Skill UI

A comprehensive guide detailing the strict requirements for submitting research papers to EMNLP via the ACL Rolling Review (ARR). Key areas covered include template compliance, page length restrictions (long/short format), mandatory limitations sections, double-blind anonymization techniques, and adherence to the Responsible NLP checklist. Use this audit guide before submission to ensure full compliance and avoid desk-rejects.

This skill manages the end-to-end project lifecycle for academic conference submissions, specifically tailored for major venues like ICLR. It provides a structured timeline, defining critical milestones from initial topic selection and abstract submission through paper deadlines, public discussion, and final camera-ready versions. Use it to sequence research milestones, manage evidence paths, and ensure compliance with conference rules like anonymity audits and strict deadlines.

A comprehensive audit checklist for ensuring final submissions to the ICML conference. It verifies compliance across critical areas including LaTeX formatting, strict page limits, double-blind anonymity, impact statements, dual submission rules, and adherence to the latest LLM and ethical policies. Essential for researchers preparing papers for top-tier AI venues.

A comprehensive checklist for auditing and preparing main-track conference submissions for top-tier AI venues like IJCAI. This guide covers critical compliance points, including double-blind anonymity enforcement, strict page limits, LLM usage policies, author details verification, and identifying potential desk-reject risks before final submission.

Provides a comprehensive, detailed audit checklist for authors submitting papers intended for NAACL. This guide walks through the complex ACL Rolling Review (ARR) submission cycle, ensuring the manuscript passes all mandatory technical gates—such as anonymity checks, format compliance, structural requirements, and accurate declaration—before the final conference commitment. Essential for navigating the unique timeline and rigorous standards of top NLP conferences.

This skill simulates the rigorous peer review process used in top-tier AI and machine learning conferences (like NeurIPS). It helps users diagnose potential weaknesses in a submission regarding quality, clarity, significance, ethical compliance, and reproducibility. It guides the identification of decision-relevant issues that ACs and reviewers are likely to raise, helping authors strategically plan responses for revision.

A comprehensive audit tool designed to ensure academic paper compliance before submitting to major AI conferences like NeurIPS. It systematically checks adherence to the CFP, double-blind anonymity across all assets (PDF, code, data, supplement), correct track selection, and avoids common desk-rejection pitfalls, ensuring the submission is ready for OpenReview.

This skill audits OpenMed NER or de-identification models to detect performance disparities across sensitive demographic subgroups (e.g., sex, age, race). It calculates metrics like per-group recall and leakage disparity, helping users identify instances of 'under-protection' before deployment, ensuring equitable AI governance and compliance.

This tool benchmarks the recall of PII detection models, crucial for ensuring privacy compliance before deployment. It uses synthetic fixtures and enforces a recall floor by measuring label-aware exact-span and grapheme recall against predefined gold standards. It is essential for auditing models and preventing critical privacy leaks.

This skill evaluates de-identification and clinical NER models against rigorous leakage-first release gates (G1a-G8). Instead of relying on aggregate F1 scores, it focuses on detecting residual Protected Health Information (PHI) leakage and enforcing per-label recall floors, which is crucial for HIPAA compliance. Determines if a model is RELEASABLE or QUARANTINED.

This framework provides a rigorous pre-execution review mechanism for proposed actions by AI agents or systems. It functions as a critical safety boundary, auditing the entire decision path—from initial request to proposed tool execution—without authorizing or executing anything. It verifies action conformity, evidence integrity, temporal validity, and reviewer independence to ensure system compliance and security.

Audits AI-assisted legal, compliance, governance, and institutional decisions before reliance to determine whether the responsible human or institution has enough access to evidence, reasoning, uncertainty, authority, and review path to genuinely own the decision rather than merely approve, sign, or transmit it.