## Create Verify Job `VerifyCreateResponse alpha().verify().create(VerifyCreateParamsparams = VerifyCreateParams.none(), RequestOptionsrequestOptions = RequestOptions.none())` **post** `/api/alpha/verify` Create a Verify job. Analyzes a document for signs of doctoring (splicing, copy-move, AI generation, metadata tampering, ...). Set `file_input` to a file ID (`dfl-...`). Optionally provide a `configuration` object to control the semantic agent. The job runs asynchronously. Poll `GET /verify/{job_id}` with `expand=result` to check status and retrieve results. ### Parameters - `VerifyCreateParams params` - `Optional organizationId` - `Optional projectId` - `Optional configuration` Configuration for a Verify job. - `Optional targetPages` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Optional tier` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `AGENTIC("agentic")` - `FAST("fast")` - `Optional fileId` Deprecated: use file_input instead - `Optional fileInput` File ID of the document to analyze - `Optional transactionId` Idempotency key scoped to the project. Reusing a key returns the original job; the new request body is ignored. - `Optional> webhookConfigurationIds` IDs of saved webhook configurations to notify for this job. - `Optional> webhookConfigurations` Outbound webhook endpoints to notify on job status changes - `Optional> webhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `BATCH_CANCELLED("batch.cancelled")` - `BATCH_ERROR("batch.error")` - `BATCH_PENDING("batch.pending")` - `BATCH_RUNNING("batch.running")` - `BATCH_SUCCESS("batch.success")` - `CLASSIFY_CANCELLED("classify.cancelled")` - `CLASSIFY_ERROR("classify.error")` - `CLASSIFY_PARTIAL_SUCCESS("classify.partial_success")` - `CLASSIFY_PENDING("classify.pending")` - `CLASSIFY_RUNNING("classify.running")` - `CLASSIFY_SUCCESS("classify.success")` - `EXTRACT_CANCELLED("extract.cancelled")` - `EXTRACT_ERROR("extract.error")` - `EXTRACT_PARTIAL_SUCCESS("extract.partial_success")` - `EXTRACT_PENDING("extract.pending")` - `EXTRACT_SUCCESS("extract.success")` - `PARSE_CANCELLED("parse.cancelled")` - `PARSE_ERROR("parse.error")` - `PARSE_PARTIAL_SUCCESS("parse.partial_success")` - `PARSE_PENDING("parse.pending")` - `PARSE_RUNNING("parse.running")` - `PARSE_SUCCESS("parse.success")` - `SHEETS_CANCELLED("sheets.cancelled")` - `SHEETS_ERROR("sheets.error")` - `SHEETS_PARTIAL_SUCCESS("sheets.partial_success")` - `SHEETS_PENDING("sheets.pending")` - `SHEETS_SUCCESS("sheets.success")` - `SPLIT_CANCELLED("split.cancelled")` - `SPLIT_ERROR("split.error")` - `SPLIT_PENDING("split.pending")` - `SPLIT_PROCESSING("split.processing")` - `SPLIT_SUCCESS("split.success")` - `UNMAPPED_EVENT("unmapped_event")` - `VERIFY_CANCELLED("verify.cancelled")` - `VERIFY_ERROR("verify.error")` - `VERIFY_PENDING("verify.pending")` - `VERIFY_RUNNING("verify.running")` - `VERIFY_SUCCESS("verify.success")` - `Optional webhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `Optional webhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `Optional webhookSigningSecret` Shared signing secret used to sign webhook deliveries. When set, each request includes an HMAC-SHA256 signature of the request body in the 'LC-Signature' header (value 'sha256='). Recompute the HMAC over the raw request body with this secret to verify the delivery is authentic. - `Optional webhookUrl` URL to receive webhook POST notifications ### Returns - `class VerifyCreateResponse:` Response for a Verify job. - `String id` Unique identifier - `Configuration configuration` Verify configuration used for this job - `Optional targetPages` Comma-separated page numbers or ranges to analyze (1-based). Omit to analyze all pages. Ignored for non-PDF inputs. - `Optional tier` Verify tier: 'fast' runs only the quick deterministic forensic checks (metadata, content integrity, container structure, pixel statistics); 'agentic' (default) runs the full pipeline including the learned detectors and the semantic review pass. - `AGENTIC("agentic")` - `FAST("fast")` - `DocumentInputType documentInputType` Type of the document input (FILE) - `FILE_ID("file_id")` - `PARSE_JOB_ID("parse_job_id")` - `URL("url")` - `String fileInput` ID of the input file - `String projectId` Project this job belongs to - `Status status` Current job status: PENDING, RUNNING, COMPLETED, FAILED, or CANCELLED - `CANCELLED("CANCELLED")` - `COMPLETED("COMPLETED")` - `FAILED("FAILED")` - `PENDING("PENDING")` - `RUNNING("RUNNING")` - `String userId` User who created this job - `Optional createdAt` Creation datetime - `Optional errorMessage` Error message if job failed - `Optional result` Result of a Verify (doctored-document) analysis. Raw per-signal detail (evidence