Search

The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions. One approach, unfolding, statistically adjusts the experimental data for detector effects. Recently, generative machine learning models have shown promise for performing unbinned unfolding in a high number of dimensions. However, all current generative approaches are limited to unfolding a fixed set of observables, making them unable to perform full-event unfolding in the variable dimensional environment of collider data. A novel modification to the variational latent diffusion model (VLD) approach to generative unfolding is presented, which allows for unfolding of high- and variable-dimensional feature spaces. The performance of this method is evaluated in the context of semi-leptonic top quark pair production at the Large Hadron Collider., Comment: Submission to SciPost

Recent innovations from machine learning allow for data unfolding, without binning and including correlations across many dimensions. We describe a set of known, upgraded, and new methods for ML-based unfolding. The performance of these approaches are evaluated on the same two datasets. We find that all techniques are capable of accurately reproducing the particle-level spectra across complex observables. Given that these approaches are conceptually diverse, they offer an exciting toolkit for a new class of measurements that can probe the Standard Model with an unprecedented level of detail and may enable sensitivity to new phenomena.

This Letter reports a search for charge-parity (CP) symmetry violating non-standard interactions (NSI) of neutrinos with matter using the NOvA Experiment, and examines their effects on the determination of the standard oscillation parameters. Data from $\nu_{\mu}(\bar{\nu}_{\mu})\rightarrow\nu_{\mu}(\bar{\nu}_{\mu})$ and $\nu_{\mu}(\bar{\nu}_{\mu})\rightarrow\nu_{e}(\bar{\nu}_{e})$ oscillation channels are used to measure the effect of the NSI parameters $\varepsilon_{e\mu}$ and $\varepsilon_{e\tau}$. With 90% C.L. the magnitudes of the NSI couplings are constrained to be $|\varepsilon_{e\mu}| \, \lesssim 0.3$ and $|\varepsilon_{e\tau}| \, \lesssim 0.4$. A degeneracy at $|\varepsilon_{e\tau}| \, \approx 1.8$ is reported, and we observe that the presence of NSI limits sensitivity to the standard CP phase $\delta_{\tiny\text{CP}}$.

The industrial multi-generator Wave Energy Converters (WEC) must handle multiple simultaneous waves coming from different directions called spread waves. These complex devices in challenging circumstances need controllers with multiple objectives of energy capture efficiency, reduction of structural stress to limit maintenance, and proactive protection against high waves. The Multi-Agent Reinforcement Learning (MARL) controller trained with the Proximal Policy Optimization (PPO) algorithm can handle these complexities. In this paper, we explore different function approximations for the policy and critic networks in modeling the sequential nature of the system dynamics and find that they are key to better performance. We investigated the performance of a fully connected neural network (FCN), LSTM, and Transformer model variants with varying depths and gated residual connections. Our results show that the transformer model of moderate depth with gated residual connections around the multi-head attention, multi-layer perceptron, and the transformer block (STrXL) proposed in this paper is optimal and boosts energy efficiency by an average of 22.1% for these complex spread waves over the existing spring damper (SD) controller. Furthermore, unlike the default SD controller, the transformer controller almost eliminated the mechanical stress from the rotational yaw motion for angled waves. Demo: https://tinyurl.com/yueda3jh, Comment: IJCAI 2023, Proceedings of the Thirty-Second International Joint Conference on Artificial IntelligenceAugust 2023

Recent innovations from machine learning allow for data unfolding, without binning and including correlations across many dimensions. We describe a set of known, upgraded, and new methods for ML-based unfolding. The performance of these approaches are evaluated on the same two datasets. We find that all techniques are capable of accurately reproducing the particle-level spectra across complex observables. Given that these approaches are conceptually diverse, they offer an exciting toolkit for a new class of measurements that can probe the Standard Model with an unprecedented level of detail and may enable sensitivity to new phenomena.

The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions. One approach, unfolding, statistically adjusts the experimental data for detector effects. Recently, generative machine learning models have shown promise for performing unbinned unfolding in a high number of dimensions. However, all current generative approaches are limited to unfolding a fixed set of observables, making them unable to perform full-event unfolding in the variable dimensional environment of collider data. A novel modification to the variational latent diffusion model (VLD) approach to generative unfolding is presented, which allows for unfolding of high- and variable-dimensional feature spaces. The performance of this method is evaluated in the context of semi-leptonic top quark pair production at the Large Hadron Collider., Comment: Submission to SciPost

Background: Chemotherapy crosses the placenta, however, it remains unclear to what extent it affects fetal growth. The current literature suggests up to 21% of the offspring of women receiving chemotherapy are small for gestational age (SGA, birth weight <10th percentile). Limiting research to birth weights only might misjudge fetal growth restriction (FGR) in this high-risk population with multiple risk factors for impaired fetal growth. Moreover, the role of the duration of chemotherapy and gestational age at initiation of chemotherapy in fetal growth is yet poorly understood. Objective: This retrospective cohort study evaluates fetal growth and neonatal birthweights in pregnant women receiving chemotherapy. Study design: All pregnant patients, registered by the International Network of Cancer, Infertility and Pregnancy (INCIP), treated with chemotherapy with at least two ultrasounds reporting on fetal growth, were eligible for this study. Duration and gestational age at initiation of chemotherapy were our major determinants, followed by cancer type and stage, maternal characteristics (parity, BMI, ethnicity hypertension, and diabetes) and individual cytotoxic agents (anthracycline, taxanes, and platinum). Fetal growth outcomes were described using the following mutually exclusive groups (1) FGR, based on a Delphi consensus (2016); (2) “low risk SGA” (birth weight below the 10th percentile), but an estimated growth above the 10th percentile; (3) “fetal growth disturbance”, which did not meet all FGR criteria; (4) “non-FGR”. Obstetric and oncological characteristics were compared between the growth impaired groups and non-FGR group. We calculated estimated fetal weight (EFW) according to Hadlock’s formula (1991) and birth weight percentile according to Nicolaides (2018). We used univariable and multivariable regression, and linear mixed effect models to investigate the effect of duration and gestational age at initiation of chemotherapy on birth weight, and feta

01 januari 2023, Item does not contain fulltext, BACKGROUND: Peripartum management of women using low-molecular-weight heparin (LMWH) varies widely. Minimum time intervals are required between LMWH injection and neuraxial procedure, and they differ by dose. OBJECTIVES: The objective of this study was to describe the onset of labor and use of analgesia in women using LMWH and to compare practices between intermediate-dose and low-dose LMWH. METHODS: In the Highlow study (NCT01828697), 1110 women were randomized to intermediate-dose or low-dose LMWH and were instructed to discontinue LMWH when labor commenced unplanned or 24 hours prior to planned delivery. The required time interval since last injection to receive a neuraxial procedure was ≥24 hours for intermediate-dose LMWH or ≥12 hours for low-dose LMWH. RESULTS: In total, 1018 women had an ongoing pregnancy for ≥24 weeks. Onset of labor was spontaneous in 198 of 509 (39%) women on intermediate-dose LMWH and in 246 of 509 (49%) on low-dose LMWH. With unplanned onset, a neuraxial procedure was performed in 37% on intermediate-dose and in 48% on low-dose LMWH (risk difference -11%, 95% CI -20% to -2%). Based on time interval, 61% on intermediate-dose and 82% on low-dose LMWH were eligible for a neuraxial procedure. With planned onset, 68% on intermediate-dose and 66% on low-dose LMWH received a neuraxial procedure, whereas 81% and 93%, respectively, were eligible for a neuraxial procedure (risk difference -13%, 95% CI -18% to -8%). CONCLUSION: With spontaneous onset of labor, neuraxial procedures were performed less often in women using intermediate-dose LMWH. Irrespective of onset, fewer women on intermediate-dose LMWH than those on low-dose LMWH were eligible for neuraxial procedures based on required time intervals since the last LMWH injection.

