Abstract: A reaction pathfinder system can leverage historical chemical reaction data and determine a synthesis route in a reaction network. The reaction pathfinder system can account for various performance criteria of chemical reactions such as a highest yield for a molecule or a minimal number of reaction steps. A reaction pathfinder system receives a user request for a synthesis route including one of a user-specified molecule or a user-specified reaction. The reaction pathfinder system may then query a reaction network that has various synthesis routes and represents reactions of reactants to produce respective molecules. The reaction network may be composed of molecule nodes and reaction nodes. The reaction pathfinder system determines, using the reaction network, the synthesis route from the synthesis routes to fulfill the user's request.

Abstract: As a data science project goes into the production stage, model maintenance to maintain model quality and predictive accuracy becomes a concern. Manual model maintenance by data scientists can become a time- and labor-intensive process, especially for large scale data science projects. An early warning system addresses this by performing systematic statistical and algorithmic checks for prediction accuracy, stability, and model assumption validity. A diagnostic report is generated that helps data scientists to assess the health of the model and identify sources of error as needed. Well-performing models can be automatically deployed without further human intervention while poor performing models trigger a warning or alert to the data scientists for further investigation and may be removed from production until the performance issues are addressed.

Abstract: As a data science project goes into the production stage, model maintenance to maintain model quality and predictive accuracy becomes a concern. Manual model maintenance by data scientists can become a time- and labor-intensive process, especially for large scale data science projects. An early warning system addresses this by performing systematic statistical and algorithmic checks for prediction accuracy, stability, and model assumption validity. A diagnostic report is generated that helps data scientists to assess the health of the model and identify sources of error as needed. Well-performing models can be automatically deployed without further human intervention while poor performing models trigger a warning or alert to the data scientists for further investigation and may be removed from production until the performance issues are addressed.

Abstract: A turnaround management system receives a set of tasks. The turnaround management system generates a directed acyclic graph based on the received set of tasks. The turnaround management system determines longest paths through the graph and generates an optimal schedule for the set of tasks based on the determined longest paths. The turnaround management system may additionally analyze the optimal schedule for risk assessment or to predict delay.

Abstract: The registration board assembly for pre-press printing proofs and printing plates includes a substantially planar layer or registration board, a backing layer adjacent and affixed to the planar layer, and a cavity formed between the planar layer and the backing layer. A register pin extends through an aperture in the planar layer. An elastomeric member such as a rubber diaphragm is disposed within the cavity and biases a barrel portion of the register pin through the planar layer aperture. The elastomeric member is mounted so that it is removable and replaceable. One way of mounting the elastomeric member is to provide a hole in the backing layer through which the elastomeric member is pulled to remove it. A new elastomeric member is then pushed through the backing layer hole. In a second embodiment, a threaded plug in the backing layer holds the elastomeric member in place. The threaded plug is removed to replace the elastomeric member.