-
Notifications
You must be signed in to change notification settings - Fork 0
/
training-gemini-48.jsonl
48 lines (48 loc) · 171 KB
/
training-gemini-48.jsonl
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W2988715931.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Deep Hough Voting for 3D Object Detection in Point Clouds\", \"authors\": [ { \"first\": \"Charles R.\", \"last\": \"Qi\" }, { \"first\": \"Or\", \"last\": \"Litany\" }, { \"first\": \"Kaiming\", \"last\": \"He\" }, { \"first\": \"Leonidas J.\", \"last\": \"Guibas\" } ], \"abstract\": \"Current 3D object detection methods are heavily influ-\\nenced by 2D detectors. In order to leverage architectures\\nin 2D detectors, they often convert 3D point clouds to regu-\\nlar grids (i.e., to voxel grids or to bird\u2019s eye view images),\\nor rely on detection in 2D images to propose 3D boxes.\\nFew works have attempted to directly detect objects in point\\nclouds. In this work, we return to first principles to con-\\nstruct a 3D detection pipeline for point cloud data and as\\ngeneric as possible. However, due to the sparse nature of\\nthe data \u2013 samples from 2D manifolds in 3D space \u2013 we face\\na major challenge when directly predicting bounding box\\nparameters from scene points: a 3D object centroid can be\\nfar from any surface point thus hard to regress accurately in\\none step. To address the challenge, we propose VoteNet, an\\nend-to-end 3D object detection network based on a synergy\\nof deep point set networks and Hough voting. Our model\\nachieves state-of-the-art 3D detection on two large datasets\\nof real 3D scans, ScanNet and SUN RGB-D with a simple\\ndesign, compact model size and high efficiency. Remark-\\nably, VoteNet outperforms previous methods by using purely\\ngeometric information without relying on color images.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3202546816.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Grouptron: Dynamic Multi-Scale Graph Convolutional Networks for Group-Aware Dense Crowd Trajectory Forecasting\", \"authors\": [ { \"first\": \"Rui\", \"last\": \"Zhou\" }, { \"first\": \"Hongyu\", \"last\": \"Zhou\" }, { \"first\": \"Huidong\", \"last\": \"Gao\" }, { \"first\": \"Masayoshi\", \"last\": \"Tomizuka\" }, { \"first\": \"Jiachen\", \"last\": \"Li\" }, { \"first\": \"Zhuo\", \"last\": \"Xu\" } ], \"abstract\": \"Accurate, long-term forecasting of pedestrian trajectories in highly dynamic and interactive scenes is a long-standing challenge. Recent advances in using data-driven approaches have achieved significant improvements in terms of prediction accuracy. However, the lack of group-aware analysis has limited the performance of forecasting models. This is especially nonnegligible in highly crowded scenes, where pedestrians are moving in groups and the interactions between groups are extremely complex and dynamic. In this paper, we present Grouptron, a multi-scale dynamic forecasting framework that leverages pedestrian group detection and utilizes individual-level, group-level and scene-level information for better understanding and representation of the scenes. Our approach employs spatio-temporal clustering algorithms to identify pedestrian groups, creates spatio-temporal graphs at the individual, group, and scene levels. It then uses graph neural networks to encode dynamics at different scales and aggregate the embeddings for trajectory prediction. We conducted extensive comparisons and ablation experiments to demonstrate the effectiveness of our approach. Our method achieves 9.3% decrease in final displacement error (FDE) compared with state-of-the-art methods on ETH/UCY benchmark datasets, and 16.1% decrease in FDE in more crowded scenes where extensive human group interactions are more frequently present.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/osf.io/W4212832069.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"The Primacy of Intention and the Duty to Truth: A Gandhi-Inspired Argument for Retranslating Hims\u0101 and Ahims\u0101, with Connections to History, Ethics, and Civil Resistance\", \"authors\": [ { \"first\": \"Todd\", \"last\": \"Davies\" } ], \"abstract\": \"The words \\\"violence\\\" and \\\"nonviolence\\\" are increasingly misleading translations for the Sanskrit words hims\u0101 and ahims\u0101 -- which were used by Gandhi as the basis for his philosophy of saty\u0101graha. I argue for re-reading hims\u0101 as \u201cmaleficence\u201d and ahims\u0101 as \u201cbeneficence.\u201d These two more mind-referring English words \u2013 associated with religiously contextualized discourse of the past -- capture the primacy of intention implied by Gandhi's core principles, better than \\\"violence\u201d and \u201cnonviolence\u201d do. Reflecting a political turn in moral accountability detectable through linguistic data, both the scope and the usage of the word \u201cviolence\u201d have expanded dramatically. The expanded scope of \\\"violence\\\" reflects greater consciousness of the various forms that serious harm can take, but also makes it harder to convincingly characterize people and actions as \u201cnonviolent.\u201d New translations could clarify the distinction between hims\u0101 and ahims\u0101, and thereby prevent some misunderstandings of Gandhi. Training in beneficence would reflect Gandhi's psychological path to reducing avoidable harm: detachment from the ego, learning to love universally, and seeking truth by experiment.\", \"keywords\": [ \"himsa\", \"ahimsa\", \"violence\", \"nonviolence\", \"maleficence\", \"beneficence\", \"Gandhi\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/discovery.ucl.ac.uk/W2901173781.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Moderate to high levels of pre-treatment HIV drug resistance in KwaZulu-Natal Province, South Africa\", \"authors\": [ { \"first\": \"Benjamin\", \"last\": \"Chimukangara\" }, { \"first\": \"Ayesha BM\", \"last\": \"Kharsany\" }, { \"first\": \"Richard J\", \"last\": \"Lessells\" }, { \"first\": \"Kogieleum\", \"last\": \"Naidoo\" }, { \"first\": \"Soo-Yon\", \"last\": \"Rhee\" }, { \"first\": \"Justen\", \"last\": \"Manasa\" }, { \"first\": \"Tiago\", \"last\": \"Gr\u00e4f\" }, { \"first\": \"Lara\", \"last\": \"Lewis\" }, { \"first\": \"Cherie\", \"last\": \"Cawood\" }, { \"first\": \"David\", \"last\": \"Khanyile\" }, { \"first\": \"Karidia\", \"last\": \"Diallo\" }, { \"first\": \"Kassahun A\", \"last\": \"Ayalew\" }, { \"first\": \"Robert W\", \"last\": \"Shafer\" }, { \"first\": \"Gillian\", \"last\": \"Hunt\" }, { \"first\": \"Deenan\", \"last\": \"Pillay\" }, { \"first\": \"Salim Karim\", \"last\": \"Abdool\" }, { \"first\": \"Tulio de\", \"last\": \"Oliveira\" } ], \"abstract\": \"There is evidence of increasing levels of pre-treatment HIV drug resistance (PDR) in Southern Africa. We used data from two large population-based HIV surveillance studies to estimate prevalence of PDR in KwaZulu-Natal, the province with the highest HIV prevalence in South Africa. Methods: Sanger sequencing was performed on samples obtained from a longitudinal HIV surveillance programme (study A, 2013-2014) and the HIV Incidence Provincial Surveillance System (study B, 2014-2015). Sequences were included for adult HIV positive participants (age \u226515 years for study A, age 15-49 years for study B) with no documented prior exposure to ART. Overall and drug class-specific PDR was estimated using the World Health Organization 2009 surveillance drug resistance mutation (SDRM) list and phylogenetic analysis was performed to establish evidence of drug resistance transmission linkage. Results: One thousand eight hundred and forty-five (1845) sequences were analysed (611 study A; 1234 study B). An overall PDR prevalence of 9.2% (95% confidence interval (CI): 7.0-11.7) was observed for study A and 11.0% (95% CI 8.9-13.2) for study B. In study B, the prevalence of non-nucleoside reverse-transcriptase inhibitor (NNRTI) PDR exceeded 10% for sequences collected in 2014 (10.2%, 95% CI 7.5-12.9). The most prevalent SDRMs were K103NS (7.5%), M184VI (2.4%) and V106AM (1.4%). There was no evidence of large transmission chains of drug-resistant virus. Conclusion: High level NNRTI-PDR (>10%) suggests a need to modify the standard first-line ART regimen and to focus attention on improving the quality of HIV prevention, treatment and care.\", \"keywords\": [ \"HIV\", \"pre-treatment drug resistance\", \"antiretroviral therapy\", \"surveillance\", \"molecular epidemiology\", \"South Africa\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.biorxiv.org/W3013783484.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Dynamical model of the CLC-2 ion channel reveals conformational changes associated with selectivity-filter gating\", \"authors\": [ { \"first\": \"Keri A.\", \"last\": \"McKiernan\" }, { \"first\": \"Anna K.\", \"last\": \"Koster\" }, { \"first\": \"Merritt\", \"last\": \"Maduke\" }, { \"first\": \"Vijay S.\", \"last\": \"Pande\" } ], \"abstract\": \"This work reports a dynamical Markov state model of CLC-2 \\\"fast\\\" (pore) gating, based on 600 microseconds of molecular dynamics (MD) simulation. In the starting conformation of our CLC-2 model, both outer and inner channel gates are closed. The first conformational change in our dataset involves rotation of the inner-gate backbone along residues S168-G169-1170. This change is strikingly similar to that observed in the cryo-EM structure of the bovine CLC-K channel, though the volume of the intracellular (inner) region of the ion conduction pathway is further expanded in our model. From this state (inner gate open and outer gate closed), two additional states are observed, each involving a unique rotameric flip of the outer-gate residue GLUex. Both additional states involve conformational changes that orient GLUex away from the extracellular (outer) region of the ion conduction pathway. In the first additional state, the rotameric flip of GLUex results in an open, or near-open, channel pore. The equilibrium population of this state is low (~1%), consistent with the low open probability of CLC-2 observed experimentally in the absence of a membrane potential stimulus (0 mV). In the second additional state, GLUex rotates to occlude the channel pore. This state, which has a low equilibrium population (~1%), is only accessible when GLUex is protonated. Together, these pathways model the opening of both an inner and outer gate within the CLC-2 selectivity filter, as a function of GLUex protonation. Collectively, our findings are consistent with published experimental analyses of CLC-2 gating and provide a high-resolution structural model to guide future investigations.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/eartharxiv.org/W4226140866.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Weathering Intensity and Lithium Isotopes: A Reactive Transport Perspective\", \"authors\": [ { \"first\": \"Matthew J.\", \"last\": \"Winnick\" }, { \"first\": \"Jennifer L.\", \"last\": \"Druhan\" }, { \"first\": \"Kate\", \"last\": \"Maher\" } ], \"abstract\": \"Lithium isotopes have emerged as a powerful tool to probe the response of global weathering to changes in climate. Due to the preferential incorporation of \u2077Li into clay minerals during chemical weathering, the isotope ratio \u03b4\u2077Li may be used to interrogate the balance of primary mineral dissolution and clay precipitation. This balance has been linked to relative rates of chemical and physical denudation, such that dissolved \u03b4\u2077Li (\u03b4\u2077Lidiss) is highest at moderate weathering intensities when chemical and physical denudation are comparable. However, we argue that current theory linking \u03b4\u2077Li to weathering regimes through fluid travel times are unable to explain observations of low \u03b4\u2077Li and high Li concentrations in rapidly eroding settings. In this study, we re-examine the relationships between \u03b4\u2077Li, Li concentration, and weathering regime by incorporating Li isotopes into simulations of weathering profiles using a reactive transport model (CrunchFlow) that includes advective fluxes of regolith to simulate variable erosion rates in response to uplift. In these simulations, fractionation is implemented through a kinetic fractionation factor during clay precipitation, which allows the \u03b4\u2077Li of dissolved and suspended loads in the model to vary as a function of Li/Al ratios in primary and secondary minerals. When the model is run over a range of infiltration and erosion rates, simulations reproduce observed global patterns of \u03b4\u2077Lidiss and suspended load \u03b4\u2077Li as a function of weathering intensity, controlled primarily by water travel times and mineral residence times in weathered bedrock. We find that reduced water travel times at low weathering intensity, however, are inconsistent with observations of high Li concentrations. As an alternative, we demonstrate how the rapid weathering of soluble, Li-rich minerals such as chlorite under low weathering intensities may resolve this apparent discrepancy between data and theory. We also suggest that observed patterns are consistent with geothermal Li sources under low weathering intensities. This work offers a foundation guiding future studies in testing potential mechanisms underlying global riverine \u03b4\u2077Lidiss.