01 januari 2023, Item does not contain fulltext, BACKGROUND: Peripartum management of women using low-molecular-weight heparin (LMWH) varies widely. Minimum time intervals are required between LMWH injection and neuraxial procedure, and they differ by dose. OBJECTIVES: The objective of this study was to describe the onset of labor and use of analgesia in women using LMWH and to compare practices between intermediate-dose and low-dose LMWH. METHODS: In the Highlow study (NCT01828697), 1110 women were randomized to intermediate-dose or low-dose LMWH and were instructed to discontinue LMWH when labor commenced unplanned or 24 hours prior to planned delivery. The required time interval since last injection to receive a neuraxial procedure was ≥24 hours for intermediate-dose LMWH or ≥12 hours for low-dose LMWH. RESULTS: In total, 1018 women had an ongoing pregnancy for ≥24 weeks. Onset of labor was spontaneous in 198 of 509 (39%) women on intermediate-dose LMWH and in 246 of 509 (49%) on low-dose LMWH. With unplanned onset, a neuraxial procedure was performed in 37% on intermediate-dose and in 48% on low-dose LMWH (risk difference -11%, 95% CI -20% to -2%). Based on time interval, 61% on intermediate-dose and 82% on low-dose LMWH were eligible for a neuraxial procedure. With planned onset, 68% on intermediate-dose and 66% on low-dose LMWH received a neuraxial procedure, whereas 81% and 93%, respectively, were eligible for a neuraxial procedure (risk difference -13%, 95% CI -18% to -8%). CONCLUSION: With spontaneous onset of labor, neuraxial procedures were performed less often in women using intermediate-dose LMWH. Irrespective of onset, fewer women on intermediate-dose LMWH than those on low-dose LMWH were eligible for neuraxial procedures based on required time intervals since the last LMWH injection.

High-energy collisions at the Large Hadron Collider (LHC) provide valuable insights into open questions in particle physics. However, detector effects must be corrected before measurements can be compared to certain theoretical predictions or measurements from other detectors. Methods to solve this \textit{inverse problem} of mapping detector observations to theoretical quantities of the underlying collision are essential parts of many physics analyses at the LHC. We investigate and compare various generative deep learning methods to approximate this inverse mapping. We introduce a novel unified architecture, termed latent variation diffusion models, which combines the latent learning of cutting-edge generative art approaches with an end-to-end variational framework. We demonstrate the effectiveness of this approach for reconstructing global distributions of theoretical kinematic quantities, as well as for ensuring the adherence of the learned posterior distributions to known physics constraints. Our unified approach achieves a distribution-free distance to the truth of over 20 times less than non-latent state-of-the-art baseline and 3 times less than traditional latent diffusion models.

Reconstructing unstable heavy particles requires sophisticated techniques to sift through the large number of possible permutations for assignment of detector objects to partons. An approach based on a generalized attention mechanism, symmetry preserving attention networks (SPANet), has been previously applied to top quark pair decays at the Large Hadron Collider, which produce six hadronic jets. Here we extend the SPANet architecture to consider multiple input streams, such as leptons, as well as global event features, such as the missing transverse momentum. In addition, we provide regression and classification outputs to supplement the parton assignment. We explore the performance of the extended capability of SPANet in the context of semi-leptonic decays of top quark pairs as well as top quark pairs produced in association with a Higgs boson. We find significant improvements in the power of three representative studies: search for ttH, measurement of the top quark mass and a search for a heavy Z' decaying to top quark pairs. We present ablation studies to provide insight on what the network has learned in each case.

Reconstructing unstable heavy particles requires sophisticated techniques to sift through the large number of possible permutations for assignment of detector objects to the underlying partons. Anapproach based on a generalized attention mechanism, symmetry preserving attention networks (SPA-NET), has been previously applied to top quark pair decays at the Large Hadron Collider which produce only hadronic jets. Here we extend the SPA-NET architecture to consider multiple input object types, such as leptons, as well as global event features, such as the missing transverse momentum. Inaddition, we provide regression and classification outputs to supplement the parton assignment. We explore the performance of the extended capability of SPA-NET in the context of semi-leptonic decays of top quark pairs as well as top quark pairs produced in association with a Higgs boson. We find significant improvements in the power of three representative studies: a search for ttH, a measurement of the top quark mass, and a search for a heavy Z' decaying to top quark pairs. We present ablation studies to provide insight on what the network has learned in each case., Comment: Accepted by Nature Communications Physics, replaced with published version

The complex events observed at the NOvA long-baseline neutrino oscillation experiment contain vital information for understanding the most elusive particles in the standard model. The NOvA detectors observe interactions of neutrinos from the NuMI beam at Fermilab. Associating the particles produced in these interaction events to their source particles, a process known as reconstruction, is critical for accurately measuring key parameters of the standard model. Events may contain several particles, each producing sparse high-dimensional spatial observations, and current methods are limited to evaluating individual particles. To accurately label these numerous, high-dimensional observations, we present a novel neural network architecture that combines the spatial learning enabled by convolutions with the contextual learning enabled by attention. This joint approach, TransformerCVN, simultaneously classifies each event and reconstructs every individual particle's identity. TransformerCVN classifies events with 90\% accuracy and improves the reconstruction of individual particles by 6\% over baseline methods which lack the integrated architecture of TransformerCVN. In addition, this architecture enables us to perform several interpretability studies which provide insights into the network's predictions and show that TransformerCVN discovers several fundamental principles that stem from the standard model.

Transposons are major vehicles of horizontal gene transfer that, in addition to genes directly involved in transposition, carry cargo genes. However, characterization of these genes is hampered by the difficulty of identification of transposon boundaries.

