Skill UI

A comprehensive guide for designing, auditing, and executing rigorous experimental programs for top-tier computer vision papers (e.g., CVPR). It covers essential scientific components, including establishing fair benchmarks, structured ablation studies, documenting failure modes, quantifying computational efficiency, and demonstrating cross-dataset generalization, ensuring the research is reproducible and robust.

This comprehensive checklist is designed for auditing NLP research papers, particularly for major conferences like EACL. It serves as a claims audit, ensuring that every reported result, claim, or finding—including hyperparameters, compute costs, verbatim prompts, data sources, and significance testing—is fully documented and reproducible. It emphasizes academic rigor and transparency in AI research.

A comprehensive audit guide for authors preparing submissions for the ECAI conference. It details critical steps including selecting the correct submission regime (standalone vs. joint), managing page budgets (7-page body limit), ensuring double-blind anonymity, and adhering to strict deadlines for abstract and full paper submissions. Essential reading before uploading to the conference portal.

A comprehensive guide for designing and auditing high-stakes computer vision experiments for top-tier conferences. It covers critical areas like 'matched-substrate fairness,' 'six-month-staleness testing,' and rigorous ablation studies, ensuring that claims are robust, reproducible, and withstand intense peer review scrutiny.

A detailed auditing guide for submitting to major academic conferences, such as ECCV. It covers critical aspects including multi-stage submission deadlines (CET timezone), strict LNCS formatting rules (14 pages single-column), policy adherence (dual-submission, embargo rules), and pre-upload checks to mitigate rejection risks. Essential for researchers managing academic publishing workflows.

A comprehensive guide for structuring, auditing, and writing mathematically rigorous proofs for advanced academic papers, particularly in econometrics and statistics. It covers everything from defining assumptions and stating self-contained theorems to applying advanced proof techniques (e.g., fixed-point theorems, CLT). Use this when your central result requires impeccable rigor and completeness for top-tier publication.

This guide provides comprehensive standards for designing, auditing, and reporting empirical evaluations in database systems research. It emphasizes the principle that evidence must proportionally match the claim, requiring the use of real-world workloads, fair and tuned baselines, thorough measurement of variance and state (warm/cold), and fully reproducible evaluation harnesses. It also outlines the higher bar for 'Experiments & Analysis' papers.

This comprehensive guide outlines the rigorous standards for designing, auditing, and reporting Natural Language Processing (NLP) experiments, specifically tailored for top-tier academic conferences like EMNLP. It covers critical areas including baseline fairness checks, data contamination audits, statistical significance testing, prompt sensitivity analysis, and structured human evaluation protocols, ensuring reported claims are robust, reproducible, and methodologically sound.

A comprehensive methodological guide for auditing experimental economic designs. Use this when the causal claim hinges on strict experimental control, addressing issues like incentive compatibility, randomization robustness, and adherence to the no-deception norm. It stress-tests the underlying methodology, verifying identification through rigorous design checks.

A comprehensive guide for establishing academic rigor in AI and data science research. It outlines best practices for achieving reproducibility, emphasizing the mandatory release and documentation of raw data, trained models, and qualitative findings. Key tools include datasheets, model cards, and detailed provenance logging, ensuring that research claims are fully auditable and consistent.

A comprehensive methodology guide for achieving maximum checkability in theoretical computer science proofs, especially for high-stakes academic venues like FOCS. It outlines five critical practices: maintaining a hypothesis ledger, freezing theorem statements across all document versions, auditing external theorems, providing certificates for computed steps, and handling errata formally. This ensures proofs withstand intense academic scrutiny.

This guide provides a rigorous framework for designing and auditing empirical studies in software engineering (SE). It emphasizes that evidence must proportionally match the claims made, covering topics like using real subject systems, establishing fair baselines, calculating SE-standard statistics (effect sizes, CIs), and ensuring thorough provenance, especially for LLM-based work. It helps researchers strengthen their research methodology before publication.