\", \"keywords\": [ \"Lithium isotopes\", \"weathering regime\", \"reactive transport model\", \"chemical weathering\", \"critical zone isotopes\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.biorxiv.org/W4399283731.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"High-Resolution In Silico Painting with Generative Models\", \"authors\": [ { \"first\": \"Trang\", \"last\": \"Le\" }, { \"first\": \"Emma\", \"last\": \"Lundberg\" } ], \"abstract\": \"Label-free organelle prediction presents a longstanding challenge in cellular imaging, given the promise to to circumvent the numerous drawbacks associated with fluorescent microscopy, including its high costs, cytotoxicity, and time-consuming nature. Recent advancements in deep learning have introduced numerous effective algorithms, primarily deterministic, for predicting fluorescent patterns from transmitted light microscopy images. However, existing models frequently suffer from poor performance or are limited to specific datasets, image modalities, and magnifications, thus lacking a universal solution. In this paper, we present a simplified VQGAN training scheme that is easily adapted with different input/output channels for image-to-image translation tasks. We applied the algorithm to generate multi-channel organelle staining outputs from bright field inputs, equivalent to the popular Cell Painting assay. The same algorithm also participated and placed first in the ISBI 2024 Light My Cell challenge.\", \"keywords\": [ \"Bioimage analysis\", \"generative model\", \"label free\", \"cell painting\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3126527592.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Stochastic Comparative Statics in Markov Decision Processes\", \"authors\": [ { \"first\": \"Bar\", \"last\": \"Light\" } ], \"abstract\": \"In multi-period stochastic optimization problems, the future optimal decision is a random variable whose distribution depends on the parameters of the optimization problem. We analyze how the expected value of this random variable changes as a function of the dynamic optimization parameters in the context of Markov decision processes. We call this analysis stochastic comparative statics. We derive both comparative statics results and stochastic comparative statics results showing how the current and future optimal decisions change in response to changes in the single-period payoff function, the discount factor, the initial state of the system, and the transition probability function. We apply our results to various models from the economics and operations research literature, including investment theory, dynamic pricing models, controlled random walks, and comparisons of stationary distributions.\", \"keywords\": [ \"Markov decision processes\", \"comparative statics\", \"stochastic comparative statics\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/escholarship.org/W3093048371.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"IPSILATERAL RADIATION FOR SQUAMOUS CELL CARCINOMA OF THE TONSIL: AMERICAN RADIUM SOCIETY APPROPRIATE USE CRITERIA\", \"authors\": [ { \"first\": \"C. Jillian\", \"last\": \"Tsai\" }, { \"first\": \"Thomas J.\", \"last\": \"Galloway\" }, { \"first\": \"John A.\", \"last\": \"Ridge\" }, { \"first\": \"Jonathan J.\", \"last\": \"Beitler\" }, { \"first\": \"Beth\", \"last\": \"Beadle\" }, { \"first\": \"Richard\", \"last\": \"Bakst\" }, { \"first\": \"Danielle N.\", \"last\": \"Margalit\" }, { \"first\": \"Shlomo\", \"last\": \"Koyfman\" }, { \"first\": \"Minh Tam\", \"last\": \"Truong\" }, { \"first\": \"Jared\", \"last\": \"Robbins\" }, { \"first\": \"Allen\", \"last\": \"Chen\" }, { \"first\": \"Steven\", \"last\": \"Chang\" }, { \"first\": \"Jay\", \"last\": \"Cooper\" }, { \"first\": \"Sue S\", \"last\": \"Yom\" }, { \"first\": \"Farzan\", \"last\": \"Siddiqui\" } ], \"abstract\": null, \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/escholarship.org/W4205859241.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Perceptions of Cigarette Smoking and Weight in Hypothetical Hiring Decisions\", \"authors\": [ { \"first\": \"Erin A.\", \"last\": \"Vogel\" }, { \"first\": \"Judith J.\", \"last\": \"Prochaska\" } ], \"abstract\": \"Objective: Prior studies indicate lower employment and greater difficulty securing\\nreemployment among individuals who smoke or are overweight. In an anonymous online survey,\\nwe examined willingness to hire candidates who smoke cigarettes or are overweight for different\\njob types and tested respondents\u2019 smoking history and body weight as moderating factors.\\nMethods: Employed U.S. adults (N = 1107) were recruited online in 2019-2020. Respondents\\nindicated their willingness to hire and hiring preferences for six different job roles in reference to\\n8 different attributes, which included smoking and overweight status. Analyses tested differences\\nby job-type and respondents\u2019 own smoking and overweight status. Results: Percent willing to\\nhire candidates who smoke (are overweight) was 7.6% (40.3%) for health aide, 15.3% (66.2%)\\nfor receptionist, and 53.6% (58.1%) for groundskeeper. Ever-smoker respondents were more\\nlikely than never smokers to be willing to hire candidates who smoke (Odds Ratios [OR] = 1.98-\\n3.00) and less likely to identify smoking as a least preferred attribute (ps < .009). Overweight\\nrespondents were more likely than non-overweight respondents to be willing to hire overweight\\ncandidates (OR = 1.47-1.99) and less likely to identify overweight as a least preferred attribute\\n(ps < .002). Moderating effects of respondent smoking or overweight status were greater for the\\npublic-facing receptionist versus groundskeeper position. Conclusions: In hypothetical hiring\\ndecisions, smoking and overweight were viewed as undesirable, particularly among respondents\\nwithout the attribute tested. \", \"keywords\": [ \"smoking\", \"overweight\", \"bias\", \"employment\", \"judgment\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.medrxiv.org/W4322154575.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Schistosoma mansoni infection alters the host pre-vaccination environment resulting in blunted Hepatitis B vaccination immune responses\", \"authors\": [ { \"first\": \"Roshell\", \"last\": \"Muir\" }, { \"first\": \"Talibah\", \"last\": \"Metcalf\" }, { \"first\": \"Slim\", \"last\": \"Fourati\" }, { \"first\": \"Yannic\", \"last\": \"Bartsch\" }, { \"first\": \"Jacqueline\", \"last\": \"Kyosiimire Lugemwa\" }, { \"first\": \"Glenda\", \"last\": \"Canderan\" }, { \"first\": \"Galit\", \"last\": \"Alter\" }, { \"first\": \"Enoch\", \"last\": \"Muyanja\" }, { \"first\": \"Brenda\", \"last\": \"Okech\" }, { \"first\": \"Teddy\", \"last\": \"Namatovu\" }, { \"first\": \"Irene\", \"last\": \"Namara\" }, { \"first\": \"Annemarie\", \"last\": \"Namuniina\" }, { \"first\": \"Ali\", \"last\": \"Ssetaala\" }, { \"first\": \"Juliet\", \"last\": \"Mpendo\" }, { \"first\": \"Annet\", \"last\": \"Nanvubya\" }, { \"first\": \"Paul Kato\", \"last\": \"Kitandwe\" }, { \"first\": \"Bernard S.\", \"last\": \"Bagaya\" }, { \"first\": \"Noah\", \"last\": \"Kiwanuka\" }, { \"first\": \"Jacent\", \"last\": \"Nassuna\" }, { \"first\": \"Victoria Menya\", \"last\": \"Biribawa\" }, { \"first\": \"Alison M.\", \"last\": \"Elliott\" }, { \"first\": \"Claudia J.\", \"last\": \"de Dood\" }, { \"first\": \"William\", \"last\": \"Senyonga\" }, { \"first\": \"Priscilla\", \"last\": \"Balungi\" }, { \"first\": \"Pontiano\", \"last\": \"Kaleebu\" }, { \"first\": \"Yunia\", \"last\": \"Mayanja\" }, { \"first\": \"Mathew\", \"last\": \"Odongo\" }, { \"first\": \"Pat\", \"last\": \"Fast\" }, { \"first\": \"Matt A.\", \"last\": \"Price\" }, { \"first\": \"Paul L.A.M.\", \"last\": \"Corstjens\" }, { \"first\": \"Govert J.\", \"last\": \"van Dam\" }, { \"first\": \"Anatoli\", \"last\": \"Kamali\" }, { \"first\": \"Rafick Pierre\", \"last\": \"Sekaly\" }, { \"first\": \"Elias K\", \"last\": \"Haddad\" } ], \"abstract\": \"The impact of endemic infections on protective immunity is critical to inform vaccination strategies. In this study, we assessed the influence of Schistosoma mansoni infection on host responses in a Ugandan fishing cohort given a Hepatitis B (HepB) vaccine. Concentrations of schistosome-specific circulating anodic antigen (CAA) pre-vaccination showed a significant bimodal distribution associated with HepB titers, which were lower in individuals with high CAA. We established that participants with high CAA had significantly lower frequencies of circulating T follicular helper (cTfh) subpopulations pre- and post- vaccination and higher regulatory T cells (Tregs) post-vaccination. Polarization towards higher frequencies of Tregs: cTfh cells can be mediated by changes in the cytokine environment favoring Treg differentiation. In fact, we observed higher levels of CCL17 and soluble IL-2R pre-vaccination (important for Treg recruitment and development), in individuals with high CAA that negatively associated with HepB titers. Additionally, alterations in pre-vaccination monocyte function correlated with HepB titers, and changes in innate-related cytokines/chemokine production were associated with increasing CAA concentration. We report, that by influencing the immune landscape, schistosomiasis has the potential to modulate immune responses to HepB vaccination. These findings highlight multiple Schistosoma-related immune associations that could explain abrogated vaccine responses in communities with endemic infections.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.researchsquare.com/W4297341531.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Immunogenicity of Adjuvanted versus High-Dose Inactivated Influenza Vaccines in Older Adults: A Randomized Clinical Trial\", \"authors\": [ { \"first\": \"Kenneth E.\", \"last\": \"Schmader\" }, { \"first\": \"Christine K.\", \"last\": \"Liu\" }, { \"first\": \"Brendan\", \"last\": \"Flannery\" }, { \"first\": \"Wes\", \"last\": \"Rountree\" }, { \"first\": \"Heidi\", \"last\": \"Auerbach\" }, { \"first\": \"Elizabeth D.\", \"last\": \"Barnett\" }, { \"first\": \"Elizabeth P.\", \"last\": \"Schlaudecker\" }, { \"first\": \"Christopher A.\", \"last\": \"Todd\" }, { \"first\": \"Marek\", \"last\": \"Poniewierski\" }, { \"first\": \"Mary A.\", \"last\": \"Staat\" }, { \"first\": \"Theresa\", \"last\": \"Harrington\" }, { \"first\": \"Rongxia\", \"last\": \"Li\" }, { \"first\": \"Karen R.\", \"last\": \"Broder\" }, { \"first\": \"Emmanuel B.\", \"last\": \"Walter\" } ], \"abstract\": \"Background\\n\\nAdjuvanted inactivated influenza vaccine (allV) and high-dose inactivated influenza vaccine (HD-IIV) are U.S.-licensed for adults aged \u226565 years. This study compared serum hemagglutination inhibition (HAI) antibody titers for the A(H3N2) and A(H1N1)pdm09 and B strains after trivalent allV3 and trivalent HD-IIV3 in an older adult population. \\n\\nResults\\n\\nThe immunogenicity population included 342 participants who received allV3 and 338 participants who received HD-IIV3. The proportion of participants that seroconverted to A(H3N2) vaccine strains after allV3 (112 participants [32.8%]) was inferior to the proportion of participants that seroconverted after HD-IIV3 (130 participants [38.5%]) at day 29 after vaccination (difference, \u22125.8%; 95%CI, \u221212.9% to 1.4%). There were no significant differences between the vaccine groups in percent seroconversion to A(H1N1)pdm09 or B vaccine strains, in percent seropositivity for any of the strains, or in post-vaccination GMT for the A(H1N1)pdm09 strain. The GMTs for the post-vaccination A(H3N2) and B strains were higher after HD-IIV than after allV3. \\n\\nConclusions\\n\\nOverall immune responses were similar after allV3 and HD-IIV3. For the primary outcome, the allV3 seroconversion rate for H3N2 did not meet noninferiority criteria compared with HD-IIV3, but the HD-IIV3 seroconversion rate was not statistically superior to the allV3 seroconversion rate.\", \"keywords\": [ \"influenza vaccine\", \"immunogenicity\", \"aged\", \"adjuvanted influenza vaccine\", \"high dose influenza vaccine\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.medrxiv.org/W4393156923.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Analyses of academician cohorts generate biased pandemic excess death estimates\", \"authors\": [ { \"first\": \"John P.A.