list, per-family sub-scores, raw regions, forensic heatmaps) is available separately via the job's details endpoint. - `String detectorVersion` Version of the detector that produced the result - `double overallScore` Overall doctoring likelihood (0 to 1) - `Verdict verdict` Overall verdict for the document - `AUTHENTIC("AUTHENTIC")` - `DOCTORED("DOCTORED")` - `LIKELY_DOCTORED("LIKELY_DOCTORED")` - `NO_STRONG_SIGNAL("NO_STRONG_SIGNAL")` - `SUSPICIOUS("SUSPICIOUS")` - `Optional compositeScores` Composite scores, each answering one question about the document - `Optional aiGenerated` Was this content synthesized by a generative model? - `Optional applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Optional score` Score (0 to 1); null when the composite was not applicable - `Optional documentCoherence` Does the document's content agree with itself (checksums, arithmetic, machine-readable zones)? - `Optional applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Optional score` Score (0 to 1); null when the composite was not applicable - `Optional documentMetadata` Does the file's provenance / toolchain history look suspicious? Advisory: individually weak workflow-hygiene signals - `Optional applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Optional score` Score (0 to 1); null when the composite was not applicable - `Optional knownFraud` Has this asset (or its template) been seen in fraud before? - `Optional applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Optional score` Score (0 to 1); null when the composite was not applicable - `Optional manuallyEdited` Was this document altered after creation (splice, retype, redact, inpaint)? - `Optional applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Optional score` Score (0 to 1); null when the composite was not applicable - `Optional recapture` Was the document captured through a channel that destroys forensic evidence (photo of a screen, print-then-rescan)? - `Optional applicable` Whether the checks feeding this composite ran on this document. When false the document was not checked for this — not cleared of it - `Optional score` Score (0 to 1); null when the composite was not applicable - `Optional confidence` Confidence in the verdict (0 to 1): how firmly the detected signals support the verdict bucket, independent of the doctoring likelihood itself - `Optional error` Error detail when the analysis could not complete - `Optional pageCount` Number of analysed pages (1 for images/docx) - `Optional> pageDimensions` Rendered pixel size per page, so region bboxes can be scaled onto the page - `long height` Rendered page height in pixels - `long page` 0-based page index (0 for standalone images) - `long width` Rendered page width in pixels - `Optional reasoning` Explanation of the verdict - `Optional> suspectRegions` Regions that led to the suspected fraud, ranked most-suspect first, each with an explanation of what makes it suspect - `List bbox` Region bounding box as [x, y, w, h] in page-render pixels - `String explanation` Human-readable explanation of what makes this region suspect - `String kind` Kind of anomaly detected in this region - `long page` 0-based page index (0 for standalone images) - `double score` Suspicion score for this region (0 to 1) - `String source` Detector that flagged this region - `Optional primary` Whether this region is part of the small set of decisive evidence behind the verdict — the boxes a reviewer should look at first - `Optional review` Automated reviewer verdict for this region (confirmed, dismissed, unsure, or empty). A dismissed region can still be surfaced when it is the only place to look; this label says how to read it - `Optional syntheticScore` Likelihood (0 to 1) that the document is wholly generated or fabricated rather than a capture of a real document. Null for jobs completed before this score was introduced - `Optional tamperingScore` Likelihood (0 to 1) that a real captured document was locally edited — a genuine capture with regions altered after the fact. Null for jobs completed before this score was introduced - `Optional transactionId` Idempotency key - `Optional updatedAt` Update datetime ### Example ```java package ai.llamaindex.llamacloud.example; import ai.llamaindex.llamacloud.client.LlamaCloudClient; import ai.llamaindex.llamacloud.client.okhttp.LlamaCloudOkHttpClient; import ai.llamaindex.llamacloud.models.alpha.verify.VerifyCreateParams; import ai.llamaindex.llamacloud.models.alpha.verify.VerifyCreateResponse; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); VerifyCreateResponse verify = client.alpha().verify().create(); } } ``` #### 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" } ```