High-energy collisions at the Large Hadron Collider (LHC) provide valuable insights into open questions in particle physics. However, detector effects must be corrected before measurements can be compared to certain theoretical predictions or measurements from other detectors. Methods to solve this \textit{inverse problem} of mapping detector observations to theoretical quantities of the underlying collision are essential parts of many physics analyses at the LHC. We investigate and compare various generative deep learning methods to approximate this inverse mapping. We introduce a novel unified architecture, termed latent variation diffusion models, which combines the latent learning of cutting-edge generative art approaches with an end-to-end variational framework. We demonstrate the effectiveness of this approach for reconstructing global distributions of theoretical kinematic quantities, as well as for ensuring the adherence of the learned posterior distributions to known physics constraints. Our unified approach achieves a distribution-free distance to the truth of over 20 times less than non-latent state-of-the-art baseline and 3 times less than traditional latent diffusion models.

Deep learning-based reaction predictors have undergone significant architectural evolution. However, their reliance on reactions from the US Patent Office results in a lack of interpretable predictions and limited generalization capability to other chemistry domains, such as radical and atmospheric chemistry. To address these challenges, we introduce a new reaction predictor system, RMechRP, that leverages contrastive learning in conjunction with mechanistic pathways, the most interpretable representation of chemical reactions. Specifically designed for radical reactions, RMechRP provides different levels of interpretation of chemical reactions. We develop and train multiple deep-learning models using RMechDB, a public database of radical reactions, to establish the first benchmark for predicting radical reactions. Our results demonstrate the effectiveness of RMechRP in providing accurate and interpretable predictions of radical reactions, and its potential for various applications in atmospheric chemistry.

Bayesian Optimization (BO), guided by Gaussian process (GP) surrogates, has proven to be an invaluable technique for efficient, high-dimensional, black-box optimization, a critical problem inherent to many applications such as industrial design and scientific computing. Recent contributions have introduced reinforcement learning (RL) to improve the optimization performance on both single function optimization and \textit{few-shot} multi-objective optimization. However, even few-shot techniques fail to exploit similarities shared between closely related objectives. In this paper, we combine recent developments in Deep Kernel Learning (DKL) and attention-based Transformer models to improve the modeling powers of GP surrogates with meta-learning. We propose a novel method for improving meta-learning BO surrogates by incorporating attention mechanisms into DKL, empowering the surrogates to adapt to contextual information gathered during the BO process. We combine this Transformer Deep Kernel with a learned acquisition function trained with continuous Soft Actor-Critic Reinforcement Learning to aid in exploration. This Reinforced Transformer Deep Kernel (RTDK-BO) approach yields state-of-the-art results in continuous high-dimensional optimization problems., Comment: 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE)

Reconstructing unstable heavy particles requires sophisticated techniques to sift through the large number of possible permutations for assignment of detector objects to the underlying partons. Anapproach based on a generalized attention mechanism, symmetry preserving attention networks (SPA-NET), has been previously applied to top quark pair decays at the Large Hadron Collider which produce only hadronic jets. Here we extend the SPA-NET architecture to consider multiple input object types, such as leptons, as well as global event features, such as the missing transverse momentum. Inaddition, we provide regression and classification outputs to supplement the parton assignment. We explore the performance of the extended capability of SPA-NET in the context of semi-leptonic decays of top quark pairs as well as top quark pairs produced in association with a Higgs boson. We find significant improvements in the power of three representative studies: a search for ttH, a measurement of the top quark mass, and a search for a heavy Z' decaying to top quark pairs. We present ablation studies to provide insight on what the network has learned in each case., Comment: Accepted by Nature Communications Physics, replaced with published version

Online retailers often use third-party demand-side-platforms (DSPs) to conduct offsite advertising and reach shoppers across the Internet on behalf of their advertisers. The process involves the retailer participating in instant auctions with real-time bidding for each ad slot of their interest. In this paper, we introduce a bid optimization system that leverages the dimensional bidding function provided by most well-known DSPs for Walmart offsite display ad campaigns. The system starts by automatically searching for the optimal segmentation of the ad requests space based on their characteristics such as geo location, time, ad format, serving website, device type, etc. Then, it assesses the quality of impressions observed from each dimension based on revenue signals driven by the campaign effect. During the campaign, the system iteratively approximates the bid landscape based on the data observed and calculates the bid adjustments for each dimension. Finally, a higher bid adjustment factor is applied to dimensions with potentially higher revenue over ad spend (ROAS), and vice versa. The initial A/B test results of the proposed optimization system has shown its effectiveness of increasing the ROAS and conversion rate while reducing the effective cost per mille for ad serving.

Chemotherapy puts a developing fetus at risk of teratogenic effects. The standard recommendation is that chemotherapy be administered after organogenesis is complete, however, the exact gestational age that chemotherapy can be administered safely and avoid causing congenital malformations remains unknown. The goal of this study was to assess the teratogenic role of prenatal chemotherapy by gestational age, to evaluate for the presence of major and minor congenital malformations during pregnancy or at birth.This was a multicenter study that evaluated all pregnant women who received chemotherapy in the International Network on Cancer, Infertility and Pregnancy (INCIP) database between 1977 and 2019.A total of 755 pregnant women treated with chemotherapy between 1977 and 2019 were included in analysis. The median age at cancer diagnosis was 33 (14-48) years. The major congenital malformation rate was 3.6% (95% confidence interval [CI], 2.4%-5.2%), and the minor congenital malformation rate was 1.9% (95% CI, 1.0%-3.1%) among offspring. Chemotherapy exposure before 12 weeks' gestational age was associated with a high rate of major congenital malformations, at 21.7%(95% CI, 7.5%-43.7%; odds ratio, 9.24 [95% CI, 3.13-27.30]). When chemotherapy was initiated after 12 weeks' gestation, the frequency of major congenital malformations decreased to 3.0% (95% CI, 1.9%-4.6%), which was comparable to the anticipated rates in the general population. Minor malformations were similar when exposure occurred before or after 12 weeks' gestation (4.3% [95% CI, 0.1%-21.9%] vs 1.8% [95% CI, 1.0-3.0]; odds ratio, 3.13 [95% CI, 0.39-25.28]). Of 29 women who received chemotherapy before 12 weeks' gestation, 17 (58.6%) were not aware of their pregnancy, and 6 (20.7%) had a miscarriage (3 women [10.3%]) or elected to terminate their pregnancy (3 women [10.3%]).Overall, this study found that chemotherapy was associated with an increased risk of major congenital malformations only when it adminis