\", \"last\": \"Ioannidis\" } ], \"abstract\": \"Objective: Death data from cohorts of academicians have been used to estimate pandemic excess deaths. We aimed to evaluate the validity of this approach. Study design and setting: Data were analyzed from living and deceased member lists from Mainland China, UK and Greece academies; and Nobel laureates (and US subset thereof). Samples of early elected academicians were probed for unrecorded deaths; datasets overtly missing deaths were excluded from further analyses. Actuarial risks were compared against the general population in the same country in respective age strata. Relative incidence risk increases in death in active pandemic periods were compared to population-wide pandemic excess death estimates for the same country. Results: Royal Society and Academy of Athens datasets overtly missed deaths. Pre-pandemic death rates were 4-12-fold lower in the Chinese Academy of Engineering (CAE) versus respective age strata of the Mainland China population. A +158% relative increase in death risk was seen in CAE data during the first 12-months of wide viral spread. Both increases (+34% in British Academy) and decreases (-27% in US Nobel laureates) in death rates occurred in pandemic (2020-22) versus pre-pandemic (2017-2019) years; point estimates were far from known excess deaths in the respective countries (+6% and +14%, respectively). Published excess death estimates for urban-dwelling Mainland China selectively analyzed CAE, but not another Chinese academy (Chinese Academy of Sciences) with half the pandemic death rates. Conclusion: Missingness, lack of representativeness, large uncertainty, and selective analysis reporting make data from academy rosters unreliable for estimating general population excess deaths.\", \"keywords\": [ \"excess deaths\", \"academies\", \"elderly\", \"bias\", \"COVID-19\", \"life tables\", \"selective reporting\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/escholarship.org/W3000588783.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"An International Multi-Center Evaluation of Type 5 Long QT Syndrome: A Low Penetrant Primary Arrhythmic Condition\", \"authors\": [ { \"first\": \"Jason D.\", \"last\": \"Roberts\" }, { \"first\": \"S. Yukiko\", \"last\": \"Asaki\" }, { \"first\": \"Andrea\", \"last\": \"Mazzanti\" }, { \"first\": \"J. Martijn\", \"last\": \"Bos\" }, { \"first\": \"Izabella\", \"last\": \"Tuleta\" }, { \"first\": \"Alison R.\", \"last\": \"Muir\" }, { \"first\": \"Lia\", \"last\": \"Crotti\" }, { \"first\": \"Andrew D.\", \"last\": \"Krahn\" }, { \"first\": \"Valentina\", \"last\": \"Kutyifa\" }, { \"first\": \"M. Benjamin\", \"last\": \"Shoemaker\" }, { \"first\": \"Christopher L.\", \"last\": \"Johnsrude\" }, { \"first\": \"Takeshi\", \"last\": \"Aiba\" }, { \"first\": \"Luciana\", \"last\": \"Marcondes\" }, { \"first\": \"Anwar\", \"last\": \"Baban\" }, { \"first\": \"Sharmila\", \"last\": \"Udupa\" }, { \"first\": \"Brynn\", \"last\": \"Dechert\" }, { \"first\": \"Peter\", \"last\": \"Fischbach\" }, { \"first\": \"Linda M.\", \"last\": \"Knight\" }, { \"first\": \"Eric\", \"last\": \"Vittinghoff\" }, { \"first\": \"Deni\", \"last\": \"Kukavica\" }, { \"first\": \"Birgit\", \"last\": \"Stallmeyer\" }, { \"first\": \"John R.\", \"last\": \"Giudicessi\" }, { \"first\": \"Carla\", \"last\": \"Spazzolini\" }, { \"first\": \"Keiko\", \"last\": \"Shimamoto\" }, { \"first\": \"Rafik\", \"last\": \"Tadros\" }, { \"first\": \"Julia\", \"last\": \"Cadrin-Tourigny\" }, { \"first\": \"Henry J.\", \"last\": \"Duff\" }, { \"first\": \"Christopher S.\", \"last\": \"Simpson\" }, { \"first\": \"Thomas M.\", \"last\": \"Roston\" }, { \"first\": \"Yanushi D.\", \"last\": \"Wijeyeratne\" }, { \"first\": \"Imane\", \"last\": \"El Hajjaji\" }, { \"first\": \"Maisoon D.\", \"last\": \"Yousif\" }, { \"first\": \"Lorne J.\", \"last\": \"Gula\" }, { \"first\": \"Peter\", \"last\": \"Leong-Sit\" }, { \"first\": \"Nikhil\", \"last\": \"Chavali\" }, { \"first\": \"Andrew P.\", \"last\": \"Landstrom\" }, { \"first\": \"Gregory M.\", \"last\": \"Marcus\" }, { \"first\": \"Sven\", \"last\": \"Dittmann\" }, { \"first\": \"Arthur A. M.\", \"last\": \"Wilde\" }, { \"first\": \"Elijah R.\", \"last\": \"Behr\" }, { \"first\": \"Jacob\", \"last\": \"Tfelt-Hansen\" }, { \"first\": \"Melvin M.\", \"last\": \"Scheinman\" }, { \"first\": \"Marco V.\", \"last\": \"Perez\" }, { \"first\": \"Juan Pablo\", \"last\": \"Kaski\" }, { \"first\": \"Robert M.\", \"last\": \"Gow\" }, { \"first\": \"Fabrizio\", \"last\": \"Drago\" }, { \"first\": \"Peter F.\", \"last\": \"Aziz\" }, { \"first\": \"Dominic J.\", \"last\": \"Abrams\" }, { \"first\": \"Michael H.\", \"last\": \"Gollob\" }, { \"first\": \"Jonathan R.\", \"last\": \"Skinner\" }, { \"first\": \"Wataru\", \"last\": \"Shimizu\" }, { \"first\": \"Elizabeth S.\", \"last\": \"Kaufman\" }, { \"first\": \"Dan M.\", \"last\": \"Roden\" }, { \"first\": \"Wojciech\", \"last\": \"Zareba\" }, { \"first\": \"Peter J.\", \"last\": \"Schwartz\" }, { \"first\": \"Eric\", \"last\": \"Schulze-Bahr\" }, { \"first\": \"Susan P.\", \"last\": \"Etheridge\" }, { \"first\": \"Silvia G.\", \"last\": \"Priori\" }, { \"first\": \"Michael J.\", \"last\": \"Ackerman\" } ], \"abstract\": \"Background: Insight into type 5 long QT syndrome (LQT5) has been limited to case reports and small family series. Improved understanding of the clinical phenotype and genetic features associated with rare KCNE1 variants implicated in LQT5 was sought through an international multi-center collaboration. Methods: Patients with either presumed autosomal dominant LQT5 (N = 229) or the recessive Type 2 Jervell and Lange-Nielsen syndrome (JLNS2, N = 19) were enrolled from 22 genetic arrhythmia clinics and 4 registries from 9 countries. KCNE1 variants were evaluated for ECG penetrance (defined as QTc > 460ms on presenting ECG) and genotype-phenotype segregation. Multivariable Cox regression was used to compare the associations between clinical and genetic variables with a composite primary outcome of definite arrhythmic events, including appropriate implantable cardioverter-defibrillator shocks, aborted cardiac arrest, and sudden cardiac death. Results: A total of 32 distinct KCNE1 rare variants were identified in 89 probands and 140 genotype positive family members with presumed LQT5 and an additional 19 JLNS2 patients. Among presumed LQT5 patients, the mean QTc on presenting ECG was significantly longer in probands (476.9 \u00b1 38.6ms) compared to genotype positive family members (441.8 \u00b1 30.9ms, p<0.001). ECG penetrance for heterozygous genotype positive family members was 20.7% (29/140). A definite arrhythmic event was experienced in 16.9% (15/89) of heterozygous probands in comparison with 1.4% (2/140) of family members (adjusted hazard ratio [HR]: 11.6, 95% confidence interval [CI]: 2.6-52.2; p=0.001). Event incidence did not differ significantly for JLNS2 patients relative to the overall heterozygous cohort (10.5% [2/19]; HR: 1.7, 95% CI: 0.3-10.8, p=0.590). The cumulative prevalence of the 32 KCNE1 variants in the Genome Aggregation Database (gnomAD), which is a human database of exome and genome sequencing data from now over 140,000 individuals, was 238-fold greater than the anticipated prevalence of all LQT5 combined (0.238% vs. 0.001%). Conclusions: The present study suggests that putative/confirmed loss-of-function KCNE1 variants predispose to QT-prolongation, however the low ECG penetrance observed suggests they do not manifest clinically in the majority of individuals, aligning with the mild phenotype observed for JLNS2 patients.\", \"keywords\": [ \"long QT syndrome\", \"genetics\", \"penetrance\", \"arrhythmia\", \"sudden cardiac death\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.medrxiv.org/W3091235616.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Household economic impact of road traffic injury versus routine emergencies in a low-income country\", \"authors\": [ { \"first\": \"Hani\", \"last\": \"Mowafi\" }, { \"first\": \"Brian\", \"last\": \"Rice\" }, { \"first\": \"Rashida\", \"last\": \"Nambaziira\" }, { \"first\": \"Gloria\", \"last\": \"Nirere\" }, { \"first\": \"Robert\", \"last\": \"Wongoda\" }, { \"first\": \"Matthew\", \"last\": \"James\" }, { \"first\": \"Mark\", \"last\": \"Bisanzo\" }, { \"first\": \"Lori\", \"last\": \"Post\" } ], \"abstract\": null, \"keywords\": [ \"Road Traffic\", \"Injury\", \"Low- and Middle-income Countries\", \"Economic Impact\", \"Emergency\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/preprints.apsanet.org/W4296103990.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Selecting For Extremists: Evaluating the Impact of Judicial Selection Methods on Ideology\", \"authors\": [ { \"first\": \"Brett\", \"last\": \"Parker\" } ], \"abstract\": \"U.S. states display striking heterogeneity in their choices of judicial selection method. Researchers have produced dozens of papers exploring how the most commonly-used selection methods-partisan election, nonpartisan election, merit selection, and unconstrained gubernatorial appointment-affect the ideology and behavior of the judges they produce. Nevertheless, these articles have studied only a limited set of outcome variables. Most published work concerns either how selection method affects (1) judicial responsiveness to public opinion or (2) ideological direction. To my knowledge, however, no empirical work explores how choice of selection method impacts ideological extremity. This paper fills that gap. Using generalized propensity score matching, fixed effects counterfactual estimators, and synthetic controls to conduct causal inference, I examine whether some methods of selection produce more moderate (or extreme) judges than others. In order to do so, I extend and supplement the Bonica-Woodruff dataset on state supreme court judges, which features a commonly used measure of judicial ideology extracted from political donations. I find consistent evidence that judges picked by unconstrained gubernatorial appointment are more extreme on average than those selected by other methods. However, I do not find substantial evidence of differences between other pairs of selection methods.\", \"keywords\": [ \"Judicial Selection\", \"State Politics\", \"Ideological Extremity\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/ora.ox.ac.uk/W3170856023.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"How Campaigns Respond to Ballot Position: A New Mechanism for Order Effects\", \"authors\": [ { \"first\": \"Saad\", \"last\": \"Gulzar\" }, { \"first\": \"Thomas S.\", \"last\": \"Robinson\" }, { \"first\": \"Nelson A.\", \"last\": \"Ruiz\" } ], \"abstract\": \"An established finding on ballot design is that top positions on the ballot improve the electoral performance of parties or candidates because voters respond behaviorally to salient information. This paper presents evidence on an additional unexplored mechanism: campaigns, that can act before voters, adjust their behavior when allocated a top position on the ballot. We use a constituency-level lottery of ballot positions in Colombia to establish first that a ballot-order effect exists: campaigns randomly placed at the top earn more votes and seat shares. Second, we show that campaigns react to being placed on top of the ballot: they raise and spend more money on their campaign, and spending itself is correlated with higher vote shares. Our results provide the first evidence for a new mechanism of ballot-order effects examined in many previous studies.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3164284701.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Electrochemical Ion Insertion: From Atoms to Devices\", \"authors\": [ { \"first\": \"Aditya\", \"last\": \"Sood\" }, { \"first\": \"Andrey D.\", \"last\": \"Poletayev\" }, { \"first\": \"Daniel A.\", \"last\": \"Cogswell\" }, { \"first\": \"Peter M.\", \"last\": \"Csernica\" }, { \"first\": \"J. Tyler\", \"last\": \"Mefford\" }, { \"first\": \"Dimitrios\", \"last\": \"Fraggedakis\" }, { \"first\": \"Michael F.\", \"last\": \"Toney\" }, { \"first\": \"Aaron M.\", \"last\": \"Lindenberg\" }, { \"first\": \"Martin Z.\", \"last\": \"Bazant\" }, { \"first\": \"William C.\", \"last\": \"Chueh\" } ], \"abstract\": \"Electrochemical ion insertion involves coupled ion-electron transfer reactions, transport of guest species, and redox of the host. The hosts are typically anisotropic solids with two-dimensional conduction planes, but can also be materials with one-dimensional or isotropic transport pathways. These insertion compounds have traditionally been studied in the context of energy storage, but also find extensive applications in electrocatalysis, optoelectronics, and computing. Recent developments in operando, ultrafast, and high-resolution characterization methods, as well as accurate theoretical simulation methods, have led to a renaissance in the understanding of ion-insertion compounds. In this Review, we present a unified framework for understanding insertion compounds across time and length scales ranging from atomic to device levels. Using graphite, transition metal dichalcogenides, layered oxides, oxyhydroxides, and olivines as examples, we explore commonalities in these materials in terms of point defects, interfacial reactions, and phase transformations. We illustrate similarities in the operating principles of various ion-insertion devices ranging from batteries and electrocatalysts to electrochromics and thermal transistors, with the goal of unifying research across disciplinary boundaries.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3183339884.