We thank all reviewers for their valuable comments. The reviewers are generally satisfied with our writing and experiments. Other concerns are minor - we carefully respond below and will revise the paper accordingly. Can one-bit supervision reduce annotation costs? According to the authors of ILSVRC2012 [Russakovsky et al., IJCV'15], the average time for a full-bit annotation is A1: Please refer to the common question.

What if political decisions were made not by elected politicians but by a randomly selected panel of citizens?

We thank the reviewers for their insightful comments. We have done experiments showing that the Sortition Foundation's greedy algorithm gives Thanks for suggesting Banaszczyk's result: an algorithmic version is in [2,Thm 5.3]. Additionally, in Appendix D.4, we provide several pieces of

Figure 3: Comparison of the proposed Algorithm 1 (i.e., LUB-CDM) and the straightforward strategy. 's expected payoff, where the improvement is at the cost of P In this example, we compare the proposed Algorithm 1 with the patient strategy, where the latter method pulls arms according to the latent utility at the beginning stage but has more strategic behaviors as the matching proceeds. Adachi's model involves a stage discount Figure 4: Performance of the proposed Algorithm 1 (i.e., LUB-CDM) and the patient strategy. 's reservation utility under the LUB-CDM given by Note that LUB-CDM has less strategic behaviors as the matching proceeds. On the other hand, the patient strategy has more strategic behaviors as the matching proceeds.

Citizens' assemblies are an increasingly influential form of deliberative democracy, where randomly selected people discuss policy questions. The legitimacy of these assemblies hinges on their representation of the broader population, but participant dropout often leads to an unbalanced composition. In practice, dropouts are replaced by preselected alternates, but existing methods do not address how to choose these alternates. To address this gap, we introduce an optimization framework for alternate selection. Our algorithmic approach, which leverages learning-theoretic machinery, estimates dropout probabilities using historical data and selects alternates to minimize expected misrepresentation. Our theoretical bounds provide guarantees on sample complexity (with implications for computational efficiency) and on loss due to dropout probability mis-estimation. Empirical evaluation using real-world data demonstrates that, compared to the status quo, our method significantly improves representation while requiring fewer alternates.

--Model-driven engineering problems often require complex model transformations (MTs), i.e., MTs that are chained in extensive sequences. Pertinent examples of such problems include model synchronization, automated model repair, and design space exploration. Manually developing complex MTs is an error-prone and often infeasible process. Reinforcement learning (RL) is an apt way to alleviate these issues. In RL, an autonomous agent explores the state space through trial and error to identify beneficial sequences of actions, such as MTs. In these situations, human guidance can be of high utility. In this paper, we present an approach and technical framework for developing complex MT sequences through RL, guided by potentially uncertain human advice. Our framework allows user-defined MTs to be mapped onto RL primitives, and executes them as RL programs to find optimal MT sequences. Our evaluation shows that human guidance, even if uncertain, substantially improves RL performance, and results in more efficient development of complex MTs. Through a trade-off between the certainty and timeliness of human advice, our method takes a step towards RL-driven human-in-the-loop engineering methods. Modeling activities are often more complex than an atomic model transformation (MT) and rely on sequences of MTs . Pertinent examples can be found in model synchronization [1], model refactoring [2], and rule-based design-space exploration [3]. Typically, there might be more than one MT sequence that can successfully transform the source model into the target state, and choosing the most appropriate (cost-effective, efficient, safe) one manually is not tractable. This raises the need for automated methods for developing complex MTs, in which MTs are chained in sequences.

Combinatorial optimization (CO) problems are traditionally addressed using Operations Research (OR) methods, including metaheuristics. In this study, we introduce a demand selection problem for the V ehicle Routing Problem (VRP) with an emission quota, referred to as QVRP. The objective is to minimize the number of omitted deliveries while respecting the pollution quota. We focus on the demand selection part, called Maximum Feasible V ehicle Assignment (MFV A), while the construction of a routing for the VRP instance is solved using classical OR methods. We propose several methods for selecting the packages to omit, both from machine learning (ML) and OR. Our results show that, in this static problem setting, classical OR-based methods consistently outperform ML-based approaches.