/api/alpha/verify` Create a Verify job. Analyzes a document for signs of doctoring (splicing, copy-move, AI generation, metadata tampering, ...). Set `file_input` to a file ID (`dfl-...`). Optionally provide a `configuration` object to control the semantic agent. The job runs asynchronously. Poll `GET /verify/{job_id}` with `expand=result` to check status and retrieve results. ### Parameters - `params: VerifyCreateParams` - `organization_id?: string | null` Query param - `project_id?: string | null` Query param - `configuration?: Configuration | null` Body param: Configuration for a Verify job. - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `file_id?: string | null` Body param: Deprecated: use file_input instead - `file_input?: string | null` Body param: File ID of the document to analyze - `transaction_id?: string | null` Body param: Idempotency key scoped to the project. Reusing a key returns the original job; the new request body is ignored. - `webhook_configuration_ids?: Array | null` Body param: IDs of saved webhook configurations to notify for this job. - `webhook_configurations?: Array | null` Body param: Outbound webhook endpoints to notify on job status changes - `webhook_events?: Array<"batch.cancelled" | "batch.error" | "batch.pending" | 35 more> | null` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `"batch.cancelled"` - `"batch.error"` - `"batch.pending"` - `"batch.running"` - `"batch.success"` - `"classify.cancelled"` - `"classify.error"` - `"classify.partial_success"` - `"classify.pending"` - `"classify.running"` - `"classify.success"` - `"extract.cancelled"` - `"extract.error"` - `"extract.partial_success"` - `"extract.pending"` - `"extract.success"` - `"parse.cancelled"` - `"parse.error"` - `"parse.partial_success"` - `"parse.pending"` - `"parse.running"` - `"parse.success"` - `"sheets.cancelled"` - `"sheets.error"` - `"sheets.partial_success"` - `"sheets.pending"` - `"sheets.success"` - `"split.cancelled"` - `"split.error"` - `"split.pending"` - `"split.processing"` - `"split.success"` - `"unmapped_event"` - `"verify.cancelled"` - `"verify.error"` - `"verify.pending"` - `"verify.running"` - `"verify.success"` - `webhook_headers?: Record | null` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `webhook_output_format?: string | null` Response format sent to the webhook: 'string' (default) or 'json' - `webhook_signing_secret?: string | null` 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. - `webhook_url?: string | null` URL to receive webhook POST notifications ### Returns - `VerifyCreateResponse` Response for a Verify job. - `id: string` Unique identifier - `configuration: Configuration` Verify configuration used for this job - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `document_input_type: "file_id" | "parse_job_id" | "url"` Type of the document input (FILE) - `"file_id"` - `"parse_job_id"` - `"url"` - `file_input: string` ID of the input file - `project_id: string` Project this job belongs to - `status: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` - `user_id: string` User who created this job - `created_at?: string | null` Creation datetime - `error_message?: string | null` Error message if job failed - `result?: Result | null` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `detector_version: string` Version of the detector that produced the result - `overall_score: number` Overall doctoring likelihood (0 to 1) - `verdict: "AUTHENTIC" | "DOCTORED" | "LIKELY_DOCTORED" | 2 more` Overall verdict for the document - `"AUTHENTIC"` - `"DOCTORED"` - `"LIKELY_DOCTORED"` - `"NO_STRONG_SIGNAL"` - `"SUSPICIOUS"` - `composite_scores?: CompositeScores` Composite scores, each answering one question about the document - `ai_generated?: AIGenerated` Was this content synthesized by a generative model? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_coherence?: DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_metadata?: DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `known_fraud?: KnownFraud` Has this asset (or its template) been seen in fraud before? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `manually_edited?: ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` 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)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `confidence?: number` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `error?: string | null` Error detail when the analysis could not complete - `page_count?: number` Number of analysed pages (1 for images/docx) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `reasoning?: string` Explanation of the verdict - `suspect_regions?: Array` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Suspicion score for this region (0 to 1) - `source: string` Detector that flagged this region - `primary?: boolean` 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 - `synthetic_score?: number | null` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `tampering_score?: number | null` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `transaction_id?: string | null` Idempotency key - `updated_at?: string | null` Update datetime ### Example ```typescript import LlamaCloud from '@llamaindex/llama-cloud'; const client = new LlamaCloud({ apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted }); const verify = await client.alpha.verify.create(); console.log(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(stringjobID, VerifyGetParamsquery?, RequestOptionsoptions?): VerifyGetResponse` **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: VerifyGetParams` - `expand?: Array` Optional fields to include (e.g. `result`). - `organization_id?: string | null` - `project_id?: string | null` ### Returns - `VerifyGetResponse` Response for a Verify job. - `id: string` Unique identifier - `configuration: Configuration` Verify configuration used for this job - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `document_input_type: "file_id" | "parse_job_id" | "url"` Type of the document input (FILE) - `"file_id"` - `"parse_job_id"` - `"url"` - `file_input: string` ID of the input file - `project_id: string` Project this job belongs to - `status: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` - `user_id: string` User who created this job - `created_at?: string | null` Creation datetime - `error_message?: string | null` Error message if job failed - `result?: Result | null` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `detector_version: string` Version of the detector that produced the result - `overall_score: number` Overall doctoring likelihood (0 to 1) - `verdict: "AUTHENTIC" | "DOCTORED" | "LIKELY_DOCTORED" | 2 more` Overall verdict for the document - `"AUTHENTIC"` - `"DOCTORED"` - `"LIKELY_DOCTORED"` - `"NO_STRONG_SIGNAL"` - `"SUSPICIOUS"` - `composite_scores?: CompositeScores` Composite scores, each answering one question about the document - `ai_generated?: AIGenerated` Was this content synthesized by a generative model? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_coherence?: DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_metadata?: DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `known_fraud?: KnownFraud` Has this asset (or its template) been seen in fraud before? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `manually_edited?: ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` 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)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `confidence?: number` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `error?: string | null` Error detail when the analysis could not complete - `page_count?: number` Number of analysed pages (1 for images/docx) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `reasoning?: string` Explanation of the verdict - `suspect_regions?: Array` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Suspicion score for this region (0 to 1) - `source: string` Detector that flagged this region - `primary?: boolean` 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 - `synthetic_score?: number | null` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `tampering_score?: number | null` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `transaction_id?: string | null` Idempotency key - `updated_at?: string | null` Update datetime ### Example ```typescript import LlamaCloud from '@llamaindex/llama-cloud'; const client = new LlamaCloud({ apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted }); const verify = await client.alpha.verify.get('job_id'); console.log(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(stringjobID, VerifyCancelParamsparams?, RequestOptionsoptions?): VerifyCancelResponse` **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` - `params: VerifyCancelParams` - `organization_id?: string | null` - `project_id?: string | null` ### Returns - `VerifyCancelResponse` Response for a Verify job. - `id: string` Unique identifier - `configuration: Configuration` Verify configuration used for this job - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `document_input_type: "file_id" | "parse_job_id" | "url"` Type of the document input (FILE) - `"file_id"` - `"parse_job_id"` - `"url"` - `file_input: string` ID of the input file - `project_id: string` Project this job belongs to - `status: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` - `user_id: string` User who created this job - `created_at?: string | null` Creation datetime - `error_message?: string | null` Error message if job failed - `result?: Result | null` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `detector_version: string` Version of the detector that produced the result - `overall_score: number` Overall doctoring likelihood (0 to 1) - `verdict: "AUTHENTIC" | "DOCTORED" | "LIKELY_DOCTORED" | 2 more` Overall verdict for the document - `"AUTHENTIC"` - `"DOCTORED"` - `"LIKELY_DOCTORED"` - `"NO_STRONG_SIGNAL"` - `"SUSPICIOUS"` - `composite_scores?: CompositeScores` Composite scores, each answering one question about the document - `ai_generated?: AIGenerated` Was this content synthesized by a generative model? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_coherence?: DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_metadata?: DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `known_fraud?: KnownFraud` Has this asset (or its template) been seen in fraud before? