Exam Bundle

An input set with mixed-capitalization labels maps consistently while an unknown label triggers the declared quality exception. This would verify a different operation: Define a validated label encoding dictionary and reject unmapped target values before model training starts. That separate action addresses: A binary target is stored as strings with inconsistent capitalization and preprocessing silently maps one valid positive class to negative. It cannot establish the required Harborview Insurance correction for: A newly deployed Glue ingestion job tries to infer the schema of evolving JSON events, and a changed field type silently becomes a null column. The decisive acceptance check is instead: A field-type regression is quarantined and a compatible schema revision remains queryable with the expected typed attributes.

A clean automated run produces the same features as the reviewed interactive flow on a fixed reference sample. This would verify a different operation: Export and version the complete flow definition as a repeatable SageMaker processing step rather than a notebook-only action. That separate action addresses: A SageMaker Data Wrangler flow contains an interactive manual step that is not reflected in the exported production preprocessing job. It cannot establish the required Harborview Insurance correction for: A newly deployed Glue ingestion job tries to infer the schema of evolving JSON events, and a changed field type silently becomes a null column. The decisive acceptance check is instead: A field-type regression is quarantined and a compatible schema revision remains queryable with the expected typed attributes.

A multilingual test phrase yields the same token IDs in the training pipeline and deployed inference endpoint. This would verify a different operation: Version a single canonical text normalization and tokenizer artifact and use it in both processing and serving containers. That separate action addresses: A text classifier tokenizes raw Unicode text differently in batch training and the real-time inference application. It cannot establish the required Harborview Insurance correction for: A newly deployed Glue ingestion job tries to infer the schema of evolving JSON events, and a changed field type silently becomes a null column. The decisive acceptance check is instead: A field-type regression is quarantined and a compatible schema revision remains queryable with the expected typed attributes.

Implement the same window boundaries, event-time cutoff and aggregation logic for offline and online feature creation. It does not directly address the Redstone Aviation case: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The relevant acceptance criterion for this case is: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

Apply an appropriate categorical encoding while preserving the region identifier's nominal semantics and missing-value policy. It does not directly address the Redstone Aviation case: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The relevant acceptance criterion for this case is: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

Standardize image dimensions, channel ordering and value normalization in the shared preprocessing artifact. It does not directly address the Redstone Aviation case: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The relevant acceptance criterion for this case is: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

A known test image produces matching normalized pixel tensors in offline and online environments. This would verify a different operation: Standardize image dimensions, channel ordering and value normalization in the shared preprocessing artifact. That separate action addresses: An image classification pipeline resizes training images with one color-channel convention and production inputs with another. It cannot establish the required Redstone Aviation correction for: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The decisive acceptance check is instead: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

Distance-sensitive evaluation improves and the identical stored scale parameters are used during training and online inference. This would verify a different operation: Fit a standardization or scaling transform on training data only and apply the saved transform to validation and inference inputs. That separate action addresses: A churn model trains on customer age and transaction amount with unrelated scales, causing its distance-based feature representation to be dominated by transaction magnitude. It cannot establish the required Redstone Aviation correction for: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The decisive acceptance check is instead: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

A similarity check finds no synthetic descendants in test data and the external holdout result reflects genuine generalization. This would verify a different operation: Split the original records first, then apply synthetic oversampling exclusively to the training split. That separate action addresses: A fraud model is trained on synthetic minority samples generated before splitting the source data, leading to near-duplicate examples in the test set. It cannot establish the required Redstone Aviation correction for: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The decisive acceptance check is instead: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

Validate nullable field semantics and reject or impute explicit missing tokens without converting them to legitimate zero values. It does not directly address the Meadowbrook Finance case: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The relevant acceptance criterion for this case is: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

Use a stratified or otherwise class-aware splitting method with declared minimum representation checks for the holdout set. It does not directly address the Meadowbrook Finance case: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The relevant acceptance criterion for this case is: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