Importance: Chemotherapy during the first trimester of pregnancy should be avoided owing to the risk of congenital malformations. However, the precise gestational age at which chemotherapy can be initiated safely remains unclear. Objective: To assess congenital malformation rates associated with gestational age at initiation of chemotherapy among pregnant women with cancer. Design, Setting, and Participants: This multicenter cohort study evaluated all pregnant women who received chemotherapy between 1977 and 2019 registered in the International Network on Cancer, Infertility and Pregnancy (INCIP) database. Data were analyzed from February 15 to June 2, 2020. Exposures: Cancer treatment with chemotherapy during pregnancy. Main Outcomes and Measures: Analysis was focused on major and minor structural malformations in offspring, defined by EUROCAT, detected during pregnancy or at birth. Results: A total of 755 women in the INCIP database who underwent cancer treatment with chemotherapy during pregnancy were included in analysis. The median (range) age at cancer diagnosis was 33 (14-48) years. Among offspring, the major congenital malformation rate was 3.6% (95% CI, 2.4%-5.2%), and the minor congenital malformation rate was 1.9% (95% CI, 1.0%-3.1%). Chemotherapy exposure prior to 12 weeks gestational age was associated with a high rate of major congenital malformations, at 21.7% (95% CI, 7.5%-43.7%; odds ratio, 9.24 [95% CI, 3.13-27.30]). When chemotherapy was initiated after gestational age 12 weeks, the frequency of major congenital malformations was 3.0% (95% CI, 1.9%-4.6%), which was similar to the expected rates in the general population. Minor malformations were comparable when exposure occurred before or after gestational age 12 weeks (4.3% [95% CI, 0.1%-21.9%] vs 1.8% [95% CI, 1.0-3.0]; odds ratio, 3.13 [95% CI, 0.39-25.28]). Of 29 women who received chemotherapy prior to 12 weeks gestation, 17 (58.6%) were not aware of pregnancy, and 6 (20.7%) experienced a mis

A significant point-like component from the small scale (or discrete) structure in the H2 interstellar gas might be present in the Fermi-LAT data, but modeling this emission relies on observations of rare gas tracers only available in limited regions of the sky. Identifying this contribution is important to discriminate gamma-ray point sources from interstellar gas, and to better characterize extended gamma-ray sources. We design and train convolutional neural networks to predict this emission where observations of these rare tracers do not exist and discuss the impact of this component on the analysis of the Fermi-LAT data. In particular, we evaluate prospects to exploit this methodology in the characterization of the Fermi-LAT Galactic center excess through accurate modeling of point-like structures in the data to help distinguish between a point-like or smooth nature for the excess. We show that deep learning may be effectively employed to model the gamma-ray emission traced by these rare H2 proxies within statistical significance in data-rich regions, supporting prospects to employ these methods in yet unobserved regions., Comment: Submitted. Companion paper to "Improved modeling of the discrete component of the galactic interstellar gamma-ray emission and implications for the Fermi--LAT galactic center excess"

The aim of this work is to improve models for the gamma-ray discrete or small-scale structure related to H2 interstellar gas. Reliably identifying this contribution is important to disentangle gamma-ray point sources from interstellar gas, and to better characterize extended gamma-ray signals. Notably, the Fermi-LAT Galactic center (GC) excess, whose origin remains unclear, might be smooth or point-like. If the data contain a point-like contribution that is not adequately modeled, a smooth GC excess might be erroneously deemed to be point-like. We improve models for the H2-related gamma-ray discrete emission for a $50^\circ \times 1^\circ$ region along the Galactic plane via H2 proxies better suited to trace these features. We find that these are likely to contribute significantly to the gamma-ray Fermi-LAT data in this region, and the brightest ones are likely associated with detected Fermi-LAT sources, a compelling validation of this methodology. We discuss prospects to extend this methodology to other regions of the sky and implications for the characterization of the GC excess., Comment: Submitted

Item does not contain fulltext, BACKGROUND: Pregnancy-related venous thromboembolism is a leading cause of maternal morbidity and mortality, and thromboprophylaxis is indicated in pregnant and post-partum women with a history of venous thromboembolism. The optimal dose of low-molecular-weight heparin to prevent recurrent venous thromboembolism in pregnancy and the post-partum period is uncertain. METHODS: In this open-label, randomised, controlled trial (Highlow), pregnant women with a history of venous thromboembolism were recruited from 70 hospitals in nine countries (the Netherlands, France, Ireland, Belgium, Norway, Denmark, Canada, the USA, and Russia). Women were eligible if they were aged 18 years or older with a history of objectively confirmed venous thromboembolism, and with a gestational age of 14 weeks or less. Eligible women were randomly assigned (1:1), before 14 weeks of gestational age, using a web-based system and permuted block randomisation (block size of six), stratified by centre, to either weight-adjusted intermediate-dose or fixed low-dose low-molecular-weight heparin subcutaneously once daily until 6 weeks post partum. The primary efficacy outcome was objectively confirmed venous thromboembolism (ie, deep-vein thrombosis, pulmonary embolism, or unusual site venous thrombosis), as determined by an independent central adjudication committee, in the intention-to-treat (ITT) population (ie, all women randomly assigned to treatment). The primary safety outcome was major bleeding which included antepartum, early post-partum (within 24 h after delivery), and late post-partum major bleeding (24 h or longer after delivery until 6 weeks post partum), assessed in all women who received at least one dose of assigned treatment and had a known end of treatment date. This study is registered with ClinicalTrials.gov, NCT01828697, and is now complete. FINDINGS: Between April 24, 2013, and Oct 31, 2020, 1339 pregnant women were screened for eligibility, of whom 1110 were randomly assigned to

Background: Pregnancy-related venous thromboembolism is a leading cause of maternal morbidity and mortality, and thromboprophylaxis is indicated in pregnant and post-partum women with a history of venous thromboembolism. The optimal dose of low-molecular-weight heparin to prevent recurrent venous thromboembolism in pregnancy and the post-partum period is uncertain. Methods: In this open-label, randomised, controlled trial (Highlow), pregnant women with a history of venous thromboembolism were recruited from 70 hospitals in nine countries (the Netherlands, France, Ireland, Belgium, Norway, Denmark, Canada, the USA, and Russia). Women were eligible if they were aged 18 years or older with a history of objectively confirmed venous thromboembolism, and with a gestational age of 14 weeks or less. Eligible women were randomly assigned (1:1), before 14 weeks of gestational age, using a web-based system and permuted block randomisation (block size of six), stratified by centre, to either weight-adjusted intermediate-dose or fixed low-dose low-molecular-weight heparin subcutaneously once daily until 6 weeks post partum. The primary efficacy outcome was objectively confirmed venous thromboembolism (ie, deep-vein thrombosis, pulmonary embolism, or unusual site venous thrombosis), as determined by an independent central adjudication committee, in the intention-to-treat (ITT) population (ie, all women randomly assigned to treatment). The primary safety outcome was major bleeding which included antepartum, early post-partum (within 24 h after delivery), and late post-partum major bleeding (24 h or longer after delivery until 6 weeks post partum), assessed in all women who received at least one dose of assigned treatment and had a known end of treatment date. This study is registered with ClinicalTrials.gov, NCT01828697, and is now complete. Findings: Between April 24, 2013, and Oct 31, 2020, 1339 pregnant women were screened for eligibility, of whom 1110 were randomly assigned

