{
"paper_id": "ATT-0086",
"paper_type": "外生变量轻量线性预测及通道卷积插件",
"reading_recommendation": "值得读低成本外生信息融合及重参数化；机制解释和插件普遍改善需降格。",
"detailed_review_zh": "## 总体判断与历史线索\nCrossLinear最有价值的选择，是把多对一预测当作目标明确的任务：只预测需要的内生变量，用一个小卷积整合其他历史变量，再交给共享的patch投影和线性预测头。这比默认把所有变量都预测一遍更贴近许多实际需求，也提供了能接到现有模型前面的简单模块。实验覆盖七个长序列数据集和五个电价市场，同时测试多对一和多对多，工程实用性较好。创新主要在结构约束、残差参数化与评测组织，不能把通道卷积本身看成新的相关性估计理论。\n\n本次先读旧摘要，再独立阅读全文十三页及附录A至E。旧摘要关于缺重复实验、参数化归因和个别退化的线索得到原文支持，但没有沿用其总分。额外发现Traffic的DLinear原始均值与四个跨度数值不一致，足以改变该插件平均改善的方向。旧评全文没有提供，ACM页面版本也未与此arXiv v1逐字比对。\n\n## 方法实际做了什么\n式(7)把标准化后的内外生历史叠为N个通道，用核长3的一维卷积压成一条表示，式(8)再用α保留目标自身的残差。它没有用未来外生观测，因此当前证据是历史协变量辅助预测，不涵盖节假日已知未来值、天气预报轨迹等更广的外生输入接口。方法也不直接计算样本互相关函数，只是学习共享卷积系数；“cross-correlation”应理解为模块命名和结构动机。\n\n固定卷积核确实提供时间共享的归纳偏置，但一层线性融合不能保证只保留真实直接依赖，更不能排除代理变量、共同原因或数据特定的间接关系。图4把核权重求和解释为气象物理关系，缺独立真值或可识别性证明，且后续预测头、残差比例和归一化都会改变整体输入影响。因此单个核的颜色不等于系统的真实依赖强度，结果应称为学习到的权重诊断。\n\n## 重参数化与消融如何理解\n附录B正确指出，在可包含目标恒等映射且卷积无额外约束的条件下，K′=(1−α)K+αS可以把Sum形式吸收进Cross Only卷积；如使用偏置，还需同步缩放偏置。两者表达能力相同并不意味着优化过程相同。表4中Sum优于Cross Only，更合理的解释范围是初始化、残差先验、有效学习率与正则化路径，而非证明模型新增了识别真实依赖的能力。图3显示α初始接近一更好，反而支持这种优化解释。Cross Only对各通道有独立可学习权重，也并不是字面意义上强制所有变量等权。\n\n位置嵌入之后直接展平并通过线性层，固定PE在这种结构中可成为输出偏置的一部分；全局线性头本来也能区分展平位置。所以表10的PE收益可以成立，但不能单独证明“否则模型不知道位置”。类似地，patch投影与线性头连续组合主要改变低秩或分块参数化，其收益需与容量、优化约束区分。以上并非否定简化结构，恰恰说明论文的主要价值可能是良好归纳偏置，而不是更强函数表达类。\n\n## 主结果、基线与任务边界\n表2里CrossLinear相对TimeXer在多数条件较好，ECL平均MSE0.323对0.327，Traffic0.152对0.156，体现了轻量模块的竞争力。但这两个约百分之一至几的优势没有种子离散度，不能直接当稳定领先。ECL-720的0.403反而差于TimeXer0.365，ETTm2-720也不及若干线性方法；电价平均MAE0.266略差于TimeXer0.265。表3多对多Traffic的MSE0.483差于iTransformer0.428，说明简单共享卷积在高维目标联合任务仍有边界。\n\n十个深度基线包含关键TimeXer、iTransformer、PatchTST和轻量线性模型，选择总体合理。但统一长输入96限制了部分基线的最佳状态，所有模型十轮也不等于相同收敛程度。针对电价任务，文中引用NBEATSx却不比较它，也缺统计回归类强基线，因而结论是对所列深度模型的比较。附录说基线遵循原论文或仓库配置，又强调固定十轮，逐模型实际覆盖与调参预算未完全列明。Weather保留异常值并承认其导致归一化误差异常小，值得肯定，但该表难以独立代表真实气象预测效用；不能和多对多Weather或其他处理版本的误差直接横比。\n\n## 插件推广存在明确反例和汇总冲突\n表11中DLinear在Traffic-96从MSE0.268变0.338，退化很明显；ECL平均MAE也由表5的0.457变0.463。更重要的是，原图确认Traffic DLinear四个原始MSE为0.268、0.302、0.298、0.340，简单均值应为0.302，而表2、表5和表11却报0.323。插件后的四行均值为0.308。若逐跨度数字正确，这个模型的平均MSE是变差，不是汇总表展示的改善。MAE同样如此：四行原值均值0.3845，而非所报0.404；加入后均值0.39125，仍是变差。\n\n这里能确认的是“行值、均值和改善叙述不相容”，不能在没有运行记录时断定究竟哪组原始结果是对的，也不能据此指控数据造假。但它实质影响插件推广结论，需要暂停采信该项平均改善。RLinear、SparseTSF等其他表内收益仍有支持，不应一并抹去。相比“确保提高”“几乎无成本”的表述，更准确的是多数配置有潜力，但存在损失、数据和骨干相关的失败情形。\n\n## 鲁棒性、成本与复现\n缺失值实验是有用补充：分别遮掉内生和外生的50%或100%，比较零值与随机噪声。不过没有与其他模型做同样缺失协议的对照，也没有清楚交代遮挡是在RevIN统计计算之前还是之后。若完全遮掉目标却仍使用原目标的均值和尺度，所谓完全无内生信息就不成立；若先遮挡，零方差如何处理又影响实现。这里只标记协议未知，不断言存在泄漏。该实验亦不覆盖长时间连续缺测、非随机故障或关系变号。\n\n复杂度O(T)对固定变量数、核长、隐维和输出跨度成立，并不等于所有尺度都便宜：多对一卷积约随TNK增长，多对多全通道卷积可随TN²K增长，预测头还依赖输出长度。图4(b)在同批量ECL上显示相对TimeXer有速度与误差优势，是有用的实测点；但没有插件逐骨干开销、完整推理内存和多变量数扩展曲线，“近乎免费”超出证据。代码与Zenodo入口明确，附录给优化器、学习率范围及核配置，可作为复用起点；本次未执行或验证代码快照。\n\n整体上，保留其作为低成本历史协变量融合方案的价值，收缩物理解释、普遍改善和扩展效率承诺。缺少随机种子与误差区间、关键汇总冲突及归因竞争解释，是当前最限制可信度的因素。这些是论文证据边界和条件化研究问题，不向用户布置实验任务；四项个人相关性因背景未知而不评分。",