Define a validated label encoding dictionary and reject unmapped target values before model training starts. It does not directly address the Meadowbrook Finance case: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The relevant acceptance criterion for this case is: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

A scheduled retention test can still retrieve every manifest object needed to reproduce the archived model version. This would verify a different operation: Apply retention and lifecycle rules compatible with artifact lineage and archive immutable source objects required for approved reproducibility. That separate action addresses: A training manifest refers to S3 objects that were removed by an aggressive lifecycle rule, so reproducible model builds fail months later. It cannot establish the required Meadowbrook Finance correction for: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The decisive acceptance check is instead: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

The feature vector dimensions stay bounded and an evaluation report measures collisions or embedding quality on held-out accounts. This would verify a different operation: Use a suitable embedding or hashing approach with collision and memory impact assessed for the model objective. That separate action addresses: A recommendation model's high-cardinality account IDs explode into impractically wide one-hot sparse features. It cannot establish the required Meadowbrook Finance correction for: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The decisive acceptance check is instead: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

A known test image produces matching normalized pixel tensors in offline and online environments. This would verify a different operation: Standardize image dimensions, channel ordering and value normalization in the shared preprocessing artifact. That separate action addresses: An image classification pipeline resizes training images with one color-channel convention and production inputs with another. It cannot establish the required Meadowbrook Finance correction for: A training pipeline needs recent transaction attributes from DynamoDB, but its ad hoc full table scan increases read capacity consumption during business hours. The decisive acceptance check is instead: A reproducible export contains the required records while production capacity and latency remain inside agreed limits.

Define an as-of-time feature cutoff and exclude any data collected after the target prediction time. It does not directly address the Maplewood Schools case: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The relevant acceptance criterion for this case is: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

Perform approved irreversible masking or tokenization before feature extraction and restrict the original identifier fields. It does not directly address the Maplewood Schools case: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The relevant acceptance criterion for this case is: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

Use explicit versioned feature names and document producer-consumer contracts for the stored feature definitions. It does not directly address the Maplewood Schools case: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The relevant acceptance criterion for this case is: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

A clean automated run produces the same features as the reviewed interactive flow on a fixed reference sample. This would verify a different operation: Export and version the complete flow definition as a repeatable SageMaker processing step rather than a notebook-only action. That separate action addresses: A SageMaker Data Wrangler flow contains an interactive manual step that is not reflected in the exported production preprocessing job. It cannot establish the required Maplewood Schools correction for: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The decisive acceptance check is instead: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

The held-out split does not affect learned fill values and a repeated inference request reproduces the expected imputed feature. This would verify a different operation: Learn imputation statistics exclusively from the training split and reuse those fixed values on held-out datasets. That separate action addresses: A training dataset has missing sensor measurements that are filled using the global mean calculated from test and validation records. It cannot establish the required Maplewood Schools correction for: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The decisive acceptance check is instead: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

The model input schema contains no disallowed raw identifiers while the join workflow retains authorized traceable tokens. This would verify a different operation: Perform approved irreversible masking or tokenization before feature extraction and restrict the original identifier fields. That separate action addresses: A team concatenates customer names into feature vectors before masking personal data despite a training dataset policy forbidding direct identifiers. It cannot establish the required Maplewood Schools correction for: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The decisive acceptance check is instead: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

Validate nullable field semantics and reject or impute explicit missing tokens without converting them to legitimate zero values. It does not directly address the Highland Education case: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The relevant acceptance criterion for this case is: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

Profile the feature distribution by label and apply documented context-aware outlier handling rather than global blind filtering. It does not directly address the Highland Education case: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The relevant acceptance criterion for this case is: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

Perform approved irreversible masking or tokenization before feature extraction and restrict the original identifier fields. It does not directly address the Highland Education case: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The relevant acceptance criterion for this case is: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

A test replay with multiple versions yields one expected customer record and preserves the authorized last-update fields. This would verify a different operation: Deduplicate on stable business identity and event-version rules, retaining the latest accepted entity state as required. That separate action addresses: An ETL pipeline drops duplicate customers using every column as a key even though repeated events have different update timestamps. It cannot establish the required Highland Education correction for: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The decisive acceptance check is instead: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

