◇ Paper · Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search

{
  "schema_version": "0.5",
  "entry_id": "ASR-PAPER-20260818-2608-15669",
  "record_type": "paper",
  "title": "今日论文 · Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search",
  "observed_at": "2026-08-18",
  "source": {
    "name": "huggingface.co/api/daily_papers",
    "url": "https://huggingface.co/api/daily_papers?limit=10",
    "snapshot_hash": "652c1f13fb67dd93f7d60fecc11565d77173419a1e4693958922f4b73738fb42",
    "fetched_at": "2026-08-18T10:51:18+00:00"
  },
  "confidence": "medium",
  "human_stream": {
    "summary": "Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epi",
    "key_points": [
      "论文 ID 2608.15669",
      "作者 Zhongwei Yu、Yan Song、Xue Yan、Anjie Liu、Xingyu Lu、Yihang Chen",
      "发布 2026-08-16T00:00:00.000Z"
    ],
    "note": "来源为 HuggingFace daily papers 公开 API；完整阅读请走原文链接。",
    "what_it_is": "今日论文《今日论文 · Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search》（Zhongwei Yu、Yan Song、Xue Yan、Anjie Liu、Xingyu Lu、Yihang Chen），来自 HF Daily Papers 公开源。",
    "worth_it": "进入 HF 每日精选说明有社区关注度；是否与你的问题相关需要读原文判断，本条目不评价研究质量。",
    "how_to_start": "先读摘要，需要再读全文（https://huggingface.co/papers/2608.15669）；对照论文 ID（2608.15669）可找实现与讨论。",
    "evidence": [
      "论文 ID 2608.15669",
      "作者 Zhongwei Yu、Yan Song、Xue Yan、Anjie Liu、Xingyu Lu、Yihang Chen"
    ],
    "cautions": "摘要来自作者原文，未做同行评议级核验；引用请以正式发表版本为准。"
  },
  "ai_stream": {
    "structured": {
      "paper_id": "2608.15669",
      "title": "Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search",
      "authors": [
        "Zhongwei Yu",
        "Yan Song",
        "Xue Yan",
        "Anjie Liu",
        "Xingyu Lu",
        "Yihang Chen",
        "Huichi Zhou",
        "Siyuan Guo",
        "Luoyang Sun",
        "Sihan Chen",
        "Xiangning Yu",
        "Jun Wang"
      ],
      "published_at": "2026-08-16T00:00:00.000Z",
      "url": "https://huggingface.co/papers/2608.15669",
      "source_label": "hf-daily-papers"
    },
    "raw": [
      {
        "paper_id": "2608.15669",
        "title": "Large Discovery Models: Empirically-grounded Model-Based Open-Ended Search",
        "authors": [
          "Zhongwei Yu",
          "Yan Song",
          "Xue Yan",
          "Anjie Liu",
          "Xingyu Lu",
          "Yihang Chen",
          "Huichi Zhou",
          "Siyuan Guo",
          "Luoyang Sun",
          "Sihan Chen",
          "Xiangning Yu",
          "Jun Wang"
        ],
        "summary": "Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs. Generative models such as large language models (LLMs) provide expressive priors over such spaces, but their likelihoods and self-assessments are unreliable proxies for the objectives and calibrated epistemic uncertainty, especially for novel candidates outside the observed data distribution. We introduce the Large Discovery Model (LDM), an empirically grounded recurrent architecture that couples a ",
        "published_at": "2026-08-16T00:00:00.000Z",
        "submitted_on_daily_at": null,
        "url": "https://huggingface.co/papers/2608.15669"
      }
    ]
  },
  "token_cost": {
    "total": 0.0,
    "currency": "USD",
    "breakdown": {
      "crawl": 0.0,
      "clean": 0.0,
      "elevate": 0.0,
      "verify": 0.0
    }
  },
  "machine_verified": true,
  "review": {
    "status": "agent_reviewed",
    "reviewer": "pipeline-validate",
    "reviewed_at": "2026-08-18T10:54:20+00:00",
    "comments": "机检通过（schema 0 error + 溯源一致 + 成本达标）"
  },
  "provenance": {
    "extracted_by": "codex",
    "extracted_at": "2026-08-18T10:53:05+00:00",
    "pipeline": "collect_hf_papers.py + build_entries.py v0.2（规则管线）",
    "access_urls": [
      "https://huggingface.co/api/daily_papers?limit=10"
    ],
    "card_generated_at": "2026-08-18T10:53:05+00:00",
    "card_pipeline": "enrich_human_stream.py v0.1（规则模板，零 Token）"
  }
}