Exam Bundle

A controlled shifted feature batch triggers the intended drift alert while a reference batch remains within its baseline threshold. This would verify a different operation: Create a SageMaker Model Monitor data-quality baseline and schedule inference feature-distribution checks against it. That separate action addresses: A customer churn model starts receiving features with a distribution that differs sharply from training, but the endpoint tracks only CPU and availability. It cannot establish the required Oakridge Public Services correction for: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The decisive acceptance check is instead: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

The monitoring metadata links the live model package to its correct reviewed baseline and tests produce expected alerts. This would verify a different operation: Version monitoring baselines with each released model and capture a reviewed transition policy between old and new expectations. That separate action addresses: A model owner uses one unversioned monitoring baseline for every retraining run, so legitimate model improvements trigger constant false alarms. It cannot establish the required Oakridge Public Services correction for: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The decisive acceptance check is instead: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

The monitoring report labels distribution shift and actual error metrics distinctly and does not infer accuracy loss from drift alone. This would verify a different operation: Distinguish covariate drift from verified performance degradation and evaluate outcome labels and model-quality metrics separately. That separate action addresses: An operations dashboard treats a rising model input drift score as proof that prediction correctness already decreased without label evidence. It cannot establish the required Oakridge Public Services correction for: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The decisive acceptance check is instead: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

Require appropriate SSE-KMS settings on the output bucket and ensure the training role is authorized to use the chosen key. It does not directly address the Harborview Insurance case: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The relevant acceptance criterion for this case is: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

Apply input validation with monitored missingness and a documented safe fallback or rejection policy for out-of-contract requests. It does not directly address the Harborview Insurance case: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The relevant acceptance criterion for this case is: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

Track total received records, rejected records and successful predictions with clear denominators across batch processing. It does not directly address the Harborview Insurance case: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The relevant acceptance criterion for this case is: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

An authorized tenant role decrypts only its dataset and a cross-tenant key operation is denied. This would verify a different operation: Apply dataset-specific KMS grants or key policies and distinct IAM roles aligned with tenant segregation requirements. That separate action addresses: An ML feature store contains regulated fields encrypted with an AWS KMS key, but a shared role can decrypt every organization's dataset. It cannot establish the required Harborview Insurance correction for: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The decisive acceptance check is instead: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

A missing-feature test request raises the expected data-quality signal and compatible requests retain their normal score output. This would verify a different operation: Monitor inference request schema and null-value rates against a versioned accepted contract before treating the endpoint as healthy. That separate action addresses: A deployed model's training-serving schema changes silently when one upstream feature is renamed, leaving most online predictions based on missing values. It cannot establish the required Harborview Insurance correction for: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The decisive acceptance check is instead: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

A deliberately miscalibrated sample breaches the documented reliability threshold while a well-calibrated control remains acceptable. This would verify a different operation: Monitor predicted probability buckets against observed outcome frequencies using suitable delayed labels and calibration baselines. That separate action addresses: A quality dashboard plots only the mean model score, hiding gradual calibration drift as actual event rates change over time. It cannot establish the required Harborview Insurance correction for: A model's endpoint throughput suddenly falls but the operator adds instances before investigating payload size changes in incoming traffic. The decisive acceptance check is instead: A controlled payload replay reproduces the bottleneck and the targeted correction restores throughput without indiscriminate scaling.

Track total received records, rejected records and successful predictions with clear denominators across batch processing. It does not directly address the Redstone Aviation case: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The relevant acceptance criterion for this case is: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

Separate training, model approval and production deployment identities with explicit role and approval boundaries. It does not directly address the Redstone Aviation case: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The relevant acceptance criterion for this case is: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

Add model-specific output-validity checks and application error metrics alongside endpoint health measurements. It does not directly address the Redstone Aviation case: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The relevant acceptance criterion for this case is: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

A deliberately vulnerable test image is blocked and a compliant approved digest reaches the deployment stage. This would verify a different operation: Integrate ECR image scanning and an enforced reviewed vulnerability acceptance gate before deploying the immutable image digest. That separate action addresses: A training pipeline publishes an unscanned container image with known vulnerable dependencies directly to the production ECR repository. It cannot establish the required Redstone Aviation correction for: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The decisive acceptance check is instead: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

A controlled event's original prediction joins to the matching eventual label without exposing unauthorized personal identifiers. This would verify a different operation: Retain privacy-preserving stable correlation keys through prediction capture and delayed outcome ingestion. That separate action addresses: An inference monitoring workflow cannot associate captured predictions with later labels because request identifiers are stripped during processing. It cannot establish the required Redstone Aviation correction for: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The decisive acceptance check is instead: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

A representative request cohort produces traceable per-model score differences and unacceptable changes block promotion. This would verify a different operation: Run shadow or controlled A/B inference comparisons with logged model version and matched request IDs before full rollout. That separate action addresses: A retrained model is deployed without comparing its output distributions with the approved production model, causing unexplained score shifts. It cannot establish the required Redstone Aviation correction for: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The decisive acceptance check is instead: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

Version monitoring baselines with each released model and capture a reviewed transition policy between old and new expectations. It does not directly address the Meadowbrook Finance case: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The relevant acceptance criterion for this case is: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

