Hugging Face Daily Papers · · 5 min read

PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams

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

Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which interests shift and feedback accumulates. We introduce PaperFlow, a framework that organizes it into three coupled stages: Profiling, which constructs and maintains a structured, inspectable scholarly profile from heterogeneous cold-start evidence; Recommending, which ranks each date-specific paper stream through multi-signal aggregation under a fixed display budget; and Adapting, which updates user state from semantically distinct feedback signals and models interest drift across days. We further define a longitudinal user-day benchmark that fixes users, dates, candidate pools, visible inputs, and hidden simulated relevance labels under a shared temporal information boundary. The benchmark contains 24 simulated research users, 50 daily paper streams, 1,200 user-day episodes, 20,727 unique papers, and 497,448 episode-paper records. We additionally specify a blind human-evaluation protocol to validate alignment between automatic metrics and expert judgments. Experiments against five scientific recommendation baselines show that PaperFlow achieves the strongest oracle-based ranking, the highest behavioral alignment with simulated reading selections, and the best blind human-evaluation score.</p>\n","updatedAt":"2026-06-08T03:16:48.550Z","author":{"_id":"64be296a46cc3cdfbb057f7e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64be296a46cc3cdfbb057f7e/jSHeNY2AcPifCZzJyFhr4.jpeg","fullname":"Cheng Tan","name":"chengtan9907","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":7,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8711252808570862},"editors":["chengtan9907"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/64be296a46cc3cdfbb057f7e/jSHeNY2AcPifCZzJyFhr4.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2606.07454","authors":[{"_id":"6a2633c1e4c258a029492016","name":"Fuqiang Wang","hidden":false},{"_id":"6a2633c1e4c258a029492017","name":"Song Tan","hidden":false},{"_id":"6a2633c1e4c258a029492018","name":"Zheng Guo","hidden":false},{"_id":"6a2633c1e4c258a029492019","name":"Jiaohao Fu","hidden":false},{"_id":"6a2633c1e4c258a02949201a","name":"Xinglong Xu","hidden":false},{"_id":"6a2633c1e4c258a02949201b","name":"Bihui Yu","hidden":false},{"_id":"6a2633c1e4c258a02949201c","name":"Jie Dong","hidden":false},{"_id":"6a2633c1e4c258a02949201d","name":"Zheng Sun","hidden":false},{"_id":"6a2633c1e4c258a02949201e","name":"Siyuan Li","hidden":false},{"_id":"6a2633c1e4c258a02949201f","name":"Jingxuan Wei","hidden":false},{"_id":"6a2633c1e4c258a029492020","name":"Cheng Tan","hidden":false}],"publishedAt":"2026-06-05T00:00:00.000Z","submittedOnDailyAt":"2026-06-08T00:00:00.000Z","title":"PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams","submittedOnDailyBy":{"_id":"64be296a46cc3cdfbb057f7e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64be296a46cc3cdfbb057f7e/jSHeNY2AcPifCZzJyFhr4.jpeg","isPro":false,"fullname":"Cheng Tan","user":"chengtan9907","type":"user","name":"chengtan9907"},"summary":"Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which interests shift and feedback accumulates. We introduce PaperFlow, a framework that organizes it into three coupled stages: Profiling, which constructs and maintains a structured, inspectable scholarly profile from heterogeneous cold-start evidence; Recommending, which ranks each date-specific paper stream through multi-signal aggregation under a fixed display budget; and Adapting, which updates user state from semantically distinct feedback signals and models interest drift across days. We further define a longitudinal user-day benchmark that fixes users, dates, candidate pools, visible inputs, and hidden simulated relevance labels under a shared temporal information boundary. The benchmark contains 24 simulated research users, 50 daily paper streams, 1,200 user-day episodes, 20,727 unique papers, and 497,448 episode-paper records. We additionally specify a blind human-evaluation protocol to validate alignment between automatic metrics and expert judgments. Experiments against five scientific recommendation baselines show that PaperFlow achieves the strongest oracle-based ranking, the highest behavioral alignment with simulated reading selections, and the best blind human-evaluation score.","upvotes":6,"discussionId":"6a2633c1e4c258a029492021","projectPage":"https://openraiser.github.io/PaperFlow","githubRepo":"https://github.com/OpenRaiser/PaperFlow","githubRepoAddedBy":"user","ai_summary":"PaperFlow is a framework for scientific paper recommendation that processes user profiles, daily paper streams, and interest drift through three stages: profiling, recommending, and adapting, using a longitudinal benchmark with 24 users, 50 daily streams, and 1,200 episodes.","ai_keywords":["scientific paper recommendation","longitudinal process","user profiling","multi-signal aggregation","user state update","interest drift","temporal information boundary","user-day benchmark","oracle-based ranking","behavioral alignment"],"ai_summary_model":"Qwen/Qwen2.5-Coder-32B-Instruct","githubStars":4,"organization":{"_id":"66ce9d1f5e180b9b9c8e6f31","name":"opendatalab","fullname":"OpenDataLab","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/639c3afa7432f2f5d16b7296/yqxxBknyeqkGnYsjoaR4M.png"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"64be296a46cc3cdfbb057f7e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/64be296a46cc3cdfbb057f7e/jSHeNY2AcPifCZzJyFhr4.jpeg","isPro":false,"fullname":"Cheng Tan","user":"chengtan9907","type":"user"},{"_id":"69d74bc2114801b52915e76a","avatarUrl":"/avatars/b3993a22ea768f5a46294cd2a3a2ec0c.svg","isPro":false,"fullname":"谭松","user":"Sereints","type":"user"},{"_id":"69f2096fc43eaf8eb4634141","avatarUrl":"/avatars/5a4321d0af24113c5df2e881faaa4406.svg","isPro":false,"fullname":"tttsss","user":"ttttttttsssssss","type":"user"},{"_id":"69f207e761e7d7772209413b","avatarUrl":"/avatars/073069e6917daf0acbfd3d591a359ae0.svg","isPro":false,"fullname":"1qweq","user":"tttsssxxx","type":"user"},{"_id":"69f2064398c6402a87b214e2","avatarUrl":"/avatars/85e8e1f8da0ac00741068740e918fa85.svg","isPro":false,"fullname":"aaa","user":"tsxtsx","type":"user"},{"_id":"69f20a9722877def46600036","avatarUrl":"/avatars/1022f777ce1d8e3170fa2ab86bb78cdf.svg","isPro":false,"fullname":"sssssqq","user":"ttttttttttaaaann","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"66ce9d1f5e180b9b9c8e6f31","name":"opendatalab","fullname":"OpenDataLab","avatar":"https://cdn-avatars.huggingface.co/v1/production/uploads/639c3afa7432f2f5d16b7296/yqxxBknyeqkGnYsjoaR4M.png"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2606/2606.07454.md"}">
Papers
arxiv:2606.07454

PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams

Published on Jun 5
· Submitted by
Cheng Tan
on Jun 8
Authors:
,
,
,
,
,
,
,
,
,
,

Abstract

PaperFlow is a framework for scientific paper recommendation that processes user profiles, daily paper streams, and interest drift through three stages: profiling, recommending, and adapting, using a longitudinal benchmark with 24 users, 50 daily streams, and 1,200 episodes.

Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which interests shift and feedback accumulates. We introduce PaperFlow, a framework that organizes it into three coupled stages: Profiling, which constructs and maintains a structured, inspectable scholarly profile from heterogeneous cold-start evidence; Recommending, which ranks each date-specific paper stream through multi-signal aggregation under a fixed display budget; and Adapting, which updates user state from semantically distinct feedback signals and models interest drift across days. We further define a longitudinal user-day benchmark that fixes users, dates, candidate pools, visible inputs, and hidden simulated relevance labels under a shared temporal information boundary. The benchmark contains 24 simulated research users, 50 daily paper streams, 1,200 user-day episodes, 20,727 unique papers, and 497,448 episode-paper records. We additionally specify a blind human-evaluation protocol to validate alignment between automatic metrics and expert judgments. Experiments against five scientific recommendation baselines show that PaperFlow achieves the strongest oracle-based ranking, the highest behavioral alignment with simulated reading selections, and the best blind human-evaluation score.

Community

Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which interests shift and feedback accumulates. We introduce PaperFlow, a framework that organizes it into three coupled stages: Profiling, which constructs and maintains a structured, inspectable scholarly profile from heterogeneous cold-start evidence; Recommending, which ranks each date-specific paper stream through multi-signal aggregation under a fixed display budget; and Adapting, which updates user state from semantically distinct feedback signals and models interest drift across days. We further define a longitudinal user-day benchmark that fixes users, dates, candidate pools, visible inputs, and hidden simulated relevance labels under a shared temporal information boundary. The benchmark contains 24 simulated research users, 50 daily paper streams, 1,200 user-day episodes, 20,727 unique papers, and 497,448 episode-paper records. We additionally specify a blind human-evaluation protocol to validate alignment between automatic metrics and expert judgments. Experiments against five scientific recommendation baselines show that PaperFlow achieves the strongest oracle-based ranking, the highest behavioral alignment with simulated reading selections, and the best blind human-evaluation score.

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 2606.07454
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.07454 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.07454 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.07454 in a Space README.md to link it from this page.

Collections including this paper 0

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