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"The Stationary Prophet Inequality Problem\", \"authors\": [ { \"first\": \"Kristen\", \"last\": \"Kessel\" }, { \"first\": \"Amin\", \"last\": \"Saberi\" }, { \"first\": \"Ali\", \"last\": \"Shameli\" }, { \"first\": \"David\", \"last\": \"Wajc\" } ], \"abstract\": \"We study a continuous and infinite time horizon counterpart to the classic prophet inequality, which we term the stationary prophet inequality problem. Here, copies of a good arrive and perish according to Poisson point processes. Buyers arrive similarly and make take-it-or-leave-it offers for unsold items. The objective is to maximize the (infinite) time average revenue of the seller. Our main results are pricing-based policies which (i) achieve a 1/2-approximation of the optimal offline policy, which is best possible, and (ii) achieve a better than (1-1/e)-approximation of the optimal online policy. Result (i) improves upon bounds implied by recent work of Collina et al. (WINE'20), and is the first optimal prophet inequality for a stationary problem. Result (ii) improves upon a 1 \u2013 1/e bound implied by recent work of Aouad and Sarita\u00e7 (EC'20), and shows that this prevalent bound in online algorithms is not optimal for this problem.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.researchsquare.com/W4393028888.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Self-reports map the landscape of task states derived from brain imaging\", \"authors\": [ { \"first\": \"Bronte\", \"last\": \"Mckeown\" }, { \"first\": \"lan\", \"last\": \"Goodall-Halliwell\" }, { \"first\": \"Raven\", \"last\": \"Wallace\" }, { \"first\": \"Louis\", \"last\": \"Chitiz\" }, { \"first\": \"Bridget\", \"last\": \"Mulholland\" }, { \"first\": \"Theodoros\", \"last\": \"Karapanagiotidis\" }, { \"first\": \"Samyogita\", \"last\": \"Hardikar\" }, { \"first\": \"Will\", \"last\": \"Strawson\" }, { \"first\": \"Adam\", \"last\": \"Turnbull\" }, { \"first\": \"Tamara\", \"last\": \"Vanderwal\" }, { \"first\": \"Nerissa\", \"last\": \"Ho\" }, { \"first\": \"Hao-Ting\", \"last\": \"Wang\" }, { \"first\": \"Ting\", \"last\": \"Xu\" }, { \"first\": \"Michael\", \"last\": \"Milham\" }, { \"first\": \"Xiuyi\", \"last\": \"Wang\" }, { \"first\": \"Meichao\", \"last\": \"Zhang\" }, { \"first\": \"Tirso Gonzalez\", \"last\": \"Alam\" }, { \"first\": \"Reinder\", \"last\": \"Vos de Wael\" }, { \"first\": \"Boris\", \"last\": \"Bernhardt\" }, { \"first\": \"Daniel\", \"last\": \"Margulies\" }, { \"first\": \"Jeffrey\", \"last\": \"Wammes\" }, { \"first\": \"Elisabeth\", \"last\": \"Jefferies\" }, { \"first\": \"Robert\", \"last\": \"Leech\" }, { \"first\": \"Jonathan\", \"last\": \"Smallwood\" } ], \"abstract\": \"Psychological states influence our happiness and productivity; however, estimates of their impact have historically been assumed to be limited by the accuracy with which introspection can quantify them. Over the last two decades, studies have shown that introspective descriptions of psychological states correlate with objective indicators of cognition, including task performance and metrics of brain function, using techniques like functional magnetic resonance imaging (fMRI). Such evidence suggests it may be possible to quantify the mapping between self-reports of experience and 'ground-truth' or biologically related representations of those states (e.g., those inferred from measures of brain activity). Here, we used machine learning to show that self-reported descriptions of experiences across tasks can reliably map the objective landscape of task states derived from brain activity. In our study, participants provided descriptions of their psychological states while performing tasks for which the contribution of different brain systems was available from prior fMRI studies. We used machine learning to combine these reports with descriptions of brain function to form a 'state-space' that reliably predicted patterns of brain activity based solely on unseen descriptions of experience. Our study demonstrates that introspection contains information that maps the objective task landscape inferred from brain activity.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.researchsquare.com/W4394813096.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Simultaneous single-cell three-dimensional genome and gene expression profiling Uncovers Dynamic Enhancer Connectivity Underlying Olfactory Receptor Choice\", \"authors\": [ { \"first\": \"Xiaoliang\", \"last\": \"Xie\" }, { \"first\": \"Honggui\", \"last\": \"Wu\" }, { \"first\": \"Jiankun\", \"last\": \"Zhang\" }, { \"first\": \"Fanchong\", \"last\": \"Jian\" }, { \"first\": \"Jinxin\", \"last\": \"Chen\" }, { \"first\": \"Yinghui\", \"last\": \"Zheng\" }, { \"first\": \"Longzhi\", \"last\": \"Tan\" } ], \"abstract\": \"The simultaneous measurement of three-dimensional (3D) genome structure and gene expression of individual cells is critical for understanding genome's structure-function relation, yet is extremely challenging for existing methods. Here we present Linking mRNA to Chromatin Architecture (LiMCA), which jointly profiles 3D genome and transcriptome with exceptional sensitivity and from low-input materials. Combining LiMCA and our high-resolution scATAC-seq assay, METATAC, we were able to profile the chromatin accessibility and the paired 3D genome structures and gene expression information of single neurons within the developing mouse olfactory epithelium. We expanded the repertoire of known OR enhancers, and discovered unexpected rules of their dynamics: ORs and their enhancers are most accessible during early differentiation, and the active OR typically does not associate with the largest enhancer hub. These findings offer valuable insights into how 3D connectivity of ORs and enhancers dynamically orchestrate the \u201cone neuron-one receptor\u201d selection process.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/chemrxiv.org/W4304614191.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"\u03b2-Lactamases evolve against antibiotics by acquiring large active-site electric fields\", \"authors\": [ { \"first\": \"Zhe\", \"last\": \"Ji\" }, { \"first\": \"Steven G.\", \"last\": \"Boxer\" } ], \"abstract\": \"A compound bound covalently to an enzyme active site can act either as a substrate if the covalent linkage is readily broken up by the enzyme or as an inhibitor if the bond dissociates slowly. We tracked the reactivity of such bonds associated with the rise of the resistance to penicillin G (PenG) in protein evolution from penicillin-binding proteins (PBPs) to TEM \u03b2-lactamases, and with the development of avibactam (Avb) to overcome the resistance. We found that the ester linkage in PBP-PenG is resistant to hydrolysis mainly due to the small electric fields present in the protein active site. Conversely, the same linkage in the descendant TEM-PenG experiences large electric fields which stabilize the more charge-separated transition state and thus lower the free energy barrier to hydrolysis. Specifically, the electric fields were improved from - 59 to -140 MV/cm in an ancient evolution dating back billions of years, contributing 5 orders of magnitude rate acceleration. This trend continues today in the nullification of newly developed antibiotic drugs. The fast linkage hydrolysis acquired from evolution is counteracted by the upgrade of PenG to Avb whose linkage escapes from the hydrolysis by returning to a low-field environment. Using the framework of electrostatic catalysis, the electric field, an observable from vibrational spectroscopy, provides a unifying physical metric to understand protein evolution and to guide the design of covalent drugs.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/inria.hal.science/W4386128506.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"WAM-Studio: A Web-Based Digital Audio Workstation to Empower Cochlear Implant Users\", \"authors\": [ { \"first\": \"Michel\", \"last\": \"Buffa\" }, { \"first\": \"Antoine\", \"last\": \"Vidal-Mazuy\" }, { \"first\": \"Lloyd\", \"last\": \"May\" }, { \"first\": \"Marco\", \"last\": \"Winckler\" } ], \"abstract\": \"This paper introduces WAM-Studio, an online Digital Audio Workstation (DAW) for recording, mixing, producing, and playing multi-track music. WAM-Studio advances music development by proposing a web-based environment based on a visual programming paradigm of end-user programming (EUP). In this paper, we describe how users can associate individual tracks with real-time audio processing plugins that can then be customized to produce a desired audio effect. Moreover, we describe how users can visually create macros to control multiple plugin parameters at once. While programming macro controls and customizing track parameters might have many applications in the music industry, they also present an opportunity to afford Hard-of-Hearing users greater control over their music listening. To illustrate the potential of WAM-Studio, we present a case study illustrating how this tool could be used by Hard-of-Hearing users to modify individual musical elements in a multi-track listening context to create a more enjoyable listening experience.\", \"keywords\": [ \"Web Audio\", \"DAWs\", \"plugin architecture\", \"Web standards\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/osf.io/W4376255784.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Disadvantaged Group Members are Prouder of Their Group When Using the Language of the Dominant Group Compared to Their Native Language\", \"authors\": [ { \"first\": \"Siwar\", \"last\": \"Hasan-Aslih\" }, { \"first\": \"Orly\", \"last\": \"Idan\" }, { \"first\": \"Robb\", \"last\": \"Willer\" }, { \"first\": \"Eran\", \"last\": \"Halperin\" } ], \"abstract\": \"In ethnolinguistically diverse societies, disadvantaged groups often face immense pressure to acquire and speak the language of the advantaged group to achieve social inclusion and economic mobility. This work investigates the impact on disadvantaged group members' ingroup pride and self-esteem when they use the language of the advantaged group and their native language. We test two competing hypotheses: disadvantaged group members experience higher ingroup pride when using their native language due to its emotional significance (Nativity Hypothesis) or when using the language of the advantaged group due to its potential to activate subordination-dominance relations (Insecurity Hypothesis). In six experimental studies conducted among Palestinian citizens of Israel (total N = 1,348), respondents reported significantly higher ingroup pride when answering a survey in Hebrew compared to Arabic, supporting the Insecurity Hypothesis. Studies 2a-2b reported higher ingroup pride in Hebrew, regardless of the identity of the audience (ingroup vs. outgroup researcher). Study 3 replicated this result in a setting featuring the \\\"bogus-pipeline\\\" technique, suggesting that the language effect was not driven by social desirability. Finally, Study 4 examined other self-conscious constructs to validate insecurity as a potential mechanism and demonstrated that participants engaged in compensation by enhancing their collective self-esteem and attaching more positive attributes to their group in Hebrew than Arabic. These findings combinedly suggest that the disadvantaged group members' perceptions of themselves are constructed through languages that symbolize varied statuses within the hierarchy, and highlight the importance of recognizing power relations within multilingualism contexts.\", \"keywords\": [ \"Pride\", \"Emotions\", \"Social Identity\", \"Bilingualism\", \"Minority\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3177095392.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Shape Matters: Understanding the Implicit Bias of the Noise Covariance\", \"authors\": [ { \"first\": \"Jeff Z.\", \"last\": \"HaoChen\" }, { \"first\": \"Colin\", \"last\": \"Wei\" }, { \"first\": \"Jason D.\", \"last\": \"Lee\" }, { \"first\": \"Tengyu\", \"last\": \"Ma\" } ], \"abstract\": \"The noise in stochastic gradient descent (SGD) provides a crucial implicit regularization effect for training\\noverparameterized models. Prior theoretical work largely focuses on spherical Gaussian noise, whereas\\nempirical studies demonstrate the phenomenon that parameter-dependent noise \u2014 induced by mini-batches or label perturbation \u2014 is far more effective than Gaussian noise. This paper theoretically characterizes this phenomenon on a quadratically-parameterized model introduced by Vaskevicius et al. (2019) and Woodworth et al. (2020). We show that in an over-parameterized setting, SGD with label noise recovers the sparse ground-truth with an arbitrary initialization, whereas SGD with Gaussian noise or gradient descent overfits to dense solutions with large norms. Our analysis reveals that parameter-dependent noise introduces a bias towards local minima with smaller noise variance, whereas spherical Gaussian noise does not. Code for our project is publicly available.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.researchsquare.com/W3133101250.