Consensus clustering aggregates partitions in order to find a better fit by reconciling clustering results from different sources/executions. In practice, there exist noise and outliers in clustering task, which, however, may significantly degrade the performance. To address this issue, we propose a novel algorithm -- robust consensus clustering that can find common ground truth among experts' opinions, which tends to be minimally affected by the bias caused by the outliers. In particular, we formalize the robust consensus clustering problem as a constraint optimization problem, and then derive an effective algorithm upon alternating direction method of multipliers (ADMM) with rigorous convergence guarantee. Our method outperforms the baselines on benchmarks. We apply the proposed method to the real-world advertising campaign segmentation and forecasting tasks using the proposed consensus clustering results based on the similarity computed via Kolmogorov-Smirnov Statistics. The accurate clustering result is helpful for building the advertiser profiles so as to perform the forecasting., Comment: 8 pages

In cost-per-click (CPC) or cost-per-impression (CPM) advertising campaigns, advertisers always run the risk of spending the budget without getting enough conversions. Moreover, the bidding on advertising inventory has few connections with propensity one that can reach to target cost-per-acquisition (tCPA) goals. To address this problem, this paper presents a bid optimization scenario to achieve the desired tCPA goals for advertisers. In particular, we build the optimization engine to make a decision by solving the rigorously formalized constrained optimization problem, which leverages the bid landscape model learned from rich historical auction data using non-parametric learning. The proposed model can naturally recommend the bid that meets the advertisers' expectations by making inference over advertisers' historical auction behaviors, which essentially deals with the data challenges commonly faced by bid landscape modeling: incomplete logs in auctions, and uncertainty due to the variation and fluctuations in advertising bidding behaviors. The bid optimization model outperforms the baseline methods on real-world campaigns, and has been applied into a wide range of scenarios for performance improvement and revenue liftup.

In computational advertising, a challenging problem is how to recommend the bid for advertisers to achieve the best return on investment (ROI) given budget constraint. This paper presents a bid recommendation scenario that discovers the concavity changes in click prediction curves. The recommended bid is derived based on the turning point from significant increase (i.e. concave downward) to slow increase (convex upward). Parametric learning based method is applied by solving the corresponding constraint optimization problem. Empirical studies on real-world advertising scenarios clearly demonstrate the performance gains for business metrics (including revenue increase, click increase and advertiser ROI increase)., Comment: 10 pages

Recent Wave Energy Converters (WEC) are equipped with multiple legs and generators to maximize energy generation. Traditional controllers have shown limitations to capture complex wave patterns and the controllers must efficiently maximize the energy capture. This paper introduces a Multi-Agent Reinforcement Learning controller (MARL), which outperforms the traditionally used spring damper controller. Our initial studies show that the complex nature of problems makes it hard for training to converge. Hence, we propose a novel skip training approach which enables the MARL training to overcome performance saturation and converge to more optimum controllers compared to default MARL training, boosting power generation. We also present another novel hybrid training initialization (STHTI) approach, where the individual agents of the MARL controllers can be initially trained against the baseline Spring Damper (SD) controller individually and then be trained one agent at a time or all together in future iterations to accelerate convergence. We achieved double-digit gains in energy efficiency over the baseline Spring Damper controller with the proposed MARL controllers using the Asynchronous Advantage Actor-Critic (A3C) algorithm., Comment: 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) August 20-24, 2022

It is fundamental for science and technology to be able to predict chemical reactions and their properties. To achieve such skills, it is important to develop good representations of chemical reactions, or good deep learning architectures that can learn such representations automatically from the data. There is currently no universal and widely adopted method for robustly representing chemical reactions. Most existing methods suffer from one or more drawbacks, such as: (1) lacking universality; (2) lacking robustness; (3) lacking interpretability; or (4) requiring excessive manual pre-processing. Here we exploit graph-based representations of molecular structures to develop and test a hypergraph attention neural network approach to solve at once the reaction representation and property-prediction problems, alleviating the aforementioned drawbacks. We evaluate this hypergraph representation in three experiments using three independent data sets of chemical reactions. In all experiments, the hypergraph-based approach matches or outperforms other representations and their corresponding models of chemical reactions while yielding interpretable multi-level representations.

A significant point-like component from the small scale (or discrete) structure in the H2 interstellar gas might be present in the Fermi-LAT data, but modeling this emission relies on observations of rare gas tracers only available in limited regions of the sky. Identifying this contribution is important to discriminate gamma-ray point sources from interstellar gas, and to better characterize extended gamma-ray sources. We design and train convolutional neural networks to predict this emission where observations of these rare tracers do not exist and discuss the impact of this component on the analysis of the Fermi-LAT data. In particular, we evaluate prospects to exploit this methodology in the characterization of the Fermi-LAT Galactic center excess through accurate modeling of point-like structures in the data to help distinguish between a point-like or smooth nature for the excess. We show that deep learning may be effectively employed to model the gamma-ray emission traced by these rare H2 proxies within statistical significance in data-rich regions, supporting prospects to employ these methods in yet unobserved regions., Comment: Submitted. Companion paper to "Improved modeling of the discrete component of the galactic interstellar gamma-ray emission and implications for the Fermi--LAT galactic center excess"

The aim of this work is to improve models for the gamma-ray discrete or small-scale structure related to H2 interstellar gas. Reliably identifying this contribution is important to disentangle gamma-ray point sources from interstellar gas, and to better characterize extended gamma-ray signals. Notably, the Fermi-LAT Galactic center (GC) excess, whose origin remains unclear, might be smooth or point-like. If the data contain a point-like contribution that is not adequately modeled, a smooth GC excess might be erroneously deemed to be point-like. We improve models for the H2-related gamma-ray discrete emission for a $50^\circ \times 1^\circ$ region along the Galactic plane via H2 proxies better suited to trace these features. We find that these are likely to contribute significantly to the gamma-ray Fermi-LAT data in this region, and the brightest ones are likely associated with detected Fermi-LAT sources, a compelling validation of this methodology. We discuss prospects to extend this methodology to other regions of the sky and implications for the characterization of the GC excess., Comment: Submitted

A significant point-like component from the small scale (or discrete) structure in the H2 interstellar gas might be present in the Fermi-LAT data, but modeling this emission relies on observations of rare gas tracers only available in limited regions of the sky. Identifying this contribution is important to discriminate gamma-ray point sources from interstellar gas, and to better characterize extended gamma-ray sources. We design and train convolutional neural networks to predict this emission where observations of these rare tracers do not exist and discuss the impact of this component on the analysis of the Fermi-LAT data. In particular, we evaluate prospects to exploit this methodology in the characterization of the Fermi-LAT Galactic center excess through accurate modeling of point-like structures in the data to help distinguish between a point-like or smooth nature for the excess. We show that deep learning may be effectively employed to model the gamma-ray emission traced by these rare H2 proxies within statistical significance in data-rich regions, supporting prospects to employ these methods in yet unobserved regions., Comment: Submitted. Companion paper to "Improved modeling of the discrete component of the galactic interstellar gamma-ray emission and implications for the Fermi--LAT galactic center excess"

