学習中のモデルの損失や評価指標を定期的に確認し、NaNや発散、停滞、評価失敗などを根拠とともに報告して、継続・待機・停止を判断します。
- WandBの学習指標を定期的に監視したいとき
- WandBが使えずログから学習状況を確認したいとき
- 評価指標をベースラインと比較したいとき
学習中のモデルの損失や評価指標を定期的に確認し、NaNや発散、停滞、評価失敗などを根拠とともに報告して、継続・待機・停止を判断します。
最大次数と直径を指定した有限グラフの構成や上界を調べ、実際の頂点・辺・距離の検証を原題の条件につなげます。
Construct degree–diameter graphs from a real source and a proved coverage interface: current-radius extensions, frozen full-neighborhood clones, affine route-image unions and opposite-GQ spread fill. Use during route or proof development; return an actual graph definition and all-pair/degree proof or exact missing assumptions, not a parameter formula alone.
日本語の概要は準備中です。原文の説明を表示しています。
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
日本語の概要は準備中です。原文の説明を表示しています。
Evolve an existing MathRSI version from real mathematical research evidence. Distill successful and failed work into base changes, domain plugins, task-local knowledge or deferred proposals; implement, use and reconcile the actual changes. Use for MathRSI iteration or absorbing a completed research project, not for silently changing a running theorem-solving workflow.
日本語の概要は準備中です。原文の説明を表示しています。
数学研究的准备子工作流,实际串联原题初步澄清、广泛文献与反例勘误调查、正式规格定稿及wiki恢复。已有研究按真实断点进入后继阶段,不重复从零调查。
日本語の概要は準備中です。原文の説明を表示しています。
Search and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
日本語の概要は準備中です。原文の説明を表示しています。
整理数学研究的初步问题或恢复既有任务,并在文献调查后定稿原对象、量词、参数、依赖与验收。用于新题起步、原题含糊或已有规格需要对齐;不负责替用户换题或评选求解路线。
日本語の概要は準備中です。原文の説明を表示しています。
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific proof obligation benefits from formal verification; use proof-writer for ordinary mathematical drafting.
日本語の概要は準備中です。原文の説明を表示しています。
调查数学问题的异名、等价表述、已有结论与反例勘误,深读关键原文形成可调用的数学进口和准确基线,并持续接回任务wiki。用于新题广搜、换参数或方法后的查漏及文献断点恢复;不以查新分数替代证明或自行更改原目标。
日本語の概要は準備中です。原文の説明を表示しています。
Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with cross-model jury and human approval at landing. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.
日本語の概要は準備中です。原文の説明を表示しています。
Search academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information. Use when user says "openalex search", "search openalex", "open citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar.
日本語の概要は準備中です。原文の説明を表示しています。
Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
日本語の概要は準備中です。原文の説明を表示しています。
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
日本語の概要は準備中です。原文の説明を表示しています。
Get a deep critical review of research from a selected reviewer (Codex by default, Gemini, Grok, Claude Code, or manual). Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
日本語の概要は準備中です。原文の説明を表示しています。
执行ARIS auto-review-loop的数学路线适配,准备具体方法,经真实research-review、持续reviewer memory、实际推导或探针、修复复核与逐轮恢复,交付可执行求解路线和未证义务。用于选择或改造证明方法及重判卡住的路线;完整证明验收交给mathrsi-verify。
日本語の概要は準備中です。原文の説明を表示しています。
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
日本語の概要は準備中です。原文の説明を表示しています。
Persistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.
日本語の概要は準備中です。原文の説明を表示しています。
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
日本語の概要は準備中です。原文の説明を表示しています。
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
日本語の概要は準備中です。原文の説明を表示しています。
Fill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers/ as TODO scaffolds.
日本語の概要は準備中です。原文の説明を表示しています。
Autonomous multi-round research review loop. Uses a fresh Codex agent or selected Gemini, Grok, or Claude Code reviewer, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
日本語の概要は準備中です。原文の説明を表示しています。
Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved, with a fresh landing review and human approval. Base Codex review is same-family provisional. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.
日本語の概要は準備中です。原文の説明を表示しています。
Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact.
日本語の概要は準備中です。原文の説明を表示しています。