Abstract: A method, system, and computer program product generate precomputed explanation scores in AI systems. The method includes obtaining a set of labeled transactions comprising input features and corresponding output labels generated by a machine learning (ML) model and generating an explainable artificial intelligence (XAI) module. The generating includes clustering the labeled transactions based on the input features, scoring homogeneity of the clustered transactions based on the corresponding output labels, and selecting at least one cluster from the clustered transactions based on the homogeneity scoring. The generating further includes obtaining, by an explainability model, explainability scores for transactions in the at least one cluster, generating a unified explainability score for the at least one cluster based on the explainability scores, and storing the unified explainability score in a set of precomputed explanations.

Abstract: A first input transaction is classified into a first input space cluster in a set of input space clusters. It is determined that the first input space cluster maps to a single explainability space cluster in a set of explainability space clusters. Using an interpretable model corresponding to the single explainability space cluster, a first machine learning model prediction is explained, the first machine learning model prediction resulting from processing, by a machine learning model, the first input transaction.

Abstract: In an approach to creating explanatory confusion matrices, responsive to receiving a machine learning model for analysis, a confusion matrix is calculated for the machine learning model, where each cell in the confusion matrix has a corresponding set of data. A link is created from each cell in the confusion matrix to the corresponding set of data. Responsive to a user selecting in a user interface a specific cell of the confusion matrix, the corresponding set of data to the specific cell is displayed on the user interface.

Abstract: Concepts for managing a supervised machine learning model of a set of documents are presented. A system obtains annotated versions of the documents, the documents being annotated by annotators. A conflict between a plurality of annotations of the annotated versions of the documents is identified. The machine learning model includes a set of entities and relations defining relationships between entities. The identified conflict is resolved by at least one of identifying the correct annotation between the conflicting options, splitting the annotated text into two separate entities or relations, generating a new entity at the same or a less specific hierarchical level as the entities or relation in conflict, and/or changing an annotation of the annotated version of the document.

Abstract: Concepts for managing a supervised machine learning model of a set of documents are presented. A system obtains annotated versions of the documents, the documents being annotated by annotators. A conflict between a plurality of annotations of the annotated versions of the documents is identified. The machine learning model includes a set of entities and relations defining relationships between entities. The identified conflict is resolved by at least one of identifying the correct annotation between the conflicting options, splitting the annotated text into two separate entities or relations, generating a new entity at the same or a less specific hierarchical level as the entities or relation in conflict, and/or changing an annotation of the annotated version of the document.

Abstract: A worksurface assembly includes a worksurface member having an upper surface, a bottom surface, a forward edge, a rearward edge, and an aperture that opens both upwardly and forwardly from the worksurface member, and a storage member including a pair of sidewalls, a rear wall and a bottom wall that cooperate to form an interior storage area having a height to width ratio of greater than or equal to about 1:1 at at least one position along a length of the storage member, wherein the storage member has a forwardly facing opening and an upwardly facing opening, and wherein the storage member is readily detachably secured to the worksurface member such that the interior storage of the storage member is accessible through the aperture of the worksurface member and such that access to the interior space is uninterrupted between the forwardly facing opening and the upwardly facing opening of the storage member.

Abstract: A worksurface assembly includes a worksurface member having an upper surface, a bottom surface, a forward edge, a rearward edge, and an aperture that opens both upwardly and forwardly from the worksurface member, and a storage member including a pair of sidewalls, a rear wall and a bottom wall that cooperate to form an interior storage area having a height to width ratio of greater than or equal to about 1:1 at at least one position along a length of the storage member, wherein the storage member has a forwardly facing opening and an upwardly facing opening, and wherein the storage member is readily detachably secured to the worksurface member such that the interior storage of the storage member is accessible through the aperture of the worksurface member and such that access to the interior space is uninterrupted between the forwardly facing opening and the upwardly facing opening of the storage member.

Abstract: An apparatus for processing wafers one at a time. The apparatus has a vacuum chamber into which wafers are loaded through a pair of loadlocks which are spaced one above the other. A robot within the vacuum chamber has a pair of gripper arms which are moveable along and rotatable about a vertical axis so as to be moveable between the loadlocks and a wafer processing position. Each of the loadlocks has a vertically moveable portion which is moveable away from the remainder of the loadlock to provide access in a horizontal plane for one of the gripper arms. Signals from encoders and optical sensors are used to determine that a handoff position has been reached.

Abstract: The correct handover position between the gripper and the e-chuck is located using a light source and a 2-D photosensor. As the e-chuck is in the loading position it can be driven forwards or backwards in the beam direction by rotating the main whisper scan rotor. The line drawn across the 2-D array by a spot of light from the light source passing through a hole in a flag attached to the e-chuck is recorded. Similarly, the line drawn by a spot of light from the same source passing through a hole in the flag attached to the gripper is also recorded. The point of intersection is the ideal transfer point. For transfer the e-chuck is then driven to this point which can be checked from the 2-D sensor. The gripper is then also driven to the same point and alignment can be checked using the light source and sensor.