In this paper, the authors present the results of software verification for solving magnetohydrodynamic problem in duct exposed to constant magnetic fields. The proposed approach uses the following open source software: OpenFOAM for solving problems of continuum mechanics using the finite volume method, Elmer for solving magnetic field distribution based on the finite element method, and EOF-library for data exchange between these two programs. The verification results were demonstrated by fluid flow in a square duct exposed to constant uniform spanwise magnetic field. The research was carried out with a laminar fluid flow, which makes it similar to the Hartmann's problem. The existing experience of calculating such problems, their verification and application were discussed. The paper provides a brief mathematical description of the proposed solution and basic procedures for implementing the code proposed by the authors. At the first stage of verification, the comparison of fluid velocity distribution results at Hartmann’s numbers equal to 1, 10, 20 and 50 was demonstrated. These results were obtained by means of proposed software, an analytical solution, and a test problem provided by OpenFOAM developers for two-dimensional case. At the second stage of software verification, sufficient convergence of the results was shown for fluid velocity distribution in the three-dimensional case of the Hartmann’s problem compared with the OpenFOAM test problem data and the results obtained by Comsol Multiphisics and ANSYS. As a result, distributions of the fluid flow velocity between Hartmann’s walls were obtained for various study cases: a two-dimensional problem, a three-dimensional problem with electrically insulated walls, and a three-dimensional problem with walls having infinite electrical conductivity. The last stage of the study corresponds to assessing of software performance in comparison with the built-in OpenFOAM solver and commercial software Comsol Multiphysics a

В настоящей выпускной квалификационной работе «Исследование процесса удаления серы из полупродукта на установке десульфурации в условиях АО «ЕВРАЗ НТМК» рассмотрено распределение серы по переделам металлургического производства АО «ЕВРАЗ НТМК» а также проведена работа по повышению стойкости фурмы установки десульфурации чугуна., In this final qualifying work " Study of the process of removing sulfur from a semi-product at a desulfurization plant in the conditions of JSC "EVRAZ NTMK", the distribution of sulfur in the metallurgical production processes of JSC" EVRAZ NTMK " is considered, and work is also carried out to improve the durability of the tuyere of the pig iron desulfurization plant.

This work presents the results from a study of the structure and transport properties of Ca-doped La2NiO4+δ. La2−xCaxNiO4+δ (x = 0–0.4) materials that were synthesized via combustion of organic-nitrate precursors and characterized by X-ray diffraction (XRD), in situ XRD using synchrotron radiation, thermogravimetric analysis (TGA) and isotope exchange of oxygen with C18O2. The structure was defined as orthorhombic (Fmmm) for x = 0 and tetragonal (I4/mmm) for x = 0.1–0.4. Changes that occurred in the unit cell parameters and volume as the temperature changed during heating were shown to be caused by the excess oxygen loss. Typical for Ruddlesden–Popper phases, oxygen mobility and surface reactivity decreased as the Ca content was increased due to a reduction in the over-stoichiometric oxygen content with the exception of x = 0.1. This composition demonstrated its superior oxygen transport properties compared to La2NiO4+δ due to the enhanced oxygen mobility caused by structural features. Electrochemical data obtained showed relatively low polarization resistance for the electrodes with a low Ca content, which correlates well with oxygen transport properties. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.

Contains fulltext : 232066.pdf (Publisher’s version ) (Closed access), This cohort study of the International Network on Cancer, Infertility and Pregnancy (INCIP) reports the maternal and neonatal outcomes of 80 pregnant patients diagnosed with non-Hodgkin lymphoma (NHL) between 1986 and 2019, focussing on 57 (71%) patients with diffuse large B-cell lymphoma (DLBCL). Of all 80 patients, 54 (68%) pregnant patients received chemotherapy; mostly (89%) CHOP-like (cyclophosphamide, doxorubicin, vincristine, and prednisone) regimens. Four early pregnancies were terminated. Among 76 ongoing pregnancies, there was one stillbirth (1·3%). Overall, there was a high incidence of small for gestational age neonates (39%), preterm delivery (52%), obstetric (41%) and neonatal complications (12·5%), and this could not exclusively be explained by the receipt of antenatal chemotherapy. Half of preterm deliveries (46%) were planned in order to tailor oncological treatment. The 3-year progression-free and overall survival for patients with DLBCL treated with rituximab-CHOP was 83·4% and 95·7% for limited stage (n = 29) and 60·6% and 73·3% for advanced stage (n = 15). Of 36 pregnant patients who received rituximab, five (13%) cases with neonatal complications and three (8%) with maternal infections were reported. In conclusion, standard treatment for DLBCL can be offered to pregnant patients in obstetric centres that cater for high-risk patients.

Contains fulltext : 234977.pdf (Publisher’s version ) (Open Access)

Importance: Chemotherapy during the first trimester of pregnancy should be avoided owing to the risk of congenital malformations. However, the precise gestational age at which chemotherapy can be initiated safely remains unclear. Objective: To assess congenital malformation rates associated with gestational age at initiation of chemotherapy among pregnant women with cancer. Design, Setting, and Participants: This multicenter cohort study evaluated all pregnant women who received chemotherapy between 1977 and 2019 registered in the International Network on Cancer, Infertility and Pregnancy (INCIP) database. Data were analyzed from February 15 to June 2, 2020. Exposures: Cancer treatment with chemotherapy during pregnancy. Main Outcomes and Measures: Analysis was focused on major and minor structural malformations in offspring, defined by EUROCAT, detected during pregnancy or at birth. Results: A total of 755 women in the INCIP database who underwent cancer treatment with chemotherapy during pregnancy were included in analysis. The median (range) age at cancer diagnosis was 33 (14-48) years. Among offspring, the major congenital malformation rate was 3.6% (95% CI, 2.4%-5.2%), and the minor congenital malformation rate was 1.9% (95% CI, 1.0%-3.1%). Chemotherapy exposure prior to 12 weeks gestational age was associated with a high rate of major congenital malformations, at 21.7% (95% CI, 7.5%-43.7%; odds ratio, 9.24 [95% CI, 3.13-27.30]). When chemotherapy was initiated after gestational age 12 weeks, the frequency of major congenital malformations was 3.0% (95% CI, 1.9%-4.6%), which was similar to the expected rates in the general population. Minor malformations were comparable when exposure occurred before or after gestational age 12 weeks (4.3% [95% CI, 0.1%-21.9%] vs 1.8% [95% CI, 1.0-3.0]; odds ratio, 3.13 [95% CI, 0.39-25.28]). Of 29 women who received chemotherapy prior to 12 weeks gestation, 17 (58.6%) were not aware of pregnancy, and 6 (20.7%) experienced a