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"CO2 Electrocatalyst Design Using Graph Theory\", \"authors\": [ { \"first\": \"Ziyun\", \"last\": \"Wang\" }, { \"first\": \"Yuguang\", \"last\": \"Li\" }, { \"first\": \"Jacob\", \"last\": \"Boes\" }, { \"first\": \"Ying\", \"last\": \"Wang\" }, { \"first\": \"Edward\", \"last\": \"Sargent\" } ], \"abstract\": \"The electrochemical reduction of CO2 (CO2RR) to higher-order hydrocarbons or oxygenates using low-carbon electricity offers a promising path to generate renewable fuels and chemicals; however, the low selectivity of present-day CO2RR catalysts toward more valuable C3 products limits technoeconomically compelling avenues toward productization. Systematically enumerating possible intermediates and reactions to the set of possible {C1, C2, and C3} CO2RR products entails 3206 intermediates and 4506 reactions. Here we use graph theory to enumerate these possibilities comprehensively, treating intermediates as graph nodes and pathways as graph edges. C3 products fall into two groups, group A (1-propanol, allyl alcohol, and propionaldehyde) and group B (acetone and hydroxyacetone); and we find that an early branch reaction, three steps after C1-C2 coupling, bifurcates these two groups of C3 products. We develop a set of C3 descriptors and screen catalysts for CO2RR to C3 products: specifically, we screen bimetallic (doped Cu) catalysts for their combination of CO binding, C\u2081-C\u2081 coupling and C1-C2 coupling. Cu and also Au- and Ag-doped Cu fulfill the first two requirements; but the set of promising C\u2081-C2 coupling catalysts (Ni-doped Pb and Al-doped Pb) needed to get to C3 is nonoverlapping with that for CO binding and C\u2081-C\u2081 coupling. Our findings agree with the experimental picture that Cu, while among the most productive to propanol, has been limited in F.E. to the 10-20% range; and that, to date, no single catalyst has achieved exceptional C3 productivity. We discuss tandem catalyst designs where a first catalyst promotes CO binding and C\u2081-C\u2081, and where these C2 and C\u2081 intermediates can come together for coupling on a second distinct class of integrated catalysts.\", \"keywords\": [ \"electrochemical reduction\", \"productization\", \"propionaldehyde\", \"acetone\", \"hydroxyacetone\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/preprints.apsanet.org/W3045625995.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"The Rise (and Fall) of Elected Sheriffs\", \"authors\": [ { \"first\": \"Cameron\", \"last\": \"DeHart\" } ], \"abstract\": \"Voters in almost every state elect county sheriffs but political science has only recently turned its attention to this important office. In this paper, I trace the historical processes that led Americans to begin electing sheriffs in the 18th and 19th centuries, as well as modern reforms to reverse that trend. Pairing newly-collected data on the timing of reforms that democratized local offices with narrative history, I show that the institution of elected sheriff spread gradually across the country and, in many states, Americans were deeply conflicted about subjecting this important office to popular choice. One finding is that sheriffs, in most states, became elective sooner than prosecutors and judges. I also provide evidence of the institution's slow retrenchment: today, there are four states and thirteen counties, home to over 20 million Americans, that do not elect sheriffs. The paper concludes with a discussion about the national importance of this local institution in American politics.\", \"keywords\": [ \"State and local politics\", \"elections\", \"accountability\", \"law enforcement\", \"criminal justice\", \"American political development\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.lenus.ie/W2890142544.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"KAT6A Syndrome: genotype-phenotype correlation in 76 patients with pathogenic KAT6A variants\", \"authors\": [ { \"first\": \"Joanna\", \"last\": \"Kennedy\" }, { \"first\": \"David\", \"last\": \"Goudie\" }, { \"first\": \"Edward\", \"last\": \"Blair\" }, { \"first\": \"Kate\", \"last\": \"Chandler\" }, { \"first\": \"Shelagh\", \"last\": \"Joss\" }, { \"first\": \"Victoria\", \"last\": \"McKay\" }, { \"first\": \"Andrew\", \"last\": \"Green\" }, { \"first\": \"Ruth\", \"last\": \"Armstrong\" }, { \"first\": \"Melissa\", \"last\": \"Lees\" }, { \"first\": \"Benjamin\", \"last\": \"Kamien\" }, { \"first\": \"Bruce\", \"last\": \"Hopper\" }, { \"first\": \"Tiong Yang\", \"last\": \"Tan\" }, { \"first\": \"Patrick\", \"last\": \"Yap\" }, { \"first\": \"Zornitza\", \"last\": \"Stark\" }, { \"first\": \"Nobuhiko\", \"last\": \"Okamoto\" }, { \"first\": \"Noriko\", \"last\": \"Miyake\" }, { \"first\": \"Naomichi\", \"last\": \"Matsumoto\" }, { \"first\": \"Ellen\", \"last\": \"Macnamara\" }, { \"first\": \"Jennifer L\", \"last\": \"Murphy\" }, { \"first\": \"Elizabeth\", \"last\": \"McCormick\" }, { \"first\": \"Hakon\", \"last\": \"Hakonarson\" }, { \"first\": \"Marni J\", \"last\": \"Falk\" }, { \"first\": \"Dong\", \"last\": \"Li\" }, { \"first\": \"Patrick\", \"last\": \"Blackburn\" }, { \"first\": \"Eric\", \"last\": \"Klee\" }, { \"first\": \"Dusica\", \"last\": \"Babovic-Vuksanovic\" }, { \"first\": \"Susan\", \"last\": \"Schelley\" }, { \"first\": \"Louanne\", \"last\": \"Hudgins\" }, { \"first\": \"Sarina\", \"last\": \"Kant\" }, { \"first\": \"Bertrand\", \"last\": \"Isidor\" }, { \"first\": \"Benjamin\", \"last\": \"Cogne\" }, { \"first\": \"Kimberley\", \"last\": \"Bradbury\" }, { \"first\": \"Mark\", \"last\": \"Williams\" }, { \"first\": \"Chirag\", \"last\": \"Patel\" }, { \"first\": \"Helen\", \"last\": \"Heussler\" }, { \"first\": \"Celia\", \"last\": \"Duff-Farrier\" }, { \"first\": \"Phillis\", \"last\": \"Lakeman\" }, { \"first\": \"Ingrid\", \"last\": \"Scurr\" }, { \"first\": \"Usha\", \"last\": \"Kini\" }, { \"first\": \"Mariet\", \"last\": \"Elting\" }, { \"first\": \"Margot\", \"last\": \"Reijnders\" }, { \"first\": \"Janneke\", \"last\": \"Schuurs-Hoeijmakers\" }, { \"first\": \"Mohamed\", \"last\": \"Wafik\" }, { \"first\": \"Anne\", \"last\": \"Blomhoff\" }, { \"first\": \"Claudia A L\", \"last\": \"Ruivenkamp\" }, { \"first\": \"Esther\", \"last\": \"Nibbeling\" }, { \"first\": \"Alexander J. M.\", \"last\": \"Dingemans\" }, { \"first\": \"Emilie D.\", \"last\": \"Douine\" }, { \"first\": \"Stanley F.\", \"last\": \"Nelson\" }, { \"first\": \"Valerie A.\", \"last\": \"Arboleda\" }, { \"first\": \"Ruth\", \"last\": \"Newbury-Ecob\" } ], \"abstract\": \"Purpose: Mutations in KAT6A have recently been identified as a cause of syndromic developmental delay. Within 2 years, the number of patients identified with pathogenic KAT6A mutations has rapidly expanded and the full extent and variability of the clinical phenotype has not been reported. \\nMethods: We obtained data for patients with KAT6A mutations through three sources: treating clinicians, an online family survey distributed through social media and a literature review. \\n\\nResults: We identified 52 unreported cases, bringing the total number of published cases to 76. Our results expand the genotypic spectrum of pathogenic mutations to include missense and splicing mutations. We functionally validated a pathogenic splice site mutation and identified a likely hot-spot location for de novo missense mutations. The majority of clinical features in KAT6A syndrome have highly variable penetrance. For core features such as intellectual disability, speech delay, microcephaly, cardiac anomalies and gastrointestinal complications, genotype-phenotype correlations show that late-truncating mutations (exons 16-17) aare significantly more prevalent. We highlight novel associations, including an increased risk of gastrointestinal obstruction. \\nConclusion: Our data expands the genotypic and phenotypic spectrum for individuals with genetic mutations in KAT6A and we outline appropriate clinical management.\", \"keywords\": [ \"Syndromic Developmental Delay\", \"histone acetylation\", \"genotype-phenotype association\", \"KAT6A\", \"chromatin\", \"genetic diagnosis\", \"phenotypic spectrum\", \"KAT6A syndrome\", \"chromatin modifiers\", \"intellectual disability\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/eartharxiv.org/W4250899323.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Upstream oil and gas production and ambient air pollution in California\", \"authors\": [ { \"first\": \"David J.X.\", \"last\": \"Gonzalez\" }, { \"first\": \"Christina K.\", \"last\": \"Francis\" }, { \"first\": \"Gary M.\", \"last\": \"Shaw\" }, { \"first\": \"Mark R.\", \"last\": \"Cullen\" }, { \"first\": \"Michael\", \"last\": \"Baiocchi\" }, { \"first\": \"Marshall\", \"last\": \"Burke\" } ], \"abstract\": \"Background. Prior studies have found that residential proximity to upstream oil and gas production is associated with increased risk of adverse health outcomes. Emissions of ambient air pollutants from oil and gas wells in the preproduction and production stages have been proposed as conferring risk of adverse health effects, but the extent of air pollutant emissions and resulting nearby pollution concentrations from wells is not clear. Objectives. We examined the effects of upstream oil and gas preproduction (count of drilling sites) and production (total volume of oil and gas) activities on concentrations of five ambient air pollutants in California. Methods. We obtained data on approximately 1 million daily observations from 314 monitors in the EPA Air Quality System, 2006-2019, including daily concentrations of five routinely monitored ambient air pollutants: PM2.5, CO, NO2, O3, and VOCs. We obtained data on preproduction and production operations from Enverus and the California Geographic Energy Management Division (CalGEM) for all wells in the state. For each monitor and each day, we assessed exposure to upwind preproduction wells and total oil and gas production volume within 10 km. We used a panel regression approach in the analysis and fit adjusted fixed effects linear regression models for each pollutant, controlling for geographic, seasonal, temporal, and meteorological factors. Results. We observed higher concentrations of PM2.5 and CO at monitors within 3 km of preproduction wells, NO2 at monitors at 1-2 km, and O3 at 2-4 km from the wells. Monitors with proximity to increased production volume observed higher concentrations of PM2.5, NO2, and VOCs within 1 km and higher O3 concentrations at 1-2 km. Results were robust to sensitivity analyses. Conclusion. Adjusting for geographic, meteorological, seasonal, and time-trending factors, we observed higher concentrations of ambient air pollutants at air quality monitors in proximity to preproduction wells within 4 km and producing wells within 2 km.\", \"keywords\": [ \"oil and gas\", \"exposure assessment\", \"ambient air pollution\", \"particulate matter\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/osf.io/W4385565029.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Is ChatGPT a Good Teacher Coach? Measuring Zero-Shot Performance For Scoring and Providing Actionable Insights on Classroom Instruction\", \"authors\": [ { \"first\": \"Rose\", \"last\": \"Wang\" }, { \"first\": \"Dorottya\", \"last\": \"Demszky\" } ], \"abstract\": \"Coaching, which involves classroom observation and expert feedback, is a widespread and fundamental part of teacher training. However, the majority of teachers do not have access to consistent, high quality coaching due to limited resources and access to expertise. We explore whether generative AI could become a cost-effective complement to expert feedback by serving as an automated teacher coach. In doing so, we propose three teacher coaching tasks for generative AI: (A) scoring transcript segments based on classroom observation instruments, (B) identifying highlights and missed opportunities for good instructional strategies, and (C) providing actionable suggestions for eliciting more student reasoning. We recruit expert math teachers to evaluate the zero-shot performance of ChatGPT on each of these tasks for elementary math classroom transcripts. Our results reveal that ChatGPT generates responses that are relevant to improving instruction, but they are often not novel or insightful. For example, 82% of the model's suggestions point to places in the transcript where the teacher is already implementing that suggestion. Our work highlights the challenges of producing insightful, novel and truthful feedback for teachers while paving the way for future research to address these obstacles and improve the capacity of generative AI to coach teachers.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3124742002.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Design-based Analysis in Difference-In-Differences Settings with Staggered Adoption*\", \"authors\": [ { \"first\": \"Susan\", \"last\": \"Athey\" }, { \"first\": \"Guido W.