"reading_record": {
"legacy": "先读历史摘要；独立复核表11退化和附录B，不读其他新评；旧全文缺失",
"full_text": "PDF1–13全部正文、参考文献、附录A–E、所有表格和展示图",
"visual_checks": "p9敏感性/依赖热图/效率；p12原始表11逐格核对DLinear Traffic；p13等价证明与预测展示",
"arithmetic_checks": "DLinear Traffic原MSE均值0.302、插件0.308；原MAE均值0.3845、插件0.39125，均由表11四跨度直接计算",
"code_executed": false,
"data_versions": "2505.23116v1；未核对ACM文本同一性、Zenodo具体归档或实验数据哈希"
},
"claims": [
{
"claim_id": "CL01",
"claim": "简单历史协变量融合在多领域有精度成本竞争力",
"claim_type": "经验性能",
"conditions": "文中固定输入长度与十轮训练配置",
"support_status": "条件性支持，不是所有数据任务或损失领先",
"location": "表2/3、图4b"
},
{
"claim_id": "CL02",
"claim": "Sum与Cross Only可用卷积重参数化得到相同映射",
"claim_type": "技术等价",
"conditions": "卷积含恒等选择核，约束和偏置同步处理",
"support_status": "支持表达类等价，不支持训练轨迹或机制等价",
"location": "附录B式14–18"
},
{
"claim_id": "CL03",
"claim": "插件在各模型上稳定改善预测",
"claim_type": "迁移泛化",
"conditions": "五骨干与所列数据",
"support_status": "多数支持但有退化；DLinear Traffic平均改善暂不采信",
"location": "表5/11"
},
{
"claim_id": "CL04",
"claim": "学习核只捕捉直接不变的真实物理依赖",
"claim_type": "机制解释",
"conditions": "需可识别或独立关系真值",
"support_status": "未证，只有结构先验与个案权重图",
"location": "3.4、4.4.2"
}
],
"risks": [
{
"risk_id": "R01",
"severity": "重要问题",
"certainty": "原图与算术确定，实际运行输出未知",
"description": "DLinear Traffic四行均值0.302/0.3845而非0.323/0.404；按行值插件平均反而退化",
"location": "p6表2、p8表5、p12表11",
"question": "哪些行或均值是最终运行结果，修正后插件平均结论是什么？"
},
{
"risk_id": "R02",
"severity": "重要问题",
"certainty": "表达类等价已证明，实际优化归因未分离",
"description": "Sum优势不能独立证明真实直接依赖学习，权重热图不具物理可识别性",
"location": "表4、附录B、图4a",
"question": "当前证据能否将结论收缩为残差参数化的经验收益？"
},
{
"risk_id": "R03",
"severity": "重要问题",
"certainty": "报告缺失",
"description": "主表和消融缺种子数量、误差区间及配对比较",
"location": "表2–6、附录A–D",
"question": "千分级差距在现有证据下应保留多大不确定性？"
},
{
"risk_id": "R04",
"severity": "重要问题",
"certainty": "协议未知，不等同确认泄漏",
"description": "完全目标遮挡时RevIN统计的计算顺序未说明，缺失鲁棒性解释依赖此条件",
"location": "4.3.2、表6、式3–6",
"question": "遮挡前后是否还利用未遮挡目标的均值或尺度？"
},
{
"risk_id": "R05",
"severity": "重要问题",
"certainty": "成本模型可分析，实际扩大规模性能未验证",
"description": "O(T)隐藏变量数与输出跨度，多对多卷积存在N平方项，不能推成几乎免费",
"location": "3.6、4.4.3、表7",
"question": "效率结论在什么变量数和预测长度范围内成立？"
}
],
"rubric_version": "PAPER-RUBRIC-1.0",
"reviewer_id": "A",
"paper_title": "CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables",
"paper_version": "2505.23116v1",
"first_public_date": "2025/05/29",
"version_date": "2025/05/29",
"assessment_date": "2026-11-08",
"analysis_mode": "standard",
"independence": {
"other_new_reviews_read": false,