Chemotherapy during the first trimester of pregnancy should be avoided owing to the risk of congenital malformations. However, the precise gestational age at which chemotherapy can be initiated safely remains unclear. To assess congenital malformation rates associated with gestational age at initiation of chemotherapy among pregnant women with cancer. This multicenter cohort study evaluated all pregnant women who received chemotherapy between 1977 and 2019 registered in the International Network on Cancer, Infertility and Pregnancy (INCIP) database. Data were analyzed from February 15 to June 2, 2020. Cancer treatment with chemotherapy during pregnancy. Analysis was focused on major and minor structural malformations in offspring, defined by EUROCAT, detected during pregnancy or at birth. A total of 755 women in the INCIP database who underwent cancer treatment with chemotherapy during pregnancy were included in analysis. The median (range) age at cancer diagnosis was 33 (14-48) years. Among offspring, the major congenital malformation rate was 3.6% (95% CI, 2.4%-5.2%), and the minor congenital malformation rate was 1.9% (95% CI, 1.0%-3.1%). Chemotherapy exposure prior to 12 weeks gestational age was associated with a high rate of major congenital malformations, at 21.7% (95% CI, 7.5%-43.7%; odds ratio, 9.24 [95% CI, 3.13-27.30]). When chemotherapy was initiated after gestational age 12 weeks, the frequency of major congenital malformations was 3.0% (95% CI, 1.9%-4.6%), which was similar to the expected rates in the general population. Minor malformations were comparable when exposure occurred before or after gestational age 12 weeks (4.3% [95% CI, 0.1%-21.9%] vs 1.8% [95% CI, 1.0-3.0]; odds ratio, 3.13 [95% CI, 0.39-25.28]). Of 29 women who received chemotherapy prior to 12 weeks gestation, 17 (58.6%) were not aware of pregnancy, and 6 (20.7%) experienced a miscarriage (3 women [10.3%]) or decided to terminate their pregnancy (3 women [10.3%]). This cohort study fo

This cohort study of the International Network on Cancer, Infertility and Pregnancy (INCIP) reports the maternal and neonatal outcomes of 80 pregnant patients diagnosed with non-Hodgkin lymphoma (NHL) between 1986 and 2019, focussing on 57 (71%) patients with diffuse large B-cell lymphoma (DLBCL). Of all 80 patients, 54 (68%) pregnant patients received chemotherapy; mostly (89%) CHOP-like (cyclophosphamide, doxorubicin, vincristine, and prednisone) regimens. Four early pregnancies were terminated. Among 76 ongoing pregnancies, there was one stillbirth (1·3%). Overall, there was a high incidence of small for gestational age neonates (39%), preterm delivery (52%), obstetric (41%) and neonatal complications (12·5%), and this could not exclusively be explained by the receipt of antenatal chemotherapy. Half of preterm deliveries (46%) were planned in order to tailor oncological treatment. The 3-year progression-free and overall survival for patients with DLBCL treated with rituximab-CHOP was 83·4% and 95·7% for limited stage (n = 29) and 60·6% and 73·3% for advanced stage (n = 15). Of 36 pregnant patients who received rituximab, five (13%) cases with neonatal complications and three (8%) with maternal infections were reported. In conclusion, standard treatment for DLBCL can be offered to pregnant patients in obstetric centres that cater for high-risk patients.

IMPORTANCE: chemotherapy during the first trimester of pregnancy should be avoided owing to the risk of congenital malformations. however, the precise gestational age at which chemotherapy can be initiated safely remains unclear. OBJECTIVE: To assess congenital malformation rates associated with gestational age at initiation of chemotherapy among pregnant women with cancer. DESIGN, SETTING, AND PARTICIPANTS: This multicenter cohort study evaluated all pregnant women who received chemotherapy between 1977 and 2019 registered in the International Network on Cancer, Infertility and Pregnancy (INCIP) database. Data were analyzed from February 15 to June 2, 2020. EXPOSURES: Cancer treatment with chemotherapy during pregnancy. MAIN OUTCOMES AND MEASURES: Analysis was focused on major and minor structural malformations in offspring, defined by EUROCAT, detected during pregnancy or at birth. RESULTS: A total of 755 women in the INCIP database who underwent cancer treatment with chemotherapy during pregnancy were included in analysis. The median (range) age at cancer diagnosis was 33 (14-48) years. Among offspring, the major congenital malformation rate was 3.6% (95% CI, 2.4%-5.2%), and the minor congenital malformation rate was 1.9% (95% CI, 1.0%-3.1%). Chemotherapy exposure prior to 12 weeks gestational age was associated with a high rate of major congenital malformations, at 21.7% (95% CI, 7.5%-43.7%; odds ratio, 9.24 [95% CI, 3.13-27.30]). When chemotherapy was initiated after gestational age 12 weeks, the frequency of major congenital malformations was 3.0% (95% CI, 1.9%-4.6%), which was similar to the expected rates in the general population. Minor malformations were comparable when exposure occurred before or after gestational age 12 weeks (4.3% [95% CI, 0.1%-21.9%] vs 1.8% [95% CI, 1.0-3.0]; odds ratio, 3.13 [95% CI, 0.39-25.28]). Of 29 women who received chemotherapy prior to 12 weeks gestation, 17 (58.6%) were not aware of pregnancy, and 6 (20.7%) experienced a mis

Contains fulltext : 232066.pdf (Publisher’s version ) (Closed access), This cohort study of the International Network on Cancer, Infertility and Pregnancy (INCIP) reports the maternal and neonatal outcomes of 80 pregnant patients diagnosed with non-Hodgkin lymphoma (NHL) between 1986 and 2019, focussing on 57 (71%) patients with diffuse large B-cell lymphoma (DLBCL). Of all 80 patients, 54 (68%) pregnant patients received chemotherapy; mostly (89%) CHOP-like (cyclophosphamide, doxorubicin, vincristine, and prednisone) regimens. Four early pregnancies were terminated. Among 76 ongoing pregnancies, there was one stillbirth (1·3%). Overall, there was a high incidence of small for gestational age neonates (39%), preterm delivery (52%), obstetric (41%) and neonatal complications (12·5%), and this could not exclusively be explained by the receipt of antenatal chemotherapy. Half of preterm deliveries (46%) were planned in order to tailor oncological treatment. The 3-year progression-free and overall survival for patients with DLBCL treated with rituximab-CHOP was 83·4% and 95·7% for limited stage (n = 29) and 60·6% and 73·3% for advanced stage (n = 15). Of 36 pregnant patients who received rituximab, five (13%) cases with neonatal complications and three (8%) with maternal infections were reported. In conclusion, standard treatment for DLBCL can be offered to pregnant patients in obstetric centres that cater for high-risk patients.

