Hugging Face Daily Papers · · 3 min read

PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation

Mirrored from Hugging Face Daily Papers for archival readability. Support the source by reading on the original site.

.</p>\n","updatedAt":"2026-09-03T02:09:54.682Z","author":{"_id":"652066649004117947e46ed6","avatarUrl":"/avatars/972c97df6f26d2c3d6ce71ec579984bb.svg","fullname":"Jaehong Yoon","name":"jaehong31","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":5,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"fr","probability":0.32275810837745667},"editors":["jaehong31"],"editorAvatarUrls":["/avatars/972c97df6f26d2c3d6ce71ec579984bb.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2609.02272","authors":[{"_id":"6a98d6d7fea818274321fe6b","name":"Yunhao Liu","hidden":false},{"_id":"6a98d6d7fea818274321fe6c","name":"Hong Phuc Pham","hidden":false},{"_id":"6a98d6d7fea818274321fe6d","name":"Jaehong Yoon","hidden":false}],"publishedAt":"2026-09-02T00:00:00.000Z","submittedOnDailyAt":"2026-09-03T00:00:00.000Z","title":"PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation","submittedOnDailyBy":{"_id":"652066649004117947e46ed6","avatarUrl":"/avatars/972c97df6f26d2c3d6ce71ec579984bb.svg","isPro":false,"fullname":"Jaehong Yoon","user":"jaehong31","type":"user","name":"jaehong31"},"summary":"Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated repositories to preserve method logic, evaluation protocols, and cross-file consistency. Despite recent advances in paper-to-code agents, their intermediate outputs are often presented as free-form plans or summaries that downstream coding agents may ignore, reinterpret, or compress, leading to algorithmic simplification and inconsistent repository structure. To address these challenges, we introduce PaperCompiler, a paper-to-code generation framework that compiles paper-grounded evidence into explicit repository-level implementation specifications. PaperCompiler grounds implementation-relevant evidence while preserving source provenance and distinguishing paper-supported, inferred, externally delegated, and unresolved information. The resulting specifications encode non-degradation requirements, ownership assignments, cross-file dependencies, and file-level constraints. Repository generation proceeds under these compiled specifications while retaining flexibility over local engineering choices not fixed by the paper. PaperCompiler outperforms strong baselines on Paper2CodeBench, achieving a 13.8% relative improvement in reference-based fidelity (from 3.64 to 4.15) and reducing high-severity evaluator critiques (from 13.2% to 6.1%).","upvotes":5,"discussionId":"6a98d6d7fea818274321fe6e","githubRepo":"https://github.com/Daethalous/PaperCompiler","githubRepoAddedBy":"user","ai_summary":"PaperCompiler converts research papers into structured repository specifications that preserve method logic and cross-file consistency, improving code fidelity and reducing critical errors.","ai_keywords":["paper-to-code generation","repository-level specifications","cross-file dependencies","non-degradation requirements","provenance tracking","PaperCompiler","Paper2CodeBench"],"ai_summary_model":"thinkingmachines/Inkling-Small","organization":{"_id":"6371470aafbe42caa5a76208","name":"nanyang-technological-university-singapore","fullname":"Nanyang Technological University Singapore","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/637146c5afbe42caa5a75e1b/sZyHSA1AQaAS4nrGan682.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"652066649004117947e46ed6","avatarUrl":"/avatars/972c97df6f26d2c3d6ce71ec579984bb.svg","isPro":false,"fullname":"Jaehong Yoon","user":"jaehong31","type":"user"},{"_id":"63ac5701c21e60a3e9b58aa7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ac5701c21e60a3e9b58aa7/g6EX7diOpuA94R2ab-rZC.png","isPro":true,"fullname":"Dipankar Sarkar","user":"dipankarsarkar","type":"user"},{"_id":"69bcf5d20b92270da8a7c503","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/MjiG7LPVr9s8Y0lX5P7Jp.png","isPro":false,"fullname":"佐々木 咲良","user":"lucasifg4","type":"user"},{"_id":"6a2da6c8ca070ee12c6e396c","avatarUrl":"/avatars/0355287dcabaa67dbc7f0b10b87451f9.svg","isPro":false,"fullname":"Joe Mama","user":"JoeMama123123123","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"6371470aafbe42caa5a76208","name":"nanyang-technological-university-singapore","fullname":"Nanyang Technological University Singapore","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/637146c5afbe42caa5a75e1b/sZyHSA1AQaAS4nrGan682.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2609/2609.02272.md","query":{}}">
Papers
arxiv:2609.02272

PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation

Published on Sep 2
· Submitted by
Jaehong Yoon
on Sep 3
Authors:
,

Abstract

PaperCompiler converts research papers into structured repository specifications that preserve method logic and cross-file consistency, improving code fidelity and reducing critical errors.

Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated repositories to preserve method logic, evaluation protocols, and cross-file consistency. Despite recent advances in paper-to-code agents, their intermediate outputs are often presented as free-form plans or summaries that downstream coding agents may ignore, reinterpret, or compress, leading to algorithmic simplification and inconsistent repository structure. To address these challenges, we introduce PaperCompiler, a paper-to-code generation framework that compiles paper-grounded evidence into explicit repository-level implementation specifications. PaperCompiler grounds implementation-relevant evidence while preserving source provenance and distinguishing paper-supported, inferred, externally delegated, and unresolved information. The resulting specifications encode non-degradation requirements, ownership assignments, cross-file dependencies, and file-level constraints. Repository generation proceeds under these compiled specifications while retaining flexibility over local engineering choices not fixed by the paper. PaperCompiler outperforms strong baselines on Paper2CodeBench, achieving a 13.8% relative improvement in reference-based fidelity (from 3.64 to 4.15) and reducing high-severity evaluator critiques (from 13.2% to 6.1%).

Community

Paper submitter about 7 hours ago
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images

· Sign up or log in to comment

Get this paper in your agent:

hf papers read 2609.02272
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper

No model linking this paper

Cite arxiv.org/abs/2609.02272 in a model README.md to link it from this page.

Datasets citing this paper

No dataset linking this paper

Cite arxiv.org/abs/2609.02272 in a dataset README.md to link it from this page.

Spaces citing this paper

No Space linking this paper

Cite arxiv.org/abs/2609.02272 in a Space README.md to link it from this page.

Collections including this paper

No Collection including this paper

Add this paper to a collection to link it from this page.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Hugging Face Daily Papers