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `manually_edited?: ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` 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)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `confidence?: number` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `error?: string | null` Error detail when the analysis could not complete - `page_count?: number` Number of analysed pages (1 for images/docx) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `reasoning?: string` Explanation of the verdict - `suspect_regions?: Array` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Suspicion score for this region (0 to 1) - `source: string` Detector that flagged this region - `primary?: boolean` 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 - `synthetic_score?: number | null` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `tampering_score?: number | null` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `transaction_id?: string | null` Idempotency key - `updated_at?: string | null` Update datetime ### Example ```typescript import LlamaCloud from '@llamaindex/llama-cloud'; const client = new LlamaCloud({ apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted }); const response = await client.alpha.verify.cancel('job_id'); console.log(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(stringjobID, VerifyGetDetailsParamsquery?, RequestOptionsoptions?): VerifyGetDetailsResponse` **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: VerifyGetDetailsParams` - `organization_id?: string | null` - `project_id?: string | null` ### Returns - `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. - `job_id: string` ID of the Verify job - `degraded_tools?: Array` 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?: Array` 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: number` Evidence strength score - `tool: string` Tool that produced this evidence - `hard?: boolean` Whether this is hard (conclusive) evidence - `metadata_tool?: Record` Raw values from the tool behind this finding; the shape varies by tool - `heatmaps?: Array` Per-page forensic heatmap overlays as presigned image URLs - `expires_at: string` The time at which the presigned URL expires - `kind: string` Producing signal, e.g. double_compression, ela, noise - `page: number` 0-based page index (0 for standalone images) - `url: string` Presigned URL to the heatmap PNG (page overlay) - `score?: number` Producing tool's max score (for ranking) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `regions?: Array` Suspicious regions localized on rendered pages - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Region-level doctoring likelihood score - `source: string` Detector/tool that produced this region - `primary?: boolean` 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 - `review_note?: string` Free-form review note for this region - `sub_scores?: Record` Per-family scores (metadata, ai_generation, splicing, copy_move, compression, noise, coherence, pdf_structure) ### Example ```typescript import LlamaCloud from '@llamaindex/llama-cloud'; const client = new LlamaCloud({ apiKey: process.env['LLAMA_CLOUD_API_KEY'], // This is the default and can be omitted }); const response = await client.alpha.verify.getDetails('job_id'); console.log(response.job_id); ``` #### 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 } } ``` ## Domain Types ### Verify List Response - `VerifyListResponse` Response for a Verify job. - `id: string` Unique identifier - `configuration: Configuration` Verify configuration used for this job - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `document_input_type: "file_id" | "parse_job_id" | "url"` Type of the document input (FILE) - `"file_id"` - `"parse_job_id"` - `"url"` - `file_input: string` ID of the input file - `project_id: string` Project this job belongs to - `status: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` - `user_id: string` User who created this job - `created_at?: string | null` Creation datetime - `error_message?: string | null` Error message if job failed - `result?: Result | null` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `detector_version: string` Version of the detector that produced the result - `overall_score: number` Overall doctoring likelihood (0 to 1) - `verdict: "AUTHENTIC" | "DOCTORED" | "LIKELY_DOCTORED" | 2 more` Overall verdict for the document - `"AUTHENTIC"` - `"DOCTORED"` - `"LIKELY_DOCTORED"` - `"NO_STRONG_SIGNAL"` - `"SUSPICIOUS"` - `composite_scores?: CompositeScores` Composite scores, each answering one question about the document - `ai_generated?: AIGenerated` Was this content synthesized by a generative model? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_coherence?: DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_metadata?: DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `known_fraud?: KnownFraud` Has this asset (or its template) been seen in fraud before? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `manually_edited?: ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` 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)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `confidence?: number` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `error?: string | null` Error detail when the analysis could not complete - `page_count?: number` Number of analysed pages (1 for images/docx) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `reasoning?: string` Explanation of the verdict - `suspect_regions?: Array` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Suspicion score for this region (0 to 1) - `source: string` Detector that flagged this region - `primary?: boolean` 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 - `synthetic_score?: number | null` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `tampering_score?: number | null` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `transaction_id?: string | null` Idempotency key - `updated_at?: string | null` Update datetime ### Verify Create Response - `VerifyCreateResponse` Response for a Verify job. - `id: string` Unique identifier - `configuration: Configuration` Verify configuration used for this job - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `document_input_type: "file_id" | "parse_job_id" | "url"` Type of the document input (FILE) - `"file_id"` - `"parse_job_id"` - `"url"` - `file_input: string` ID of the input file - `project_id: string` Project this job belongs to - `status: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` - `user_id: string` User who created this job - `created_at?: string | null` Creation datetime - `error_message?: string | null` Error message if job failed - `result?: Result | null` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `detector_version: string` Version of the detector that produced the result - `overall_score: number` Overall doctoring likelihood (0 to 1) - `verdict: "AUTHENTIC" | "DOCTORED" | "LIKELY_DOCTORED" | 2 more` Overall verdict for the document - `"AUTHENTIC"` - `"DOCTORED"` - `"LIKELY_DOCTORED"` - `"NO_STRONG_SIGNAL"` - `"SUSPICIOUS"` - `composite_scores?: CompositeScores` Composite scores, each answering one question about the document - `ai_generated?: AIGenerated` Was this content synthesized by a generative model? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_coherence?: DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_metadata?: DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `known_fraud?: KnownFraud` Has this asset (or its template) been seen in fraud before? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `manually_edited?: ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` 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)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `confidence?: number` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `error?: string | null` Error detail when the analysis could not complete - `page_count?: number` Number of analysed pages (1 for images/docx) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `reasoning?: string` Explanation of the verdict - `suspect_regions?: Array` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Suspicion score for this region (0 to 1) - `source: string` Detector that flagged this region - `primary?: boolean` 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 - `synthetic_score?: number | null` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `tampering_score?: number | null` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `transaction_id?: string | null` Idempotency key - `updated_at?: string | null` Update datetime ### Verify Get Response - `VerifyGetResponse` Response for a Verify job. - `id: string` Unique identifier - `configuration: Configuration` Verify configuration used for this job - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `document_input_type: "file_id" | "parse_job_id" | "url"` Type of the document input (FILE) - `"file_id"` - `"parse_job_id"` - `"url"` - `file_input: string` ID of the input file - `project_id: string` Project this job belongs to - `status: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` - `user_id: string` User who created this job - `created_at?: string | null` Creation datetime - `error_message?: string | null` Error message if job failed - `result?: Result | null` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `detector_version: string` Version of the detector that produced the result - `overall_score: number` Overall doctoring likelihood (0 to 1) - `verdict: "AUTHENTIC" | "DOCTORED" | "LIKELY_DOCTORED" | 2 more` Overall verdict for the document - `"AUTHENTIC"` - `"DOCTORED"` - `"LIKELY_DOCTORED"` - `"NO_STRONG_SIGNAL"` - `"SUSPICIOUS"` - `composite_scores?: CompositeScores` Composite scores, each answering one question about the document - `ai_generated?: AIGenerated` Was this content synthesized by a generative model? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_coherence?: DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_metadata?: DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `known_fraud?: KnownFraud` Has this asset (or its template) been seen in fraud before? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `manually_edited?: ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` 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)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `confidence?: number` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `error?: string | null` Error detail when the analysis could not complete - `page_count?: number` Number of analysed pages (1 for images/docx) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `reasoning?: string` Explanation of the verdict - `suspect_regions?: Array` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Suspicion score for this region (0 to 1) - `source: string` Detector that flagged this region - `primary?: boolean` 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 - `synthetic_score?: number | null` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `tampering_score?: number | null` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `transaction_id?: string | null` Idempotency key - `updated_at?: string | null` Update datetime ### Verify Cancel Response - `VerifyCancelResponse` Response for a Verify job. - `id: string` Unique identifier - `configuration: Configuration` Verify configuration used for this job - `target_pages?: string | null` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `tier?: "agentic" | "fast"` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `"agentic"` - `"fast"` - `document_input_type: "file_id" | "parse_job_id" | "url"` Type of the document input (FILE) - `"file_id"` - `"parse_job_id"` - `"url"` - `file_input: string` ID of the input file - `project_id: string` Project this job belongs to - `status: "CANCELLED" | "COMPLETED" | "FAILED" | 2 more` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `"CANCELLED"` - `"COMPLETED"` - `"FAILED"` - `"PENDING"` - `"RUNNING"` - `user_id: string` User who created this job - `created_at?: string | null` Creation datetime - `error_message?: string | null` Error message if job failed - `result?: Result | null` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `detector_version: string` Version of the detector that produced the result - `overall_score: number` Overall doctoring likelihood (0 to 1) - `verdict: "AUTHENTIC" | "DOCTORED" | "LIKELY_DOCTORED" | 2 more` Overall verdict for the document - `"AUTHENTIC"` - `"DOCTORED"` - `"LIKELY_DOCTORED"` - `"NO_STRONG_SIGNAL"` - `"SUSPICIOUS"` - `composite_scores?: CompositeScores` Composite scores, each answering one question about the document - `ai_generated?: AIGenerated` Was this content synthesized by a generative model? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_coherence?: DocumentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `document_metadata?: DocumentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `known_fraud?: KnownFraud` Has this asset (or its template) been seen in fraud before? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `manually_edited?: ManuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` 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)? - `applicable?: boolean` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `score?: number | null` Score (0 to 1); null when the composite was not applicable - `confidence?: number` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `error?: string | null` Error detail when the analysis could not complete - `page_count?: number` Number of analysed pages (1 for images/docx) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `reasoning?: string` Explanation of the verdict - `suspect_regions?: Array` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Suspicion score for this region (0 to 1) - `source: string` Detector that flagged this region - `primary?: boolean` 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 - `synthetic_score?: number | null` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `tampering_score?: number | null` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `transaction_id?: string | null` Idempotency key - `updated_at?: string | null` Update datetime ### Verify Get Details Response - `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. - `job_id: string` ID of the Verify job - `degraded_tools?: Array` 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?: Array` 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: number` Evidence strength score - `tool: string` Tool that produced this evidence - `hard?: boolean` Whether this is hard (conclusive) evidence - `metadata_tool?: Record` Raw values from the tool behind this finding; the shape varies by tool - `heatmaps?: Array` Per-page forensic heatmap overlays as presigned image URLs - `expires_at: string` The time at which the presigned URL expires - `kind: string` Producing signal, e.g. double_compression, ela, noise - `page: number` 0-based page index (0 for standalone images) - `url: string` Presigned URL to the heatmap PNG (page overlay) - `score?: number` Producing tool's max score (for ranking) - `page_dimensions?: Array` Rendered pixel size per page, so region bboxes can be scaled onto the page - `height: number` Rendered page height in pixels - `page: number` 0-based page index (0 for standalone images) - `width: number` Rendered page width in pixels - `regions?: Array` Suspicious regions localized on rendered pages - `bbox: Array` 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: number` 0-based page index (0 for standalone images) - `score: number` Region-level doctoring likelihood score - `source: string` Detector/tool that produced this region - `primary?: boolean` 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 - `review_note?: string` Free-form review note for this region - `sub_scores?: Record` Per-family scores (metadata, ai_generation, splicing, copy_move, compression, noise, coherence, pdf_structure)