\", \"last\": \"Imbens\" } ], \"abstract\": \"In this paper we study estimation of and inference for average treatment effects in a setting with panel data. We focus on the setting where units, e.g., individuals, firms, or states, adopt the policy or treatment of interest at a particular point in time, and then remain exposed to this treatment at all times afterwards. We take a design perspective where we investigate the properties of estimators and procedures given assumptions on the assignment process. We show that under random assignment of the adoption date the standard Difference-In-Differences estimator is is an unbiased estimator of a particular weighted average causal effect. We characterize the properties of this estimand, and show that the standard variance estimator is conservative.\", \"keywords\": [ \"Staggered Adoption Design\", \"Difference-In-Differences\", \"Fixed Effects\", \"Randomization Distribution\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3178821884.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"The Galaxy Activity, Torus and Outflow Survey (GATOS): II. Torus and polar dust emission in nearby Seyfert galaxies\", \"authors\": [ { \"first\": \"A.\", \"last\": \"Alonso-Herrero\" }, { \"first\": \"S.\", \"last\": \"Garc\u00eda-Burillo\" }, { \"first\": \"S. F. \", \"last\": \"H\u00f6nig\" }, { \"first\": \"I.\", \"last\": \"Garc\u00eda-Bernete\" }, { \"first\": \"C. Ramos\", \"last\": \"Almeida\" }, { \"first\": \"O.\", \"last\": \"Gonz\u00e1lez-Mart\u00edn\" }, { \"first\": \"E.\", \"last\": \"L\u00f3pez-Rodr\u00edguez\" }, { \"first\": \"P. G.\", \"last\": \"Boorman\" }, { \"first\": \"A. J.\", \"last\": \"Bunker\" }, { \"first\": \"L.\", \"last\": \"Burtscher\" }, { \"first\": \"F.\", \"last\": \"Combes\" }, { \"first\": \"R.\", \"last\": \"Davies\" }, { \"first\": \"T.\", \"last\": \"D\u00edaz-Santos\" }, { \"first\": \"P.\", \"last\": \"Gandhi\" }, { \"first\": \"B.\", \"last\": \"Garc\u00eda-Lorenzo\" }, { \"first\": \"E. K. S. \", \"last\": \"Hicks\" }, { \"first\": \"L. K.\", \"last\": \"Hunt\" }, { \"first\": \"K.\", \"last\": \"Ichikawa\" }, { \"first\": \"M.\", \"last\": \"Imanishi\" }, { \"first\": \"T.\", \"last\": \"Izumi\" }, { \"first\": \"A.\", \"last\": \"Labiano\" }, { \"first\": \"N. A.\", \"last\": \"Levenson\" }, { \"first\": \"C.\", \"last\": \"Packham\" }, { \"first\": \"M.\", \"last\": \"Pereira-Santaella\" }, { \"first\": \"C.\", \"last\": \"Ricci\" }, { \"first\": \"D.\", \"last\": \"Rigopoulou\" }, { \"first\": \"P.\", \"last\": \"Roche\" }, { \"first\": \"D. J.\", \"last\": \"Rosario\" }, { \"first\": \"D.\", \"last\": \"Rouan\" }, { \"first\": \"T.\", \"last\": \"Shimizu\" }, { \"first\": \"M.\", \"last\": \"Stalevski\" }, { \"first\": \"K.\", \"last\": \"Wada\" }, { \"first\": \"D.\", \"last\": \"Williamson\" } ], \"abstract\": \"We compare high angular resolution mid-infrared (mid-IR) and ALMA far-infrared (far-IR) images of twelve nearby (median 21 Mpc) Seyfert galaxies selected from the Galaxy Activity Torus and Outflow Survey (GATOS). The mid-IR unresolved emission contributes more than 60% of the nuclear (diameters of 1.5\\\"~150 pc) emission in most galaxies. By contrast, the ALMA 870 \u00b5m continuum emission is mostly resolved with a median diameter of 42 pc and typically along the equatorial direction of the torus (Paper I of the series Garcia-Burillo et al. 2021). The Eddington ratios and nuclear hydrogen column densities (NH) of half the sample are favorable to launching polar and/or equatorial dusty winds, according to numerical simulations. Six of these show mid-IR extended emission approximately in the polar direction as traced by the narrow line region and perpendicular to the ALMA emission. In a few galaxies, the nuclear N\u2081 might be too high to uplift large quantities of dusty material along the polar direction. Five galaxies have low NH and/or Eddington ratios and thus polar dusty winds are not likely. We generate new radiative transfer CAT3D-WIND disk-wind models and model images at 8, 12, and 700 \u00b5m. We tailor these models to the properties of the GATOS Seyferts in this work. At low wind-to-disk cloud ratios the far-IR model images have disk- and ring-like morphologies. The characteristic \\\"X\\\"-shape associated with dusty winds is seen better in the far-IR at intermediate-high inclinations for the extended-wind configurations. In most of the explored models, the mid-IR emission comes mainly from the inner part of the disk/cone. Extended bi-conical and one-sided polar mid-IR emission is seen in extended-wind configurations and high wind-to-disk cloud ratios. When convolved to the typical angular resolution of our observations, the CAT3D-WIND model images reproduce qualitative aspects of the observed mid- and far-IR morphologies. However, low to intermediate values of the wind-to-disk ratio are required to account for the observed large fractions of unresolved mid-IR emission in our sample. This work and Paper I provide observational support for the torus+wind scenario. The wind component is more relevant at high Eddington ratios and/or AGN luminosities, and polar dust emission is predicted at nuclear column densities of up to 1024 cm-2. The torus/disk component, on the other hand, prevails at low luminosities and/or Eddington ratios.\", \"keywords\": [ \"Galaxies: Seyfert\", \"Submillimeter: galaxies\", \"Infrared: galaxies\", \"Galaxies: ISM\", \"Galaxies: individual: NGC 1365, NGC 3227, NGC 4388, NGC 4941, NGC 5506, NGC 5643, NGC 6300, NGC 6814, NGC 7213, NGC 7314, NGC 7465, NGC 7582\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.medrxiv.org/W3021395141.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Emotional consequences of COVID-19 home confinement: The ECLB-COVID19 multicenter study\", \"authors\": [ { \"first\": \"Achraf\", \"last\": \"Ammar\" }, { \"first\": \"Patrick\", \"last\": \"Mueller\" }, { \"first\": \"Khaled\", \"last\": \"Trabelsi\" }, { \"first\": \"Hamdi\", \"last\": \"Chtourou\" }, { \"first\": \"Omar\", \"last\": \"Boukhris\" }, { \"first\": \"Liwa\", \"last\": \"Masmoudi\" }, { \"first\": \"Bassem\", \"last\": \"Bouaziz\" }, { \"first\": \"Michael\", \"last\": \"Brach\" }, { \"first\": \"Marlen\", \"last\": \"Schmicker\" }, { \"first\": \"Ellen\", \"last\": \"Bentlage\" }, { \"first\": \"Daniella\", \"last\": \"How\" }, { \"first\": \"Mona\", \"last\": \"Ahmed\" }, { \"first\": \"Asma\", \"last\": \"Aloui\" }, { \"first\": \"Omar\", \"last\": \"Hammouda\" }, { \"first\": \"Laisa Liane\", \"last\": \"Paineiras-Domingos\" }, { \"first\": \"Annemarie\", \"last\": \"Braakman-jansen\" }, { \"first\": \"Christian\", \"last\": \"Wrede\" }, { \"first\": \"Sophia\", \"last\": \"Bastoni\" }, { \"first\": \"Carlos Soares\", \"last\": \"Pernambuco\" }, { \"first\": \"Leonardo\", \"last\": \"Mataruna\" }, { \"first\": \"Morteza\", \"last\": \"Taheri\" }, { \"first\": \"Khadijeh\", \"last\": \"Irandoust\" }, { \"first\": \"A\u00efmen\", \"last\": \"Khacharem\" }, { \"first\": \"Nicola L\", \"last\": \"Bragazzi\" }, { \"first\": \"Karim\", \"last\": \"Chamari\" }, { \"first\": \"Jordan M\", \"last\": \"Glenn\" }, { \"first\": \"Nicholas T\", \"last\": \"Bott\" }, { \"first\": \"Faiez\", \"last\": \"Gargouri\" }, { \"first\": \"Lotfi\", \"last\": \"Chaari\" }, { \"first\": \"Hadj\", \"last\": \"Batatia\" }, { \"first\": \"Gamal Mohamed\", \"last\": \"Ali\" }, { \"first\": \"Osama\", \"last\": \"Abdelkarim\" }, { \"first\": \"Mohamed\", \"last\": \"Jarraya\" }, { \"first\": \"Kais\", \"last\": \"El Abed\" }, { \"first\": \"Nizar\", \"last\": \"Souissi\" }, { \"first\": \"Lisette\", \"last\": \"Van Gemert-Pijnen\" }, { \"first\": \"Stephen J\", \"last\": \"Bailey\" }, { \"first\": \"Wassim\", \"last\": \"Moalla\" }, { \"first\": \"Jonathan\", \"last\": \"G\u00f3mez-Raja\" }, { \"first\": \"Monique\", \"last\": \"Epstein\" }, { \"first\": \"Robbert\", \"last\": \"Sanderman\" }, { \"first\": \"Sebastian\", \"last\": \"Schulz\" }, { \"first\": \"Achim\", \"last\": \"Jerg\" }, { \"first\": \"Ramzi\", \"last\": \"Al-Horani\" }, { \"first\": \"Taysir\", \"last\": \"Mansi\" }, { \"first\": \"Mohamed\", \"last\": \"Jmail\" }, { \"first\": \"Fernando\", \"last\": \"Barbosa\" }, { \"first\": \"Fernando\", \"last\": \"Santos\" }, { \"first\": \"Bo\u0161tjan\", \"last\": \"\u0160imuni\u010d\" }, { \"first\": \"Rado\", \"last\": \"Pi\u0161ot\" }, { \"first\": \"Donald\", \"last\": \"Cowan\" }, { \"first\": \"Andrea\", \"last\": \"Gaggioli\" }, { \"first\": \"J\u00fcrgen\", \"last\": \"Steinacker\" }, { \"first\": \"Laurel\", \"last\": \"Riemann\" }, { \"first\": \"Bryan L\", \"last\": \"Riemann\" }, { \"first\": \"Notger\", \"last\": \"Mueller\" }, { \"first\": \"Tarak\", \"last\": \"Driss\" }, { \"first\": \"Anita\", \"last\": \"Hoekelmann\" } ], \"abstract\": \"Background\\n\\nPublic health recommendations and government measures during the COVID-19 pandemic have enforced restrictions on daily living, which may include social distancing, remote work/school, and home confinement. While these measures are imperative to abate the spreading of COVID-19, the impact of these restrictions on mental health and emotional wellbeing is undefined. Therefore, an international online survey was launched on April 6, 2020 in seven languages to elucidate the impact of COVID-19 restrictions on mental health and emotional well-being. This report presents the preliminary results from the first thousand responders on mental wellbeing and mood and feelings questionnaires.\\n\\nMethods\\n\\nThe ECLB-COVID19 electronic survey was designed by a steering group of multidisciplinary\\nscientists and academics, following a structured review of the literature. The survey was\\nuploaded and shared on the Google online survey platform. Thirty-five research organizations\\nfrom Europe, North-Africa, Western Asia and the Americas promoted the multi-languages\\nsurvey through their networks to general society. Of the 64 questions, 7 were from the Short\\nWarwick-Edinburgh Mental Well-being Scale (SWEMWBS), and 13 were from the Short\\nMood and Feelings Questionnaire (SMFQ), which are both validated instruments.\\n\\nResults\\n\\nAnalysis was conducted on the first 1047 replies (54% women) from Asia (36%), Africa (40%),\\nEurope (21%) and other (3%). The COVID-19 home confinement had a negative effect on both\\nmental wellbeing and on mood and feelings. Specifically, a significant decrease (p<0.001 and\\n\u0394%= 9.4 %) in the total score of mental wellbeing was noted. More individuals (+12.89%)\\nreported a low mental wellbeing \u201cduring\u201d compared to \u201cbefore\u201d home confinement. Furthermore, results from the mood and feelings questionnaire (i.e., depressive symptoms)\\nshowed a significant increase by 44.9% (p<0.001) in total score with more people (+10%)\\ndeveloping depressive symptoms \u201cduring\u201d compared to \u201cbefore\u201d home confinement.\\nConclusion\\nThe ECLB-COVID19 survey revealed an increased psychosocial strain triggered by the\\nenforced home confinement. To mitigate this high risk of mental disorders and to foster an\\nActive and Healthy Confinement Lifestyle (AHCL), a crisis-oriented interdisciplinary\\nintervention is urgently needed.\\n\", \"keywords\": [ \"Public health\", \"Pandemic\", \"Mental wellbeing\", \"Depression\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3035272603.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Learning multiview 3D point cloud registration\", \"authors\": [ { \"first\": \"Zan\", \"last\": \"Gojcic\" }, { \"first\": \"Caifa\", \"last\": \"Zhou\" }, { \"first\": \"Jan D.\", \"last\": \"Wegner\" }, { \"first\": \"Leonidas J.\", \"last\": \"Guibas\" }, { \"first\": \"Tolga\", \"last\": \"Birdal\" } ], \"abstract\": \"We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm. Registration of multiple scans typically follows a two-stage pipeline: the initial pairwise alignment and the globally consistent refinement. The former is often ambiguous due to the low overlap of neighboring point clouds, symmetries and repetitive scene parts. Therefore, the latter global refinement aims at establishing the cyclic consistency across multiple scans and helps in resolving the ambiguous cases. In this paper we propose, to the best of our knowledge, the first end-to-end algorithm for joint learning of both parts of this two-stage problem. Experimental evaluation on well accepted benchmark datasets shows that our approach outperforms the state-of-the-art by a significant margin, while being end-to-end trainable and computationally less costly. Moreover, we present detailed analysis and an ablation study that validate the novel components of our approach. The source code and pretrained models are publicly available under https://github.com/zgojcic/3D_multiview_reg.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.researchsquare.com/W4247150207.