From 5333d2bcd3122e1c7092eda158fce58715e53774 Mon Sep 17 00:00:00 2001 From: Chen Gu Date: Sun, 8 Mar 2026 15:07:50 +0800 Subject: [PATCH] Enhance arXiv digest with plain-language Top3 summaries --- org/cases/arxiv_digest/arxiv_daily_digest.py | 18 +++++++++++++++++ org/cases/arxiv_digest/output/2026-03-08.md | 21 +++++++++++++++----- org/cases/arxiv_digest/output/latest.md | 21 +++++++++++++++----- 3 files changed, 50 insertions(+), 10 deletions(-) diff --git a/org/cases/arxiv_digest/arxiv_daily_digest.py b/org/cases/arxiv_digest/arxiv_daily_digest.py index b1e880f..512e99c 100755 --- a/org/cases/arxiv_digest/arxiv_daily_digest.py +++ b/org/cases/arxiv_digest/arxiv_daily_digest.py @@ -105,6 +105,18 @@ def one_liner(p): return f"{t}（{p['primary']}）" +def plain_summary(p): + s = p.get('summary', '') + s = re.sub(r'\s+', ' ', s).strip() + if not s: + return '这篇主要在提出一个新方法，并用实验验证它是否更好。' + # take first sentence-like chunk + chunk = re.split(r'(?<=[\.!?])\s+', s)[0] + if len(chunk) > 120: + chunk = chunk[:117] + '...' + return f"它在做的事：{chunk}" + + def build_digest(papers): # limit scoring set for speed/stability recent_pool = sorted(papers, key=lambda x: x['published'], reverse=True)[:40] @@ -125,6 +137,12 @@ def to_md(hot, latest): lines = [] lines.append(f"# ArXiv Daily Brief - {today}") lines.append('') + lines.append('## 🧠 今日 Top 3（普通人版概述）') + for i, p in enumerate(hot[:3], 1): + lines.append(f"{i}. **{p['title']}**") + lines.append(f" - 一句话看懂: {plain_summary(p)}") + lines.append(f" - 你可能会关心: {one_liner(p)}") + lines.append('') lines.append('## 🔥 今日热度 Top 5（新鲜度+关键词+HN提及+代码线索）') for i, p in enumerate(hot, 1): lines.append(f"{i}. **{p['title']}**") diff --git a/org/cases/arxiv_digest/output/2026-03-08.md b/org/cases/arxiv_digest/output/2026-03-08.md index 62bed32..f797dc7 100644 --- a/org/cases/arxiv_digest/output/2026-03-08.md +++ b/org/cases/arxiv_digest/output/2026-03-08.md @@ -1,25 +1,36 @@ # ArXiv Daily Brief - 2026-03-08 +## 🧠 今日 Top 3（普通人版概述） +1. **SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis** + - 一句话看懂: 它在做的事：Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applic... + - 你可能会关心: SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival An...（cs.LG） +2. **Accelerating Text-to-Video Generation with Calibrated Sparse Attention** + - 一句话看懂: 它在做的事：Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. + - 你可能会关心: Accelerating Text-to-Video Generation with Calibrated Sparse Attention（cs.CV） +3. **Observing and Controlling Features in Vision-Language-Action Models** + - 一句话看懂: 它在做的事：Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. + - 你可能会关心: Observing and Controlling Features in Vision-Language-Action Models（cs.RO） + ## 🔥 今日热度 Top 5（新鲜度+关键词+HN提及+代码线索） 1. **SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis** - arXiv: http://arxiv.org/abs/2603.05483v1 - - 类别: cs.LG | HotScore: 33.06 | 作者: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss + - 类别: cs.LG | HotScore: 32.79 | 作者: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss - 速读: SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival An...（cs.LG） 2. **Accelerating Text-to-Video Generation with Calibrated Sparse Attention** - arXiv: http://arxiv.org/abs/2603.05503v1 - - 类别: cs.CV | HotScore: 28.17 | 作者: Shai Yehezkel, Shahar Yadin, Noam Elata + - 类别: cs.CV | HotScore: 27.9 | 作者: Shai Yehezkel, Shahar Yadin, Noam Elata - 速读: Accelerating Text-to-Video Generation with Calibrated Sparse Attention（cs.CV） 3. **Observing and Controlling Features in Vision-Language-Action Models** - arXiv: http://arxiv.org/abs/2603.05487v1 - - 类别: cs.RO | HotScore: 28.08 | 作者: Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann + - 类别: cs.RO | HotScore: 27.81 | 作者: Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann - 速读: Observing and Controlling Features in