{
"rubric_version": "PAPER-RUBRIC-1.0",
"reviewer": "E",
"paper_id": "ATT-0086",
"paper_title": "CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables",
"paper_version": "arXiv 2505.23116v1",
"version_date": "2025/05/29",
"first_public_date": "2025/05/29",
"assessment_date": "2026-11-08",
"reading_record": {
"completed_at_utc": "2026-11-08T02:58:13.283704+00:00",
"pdf_pages": 13,
"coverage": "逐页全文及附录文本阅读；关键公式或表格按需原页视觉核对。参考文献已检查关联定位，未逐篇读取全部前作。",
"experimental_execution": false
},
"paper_type": [
"方法或算法",
"实证分析"
],
"analysis_mode": "standard",
"user_context": {
"research_question": null,
"prior_knowledge": null,
"constraints": null
},
"legacy_review": {
"read_before_new_review": true,
"full_old_review_available": false,
"history_counts_as_new_review": false,
"record": {
"candidate_id": "ATT-0086",
"counts_as_review": false,
"sidecar_files_supplied": false,
"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
}
]
},
"handling": "旧完整评语及评分sidecar未提供；历史条目仅作为待核线索，不继承旧分数。"
},
"claims": [
{
"claim_id": "CL01",
"claim": "CrossLinear是多对一预测的高效竞争方法。",
"assessment": "支持有限设置下竞争力，普遍及显著领先未证实。",
"location": "PDF5—9"
},
{
"claim_id": "CL02",
"claim": "残差Sum与Cross Only表示能力不同或后者只能同等看待变量。",
"assessment": "不支持；作者自身证明可重参数化，差异需从优化和约束理解。",
"location": "PDF4、7、11—13"
},
{
"claim_id": "CL03",
"claim": "插件在各模型各设置持续提升。",
"assessment": "不成立；Traffic DLinear平均数校正后整组反而退化。",
"location": "PDF8、12"
},
{
"claim_id": "CL04",
"claim": "单层卷积识别直接物理依赖且扩展几乎无成本。",
"assessment": "证据不足；权重不等于因果依赖，多对多变量成本为平方级。",
"location": "PDF4、9"
}
],
"scores": [
{
"dimension_id": "A1",
"dimension_name": "问题重要性",
"score": 85,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "只预测目标且利用辅助历史是重要实际设定。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 1—3"
},
{
"dimension_id": "A2",
"dimension_name": "原创性",
"score": 55,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "一层卷积加残差与patch整合实用，基础操作及任务并非新概念。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 2—4"
},
{
"dimension_id": "A3",
"dimension_name": "实质推进程度",
"score": 65,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "多任务竞争力良好，提升多为小幅且若干边界不领先。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 6—7"
},
{
"dimension_id": "A4",
"dimension_name": "知识与解释增量",
"score": 55,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "重参数化说明有价值，直接依赖与热图解释缺独立验证。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 9、11—13"
},
{
"dimension_id": "B1",
"dimension_name": "问题定义与评价有效性",
"score": 70,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "历史协变量任务定义清楚，但目标通道和缺失协议信息不足。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 3—5、8、11"
},
{
"dimension_id": "B2",
"dimension_name": "技术与论证正确性",
"score": 60,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "主体线性结构合理，插件平均数错误、表达能力解释过强。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 4、8、12—13"
},
{
"dimension_id": "B3",
"dimension_name": "数据与评测流程完整性",
"score": 60,
"status": "tentative",
"confidence": "中",
"judgment_range": [
45,
75
],
"rationale": "给切分数量与部分训练配置，未清楚列目标选择、验证选型和随机控制。",
"missing_information": "给切分数量与部分训练配置，未清楚列目标选择、验证选型和随机控制。",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5、11"
},
{
"dimension_id": "B4",
"dimension_name": "比较对象与比较公平性",
"score": 60,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "TimeXer等相关基线齐全，缺等调参预算与统计外生预测强基线。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5—7、11"
},
{
"dimension_id": "C1",
"dimension_name": "核心主张的证据充分度",
"score": 60,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "支持强简单模型，普遍插件收益与稳定领先证据不足。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 6—8、12"
},
{
"dimension_id": "C2",
"dimension_name": "机制归因与竞争解释区分度",
"score": 50,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "Sum与Cross Only函数类等价，消融未隔离优化/初始化及容量因素。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 7—9、11—13"
},
{
"dimension_id": "C3",
"dimension_name": "结果稳定性与不确定性处理",
"score": 30,
"status": "tentative",
"confidence": "中",
"judgment_range": [
20,
45
],
"rationale": "全文与附录未见重复次数、种子、误差条或配对不确定性。",
"missing_information": "全文与附录未见重复次数、种子、误差条或配对不确定性。",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 6—8、11—12"
},
{
"dimension_id": "C4",
"dimension_name": "适用范围与边界验证",
"score": 65,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "两任务十二数据集及缺失试验较广，时变和伪相关边界未系统测。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5—9"
},
{
"dimension_id": "D1",
"dimension_name": "过程透明度",
"score": 60,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "主要方程与范围清楚，最终配置及缺失归一化顺序缺失。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 4、8、11"
},
{
"dimension_id": "D2",
"dimension_name": "研究资源可获得性",
"score": 75,
"status": "tentative",
"confidence": "中",
"judgment_range": [
60,
85
],