"legacy_read_before_fulltext": true,
"legacy_full_reviews_available": false,
"legacy_records": [
{
"source_record_id": "S5-086",
"source_id": "S5",
"source_library_file_id": "libfile_849759d66a808191813dbe9bd1605bb4",
"source_filename": "已粘贴的文本(5).txt",
"source_line": 28,
"source_number": 86,
"title": "CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables",
"source_url": "https://doi.org/10.1145/3711896.3736899",
"raw_line": "| 12 | [P086 CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables](https://doi.org/10.1145/3711896.3736899) | 59.2 | 100% | 55% | 53.7–65.0 | 18 | arXiv:2505.23116v1；本地 PDF；ACM 论文集版本未单独读取 | **重要问题**：主表及消融未报告重复运行次数、随机种子或误差区间；例如 ECL 多对一平均 MSE 的差距为 0.004，稳定性未知。；
**重要问题**：附录 B 给出 Sum 到 Cross Only 的卷积重参数化；单靠表 4 的结果无法区分参数化、初始化、训练动态和约束作用，也缺权重物理含义的独立验证。；
**重要问题**：插件在部分设置下出现退化：表 11 中 Traffic 96 步的 DLinear MSE 从 0.268 升至 0.338；ECL 的 DLinear 平均 MAE 从 0.457 升至 0.463。 | [评审](论文/P086/评审.md) · [评分数据](论文/P086/评审.json) · 无单独复核文件 |",
"raw_cells": [
"12",
"[P086 CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables](https://doi.org/10.1145/3711896.3736899)",
"59.2",
"100%",
"55%",
"53.7–65.0",
"18",
"arXiv:2505.23116v1；本地 PDF；ACM 论文集版本未单独读取",
"**重要问题**：主表及消融未报告重复运行次数、随机种子或误差区间；例如 ECL 多对一平均 MSE 的差距为 0.004，稳定性未知。；
**重要问题**：附录 B 给出 Sum 到 Cross Only 的卷积重参数化；单靠表 4 的结果无法区分参数化、初始化、训练动态和约束作用，也缺权重物理含义的独立验证。；
**重要问题**：插件在部分设置下出现退化：表 11 中 Traffic 96 步的 DLinear MSE 从 0.268 升至 0.338；ECL 的 DLinear 平均 MAE 从 0.457 升至 0.463。",
"[评审](论文/P086/评审.md) · [评分数据](论文/P086/评审.json) · 无单独复核文件"
],
"normalized_title": "crosslinearplugandplaycrosscorrelationembeddingfortimeseriesforecastingwithexogenousvariables",
"normalized_url": "doi.org/10.1145/3711896.3736899",
"record_type": "legacy_scored",
"legacy_rank": 12,
"legacy_score": "59.2",
"legacy_coverage": "100%",
"legacy_tentative_share": "55%",
"legacy_range": "53.7–65.0",
"citation_verbatim": "18",
"legacy_review_version": "arXiv:2505.23116v1；本地 PDF；ACM 论文集版本未单独读取",
"legacy_risks_verbatim": "**重要问题**：主表及消融未报告重复运行次数、随机种子或误差区间；例如 ECL 多对一平均 MSE 的差距为 0.004，稳定性未知。；
**重要问题**：附录 B 给出 Sum 到 Cross Only 的卷积重参数化；单靠表 4 的结果无法区分参数化、初始化、训练动态和约束作用，也缺权重物理含义的独立验证。；
**重要问题**：插件在部分设置下出现退化：表 11 中 Traffic 96 步的 DLinear MSE 从 0.268 升至 0.338；ECL 的 DLinear 平均 MAE 从 0.457 升至 0.463。",
"legacy_material_links_verbatim": "[评审](论文/P086/评审.md) · [评分数据](论文/P086/评审.json) · 无单独复核文件",
"counts_as_independent_review": false
}
],
"legacy_counts_as_review": false
},
"identity": {
"candidate_id": "ATT-0086",
"title": "CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables",
"authors": [
"Zhou, Pengfei",
"Liu, Yunlong",
"Liang, Junli",
"Song, Qi",
"Li, Xiangyang"
],
"arxiv_id": "2505.23116",