A known test image produces matching normalized pixel tensors in offline and online environments. This would verify a different operation: Standardize image dimensions, channel ordering and value normalization in the shared preprocessing artifact. That separate action addresses: An image classification pipeline resizes training images with one color-channel convention and production inputs with another. It cannot establish the required Highland Education correction for: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The decisive acceptance check is instead: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

A compliance scan finds sensitive samples only in their permitted regions and a disallowed cross-region copy is denied. This would verify a different operation: Classify regional attributes and keep processing and storage in approved AWS Regions with authorized data residency controls. That separate action addresses: A data preparation flow mixes historical US and EU user records without enforcing the documented regional storage restriction for personal attributes. It cannot establish the required Highland Education correction for: Multiple processing workers simultaneously append sample files to one S3 object key and accidentally overwrite each other's contribution to the model dataset. The decisive acceptance check is instead: The completed manifest references every expected part exactly once and no writer replaces another part's S3 object.

Use time-aware joins against effective-dated reference values to reconstruct the features available when each event occurred. It does not directly address the Eastshore Energy case: A batch inference preparation job loads tens of terabytes through a single small EC2 disk, causing the local staging volume to fill before training begins. The relevant acceptance criterion for this case is: The larger test corpus completes staging without local disk exhaustion and model workers read the documented dataset version.

Version a single canonical text normalization and tokenizer artifact and use it in both processing and serving containers. It does not directly address the Eastshore Energy case: A batch inference preparation job loads tens of terabytes through a single small EC2 disk, causing the local staging volume to fill before training begins. The relevant acceptance criterion for this case is: The larger test corpus completes staging without local disk exhaustion and model workers read the documented dataset version.

Use distributed Spark transforms or scalable partitioned outputs instead of collecting the full dataset to one process. It does not directly address the Eastshore Energy case: A batch inference preparation job loads tens of terabytes through a single small EC2 disk, causing the local staging volume to fill before training begins. The relevant acceptance criterion for this case is: The larger test corpus completes staging without local disk exhaustion and model workers read the documented dataset version.

A known test image produces matching normalized pixel tensors in offline and online environments. This would verify a different operation: Standardize image dimensions, channel ordering and value normalization in the shared preprocessing artifact. That separate action addresses: An image classification pipeline resizes training images with one color-channel convention and production inputs with another. It cannot establish the required Eastshore Energy correction for: A batch inference preparation job loads tens of terabytes through a single small EC2 disk, causing the local staging volume to fill before training begins. The decisive acceptance check is instead: The larger test corpus completes staging without local disk exhaustion and model workers read the documented dataset version.

The training cutoff precedes the first validation observation and a forward rolling evaluation reproduces the expected boundaries. This would verify a different operation: Use chronological training, validation and final holdout windows with a gap where leakage risk requires one. That separate action addresses: A time-series demand model shuffles future demand records into an earlier training window, invalidating its forward-looking evaluation. It cannot establish the required Eastshore Energy correction for: A batch inference preparation job loads tens of terabytes through a single small EC2 disk, causing the local staging volume to fill before training begins. The decisive acceptance check is instead: The larger test corpus completes staging without local disk exhaustion and model workers read the documented dataset version.

Model input checks confirm no implied numerical ordering and all expected regions map to the approved encoded features. This would verify a different operation: Apply an appropriate categorical encoding while preserving the region identifier's nominal semantics and missing-value policy. That separate action addresses: A numeric categorical code such as region ID is mistakenly treated as an ordered magnitude when supplied to a linear model. It cannot establish the required Eastshore Energy correction for: A batch inference preparation job loads tens of terabytes through a single small EC2 disk, causing the local staging volume to fill before training begins. The decisive acceptance check is instead: The larger test corpus completes staging without local disk exhaustion and model workers read the documented dataset version.