Track total received records, rejected records and successful predictions with clear denominators across batch processing. It does not directly address the Meadowbrook Finance case: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The relevant acceptance criterion for this case is: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

Add model-specific output-validity checks and application error metrics alongside endpoint health measurements. It does not directly address the Meadowbrook Finance case: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The relevant acceptance criterion for this case is: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

A controlled missing-lookup request produces a measurable model-error event rather than being counted as a valid prediction. This would verify a different operation: Add model-specific output-validity checks and application error metrics alongside endpoint health measurements. That separate action addresses: A model serving container returns HTTP 200 for all requests even when its predictor emits empty outputs due to a failed feature lookup. It cannot establish the required Meadowbrook Finance correction for: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The decisive acceptance check is instead: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

The monitoring report labels distribution shift and actual error metrics distinctly and does not infer accuracy loss from drift alone. This would verify a different operation: Distinguish covariate drift from verified performance degradation and evaluate outcome labels and model-quality metrics separately. That separate action addresses: An operations dashboard treats a rising model input drift score as proof that prediction correctness already decreased without label evidence. It cannot establish the required Meadowbrook Finance correction for: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The decisive acceptance check is instead: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

A synthetic slice regression is detected even though the overall average metric remains inside its broad threshold. This would verify a different operation: Create monitored business slices and evaluate approved per-segment metrics and bias indicators using retained ground-truth labels. That separate action addresses: A service tracks only average model prediction values while a narrow segment receives systematically poor results that aggregate statistics hide. It cannot establish the required Meadowbrook Finance correction for: An expensive SageMaker hyperparameter search continues after clearly underperforming trials without any early stopping or experiment budget. The decisive acceptance check is instead: The revised sweep consumes fewer training hours and still identifies a candidate meeting the accepted validation target.

Integrate ECR image scanning and an enforced reviewed vulnerability acceptance gate before deploying the immutable image digest. It does not directly address the Maplewood Schools case: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The relevant acceptance criterion for this case is: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

Use appropriate SageMaker Clarify post-training bias measures and valid governed outcome data with documented fairness interpretation. It does not directly address the Maplewood Schools case: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The relevant acceptance criterion for this case is: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

Monitor end-to-end feature freshness, dependency errors and successful business prediction rates in addition to endpoint health. It does not directly address the Maplewood Schools case: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The relevant acceptance criterion for this case is: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources. This would verify a different operation: Replace embedded access keys with authorized IAM roles and secure short-lived credential delivery for the notebook environment. That separate action addresses: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. It cannot establish the required Maplewood Schools correction for: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The decisive acceptance check is instead: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

A controlled malformed-input batch is counted in the rejection metric and overall error reporting includes all attempted records. This would verify a different operation: Track total received records, rejected records and successful predictions with clear denominators across batch processing. That separate action addresses: A batch prediction system drops malformed records but the monitoring report tracks only successfully scored inputs and understates total error rate. It cannot establish the required Maplewood Schools correction for: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The decisive acceptance check is instead: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

The monitoring report labels distribution shift and actual error metrics distinctly and does not infer accuracy loss from drift alone. This would verify a different operation: Distinguish covariate drift from verified performance degradation and evaluate outcome labels and model-quality metrics separately. That separate action addresses: An operations dashboard treats a rising model input drift score as proof that prediction correctness already decreased without label evidence. It cannot establish the required Maplewood Schools correction for: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The decisive acceptance check is instead: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

Distinguish covariate drift from verified performance degradation and evaluate outcome labels and model-quality metrics separately. It does not directly address the Highland Education case: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The relevant acceptance criterion for this case is: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

Publish an approved data subset or governed view and grant read access only to the required machine learning project roles. It does not directly address the Highland Education case: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The relevant acceptance criterion for this case is: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

Enforce protected build contexts, isolated untrusted code execution and restricted deployment credentials available only after review. It does not directly address the Highland Education case: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The relevant acceptance criterion for this case is: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

A deliberately vulnerable test image is blocked and a compliant approved digest reaches the deployment stage. This would verify a different operation: Integrate ECR image scanning and an enforced reviewed vulnerability acceptance gate before deploying the immutable image digest. That separate action addresses: A training pipeline publishes an unscanned container image with known vulnerable dependencies directly to the production ECR repository. It cannot establish the required Highland Education correction for: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The decisive acceptance check is instead: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

The monitoring metadata links the live model package to its correct reviewed baseline and tests produce expected alerts. This would verify a different operation: Version monitoring baselines with each released model and capture a reviewed transition policy between old and new expectations. That separate action addresses: A model owner uses one unversioned monitoring baseline for every retraining run, so legitimate model improvements trigger constant false alarms. It cannot establish the required Highland Education correction for: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The decisive acceptance check is instead: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.

A code scan finds no static secret and the notebook's execution role can use only its intended dataset resources. This would verify a different operation: Replace embedded access keys with authorized IAM roles and secure short-lived credential delivery for the notebook environment. That separate action addresses: A SageMaker notebook user stores long-lived AWS credentials in the notebook source so other project members can inspect them. It cannot establish the required Highland Education correction for: An inference architecture replicates model artifacts to every deployment even though regional copies already exist and frequent downloads dominate startup time. The decisive acceptance check is instead: Endpoint startup time decreases while the loaded model checksum still matches the approved release artifact.