ideaname stringclasses 4
values | field stringclasses 1
value | subfield stringclasses 1
value | year int64 2.03k 2.03k | url stringclasses 1
value | pdf_path stringclasses 1
value | target_prompt stringclasses 4
values | generation_prompt stringclasses 4
values | yidea stringclasses 4
values |
|---|---|---|---|---|---|---|---|---|
Testing panel data | Statistics | Statistical Inference | 2,025 | from Asher | N.A. | Analysis of panel data via linear regression is widespread across disciplines. To perform statistical inference, such analyses typically assume that clusters of observations are jointly independent. For example, one might assume that observations in New York are independent of observations in New Jersey. Are such assum... | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2025-08-14
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a knowledgeabl... | <|message|>We need to write a research proposal. Format: Markdown, three parts: Introduction (research question, importance, context, background), Proposal (proposed solution, step-by-step reasoning, details for replication, why it solves the question), Discussion (potential impacts, next steps to test/validate). The q... |
Conditional conformal | Statistics | Statistical Inference | 2,025 | from Asher | N.A. | Consider the problem of constructing distribution-free prediction sets with finite-sample conditional guarantees. Prior work has shown that it is impossible to provide exact conditional coverage universally in finite samples. Thus, most popular methods only guarantee marginal coverage over the covariates or are restric... | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2025-08-14
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a knowledgeabl... | <|message|>We need to write research proposal in markdown: introduction, proposal, discussion. It's about distribution-free prediction sets with finite-sample conditional guarantees. The question acknowledges impossibility of exact conditional coverage universally. Need to develop methods with distribution-free guarant... |
Powerful knockoffs | Statistics | Statistical Inference | 2,025 | from Asher | N.A. | Model-X knockoffs (Candes et al., 2018) allows analysts to perform feature selection using almost any machine learning algorithm while still provably controlling the expected proportion of false discoveries. To apply model-X knockoffs, one must construct synthetic variables, called knockoffs, which effectively act as c... | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2025-08-14
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a knowledgeabl... | <|message|>We need to write a research proposal in Markdown. The question is about improving power of knockoffs method when features are dependent while maintaining Type-I error control. Must have 3 parts: Introduction, Proposal, Discussion. Use pure Markdown. Need to consider using ideas like hierarchical or grouped k... |
Resolution-adaptive signal detection | Statistics | Statistical Inference | 2,025 | from Asher | N.A. | Scientists often must simultaneously localize and discover signals. For instance, in genetic fine-mapping, high correlations between nearby genetic variants make it hard to identify the exact locations of causal variants. So the statistical task is to output as many disjoint regions containing a signal as possible, eac... | <|start|>system<|message|>You are ChatGPT, a large language model trained by OpenAI.
Knowledge cutoff: 2024-06
Current date: 2025-08-14
Reasoning: medium
# Valid channels: analysis, commentary, final. Channel must be included for every message.<|end|><|start|>developer<|message|># Instructions
You are a knowledgeabl... | <|message|>We need to write a research proposal in pure Markdown. The proposal must have three parts: Introduction, Proposal, Discussion. Must be a general-purpose way to localize and discover signals simultaneously with Type-I error control across many statistical models. Need to propose a method. Possibly a general f... |
README.md exists but content is empty.
- Downloads last month
- 4