[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-phd-researcher-lit-code-es":3,"seo:pack:phd-researcher-lit-code:es":98},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":97},"phd-researcher-lit-code","🎓","#7C2D12","new","Nuevo · esta semana","Pack PhD: Literatura + Código de Investigación","Diez picks para el PhD que hace revisión bibliográfica seria e intenta reproducir código de papers: Zotero, arXiv MCP, GPT Researcher, agente academic-researcher, Marker, Nougat, JupyterLab, Papermill, Overleaf, AI Scientist. Búsqueda → gestor → parseo PDF → lectura → reproducción → escritura.",[16,28,38,46,53,61,68,74,81,87],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4612,"74dca4cd-5468-11f1-9bc6-00163e2b0d79","zotero-free-research-source-manager-citation-tool-74dca4cd","Zotero — Free Research Source Manager and Citation Tool","Zotero is a free, open-source reference management tool that helps you collect, organize, annotate, cite, and share research sources. Available on Windows, macOS, Linux, and iOS, it supports one-click saving from browsers and generates citations in thousands of styles.","AI Open Source",32,0,"en","skill","Skill",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":34,"view_count":35,"vote_count":24,"lang_type":25,"type":36,"type_label":37},3201,"c1c31b4a-7f40-4b0a-9304-122f7d9b00d1","arxiv-mcp-server-search-and-analyze-papers","arXiv MCP Server — Search and Analyze Papers","arxiv-mcp-server is an MCP server for searching and analyzing arXiv papers, with uvx\u002Fuv tool stdio launch examples for reproducible research workflows.","MCP Hub",69,"mcp","MCP",{"id":39,"uuid":40,"slug":41,"title":42,"description":43,"author_name":44,"view_count":45,"vote_count":24,"lang_type":25,"type":26,"type_label":27},25,"23330210-b26a-4d97-ad97-1735c203eaa6","gpt-researcher-autonomous-research-report-agent-23330210","GPT Researcher — Autonomous Research Report Agent","AI agent that generates detailed research reports from a single query. Searches multiple sources, synthesizes findings, and cites references.","TokRepo精选",565,{"id":47,"uuid":48,"slug":49,"title":50,"description":51,"author_name":44,"view_count":52,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4354,"ed4529f4-7ba4-4886-8c82-10e48d5a0a5f","claude-code-agent-academic-researcher-ed4529f4","Claude Code Agent: Academic Researcher","Academic research specialist for scholarly sources, peer-reviewed papers, and academic literature. Use PROACTIVELY for research paper analysis, literature reviews, citation...",36,{"id":54,"uuid":55,"slug":56,"title":57,"description":58,"author_name":59,"view_count":60,"vote_count":24,"lang_type":25,"type":26,"type_label":27},210,"42976daf-a56a-4152-9afb-d5b00d130a08","marker-convert-pdf-markdown-high-accuracy-42976daf","Marker — Convert PDF to Markdown with High Accuracy","Fast, accurate PDF to Markdown + JSON converter. Handles tables, images, equations, code blocks, and multi-column layouts. GPU-accelerated. 33K+ GitHub stars.","Script Depot",135,{"id":62,"uuid":63,"slug":64,"title":65,"description":66,"author_name":22,"view_count":67,"vote_count":24,"lang_type":25,"type":26,"type_label":27},4670,"ed1264b8-54cb-11f1-9bc6-00163e2b0d79","nougat-neural-optical-understanding-academic-documents-ed1264b8","Nougat — Neural Optical Understanding for Academic Documents","Nougat is a visual transformer model from Meta that converts academic PDF pages into structured Markdown, accurately preserving mathematical equations, tables, and text formatting.",20,{"id":69,"uuid":70,"slug":71,"title":72,"description":73,"author_name":22,"view_count":35,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2527,"4de315f7-4686-11f1-9bc6-00163e2b0d79","jupyterlab-next-generation-interactive-development-4de315f7","JupyterLab — Next-Generation Interactive Development Environment","The extensible web-based IDE for notebooks, code, and data from Project Jupyter, succeeding the classic Jupyter Notebook interface.",{"id":75,"uuid":76,"slug":77,"title":78,"description":79,"author_name":22,"view_count":80,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2411,"4be4a73a-4492-11f1-9bc6-00163e2b0d79","papermill-parameterize-execute-jupyter-notebooks-4be4a73a","Papermill — Parameterize and Execute Jupyter Notebooks","Papermill is a Python tool for parameterizing, executing, and analyzing Jupyter notebooks programmatically, enabling notebook-based pipelines and report generation.",130,{"id":82,"uuid":83,"slug":84,"title":85,"description":86,"author_name":59,"view_count":35,"vote_count":24,"lang_type":25,"type":26,"type_label":27},1808,"8d4b8be6-3c4d-11f1-9bc6-00163e2b0d79","overleaf-self-hosted-collaborative-latex-editor-8d4b8be6","Overleaf — Self-Hosted Collaborative LaTeX Editor","Overleaf is an open-source web-based LaTeX editor that enables real-time collaborative document editing. Self-host it with Docker to keep your academic papers and technical documents on your own infrastructure.",{"id":88,"uuid":89,"slug":90,"title":91,"description":92,"author_name":93,"view_count":94,"vote_count":24,"lang_type":25,"type":95,"type_label":96},622,"0a2623ca-92b3-4fba-82e0-fc9a7cda45bd","ai-scientist-automated-research-paper-generation-0a2623ca","AI Scientist — Automated Research Paper Generation","Fully automated AI system that conducts research, runs experiments, and writes complete scientific papers. Generates novel ideas, implements them, and produces LaTeX manuscripts. 12,000+ stars.","Prompt Lab",165,"prompt","Prompt","tokrepo install pack\u002Fphd-researcher-lit-code",{"pageType":99,"pageKey":8,"locale":25,"title":100,"metaDescription":101,"h1":102,"tldr":103,"bodyMarkdown":104,"faq":105,"schema":121,"internalLinks":127,"citations":140,"wordCount":153,"generatedAt":154},"pack","PhD Researcher's Literature + Code Pack — 10 Tools for Lit Review and Reproducing Paper Code","Zotero, arXiv MCP, GPT Researcher, Claude academic-researcher agent, Marker, Nougat, JupyterLab, Papermill, Overleaf, AI Scientist — a deliberate pipeline for the PhD doing serious literature review and trying to actually reproduce the code in the papers they cite. Install in order.","PhD Researcher's Literature + Code Pack — 10 Picks for Lit Review and Code Repro","Ten open-source tools in install order for the working PhD: lit search → reference manager → PDF-to-clean-markdown → reading + summarization → notebook environment for reproducing code → LaTeX for writing. AI assists, it doesn't replace reading the methodology.","## What's in this pack\n\nThis is the rig for the PhD student or postdoc who is past the \"chat with ChatGPT about my topic\" phase and into the much harder work of (a) reading 200 papers properly, (b) tracking what cites what, (c) actually running the code the authors released, and (d) eventually writing something defensible. Every pick here is **open-source**, **actively maintained**, and earns its slot in the pipeline.\n\nThe sharp edge of this pack is that it refuses to pretend AI is a substitute for reading the methodology section. AI is in the loop for **lit triage**, **PDF cleanup**, **first-pass summarization**, **code-repro debugging**, and **drafting** — but a PhD who doesn't actually read the methods is a PhD whose thesis defense goes badly. The tools are arranged so the AI never sits between you and the paper itself, only around it.\n\n## Install in this order\n\n1. **Zotero** — reference manager. Start here, on day one of the PhD. Browser connector grabs metadata + PDF in one click, organizes into collections, syncs across devices, generates BibTeX. If you don't have a single source of truth for citations from week one, you will pay for it in month 36.\n2. **arXiv MCP Server** — programmatic paper search from inside Claude \u002F Cursor \u002F any MCP-aware client. Search arXiv, fetch metadata and full text, hand a paper to the model with one tool call. The replacement for \"open browser, search, copy DOI, paste back\".\n3. **GPT Researcher** — autonomous lit-review agent. Given a query (\"transformer scaling laws compute-optimal training\"), it searches multiple sources, synthesizes findings, cites references, produces a draft survey. Use as the **first-pass map** of an unfamiliar subfield — never as the final citation list.\n4. **Claude Code Agent: Academic Researcher** — a Claude Code subagent tuned for academic workflows: structured paper reading, methodology extraction, citation graph traversal. Lives in your Claude Code project so prompts and conventions are version-controlled with your thesis repo.\n5. **Marker** — PDF → clean Markdown converter. The single biggest unlock for AI-assisted reading. Marker handles math, tables, figures, multi-column layouts. Convert a 40-page paper to Markdown once, then any LLM can ingest it cleanly without OCR noise eating the methodology.\n6. **Nougat** — Meta's neural OCR specifically trained on academic documents. Where Marker is fast and general, Nougat is the heavyweight for **equation-dense** papers (theoretical ML, physics, math). LaTeX-aware output. Use it when Marker garbles a critical proof.\n7. **JupyterLab** — the notebook IDE where you actually run the paper's released code, modify it, plot variants, sanity-check claims. Multi-document workspace, terminal, file browser. Where reproducibility either happens or doesn't.