"arxiv_version": "v1",
"first_arxiv_date": "2025/05/29",
"latest_arxiv_date": "2025/05/29",
"source_urls": [
"https://doi.org/10.1145/3711896.3736899"
],
"publication_status": "KDD 2025, DOI 10.1145/3711896.3736899 verified",
"full_text_path": "/workspace/scratch/ac01e91af073/candidate_recovery/priority_packet_20261108/papers/ATT-0086/ATT-0086_paper.pdf",
"metadata_source_path": "/workspace/scratch/ac01e91af073/candidate_recovery/priority_packet_20261108/papers/ATT-0086/ATT-0086_arxiv.html",
"full_text_sha256": "0235fd4cd7a51ae05b313532abdc7d0fe4dc86ac23bc29c1105f5e3cccb814f8",
"review_state": "ready_for_five_new_independent_reviews",
"completed_new_reviews": 0,
"source_versions_not_asserted_identical": true
},
"user_context": {
"research_question": null,
"prior_knowledge": null,
"constraints": null
},
"aggregation": {
"weights": null,
"weighted_score_observed": null,
"weighted_coverage": null,
"tentative_weight_share": null,
"notes": "保留24维原始评分，不预设总分；F组个人背景未知。"
},
"scores": [
{
"dimension_id": "A1",
"dimension_name": "问题重要性",
"score": 80,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "只预测目标且利用历史协变量是重要实用场景",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"1、3.1"
],
"claim_ids": []
},
{
"dimension_id": "A2",
"dimension_name": "原创性",
"score": 55,
"status": "tentative",
"confidence": "中",
"judgment_range": [
45,
65
],
"rationale": "通道卷积、残差与patch组合有工程增量，基础操作常见",
"missing_information": "见理由及风险记录",
"source_ids": [
"S01"
],
"evidence_locations": [
"3.4/3.5"
],
"claim_ids": []
},
{
"dimension_id": "A3",
"dimension_name": "实质推进程度",
"score": 65,
"status": "tentative",
"confidence": "中",
"judgment_range": [
55,
75
],
"rationale": "多任务较强但相对强基线差距小、局部均值冲突",
"missing_information": "见理由及风险记录",
"source_ids": [
"S01"
],
"evidence_locations": [
"表2/3/11"
],
"claim_ids": []
},
{
"dimension_id": "A4",
"dimension_name": "知识与解释增量",
"score": 60,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "重参数化和低成本融合有启发，直接依赖物理解释不足",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"附录B、4.4.2"
],
"claim_ids": []
},
{
"dimension_id": "B1",
"dimension_name": "问题定义与评价有效性",
"score": 75,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "多对一与多对多分开，目标和历史输入清楚，部分目标/缺失细节不足",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"式1/2、表1/6"
],
"claim_ids": []
},
{
"dimension_id": "B2",
"dimension_name": "技术与论证正确性",
"score": 65,
"status": "tentative",
"confidence": "中",
"judgment_range": [
55,
75
],
"rationale": "核心映射和等价证明合理，但汇总计算有确定冲突",
"missing_information": "见理由及风险记录",
"source_ids": [
"S01"
],
"evidence_locations": [
"附录B、表11"
],
"claim_ids": []
},
{
"dimension_id": "B3",
"dimension_name": "数据与评测流程完整性",