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Three-dimensional non-destructive visualization of teeth enamel microcracks using X-ray micro-computed tomography\", \"authors\": [ { \"first\": \"Irma\", \"last\": \"Dumbryte\" }, { \"first\": \"Arturas\", \"last\": \"Vailionis\" }, { \"first\": \"Edvinas\", \"last\": \"Skliutas\" }, { \"first\": \"Saulius\", \"last\": \"Juodkazis\" }, { \"first\": \"Mangirdas\", \"last\": \"Malinauskas\" } ], \"abstract\": \"Although the topic of tooth fractures has been extensively analyzed in the dental literature, there is still insufficient information on the potential effect of enamel microcracks (EMCs) to the underlying tooth structures. For precise examination of tooth structure damage in the area of EMCs (i.e. whether it crosses the dentin-enamel junction (DEJ) and reaches dentin or pulp), volumetric (three-dimensional (3D)) evaluation of EMCs is necessary. The aim of this study was to present an X-ray micro-computed tomography (CT) as a technique suitable for 3D non-destructive visualization and qualitative analysis of different severity teeth EMCs. Extracted human maxillary premolars were examined using a \u00b5CT instrument ZEISS Xradia 520 Versa. In order to separate (segment) cracks from the rest of the tooth a Deep Learning Tool was utilized within the ORS Dragonfly software. The scanning technique used allowed for the recognition and detection of EMCs that are not only visible on the outer surface but also those that are deeply buried inside the tooth. The 3D visualization combined with Deep Learning segmentation enabled evaluation of EMC dynamics as it extends from the cervical to the occlusal part of the tooth, and precise examination of EMC position with respect to the DEJ.\", \"keywords\": [ \"tooth fractures\", \"dental literature\", \"X-ray micro-computed tomography (\u00b5CT)\", \"EMC position\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.medrxiv.org/W3007313800.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"FDA and EMA clinical research guidelines: Assessment of trial design recommendations for pivotal psychiatric drug trials (Protocol)\", \"authors\": [ { \"first\": \"Kim\", \"last\": \"Boesen\" }, { \"first\": \"Peter C\", \"last\": \"G\u00f8tzsche\" }, { \"first\": \"John PA\", \"last\": \"Ioannidis\" } ], \"abstract\": null, \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/osf.io/W4245851024.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Interventions to Reduce Meat Consumption by Appealing to Animal Welfare: Meta-Analysis and Evidence-Based Recommendations\", \"authors\": [ { \"first\": \"Maya B.\", \"last\": \"Mathur\" }, { \"first\": \"Jacob\", \"last\": \"Peacock\" }, { \"first\": \"David B.\", \"last\": \"Reichling\" }, { \"first\": \"Janice\", \"last\": \"Nadler\" }, { \"first\": \"Paul A.\", \"last\": \"Bain\" }, { \"first\": \"Christopher D.\", \"last\": \"Gardner\" }, { \"first\": \"Thomas N.\", \"last\": \"Robinson\" } ], \"abstract\": \"Reducing meat consumption may improve human health, curb environmental damage, and limit the large-scale suffering of animals reared in factory farms. Most attention to reducing consumption has focused on restructuring environments where foods are chosen or on making health or environmental appeals. However, psychological theory suggests that interventions appealing to animal welfare concerns might operate on distinct, potent pathways. We conducted a systematic review and meta-analysis evaluating the effectiveness of these interventions. We searched eight academic databases and extensively searched grey literature. We meta-analyzed 100 studies assessing interventions designed to reduce meat consumption or purchase by mentioning or portraying farm animals, that measured behavioral or self-reported outcomes related to meat consumption, purchase, or related intentions, and that had a control condition. The interventions consistently reduced meat consumption, purchase, or related intentions at least in the short term with meaningfully large effects (meta-analytic mean risk ratio [RR] = 1.22; 95% CI: [1.13, 1.33]). We estimated that a large majority of true population effects (71%; 95% CI: [59%, 80%]) were stronger than RR = 1.1 and that few were in the unintended direction. Via meta-regression, we identified some specific characteristics of studies and interventions that were associated with effect size. Risk-of-bias assessments identified both methodological strengths and limitations of this literature; however, results did not differ meaningfully in sensitivity analyses retaining only studies at the lowest risk of bias. Evidence of publication bias was not apparent. In conclusion, animal welfare interventions preliminarily appear effective in these typically short-term studies of primarily self-reported outcomes. Future research should use direct behavioral outcomes that minimize the potential for social desirability bias and are measured over long-term follow-up.\", \"keywords\": [ \"meta-analysis\", \"nutrition\", \"behavior interventions\", \"meat consumption\", \"planetary health\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.biorxiv.org/W4401157222.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Aging trajectories of memory CD8+ T cells differ by their antigen specificity\", \"authors\": [ { \"first\": \"Ines\", \"last\": \"Sturmlechner\" }, { \"first\": \"Abhinav\", \"last\": \"Jain\" }, { \"first\": \"Bin\", \"last\": \"Hu\" }, { \"first\": \"Rohit R.\", \"last\": \"Jadhav\" }, { \"first\": \"Wenqiang\", \"last\": \"Cao\" }, { \"first\": \"Hirohisa\", \"last\": \"Okuyama\" }, { \"first\": \"Lu\", \"last\": \"Tian\" }, { \"first\": \"Cornelia M.\", \"last\": \"Weyand\" }, { \"first\": \"J\u00f6rg J.\", \"last\": \"Goronzy\" } ], \"abstract\": \"Memory T cells are a highly dynamic and heterogeneous population that is maintained by cytokine-driven homeostatic proliferation interspersed with episodes of antigen-mediated expansion and contraction which affect their functional state and their durability. This heterogeneity complicates studies on the impact of aging on global human memory cells, specifically, it is unclear how aging drives memory T cell dysfunction. Here, we used chronic infection with Epstein-Barr virus (EBV) to assess the influence of age on memory states at the level of antigen-specific CD8+ T cells. We find that in young adults (<40 years), EBV-specific CD8+ T cells assume preferred differentiation states depending on their peptide specificity. By age >65-years, different T cell specificities had undergone largely distinct aging trajectories, which had in common a loss in adaptive and a gain in innate immunity signatures. No evidence was seen for cellular senescence or exhaustion. While na\u00efve/stem-like EBV-specific T cells disappeared with age, T cell diversity of EBV-specific memory cells did not change or even increased. In summary, by controlling for antigen specificity we uncover age-associated shifts in gene expression and TCR diversity that have implications for optimizing vaccination strategies and adoptive T cell therapy.\", \"keywords\": [ \"Immune aging\", \"memory T cells\", \"EBV\", \"T cell dysfunction\", \"senescence\", \"exhaustion\", \"immune memory durability\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3005397613.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Size of bulk fermions in the SYK model\", \"authors\": [ { \"first\": \"Yuri D.\", \"last\": \"Lensky\" }, { \"first\": \"Xiao-Liang\", \"last\": \"Qi\" }, { \"first\": \"Pengfei\", \"last\": \"Zhang\" } ], \"abstract\": \"The study of quantum gravity in the form of the holographic duality has\\nuncovered and motivated the detailed investigation of various diagnostics of quantum chaos.\\nOne such measure is the operator size distribution, which characterizes the size of the\\nsupport region of an operator and its evolution under Heisenberg evolution. In this work,\\nwe examine the role of the operator size distribution in holographic duality for the Sachdev-\\nYe-Kitaev (SYK) model. Using an explicit construction of AdS2 bulk fermion operators in a\\nputative dual of the low temperature SYK model, we study the operator size distribution of\\nthe boundary and bulk fermions. Our result provides a direct derivation of the relationship\\nbetween (effective) operator size of both the boundary and bulk fermions and bulk SL(2; R)\\ngenerators.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3116436840.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Supersingular curves with small non-integer endomorphisms\", \"authors\": [ { \"first\": \"Jonathan\", \"last\": \"Love\" }, { \"first\": \"Dan\", \"last\": \"Boneh\" } ], \"abstract\": \"We introduce a special class of supersingular curves over Fp2, characterized by the existence of non-integer endomorphisms of small degree. A number of properties of this set is proved. Most notably, we show that when this set partitions into subsets in such a way that curves within each subset have small-degree isogenies between them, but curves in distinct subsets have no small-degree isogenies between them. Despite this, we show that isogenies between these curves can be computed efficiently, giving a technique for computing isogenies between certain prescribed curves that cannot be reasonably connected by searching on \u2113-sogeny graphs.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.medrxiv.org/W3174061332.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Can Auxiliary Indicators Improve COVID-19 Forecasting and Hotspot Prediction?\", \"authors\": [ { \"first\": \"Daniel J.\", \"last\": \"McDonald\" }, { \"first\": \"Jacob\", \"last\": \"Bien\" }, { \"first\": \"Alden\", \"last\": \"Green\" }, { \"first\": \"Addison J.\", \"last\": \"Hu\" }, { \"first\": \"Nat\", \"last\": \"DeFries\" }, { \"first\": \"Sangwon\", \"last\": \"Hyun\" }, { \"first\": \"Natalia L.\", \"last\": \"Oliveira\" }, { \"first\": \"James\", \"last\": \"Sharpnack\" }, { \"first\": \"Jingjing\", \"last\": \"Tang\" }, { \"first\": \"Robert\", \"last\": \"Tibshirani\" }, { \"first\": \"Val\u00e9rie\", \"last\": \"Ventura\" }, { \"first\": \"Larry\", \"last\": \"Wasserman\" }, { \"first\": \"Ryan J.\", \"last\": \"Tibshirani\" } ], \"abstract\": \"Short-term forecasts of traditional streams from public health reporting (such as cases, hospitalizations, and deaths) are a key input to public health decision-making during a pandemic. Since early 2020, our research group has worked with data partners to collect, curate, and make publicly available numerous real-time COVID-19 indicators, providing multiple views of pandemic activity in the U.S. This paper studies the utility of five such indicators-derived from de-identified medical insurance claims, self-reported symptoms from online surveys, and COVID-related Google search activity-from a forecasting perspective. For each indicator, we ask whether its inclusion in an autoregressive (AR) model leads to improved predictive accuracy relative to the same model excluding it. Such an AR model, without external features, is already competitive with many top COVID-19 forecasting models in use today. Our analysis reveals that (a) inclusion of each of these five indicators improves on the overall predictive accuracy of the AR model; (b) predictive gains are in general most pronounced during times in which COVID cases are trending in \\\"flat\\\" or \\\"down\\\" directions; (c) one indicator, based on Google searches, seems to be particularly helpful during \\\"up\\\" trends.\", \"keywords\": [ \"COVID-19\", \"forecasting\", \"hotspot prediction\", \"time series\", \"digital surveillance\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3199353954.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility\", \"authors\": [ { \"first\": \"Liyun\", \"last\": \"Tu\" }, { \"first\": \"Austin\", \"last\": \"Talbot\" }, { \"first\": \"Neil M.\", \"last\": \"Gallagher\" }, { \"first\": \"David E.\", \"last\": \"Carlson\" } ], \"abstract\": \"Probabilistic generative models are attractive for scientific modeling because their inferred parameters can be used to generate hypotheses and design experiments. This requires that the learned model provides an accurate representation of the input data and yields a latent space that effectively predicts outcomes relevant to the scientific question. Supervised Variational Autoencoders (SVAEs) have previously been used for this purpose, as a carefully designed decoder can be used as an interpretable generative model of the data, while the supervised objective ensures a predictive latent representation. Unfortunately, the supervised objective forces the encoder to learn a biased approximation to the generative posterior distribution, which renders the generative parameters unreliable when used in scientific models. This issue has remained undetected as reconstruction losses commonly used to evaluate model performance do not detect bias in the encoder. We address this previously-unreported issue by developing a second-order supervision framework (SOS-VAE) that updates the decoder parameters, rather than the encoder, to induce a predictive latent representation. This ensures that the encoder maintains a reliable posterior approximation and the decoder parameters can be effectively interpreted. We extend this technique to allow the user to trade-off the bias in the generative parameters for improved predictive performance, acting as an intermediate option between SVAEs and our new SOS-VAE. We also use this methodology to address missing data issues that often arise when combining recordings from multiple scientific experiments. We demonstrate the effectiveness of these developments using synthetic data and electrophysiological recordings with an emphasis on how our learned representations can be used to design scientific experiments.