"rationale": "有GitHub及Zenodo持久入口，未检查完整依赖或可执行性。",
"missing_information": "有GitHub及Zenodo持久入口，未检查完整依赖或可执行性。",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 1、11"
},
{
"dimension_id": "D3",
"dimension_name": "主张克制与报告一致性",
"score": 45,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "Traffic插件汇总方向被平均数错误改变，部分普遍提升表述不符明细。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 8、12"
},
{
"dimension_id": "D4",
"dimension_name": "表达清晰度",
"score": 70,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "总体架构和实验易读，但维度措辞和若干协议表注不一致。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 3—5、8、11"
},
{
"dimension_id": "E1",
"dimension_name": "复杂度合理性",
"score": 70,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "限制交互深度合理，PE和残差作用更像参数化而非新增表达力。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 4、7、11—13"
},
{
"dimension_id": "E2",
"dimension_name": "资源效率与成本收益",
"score": 65,
"status": "tentative",
"confidence": "中",
"judgment_range": [
50,
80
],
"rationale": "ECL同批量时延支持效率；变量平方成本与插件增量未完整评估。",
"missing_information": "ECL同批量时延支持效率；变量平方成本与插件增量未完整评估。",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 4、9"
},
{
"dimension_id": "E3",
"dimension_name": "可迁移与可复用程度",
"score": 75,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "已有五模型接入实例，但收益并非每指标每长度为正。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 8、12"
},
{
"dimension_id": "E4",
"dimension_name": "后续研究启发性",
"score": 75,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "等价线性模型为何泛化不同是明确可借鉴方向。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 9、11—13"
},
{
"dimension_id": "F1",
"dimension_name": "与当前问题的相关性",
"score": null,
"status": "unknown",
"confidence": null,
"judgment_range": null,
"rationale": "未给定用户正在解决的具体预测或异常检测问题。",
"missing_information": "个人研究背景缺失；不以论文质量代填。",
"claim_ids": [],
"source_ids": [],
"location": "任务上下文（非论文证据）"
},
{
"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": "未给定用户已掌握的理论、算法或已读论文。",
"missing_information": "个人研究背景缺失；不以论文质量代填。",
"claim_ids": [],
"source_ids": [],
"location": "任务上下文（非论文证据）"
},
{
"dimension_id": "F3",
"dimension_name": "当前使用可行性",
"score": null,
"status": "unknown",
"confidence": null,
"judgment_range": null,
"rationale": "未给定用户用途、算力、数据与许可约束。",
"missing_information": "个人研究背景缺失；不以论文质量代填。",
"claim_ids": [],
"source_ids": [],
"location": "任务上下文（非论文证据）"
},
{
"dimension_id": "F4",
"dimension_name": "当前决策信息价值",
"score": null,
"status": "unknown",
"confidence": null,
"judgment_range": null,
"rationale": "未给定当前待决策的具体方法或研究路线。",
"missing_information": "个人研究背景缺失；不以论文质量代填。",
"claim_ids": [],
"source_ids": [],
"location": "任务上下文（非论文证据）"
}
],
"risks": [
{
"risk_id": "R01",
"severity": "重要",
"certainty": "已确认算术错误",
"description": "Traffic原DLinear MSE平均应0.302而非0.323，MAE应0.3845而非0.404；插件后0.308/0.39125更差，汇总改善方向反转。",
"affected_claim_ids": [
"CL03"
],
"source_ids": [
"S01"
],
"location": "PDF8表5、12表11（原页视觉复核）"
},
{
"risk_id": "R02",
"severity": "重要",
"certainty": "已确认解释边界",
"description": "Sum可并入卷积核，消融不能证明新增表达力或识别直接依赖；未控制初始化、正则化和训练动态。",
"affected_claim_ids": [
"CL02",
"CL04"
],
"source_ids": [
"S01"
],
"location": "PDF4、7、9、11—13"
},
{
"risk_id": "R03",
"severity": "重要",
"certainty": "材料未报告",
"description": "缺重复种子与不确定性，目标通道、缺失mask与RevIN顺序不足；NP窗口表注与主实验配置不一致。",
"affected_claim_ids": [
"CL01"
],
"source_ids": [
"S01"
],
"location": "PDF5—8、11—12"
},
{
"risk_id": "R04",
"severity": "重要",
"certainty": "已确认条件限制",
"description": "O(T)只固定其他维度，多对多卷积N×N×3；不能外推为随变量数也近乎免费。",
"affected_claim_ids": [
"CL04"
],
"source_ids": [
"S01"
],
"location": "PDF4、9"
}
],
"aggregation": {
"weights": null,
"weighted_score_observed": null,
"weighted_coverage": null,
"tentative_weight_share": null,
"numeric_dimensions": 20,
"applicable_dimensions": 24,
"unweighted_dimension_coverage": 0.8333333333333334,
"notes": "保留24维原始分数，不计算论文总分或跨论文排序；F组未知。"
},
"reading_recommendation": "定向查阅目标优先卷积插件及重参数化；校正插件汇总后再引用总体收益",
"recommended_sections": [
"3—4页方法",
"6—8页主表与缺失",
"9页效率及相关性解释",
"11—13页消融、重参数化与插件明细"
],
"sources": [
{
"source_id": "S01",
"source_type": "paper_pdf",
"title": "CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables",
"version_or_date": "2505.23116v1",
"location": "/workspace/scratch/ac01e91af073/candidate_recovery/priority_packet_20261108/papers/ATT-0086/ATT-0086_paper.pdf",
"sha256": "0235fd4cd7a51ae05b313532abdc7d0fe4dc86ac23bc29c1105f5e3cccb814f8",
"access_status": "已读取完整PDF文本及附录；本地版本，不推定等同会议终稿"
},
{
"source_id": "S02",
"source_type": "legacy_history",
"location": "/workspace/scratch/ac01e91af073/candidate_recovery/priority_packet_20261108/papers/ATT-0086/legacy_reference_only.json",
"access_status": "已先读；无旧完整评语"
}
],
"independence": "未读取同批其他评审的新意见。",
"narrative_chinese_characters": 1841
}