"score": 60,
"status": "tentative",
"confidence": "中",
"judgment_range": [
50,
75
],
"rationale": "切分与设置有说明，异常值和缺失统计次序仍需明确",
"missing_information": "见理由及风险记录",
"source_ids": [
"S01"
],
"evidence_locations": [
"表1、4.1、4.3.2"
],
"claim_ids": []
},
{
"dimension_id": "B4",
"dimension_name": "比较对象与比较公平性",
"score": 65,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "强深度基线较全，但固定96/十轮、任务专用电价基线不足",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"4、附录A"
],
"claim_ids": []
},
{
"dimension_id": "C1",
"dimension_name": "核心主张的证据充分度",
"score": 65,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "多数实证有支持，平均插件改善和物理机制不充分",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"表2–6、11"
],
"claim_ids": []
},
{
"dimension_id": "C2",
"dimension_name": "机制归因与竞争解释区分度",
"score": 55,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "消融覆盖多形式，表达等价导致优化竞争解释未排除",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"表4/10、附录B"
],
"claim_ids": []
},
{
"dimension_id": "C3",
"dimension_name": "结果稳定性与不确定性处理",
"score": 35,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "没有种子与区间，细微优势可靠性未知",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"实验全章、附录A"
],
"claim_ids": []
},
{
"dimension_id": "C4",
"dimension_name": "适用范围与边界验证",
"score": 70,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "十二数据与双范式、缺失测试较广，动态关系和成本边界不足",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"表2/3/6"
],
"claim_ids": []
},
{
"dimension_id": "D1",
"dimension_name": "过程透明度",
"score": 65,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "公式和附录清楚，逐模型配置/选择及缺失协议不闭合",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"附录A、4.3.2"
],
"claim_ids": []
},
{
"dimension_id": "D2",
"dimension_name": "研究资源可获得性",
"score": 75,
"status": "tentative",
"confidence": "中",
"judgment_range": [
60,
85
],
"rationale": "代码及Zenodo归档入口明确，未核验实际运行",
"missing_information": "见理由及风险记录",
"source_ids": [
"S01"
],
"evidence_locations": [
"p1资源链接"
],
"claim_ids": []
},
{
"dimension_id": "D3",
"dimension_name": "主张克制与报告一致性",
"score": 50,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "普遍提升和低成本叙述过宽，汇总矛盾影响报告一致性",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"表5/11、4.3/4.4"
],
"claim_ids": []
},
{
"dimension_id": "D4",
"dimension_name": "表达清晰度",
"score": 75,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "模块结构易懂，Stack维度文字与物理解释可更精确",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"图2、式7–11"
],
"claim_ids": []
},
{
"dimension_id": "E1",
"dimension_name": "复杂度合理性",
"score": 80,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "小模块及共享结构简洁，有组件消融和实际收益",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"3.4–3.6、表4"
],
"claim_ids": []
},
{
"dimension_id": "E2",
