[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85559-en":3,"doc-seo-85559-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},85559,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","From Paper to Program Knowledge Externalization and Bottleneck Diagnosis in AI-Assisted Quantum Many-Body Programming","Large language models can generate scientific code, but paper-to-program translation fails when correctness relies on tacit conventions rather than explicit equations. The work frames this as a knowledge-externalization problem: index choices, gauges, fermionic signs, contraction order, validation gates, and scaling constraints must be externalized into structured specifications before code generation. A multi-stage human-in-the-loop workflow is evaluated on quantum many-body tasks with auditable outputs.","arXiv :2604 .04089v5 [physics .comp-ph] 13 Jul 2026  \nFrom Paper to Program: Knowledge Externalization and Bottleneck Diagnosis in AI-Assisted Quantum Many-Body Programming  \nYi Zhou 1, ∗  \n1 Institute of Physics, Chinese Academy of Sciences, Beijing 100190, China  \n(Dated: July 14, 2026)  \nLarge language models can write scientific code, but direct paper-to-program translation remains fragile when correctness depends on tacit conventions rather than explicit equations. We frame this as a knowledge-externalization problem: index choices, gauges, fermionic signs, contraction order, validation gates, and scaling constraints must be made explicit before code generation. We evaluate a multi-stage, human-in-the-loop workflow on two quantum many-body tasks. DMRG from Schollw¨ock’s pedagogical review serves as calibration: specification-guided implementations pass in all 16 model pairings, compared with 6/13 direct attempts, and a prose-specification ablation shows that externalized content, not LATEX form, is the active ingredient. Pfaffian conversion of HFB states to MPS from the five-page Letter by Jin et al. serves as the stress test: the archived runs use a closed-world NumPy/SciPy/Matplotlib protocol, with no TeNPy, TeMFpy, or external implementation code supplied to the agents, so success depends on reconstructing tacit sign, gauge, ordering, and scalability conventions within a restricted dependency setting. Here the workflow yields 11/26 audited passes, while direct prompting yields none. Cross-specification transfer is asymmetric: nonGPT specifications implemented by GPT 5.5 pass 4/4, whereas GPT 5.5 specifications implemented by the tested non-GPT models fail 4/4 . The contrast supports a two-bottleneck picture. Externalization resolves the first bottleneck—paper-to-code ambiguity—well enough to make DMRG reproducible and Pfaffian-MPS auditable. The remaining failures expose a second bottleneck in implementation-model capability. Iterative meta-specification moves this boundary but does not eliminate it. The resulting Paper-to-Program Many-Body skill is both a reusable implementation protocol and a diagnostic instrument for AI-assisted many-body programming.  \nI. INTRODUCTION  \nA central challenge in computational science is the translation of formal theory into reliable, scalable code. Although this step is essential for scientific progress, it is often slow, error-prone, and dependent on substantial tacit expertise. Large language models (LLMs) now offer a compelling possibility: direct conversion of research papers into executable scientific software. In practice, however, this promise remains difficult to realize for algorithms whose correctness depends on precise mathematical structure. The challenge is not only that scientific code must be syntactically correct, but that it must also preserve structural assumptions—index conventions, contraction logic, gauge constraints, numerical stability, and memory scaling—that are rarely made fully explicit in the source literature.  \nWe argue that the failure of direct AI-assisted scientific programming is fundamentally a knowledgeexternalization problem. Research papers are written for human interpretation, not for unambiguous machine execution. Implementation-critical details are compressed into notation, omitted as tacit knowledge, or left to the reader’s technical judgment. When these implicit constraints are not made explicit, even highly capable models must infer them, and the resulting code becomes fragile. The central obstacle is not code generation alone, but the absence of an intermediate document that  \n∗ [yizhou@iphy.ac.cn](yizhou@iphy.ac.cn)  \nmakes explicit the computational knowledge required for implementation—knowledge that is present in no single source but must be actively externalized from the interplay of theory, convention, and numerical practice. In this work, knowledge externalization refers specifically to the active process of transforming this tacit e","cbCainQBtbRs2pau","https://ap.wps.com/l/cbCainQBtbRs2pau","pdf",2964223,2,1,19,"English","en",105,"# Introduction\n## Knowledge-externalization framing\n## Quantum many-body as a testing ground","[{\"question\":\"Why does direct paper-to-program translation by LLMs often break down for quantum many-body algorithms?\",\"answer\":\"Because correctness depends on structural assumptions and conventions that are typically compressed into notation or omitted as tacit expertise, such as index conventions, gauges, and contraction logic. When these are not made explicit, generated code becomes fragile.\"},{\"question\":\"What is meant by “knowledge externalization” in this work?\",\"answer\":\"Transforming tacit computational expertise into an explicit, structured specification that can be reviewed and validated by implementation agents. The goal is to remove reliance on implicit reader judgment during code generation.\"},{\"question\":\"How does the proposed HITL workflow improve reliability compared with direct prompting?\",\"answer\":\"It reconstructs implementation-critical details under explicit dependency and validation constraints, producing high rates of audited passes on the tested tasks. In contrast, direct prompting fails to produce any successful audited implementations in the reported stress tests.\"}]",1784204562,48,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"from-paper-to-program-knowledge-externalization-and-bottleneck-diagnosis-in-ai-assisted-quantum-many-body-programming","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/from-paper-to-program-knowledge-externalization-and-bottleneck-diagnosis-in-ai-assisted-quantum-many-body-programming/85559/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-20","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why does direct paper-to-program translation by LLMs often break down for quantum many-body algorithms?","Question",{"text":75,"@type":76},"Because correctness depends on structural assumptions and conventions that are typically compressed into notation or omitted as tacit expertise, such as index conventions, gauges, and contraction logic. When these are not made explicit, generated code becomes fragile.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is meant by “knowledge externalization” in this work?",{"text":80,"@type":76},"Transforming tacit computational expertise into an explicit, structured specification that can be reviewed and validated by implementation agents. The goal is to remove reliance on implicit reader judgment during code generation.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed HITL workflow improve reliability compared with direct prompting?",{"text":84,"@type":76},"It reconstructs implementation-critical details under explicit dependency and validation constraints, producing high rates of audited passes on the tested tasks. In contrast, direct prompting fails to produce any successful audited implementations in the reported stress tests.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]