Vision-Language-Action Models（cs.RO） 4. **Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation** - arXiv: http://arxiv.org/abs/2603.05485v1 - - 类别: cs.AI | HotScore: 27.06 | 作者: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar + - 类别: cs.AI | HotScore: 26.8 | 作者: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar - 速读: Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation（cs.AI） 5. **An interpretable prototype parts-based neural network for medical tabular data** - arXiv: http://arxiv.org/abs/2603.05423v1 - - 类别: cs.LG | HotScore: 26.1 | 作者: Jacek Karolczak, Jerzy Stefanowski + - 类别: cs.LG | HotScore: 25.83 | 作者: Jacek Karolczak, Jerzy Stefanowski - 速读: An interpretable prototype parts-based neural network for medical tabular data（cs.LG） ## 🆕 最新上新 Top 10 diff --git a/org/cases/arxiv_digest/output/latest.md b/org/cases/arxiv_digest/output/latest.md index 62bed32..f797dc7 100644 --- a/org/cases/arxiv_digest/output/latest.md +++ b/org/cases/arxiv_digest/output/latest.md @@ -1,25 +1,36 @@ # ArXiv Daily Brief - 2026-03-08 +## 🧠 今日 Top 3（普通人版概述） +1. **SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis** + - 一句话看懂: 它在做的事：Estimating heterogeneous treatment effects (HTEs) from right-censored survival data is critical in high-stakes applic... + - 你可能会关心: SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival An...（cs.LG） +2. **Accelerating Text-to-Video Generation with Calibrated Sparse Attention** + - 一句话看懂: 它在做的事：Recent diffusion models enable high-quality video generation, but suffer from slow runtimes. + - 你可能会关心: Accelerating Text-to-Video Generation with Calibrated Sparse Attention（cs.CV） +3. **Observing and Controlling Features in Vision-Language-Action Models** + - 一句话看懂: 它在做的事：Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. + - 你可能会关心: Observing and Controlling Features in Vision-Language-Action Models（cs.RO） + ## 🔥 今日热度 Top 5（新鲜度+关键词+HN提及+代码线索） 1. **SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival Analysis** - arXiv: http://arxiv.org/abs/2603.05483v1 - - 类别: cs.LG | HotScore: 33.06 | 作者: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss + - 类别: cs.LG | HotScore: 32.79 | 作者: Shahriar Noroozizadeh, Xiaobin Shen, Jeremy C. Weiss - 速读: SurvHTE-Bench: A Benchmark for Heterogeneous Treatment Effect Estimation in Survival An...（cs.LG） 2. **Accelerating Text-to-Video Generation with Calibrated Sparse Attention** - arXiv: http://arxiv.org/abs/2603.05503v1 - - 类别: cs.CV | HotScore: 28.17 | 作者: Shai Yehezkel, Shahar Yadin, Noam Elata + - 类别: cs.CV | HotScore: 27.9 | 作者: Shai Yehezkel, Shahar Yadin, Noam Elata - 速读: Accelerating Text-to-Video Generation with Calibrated Sparse Attention（cs.CV） 3. **Observing and Controlling Features in Vision-Language-Action Models** - arXiv: http://arxiv.org/abs/2603.05487v1 - - 类别: cs.RO | HotScore: 28.08 | 作者: Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann + - 类别: cs.RO | HotScore: 27.81 | 作者: Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann - 速读: Observing and Controlling Features in Vision-Language-Action Models（cs.RO） 4. **Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation** - arXiv: http://arxiv.org/abs/2603.05485v1 - - 类别: cs.AI | HotScore: 27.06 | 作者: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar + - 类别: cs.AI | HotScore: 26.8 | 作者: Benjamin Feuer, Lucas Rosenblatt, Oussama Elachqar - 速读: Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation（cs.AI） 5. **An interpretable prototype parts-based neural network for medical tabular data** - arXiv: http://arxiv.org/abs/2603.05423v1 - - 类别: cs.LG | HotScore: 26.1 | 作者: Jacek Karolczak, Jerzy Stefanowski + - 类别: cs.LG | HotScore: 25.83 | 作者: Jacek Karolczak, Jerzy Stefanowski - 速读: An interpretable prototype parts-based neural network for medical tabular data（cs.LG） ## 🆕 最新上新 Top 10