"dimension_name": "资源效率与成本收益",
"score": 65,
"status": "tentative",
"confidence": "中",
"judgment_range": [
55,
75
],
"rationale": "单数据训练成本支持竞争力，变量数和插件开销未验证",
"missing_information": "见理由及风险记录",
"source_ids": [
"S01"
],
"evidence_locations": [
"图4b、表7"
],
"claim_ids": []
},
{
"dimension_id": "E3",
"dimension_name": "可迁移与可复用程度",
"score": 80,
"status": "tentative",
"confidence": "中",
"judgment_range": [
70,
85
],
"rationale": "五骨干集成证明便于复用，但不是无条件增益",
"missing_information": "见理由及风险记录",
"source_ids": [
"S01"
],
"evidence_locations": [
"表5/11"
],
"claim_ids": []
},
{
"dimension_id": "E4",
"dimension_name": "后续研究启发性",
"score": 75,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "残差初始化与协变量低成本融合、失效边界值得研究",
"missing_information": null,
"source_ids": [
"S01"
],
"evidence_locations": [
"附录B、表11"
],
"claim_ids": []
},
{
"dimension_id": "F1",
"dimension_name": "与当前问题的相关性",
"score": null,
"status": "unknown",
"confidence": null,
"judgment_range": null,
"rationale": "用户当前研究问题、知识储备、执行资源和决策条件未提供。",
"missing_information": "用户当前研究问题、知识储备、执行资源和决策条件未提供。",
"source_ids": [
"S01"
],
"evidence_locations": [],
"claim_ids": []
},
{
"dimension_id": "F2",
"dimension_name": "相对于已有知识的学习收益",
"score": null,
"status": "unknown",
"confidence": null,
"judgment_range": null,
"rationale": "用户当前研究问题、知识储备、执行资源和决策条件未提供。",
"missing_information": "用户当前研究问题、知识储备、执行资源和决策条件未提供。",
"source_ids": [
"S01"
],
"evidence_locations": [],
"claim_ids": []
},
{
"dimension_id": "F3",
"dimension_name": "当前使用可行性",
"score": null,
"status": "unknown",
"confidence": null,
"judgment_range": null,
"rationale": "用户当前研究问题、知识储备、执行资源和决策条件未提供。",
"missing_information": "用户当前研究问题、知识储备、执行资源和决策条件未提供。",
"source_ids": [
"S01"
],
"evidence_locations": [],
"claim_ids": []
},
{
"dimension_id": "F4",
"dimension_name": "当前决策信息价值",
"score": null,
"status": "unknown",
"confidence": null,
"judgment_range": null,
"rationale": "用户当前研究问题、知识储备、执行资源和决策条件未提供。",
"missing_information": "用户当前研究问题、知识储备、执行资源和决策条件未提供。",
"source_ids": [
"S01"
],
"evidence_locations": [],
"claim_ids": []
}
],
"sources": [
{
"source_id": "S01",
"source_type": "原论文全文及附录",
"location": "/workspace/scratch/ac01e91af073/candidate_recovery/priority_packet_20261108/papers/ATT-0086/ATT-0086_paper.pdf",
"version_or_date": "2505.23116v1",
"sha256": "0235fd4cd7a51ae05b313532abdc7d0fe4dc86ac23bc29c1105f5e3cccb814f8",
"access_status": "全文可读；未运行代码或模型"
},
{
"source_id": "S02",
"source_type": "历史摘要，非完整旧评",
"location": "/workspace/scratch/ac01e91af073/candidate_recovery/priority_packet_20261108/papers/ATT-0086/legacy_reference_only.json",
"access_status": "先读；仅历史待核线索，不作新评票"
}
],
"review_chinese_char_count": 1933
}