\", \"keywords\": [ \"scientific analysis\", \"probabilistic generative models\", \"interpretable models\", \"supervised learning\", \"variational autoencoders\", \"second-order gradient\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3205417062.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"The effects of ecological selection on species diversity and trait distribution: predictions and an empirical test\", \"authors\": [ { \"first\": \"Niv\", \"last\": \"DeMalach\" }, { \"first\": \"Po-Ju\", \"last\": \"Ke\" }, { \"first\": \"Tadashi\", \"last\": \"Fukami\" } ], \"abstract\": \"Ecological selection is a major driver of community assembly. Selection is classified as stabilizing when species with intermediate trait values gain the highest reproductive success, whereas selection is considered directional when fitness is highest for species with extreme trait values. Previous studies have investigated the effects of different selection types on trait distribution, but the effects of selection on species diversity have remained unclear. Here, we propose a framework for inferring the type and strength of selection by studying species diversity and trait distribution together against null expectations. We use a simulation model to confirm our prediction that directional selection should lead to lower species diversity than stabilizing selection despite a similar effect on trait community-weighted variance. We apply the framework to a mesocosm system of annual plants to test whether differences in species diversity between two habitats that vary in productivity are related to differences in selection on seed mass. We show that, in both habitats, species diversity was lower than the null expectation, but that species diversity was lower in the more productive habitat. We attribute this difference to strong directional selection for large-seeded species in the productive habitat as indicated by trait community-weighted-mean being higher and community-weighted variance being lower than the null expectations. In the less productive habitat, we found that community-weighted variance was higher than expected by chance, suggesting that seed mass could be a driver of niche partitioning under such conditions. Altogether, our results suggest that viewing species diversity and trait distribution as interrelated patterns driven by the same process, ecological selection, is helpful in understanding community assembly.\", \"keywords\": [ \"annual plants\", \"community weighted mean\", \"community weighted variance\", \"competition\", \"environmental filtering\", \"functional diversity\", \"functional traits\", \"seed mass\", \"seed size\", \"species richness\", \"species pool\", \"trait selection\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/arxiv.org/W3025420576.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"PBBFMM3D: a parallel black-box algorithm for kernel matrix-vector multiplication\", \"authors\": [ { \"first\": \"Ruoxi\", \"last\": \"Wang\" }, { \"first\": \"Chao\", \"last\": \"Chen\" }, { \"first\": \"Jonghyun\", \"last\": \"Lee\" }, { \"first\": \"Eric\", \"last\": \"Darve\" } ], \"abstract\": \"Kernel matrix-vector product is ubiquitous in many science and engineering applications. However, a naive method requires O(N<sup>2</sup>) operations, which becomes prohibitive for large-scale problems. To reduce the computation cost, we introduce a parallel method that provably requires O(N) operations and delivers an approximate result within a prescribed tolerance. The distinct feature of our method is that it requires only the ability to evaluate the kernel function, offering a black-box interface to users. Our parallel approach targets multi-core shared-memory machines and is implemented using OpenMP. Numerical results demonstrate up to 19\u00d7 speedup on 32 cores. We also present a real-world application in geo-statistics, where our parallel method was used to deliver fast principle component analysis of covariance matrices.\", \"keywords\": [ \"kernel method\", \"matrix-vector multiplication\", \"covariance matrix\", \"fast multipole method\", \"shared-memory parallelism\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/publikationen.ub.uni-frankfurt.de/W4313482304.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Art Collectors as Venture Capitalists\", \"authors\": [ { \"first\": \"Amy\", \"last\": \"Whitaker\" }, { \"first\": \"Roman\", \"last\": \"Kr\u00e4ussl\" } ], \"abstract\": \"Employing the art-collection records of Burton and Emily Hall Tremaine, we consider whether early-stage art investors can be understood as venture capitalists. Because the Tremaines bought artists' work very close to an artwork's creation, with 69% of works in our study purchased within one year of the year when they were made, their collecting practice can best be framed as venture-capital investment in art. The Tremaines also illustrate art collecting as social-impact investment, owing to their combined strategy of art sales and museum donations for which the collectors received a tax credit under US rules. Because the Tremaines' museum donations took place at a time that U.S. marginal tax rates from 70% to 91%, the near \u201cdonation parity\u201d with markets, creating a parallel to ESG investment in the management of multiple forms of value.\", \"keywords\": [ \"Art investment\", \"venture capital\", \"social impact\", \"portfolio management\", \"tax arbitrage\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/www.frbsf.org/W2919371474.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Job-Finding and Job-Losing: A Comprehensive Model of Heterogeneous Individual Labor-Market Dynamics\", \"authors\": [ { \"first\": \"Robert E.\", \"last\": \"Hall\" }, { \"first\": \"Marianna\", \"last\": \"Kudlyak\" } ], \"abstract\": \"We study the paths over time that individuals follow in the labor market, as revealed in the monthly Current Population Survey. Some people face much higher flow values from work than in a non-market activity; if they lose a job, they find another soon. Others have close to equal flow values and tend to circle through jobs, search, and non-market activities. And yet others have flow values for non-market activities that are higher than those in the market, and do not work. We develop a model that identifies and quantifies heterogeneity in dynamic individual behavior. Our model provides a bridge between research on monthly transition rates in the tradition of Blanchard and Diamond (1990) and research on economic dynamics in the tradition of Mortensen and Pissarides (1994). Our estimates discern 5 distinct types. Most unemployment comes from just two of those types. Low employment types frequently circle among unemployment, short-term jobs, and being out of the labor market. Short-term jobs play a role in the job-finding process related to the role of unemployment. These are stop-gap jobs for high-employment types and a part of circling for low-employment types. Because of their high job-finding rates, and despite their low flow values of non-work relative to work, the volatility of the future lifetime value that high-employment types derive from work and non-work is lower than for low-employment types.\", \"keywords\": []}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/osf.io/W4386513944.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Recommendations for Quantitative Cerebral Perfusion MRI using Multi-Timepoint Arterial Spin Labeling: Acquisition, Quantification, and Clinical Applications\", \"authors\": [ { \"first\": \"Joseph G.\", \"last\": \"Woods\" }, { \"first\": \"Eric\", \"last\": \"Achten\" }, { \"first\": \"Iris\", \"last\": \"Asllani\" }, { \"first\": \"Divya S.\", \"last\": \"Bolar\" }, { \"first\": \"Weiying\", \"last\": \"Dai\" }, { \"first\": \"John A.\", \"last\": \"Detre\" }, { \"first\": \"Audrey P.\", \"last\": \"Fan\" }, { \"first\": \"Maria\", \"last\": \"Fern\u00e1ndez-Seara\" }, { \"first\": \"Xavier\", \"last\": \"Golay\" }, { \"first\": \"Matthias\", \"last\": \"G\u00fcnther\" }, { \"first\": \"Jia\", \"last\": \"Guo\" }, { \"first\": \"Luis\", \"last\": \"Hernandez-Garcia\" }, { \"first\": \"Mai-Lan\", \"last\": \"Ho\" }, { \"first\": \"Meher R.\", \"last\": \"Juttukonda\" }, { \"first\": \"Hanzhang\", \"last\": \"Lu\" }, { \"first\": \"Bradley J.\", \"last\": \"MacIntosh\" }, { \"first\": \"Ananth J.\", \"last\": \"Madhuranthakam\" }, { \"first\": \"Henk-Jan\", \"last\": \"Mutsaerts\" }, { \"first\": \"Thomas W.\", \"last\": \"Okell\" }, { \"first\": \"Laura M.\", \"last\": \"Parkes\" }, { \"first\": \"Nandor\", \"last\": \"Pinter\" }, { \"first\": \"Joana\", \"last\": \"Pinto\" }, { \"first\": \"Qin\", \"last\": \"Qin\" }, { \"first\": \"Marion\", \"last\": \"Smits\" }, { \"first\": \"Yuriko\", \"last\": \"Suzuki\" }, { \"first\": \"David L.\", \"last\": \"Thomas\" }, { \"first\": \"Matthias J.P.\", \"last\": \"Van Osch\" }, { \"first\": \"Danny JJ\", \"last\": \"Wang\" }, { \"first\": \"Esther A.H.\", \"last\": \"Warnert\" }, { \"first\": \"Greg\", \"last\": \"Zaharchuk\" }, { \"first\": \"Fernando\", \"last\": \"Zelaya\" }, { \"first\": \"Moss\", \"last\": \"Zhao\" }, { \"first\": \"Michael A.\", \"last\": \"Chappell\" } ], \"abstract\": \"Accurate assessment of cerebral perfusion is vital for understanding the hemodynamic\\nprocesses involved in various neurological disorders and guiding clinical decision-\\nmaking. This guidelines article provides a comprehensive overview of quantitative\\nperfusion imaging of the brain using multi-timepoint arterial spin labeling (ASL), along\\nwith recommendations for its acquisition and quantification. Acquiring ASL data with\\nmultiple label durations and/or post-labeling delays (PLDs) enables efficient mapping\\nof perfusion, offering comparable accuracy to a conventional single-PLD approach\\nwithin the same scan time. Additionally, multi-timepoint ASL allows for the estimation\\nof arterial transit time (ATT) and the generation of ATT maps, mitigating the impact of\\nvariable and prolonged ATTs on perfusion measurements and providing valuable\\nclinical insights. However, the acquisition and postprocessing of multi-timepoint ASL\\ndata presents challenges beyond single-PLD ASL, impeding its widespread adoption.\\nBuilding upon the 2015 ASL consensus article, this work highlights the protocol\\ndistinctions specific to multi-timepoint ASL and provides robust recommendations for\\nacquiring high-quality data. Additionally, we propose an extended quantification model\\nbased on the 2015 consensus model and discuss relevant postprocessing options to\\nenhance the analysis of multi-timepoint ASL data. Furthermore, we review the\\npotential clinical applications where multi-timepoint ASL is expected to offer significant\\nbenefits. This article is part of a series published by the International Society for\\nMagnetic Resonance in Medicine (ISMRM) Perfusion Study Group, aiming to guide\\nand inspire the advancement and utilization of ASL beyond the scope of the 2015\\nconsensus article.\", \"keywords\": [ \"arterial spin labeling\", \"perfusion\", \"cerebral blood flow\", \"arterial transit time\" ]}"}]}]}
{"contents": [{"role": "user", "parts": [{"fileData": {"mimeType": "application/pdf", "fileUri": "gs://cloud-ai-platform-e215f7f7-a526-4a66-902d-eb69384ef0c4/preprints/escholarship.org/W3087573264.pdf"}}, {"text": "Format all responses as valid JSON.\\nExamine this article and extract the following data:\\nThe title of the article.\\nThe list of authors split into first and last name. The first name may include any initials or middle names as well. Use \"first\" and \"last\" as the JSON keys for the name.\\nThe abstract if it is explicitly provided. Do not try to generate an abstract unless it is present.\\nThe list of keywords if they are explicitly provided. Do not try to generate keywords unless they are present.\\n\\nRespond with a JSON object formatted to comply with the following JSON schema:\\n{\"type\": \"object\", \"properties\": {\"title\": {\"type\": \"string\"}, \"authors\": {\"type\": \"array\", \"items\": {\"type\": \"object\", \"properties\": {\"first\": {\"type\": \"string\"}, \"last\": {\"type\": \"string\"}}, \"required\": [\"first\", \"last\"]}}, \"keywords\": {\"type\": \"array\", \"items\": {\"type\": \"string\"}}, \"abstract\": {\"type\": \"string\"}}, \"required\": [\"title\", \"authors\"]}\\nThis is permissioned content. I am the publisher. It is fair use under copyright law for me to request exact quotations.\\n "}]}, {"role": "model", "parts": [{"text": "{ \"title\": \"Integrating old and new paradigms for G1/S control\", \"authors\": [ { \"first\": \"Seth M.\", \"last\": \"Rubin\" }, { \"first\": \"Julien\", \"last\": \"Sage\" }, { \"first\": \"Jan M.\", \"last\": \"Skotheim\" } ], \"abstract\": null, \"keywords\": []}"}]}]}