\n8. **Papermill** — parameterize and execute notebooks from the command line. Critical when you need to sweep the paper's hyperparameter across 12 settings to verify the headline figure isn't a single-seed accident. Pairs with JupyterLab for production-grade experiment runs.\n9. **Overleaf (self-hosted)** — collaborative LaTeX. The actual writing environment. Self-hosted variant keeps your unpublished thesis off a third-party server, which matters in fields with strict IP \u002F embargo rules. BibTeX flows in directly from Zotero.\n10. **AI Scientist** — Sakana AI's automated end-to-end paper generation system. Not for generating your actual thesis (don't), but a fascinating reference for what the frontier of AI-assisted scientific writing looks like, and a useful tool for generating ablation-experiment writeup drafts you then heavily edit.\n\n## How they fit together (research workflow)\n\n```\n  Lit search\n  ┌────────────────────────────────────┐\n  │ arXiv MCP ──► GPT Researcher       │\n  │  (precise)    (broad map)          │\n  └─────────────────┬──────────────────┘\n                    ▼\n         ┌───────────────────┐\n         │  Zotero (truth)   │  ◄── BibTeX out to Overleaf\n         │  collections +    │\n         │  attached PDFs    │\n         └─────────┬─────────┘\n                   ▼\n  PDF parse ┌──────────────────┐\n            │ Marker (fast)    │\n            │ Nougat (math)    │\n            └────────┬─────────┘\n                     ▼ clean markdown\n        ┌─────────────────────────┐\n        │ Academic Researcher     │\n        │ Claude Code agent       │ ── summary, citation graph, gaps\n        └──────────┬──────────────┘\n                   ▼\n         Reproduce code\n         ┌───────────────────┐\n         │ JupyterLab        │\n         │   + Papermill     │ ── seed sweeps, ablations\n         └────────┬──────────┘\n                  ▼\n            Writing\n         ┌───────────────────┐\n         │ Overleaf          │  ◄── citations from Zotero\n         │ + AI Scientist    │      (draft only — you write)\n         └───────────────────┘\n```\n\nThe spine is **Zotero as the single source of truth for what you've read**. Everything upstream feeds Zotero; everything downstream reads from it. Without that discipline, the whole pipeline rots into a 4,000-tab browser and a thesis you can't reproduce.\n\n## Tradeoffs you'll hit\n\n- **AI summarizing vs actually reading** — The biggest risk in this pack. GPT Researcher and the Academic Researcher agent will happily summarize a paper in 30 seconds. That summary is **good enough to decide whether to read the paper** and **dangerously misleading as a substitute for reading the methodology**. Hard rule: if you cite a paper in your thesis, you read the methods section unaided. AI is for triage, not for cite-by-vibes.\n- **Reproducibility ceiling** — Papermill + JupyterLab let you run released code cleanly, but plenty of papers release code that no longer runs (dead dependencies, missing weights, wrong CUDA version). Budget time for environment archaeology. Pin everything in a `conda env export`. If a paper's claim collapses on rerun, that's a finding worth a footnote.\n- **Marker vs Nougat** — Marker is faster and handles tables well; Nougat is slower but actually parses LaTeX equations correctly. Run Marker first; reach for Nougat only when the math is the point.\n- **Self-hosted Overleaf vs the SaaS** — SaaS Overleaf is convenient but your draft is on someone else's machine. Self-hosted on your university cluster (or just a Docker container) is the right call for unpublished work. The cost is one afternoon of setup.\n- **AI Scientist as a tool, not a goal** — Generating papers end-to-end with AI is academically and ethically fraught. Treat it as a reference architecture for what's possible, and as a draft-generator for ablation tables — never as a way to bypass the actual scientific contribution.\n\n## Common pitfalls\n\n- **Over-trusting an AI summary of a methodology** — Summarizers compress; methodology details (loss formulation, regularization, data splits) are exactly what gets compressed away. Reviewers ask about exactly the details a summary drops. Read the methods.\n- **Zotero PDFs scattered across devices** — turn on WebDAV \u002F your own sync target on day one. Discovering on year 3 that half your annotated PDFs only exist on a dead laptop is the canonical PhD horror story.\n- **Notebook-only reproduction** — a paper's `figure_3.ipynb` may run end-to-end but skip the actual training. Read what the notebook **does** before declaring \"reproduced\".\n- **arXiv-only literature** — arXiv is fast but biased toward ML \u002F physics \u002F math. For most of biology, social science, and humanities, the lit lives in journals reachable only via institutional access. Use the arXiv MCP for what arXiv covers, not as a universal source.