Skill UI

A comprehensive pre-submission checklist for authors preparing papers for TACAS/ETAPS. It guides users through selecting the correct paper category (research, tool, case-study), adhering to specific Springer LNCS page limits, managing double-blind vs. single-blind review rules, and correctly staging mandatory tool artifacts to ensure acceptance readiness.

This skill processes unstructured, rambling, stream-of-consciousness input (like dictation or brainstorming) into a highly structured 'echo' audit. It captures the user's core mission, locked decisions, open questions, and all model inferences, ensuring the user verifies the model's belief, not just the stated doubts. Ideal for refining fuzzy ideas before committing to work.

A comprehensive guide for designing, auditing, and reporting advanced statistical and causal inference experiments. It emphasizes moving beyond simple accuracy metrics to quantify uncertainty, model robustness, and causal mechanisms. Covers metrics like coverage, KL divergence, and regret, and outlines best practices for seeding, compute fairness, and creating standardized reporting blocks (e.g., UAI standards).

This guide details advanced best practices for achieving scientific reproducibility in probabilistic modeling and deep learning research. It mandates rigorous disclosure of seeds, hyperparameters, diagnostic traces (e.g., R-hat, ELBO), and compute environments to ensure that all claims made in academic papers are verifiably backed by traceable evidence. It elevates reproducibility from a simple code run to a comprehensive audit.

This comprehensive pre-upload audit guide ensures submissions meet the strict technical and anonymity requirements for UAI OpenReview. It covers critical aspects like the 8-page main body constraint, combining all content into a single PDF, handling file size caps (15MB/50MB), and performing an identity sweep to maintain double-blind review standards.

A comprehensive audit guide for the final pre-upload submission of UIST (User Interface Software and Technology) conference papers. This document details critical steps, including adhering to strict formatting rules (e.g., two-column layout, page limits), managing the abstract and paper deadlines, and executing thorough anonymity sweeps to prevent desk rejection. Essential reading for authors preparing for major academic conferences.

A comprehensive audit checklist for designing and evaluating security experiments, adhering to the highest academic standards (e.g., USENIX Security). It guides users through verifying adaptive attacker models, calculating precision at realistic base rates, ensuring statistical honesty for stochastic results, and maintaining ethical compliance when working with live systems.

A comprehensive guide for designing and auditing visualization experiments for high-stakes academic submissions (e.g., IEEE VIS). It details how to match evidence—such as controlled studies, power analyses, and benchmarks—to the specific type of claim (perceptual, algorithmic, system). Learn best practices for statistical rigor, CVD-safe encoding, and maintaining full provenance to ensure your findings are scientifically sound and trustworthy.

A comprehensive audit guide for submitting full papers to IEEE VIS. It covers the complex, multi-stage submission process, requiring authors to adhere to journal-quality standards (IEEE TVCG). The guide details the strict deadlines for abstracts, full papers, and supplemental materials, along with critical mechanics like the 9+2 page budget, proper society/track selection, and advanced double-blind anonymization techniques.

This comprehensive guide teaches researchers how to conduct an exhaustive "reinvention audit" for academic papers, specifically in the database field. It covers searching deep historical literature (pre-2000), modern conference venues (SIGMOD, ICDE), and industrial open-source systems (PostgreSQL, RocksDB) to ensure true novelty and properly position the contribution delta.

This comprehensive guide provides researchers with structured methodologies for designing and auditing Computer Vision (CV) experiments for major conferences like WACV. It details the critical differences between the Applications and Algorithms tracks, emphasizing the need to report performance under real deployment constraints (e.g., power, latency) and ensuring fair, rigorous comparisons with baselines. Ideal for revising submissions to meet high review standards.

A comprehensive audit guide for authors submitting to WACV. It covers critical submission decisions, including choosing between Round 1 or Round 2, selecting the appropriate Applications or Algorithms track, adhering to the 8-page limit, maintaining double-blind anonymity, and ensuring all coauthors have valid OpenReview profiles to prevent desk rejection.