Keep a local paper directory and an Overleaf project in sync through the Overleaf Git bridge. Review collaborators’ changes before importing them, check for conflicting edits, and push local revisions back for shared editing.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Review communications research by searching existing libraries and notes before academic databases. Produce a paper comparison table covering methods, results, and limitations, then summarize major approaches, evidence strength, and remaining research gaps.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Audit citations in a LaTeX paper against online sources. Verify that references exist, bibliographic details are accurate, and each cited work supports the surrounding claim, then produce reports with findings and proposed corrections.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Explore a broad research direction through literature searches, idea generation, novelty checks, small pilot experiments, and critical review. Receive ranked ideas plus a refined proposal and experiment plan for the leading candidate, with evidence recorded across stages.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn a broad research direction into ranked ideas with clear hypotheses and small experiments. Survey related papers, use another model to challenge candidates, and update priorities using pilot results when suitable computing resources are available.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn method notes or figure descriptions into academic architecture and concept illustrations. Claude plans and reviews the layout, while a local Codex bridge generates images, with refinement rounds and final PNG, LaTeX snippet, and review records.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn a completed research paper into conference slides tailored to the talk format and duration. Produce a PDF, an editable PowerPoint deck, speaker notes, and a full rehearsal script with anticipated questions.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Explore hardware and electronic design configurations by repeatedly running programs, measuring results, and adjusting parameters. Track constraints and every trial, then report the best configuration found within the time and iteration limits.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Checks a research idea against recent literature, comparing its main claims with the closest published work. Produces a structured report explaining overlap, meaningful differences, risks, and whether to proceed, proceed cautiously, or abandon the idea.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Plan ablation studies, experiments that remove or replace parts of a machine learning method to test their contribution. Define reviewer questions, expected outcomes, priorities, execution order, and compute estimates, then implement experiments and record findings.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Compare machine learning experiment results from JSON or CSV files. Calculate improvements over a baseline, summarize variation across repeated runs, identify trends and unusual results, and suggest experiments to test possible explanations.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Improve a compiled paper through two rounds of external model review, source edits, and PDF rebuilding. Check claims against evidence, resolve inconsistencies, and refine figures and layout, with optional checkpoints and restrictions on which edits are allowed.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Improve research through up to four rounds of external language model review, fixes, and reassessment. Use an OpenAI-compatible API to identify weaknesses, prioritize changes, and keep a cumulative record of reviewer responses, actions, and experiment results.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Use MiniMax to review research, address weaknesses through code changes, experiments, or analysis, and request another assessment. The workflow runs up to four rounds and preserves reviewer responses, actions, results, and unresolved blockers.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Run repeated reviews of research work, implement fixes, and request another assessment for up to four rounds by default. The workflow records progress and stops when both the review score and verdict meet its acceptance rules.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Draft patent claims from invention disclosures, prior art reports, and novelty assessments. Create broad independent claims and narrower dependent claims, check their support in the specification, and adapt separate claim sets for China, the United States, or Europe.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Search open-access academic papers through DeepXiv, then move from brief summaries to section outlines and individual sections. Find trending papers and focus reading on the parts needed to answer a research question.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn a research experiment plan into training and evaluation code, run a small setup check, and launch GPU experiments. Collect initial metrics and update progress records so the results are ready for further review.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn a research proposal into an experiment plan tied to specific paper claims. Define comparisons, evaluation measures, tests that remove individual components, run order, and compute estimates, with a written plan and tracker for execution.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Audit a paper for numerical inconsistencies and other research integrity concerns. Record findings tied to source passages, track corrections and human waivers, and translate the audit report into workflow blocking or warning decisions.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn descriptions of processes, systems, or schedules into Mermaid diagrams, which use text to define visuals. Save editable source, a Markdown preview, and a rendered PNG, then check syntax, arrow directions, labels, and readability.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Apply staged improvements to skill files after explicit user selection and a fresh review by a different model family. Each applied change includes a backup, review records, and provenance details for later inspection.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Transparent, itemized impressions of AI-generated WRITING STYLE — the repo's ONLY non-integrity track. Two passes: a deterministic defensive-hedge density screen (tools/check_ai_style.py, AIS-DEFENSIVE-HEDGE) plus a fresh cross-model GROSS-cases-only semantic pass over the 13 AIS-* style tells (broken narrative arc, LLM phrase tics, jargon-stuffing, invented codenames, clause/formula walls, gratuitous pseudocode, bullet overuse, bold-module spam, restatement loops, focus drift, single-style figures, appendix dumping). Every finding is named, LOCATED, span-anchored to the evidence ledger (claims.json), carries not_integrity_finding:true + false_positive_risk:high + an fp_case, and gets ZERO verdict weight: the adjudicator forces it to info, excludes it from overall_verdict, and renders it in a SEPARATE report section. NOT an AI-text classifier — no scores, no "this is AI-written", no authorship probability; a paper can be CLEAN_GIVEN_EVIDENCE and still list many. Emits ai-style-impressions.findings.json; computes NO verdict; if a tell is actually substantive it routes to the integrity auditor. Triggers: "AI style", "vibe check", "writing fingerprint", "AI 文风", "vibe paper".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.