\n- **Conflating BibTeX entries** — Zotero will happily import the same paper twice with slightly different metadata if you click the connector on both arXiv and the journal version. Run a duplicate check before every chapter handoff.",[106,109,112,115,118],{"q":107,"a":108},"I'm at the start of my PhD — do I really need all ten of these on day one?","No — install Zotero, JupyterLab, and Overleaf in week one, because those three become muscle memory and migration cost compounds. Add arXiv MCP and the academic-researcher agent in month two once you've found your subfield. Marker, Nougat, Papermill, and AI Scientist arrive when you hit the specific problem each solves — don't preinstall solutions to problems you don't have yet.",{"q":110,"a":111},"Can an AI agent actually do my literature review for me?","Not in any way that survives a thesis defense. GPT Researcher and the academic-researcher agent are excellent at producing a first-pass map of an unfamiliar field — that map is roughly the quality of a third-year undergrad's literature review. Use it to find the seminal papers and identify the major camps, then read those papers yourself. Submitting an AI-generated review as your literature chapter is plagiarism in most universities and intellectual self-sabotage in all of them.",{"q":113,"a":114},"Marker or Nougat — which PDF-to-text tool should I install first?","Install Marker first. It's faster, handles tables and figures well, and covers 90% of papers acceptably. Add Nougat when you start working with equation-heavy theoretical papers — Nougat was trained specifically on academic documents and preserves LaTeX math far better. Running both and picking per-paper is also fine; storage and compute are cheap, missed equations are not.",{"q":116,"a":117},"How do I keep my PhD reproducible if I'm running 50 different notebooks across different papers?","Three rules. (1) Every reproduction lives in its own directory with its own `environment.yml` or `requirements.txt` pinned to exact versions. (2) Use Papermill to invoke notebooks via parameters rather than editing in-place — the source notebook stays clean, the run record stays auditable. (3) Save the executed notebook + outputs alongside the input parameters, so two years later you can prove what you ran. Conda environments, git, and a `RUNS\u002F` directory of executed Papermill outputs solve 95% of reproducibility pain.",{"q":119,"a":120},"Is it ethical to use AI Scientist or Claude to help write my thesis?","Depends entirely on your university's policy and your honest disclosure. Common consensus as of 2026: AI is fine for outlining, grammar, idea-stress-testing, and generating draft prose you then heavily rewrite — the same way a writing tutor would help. AI is not fine for generating original analysis, fabricating citations, or producing prose you submit unedited. When in doubt, disclose in the methods section. The point of a PhD is that you can defend every sentence; if you can't defend a paragraph an AI wrote, don't include it.",{"@context":122,"@type":123,"name":124,"description":125,"numberOfItems":126,"inLanguage":25},"https:\u002F\u002Fschema.org","ItemList","PhD Researcher's Literature + Code Pack","Ten open-source tools curated for PhD-level literature review, paper PDF management, citation tracking, reproducing code from papers, and academic writing.",10,[128,132,136],{"url":129,"anchor":130,"reason":131},"\u002Fen\u002Fai-tools-for\u002Fresearch","AI tools for research workflows","Broader catalog of research-adjacent assets beyond this pack",{"url":133,"anchor":134,"reason":135},"\u002Fen\u002Ftopics","Browse other topic packs","Adjacent packs cover RAG, agent memory, and second-brain workflows that overlap with lit review",{"url":137,"anchor":138,"reason":139},"\u002Fen\u002Ffeatured","Featured assets on TokRepo","These ten tools sit alongside the broader curated catalog",[141,145,149],{"claim":142,"source_name":143,"source_url":144},"Zotero is a free, open-source reference manager with browser connector and BibTeX export","Zotero official site","https:\u002F\u002Fwww.zotero.org\u002F",{"claim":146,"source_name":147,"source_url":148},"Nougat is a neural OCR system specifically trained on academic documents","Nougat GitHub","https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fnougat",{"claim":150,"source_name":151,"source_url":152},"Papermill parameterizes and executes Jupyter notebooks from the command line","Papermill docs","https:\u002F\u002Fpapermill.readthedocs.io\u002F",910,"2026-05-22T00:00:00Z"]