Contains fulltext : 234977.pdf (Publisher’s version ) (Open Access)

Contains fulltext : 234977.pdf (Publisher’s version ) (Open Access)

Contains fulltext : 232066.pdf (Publisher’s version ) (Closed access), This cohort study of the International Network on Cancer, Infertility and Pregnancy (INCIP) reports the maternal and neonatal outcomes of 80 pregnant patients diagnosed with non-Hodgkin lymphoma (NHL) between 1986 and 2019, focussing on 57 (71%) patients with diffuse large B-cell lymphoma (DLBCL). Of all 80 patients, 54 (68%) pregnant patients received chemotherapy; mostly (89%) CHOP-like (cyclophosphamide, doxorubicin, vincristine, and prednisone) regimens. Four early pregnancies were terminated. Among 76 ongoing pregnancies, there was one stillbirth (1·3%). Overall, there was a high incidence of small for gestational age neonates (39%), preterm delivery (52%), obstetric (41%) and neonatal complications (12·5%), and this could not exclusively be explained by the receipt of antenatal chemotherapy. Half of preterm deliveries (46%) were planned in order to tailor oncological treatment. The 3-year progression-free and overall survival for patients with DLBCL treated with rituximab-CHOP was 83·4% and 95·7% for limited stage (n = 29) and 60·6% and 73·3% for advanced stage (n = 15). Of 36 pregnant patients who received rituximab, five (13%) cases with neonatal complications and three (8%) with maternal infections were reported. In conclusion, standard treatment for DLBCL can be offered to pregnant patients in obstetric centres that cater for high-risk patients.

The creation of unstable heavy particles at the Large Hadron Collider is the most direct way to address some of the deepest open questions in physics. Collisions typically produce variable-size sets of observed particles which have inherent ambiguities complicating the assignment of observed particles to the decay products of the heavy particles. Current strategies for tackling these challenges in the physics community ignore the physical symmetries of the decay products and consider all possible assignment permutations and do not scale to complex configurations. Attention based deep learning methods for sequence modelling have achieved state-of-the-art performance in natural language processing, but they lack built-in mechanisms to deal with the unique symmetries found in physical set-assignment problems. We introduce a novel method for constructing symmetry-preserving attention networks which reflect the problem's natural invariances to efficiently find assignments without evaluating all permutations. This general approach is applicable to arbitrarily complex configurations and significantly outperforms current methods, improving reconstruction efficiency between 19\% - 35\% on typical benchmark problems while decreasing inference time by two to five orders of magnitude on the most complex events, making many important and previously intractable cases tractable. A full code repository containing a general library, the specific configuration used, and a complete dataset release, are avaiable at https://github.com/Alexanders101/SPANet, Comment: published in SciPost

Importance: Chemotherapy during the first trimester of pregnancy should be avoided owing to the risk of congenital malformations. However, the precise gestational age at which chemotherapy can be initiated safely remains unclear. Objective: To assess congenital malformation rates associated with gestational age at initiation of chemotherapy among pregnant women with cancer. Design, Setting, and Participants: This multicenter cohort study evaluated all pregnant women who received chemotherapy between 1977 and 2019 registered in the International Network on Cancer, Infertility and Pregnancy (INCIP) database. Data were analyzed from February 15 to June 2, 2020. Exposures: Cancer treatment with chemotherapy during pregnancy. Main Outcomes and Measures: Analysis was focused on major and minor structural malformations in offspring, defined by EUROCAT, detected during pregnancy or at birth. Results: A total of 755 women in the INCIP database who underwent cancer treatment with chemotherapy during pregnancy were included in analysis. The median (range) age at cancer diagnosis was 33 (14-48) years. Among offspring, the major congenital malformation rate was 3.6% (95% CI, 2.4%-5.2%), and the minor congenital malformation rate was 1.9% (95% CI, 1.0%-3.1%). Chemotherapy exposure prior to 12 weeks gestational age was associated with a high rate of major congenital malformations, at 21.7% (95% CI, 7.5%-43.7%; odds ratio, 9.24 [95% CI, 3.13-27.30]). When chemotherapy was initiated after gestational age 12 weeks, the frequency of major congenital malformations was 3.0% (95% CI, 1.9%-4.6%), which was similar to the expected rates in the general population. Minor malformations were comparable when exposure occurred before or after gestational age 12 weeks (4.3% [95% CI, 0.1%-21.9%] vs 1.8% [95% CI, 1.0-3.0]; odds ratio, 3.13 [95% CI, 0.39-25.28]). Of 29 women who received chemotherapy prior to 12 weeks gestation, 17 (58.6%) were not aware of pregnancy, and 6 (20.7%) experienced a

The creation of unstable heavy particles at the Large Hadron Collider is the most direct way to address some of the deepest open questions in physics. Collisions typically produce variable-size sets of observed particles which have inherent ambiguities complicating the assignment of observed particles to the decay products of the heavy particles. Current strategies for tackling these challenges in the physics community ignore the physical symmetries of the decay products and consider all possible assignment permutations and do not scale to complex configurations. Attention based deep learning methods for sequence modelling have achieved state-of-the-art performance in natural language processing, but they lack built-in mechanisms to deal with the unique symmetries found in physical set-assignment problems. We introduce a novel method for constructing symmetry-preserving attention networks which reflect the problem's natural invariances to efficiently find assignments without evaluating all permutations. This general approach is applicable to arbitrarily complex configurations and significantly outperforms current methods, improving reconstruction efficiency between 19\% - 35\% on typical benchmark problems while decreasing inference time by two to five orders of magnitude on the most complex events, making many important and previously intractable cases tractable. A full code repository containing a general library, the specific configuration used, and a complete dataset release, are avaiable at https://github.com/Alexanders101/SPANet, Comment: published in SciPost

Efficiently solving problems with large action spaces using A* search has been of importance to the artificial intelligence community for decades. This is because the computation and memory requirements of A* search grow linearly with the size of the action space. This burden becomes even more apparent when A* search uses a heuristic function learned by computationally expensive function approximators, such as deep neural networks. To address this problem, we introduce Q* search, a search algorithm that uses deep Q-networks to guide search in order to take advantage of the fact that the sum of the transition costs and heuristic values of the children of a node can be computed with a single forward pass through a deep Q-network without explicitly generating those children. This significantly reduces computation time and requires only one node to be generated per iteration. We use Q* search to solve the Rubik's cube when formulated with a large action space that includes 1872 meta-actions and find that this 157-fold increase in the size of the action space incurs less than a 4-fold increase in computation time and less than a 3-fold increase in number of nodes generated when performing Q* search. Furthermore, Q* search is up to 129 times faster and generates up to 1288 times fewer nodes than A* search. Finally, although obtaining admissible heuristic functions from deep neural networks is an ongoing area of research, we prove that Q* search is guaranteed to find a shortest path given a heuristic function that neither overestimates the cost of a shortest path nor underestimates the transition cost., Comment: Added theoretical results to show that Q* search is an admissible search algorithm. Added comparisons to deferred heuristic evaluation. Added experiments with Lights Out and the 35-Pancake puzzle