{
"rubric_version": "PAPER-RUBRIC-1.0",
"reviewer": "E",
"paper_id": "ATT-0097",
"paper_title": "Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting",
"paper_version": "arXiv 2406.03751v2",
"version_date": "2025/04/15",
"first_public_date": "2024/06/06",
"assessment_date": "2026-11-08",
"reading_record": {
"completed_at_utc": "2026-11-08T02:46:29.193324+00:00",
"pdf_pages": 14,
"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-0097",
"counts_as_review": false,
"sidecar_files_supplied": false,
"records": [
{
"source_record_id": "S5-097",
"source_id": "S5",
"source_library_file_id": "libfile_849759d66a808191813dbe9bd1605bb4",
"source_filename": "已粘贴的文本(5).txt",
"source_line": 29,
"source_number": 97,
"title": "Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting",
"source_url": "https://ojs.aaai.org/index.php/AAAI/article/view/33908",
"raw_line": "| 13 | [P097 Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting](https://ojs.aaai.org/index.php/AAAI/article/view/33908) | 59.2 | 100% | 35% | 55.5–63.5 | 74 | AAAI 2025 会议论文；补充理论与结果为 arXiv:2406.03751v2（2025-04-15） | **重要问题**：arXiv v2 附录 A 式 (13)→(14) 把分母由 a-b 变为 d(a-b) 时遗漏 d；式 (21)→(22) 的不等式也忽略不同列权重。；
**重要问题**：表 1 的 ETTh2/720 中 AMD MSE 0.402，TimeMixer 0.342；长期预测表现取决于数据与预测长度。；
**重要问题**：基线各模型调参预算和最佳输入长度选择程序未在已检查文字中完整交代；影响相对效果的可比性。 | [评审](论文/P097/评审.md) · [评分数据](论文/P097/评审.json) · 无单独复核文件 |",
"raw_cells": [
"13",
"[P097 Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting](https://ojs.aaai.org/index.php/AAAI/article/view/33908)",
"59.2",
"100%",
"35%",
"55.5–63.5",
"74",
"AAAI 2025 会议论文；补充理论与结果为 arXiv:2406.03751v2（2025-04-15）",
"**重要问题**：arXiv v2 附录 A 式 (13)→(14) 把分母由 a-b 变为 d(a-b) 时遗漏 d；式 (21)→(22) 的不等式也忽略不同列权重。；
**重要问题**：表 1 的 ETTh2/720 中 AMD MSE 0.402，TimeMixer 0.342；长期预测表现取决于数据与预测长度。；
**重要问题**：基线各模型调参预算和最佳输入长度选择程序未在已检查文字中完整交代；影响相对效果的可比性。",
"[评审](论文/P097/评审.md) · [评分数据](论文/P097/评审.json) · 无单独复核文件"
],
"normalized_title": "adaptivemultiscaledecompositionframeworkfortimeseriesforecasting",
"normalized_url": "ojs.aaai.org/index.php/aaai/article/view/33908",
"record_type": "legacy_scored",
"legacy_rank": 13,
"legacy_score": "59.2",
"legacy_coverage": "100%",
"legacy_tentative_share": "35%",
"legacy_range": "55.5–63.5",
"citation_verbatim": "74",
"legacy_review_version": "AAAI 2025 会议论文；补充理论与结果为 arXiv:2406.03751v2（2025-04-15）",
"legacy_risks_verbatim": "**重要问题**：arXiv v2 附录 A 式 (13)→(14) 把分母由 a-b 变为 d(a-b) 时遗漏 d；式 (21)→(22) 的不等式也忽略不同列权重。；
**重要问题**：表 1 的 ETTh2/720 中 AMD MSE 0.402，TimeMixer 0.342；长期预测表现取决于数据与预测长度。；
**重要问题**：基线各模型调参预算和最佳输入长度选择程序未在已检查文字中完整交代；影响相对效果的可比性。",
"legacy_material_links_verbatim": "[评审](论文/P097/评审.md) · [评分数据](论文/P097/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": "AMD多尺度组合在多任务有竞争力。",
"assessment": "支持但不是所有设置最佳。",
"location": "PDF 5—7"
},
{
"claim_id": "CL02",
"claim": "定理1证明线性多尺度预测的所述误差保证。",
"assessment": "暂停作为可靠结论使用，证明有直接反例。",
"location": "PDF 9—10"
},
{
"claim_id": "CL03",
"claim": "TopK始终提高主导模式权重。",
"assessment": "按式10和α=0配置不成立，需核对实现。",
"location": "PDF 4、12"
}
],
"scores": [
{
"dimension_id": "A1",
"dimension_name": "问题重要性",
"score": 80,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "多尺度和变量干扰是常见实际预测问题。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 1—3"
},
{
"dimension_id": "A2",
"dimension_name": "原创性",
"score": 65,
"status": "tentative",
"confidence": "中",
"judgment_range": [
55,
75
],
"rationale": "组合多尺度混合与自适应专家，前作重叠较多。",
"missing_information": "组合多尺度混合与自适应专家，前作重叠较多。",
"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": "多任务结果有竞争力但长预测非普遍领先。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5—6"
},
{
"dimension_id": "A4",
"dimension_name": "知识与解释增量",
"score": 40,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "理论证明失效且专家模式可识别性未建立。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 3、9—10"
},
{
"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": "任务与误差指标清楚，预测长度及输入搜索明确。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 3、5、11"
},
{
"dimension_id": "B2",
"dimension_name": "技术与论证正确性",
"score": 35,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "Lipschitz推导错误；α=0分支与机制叙述相反。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 4、10、12"
},
{
"dimension_id": "B3",
"dimension_name": "数据与评测流程完整性",
"score": 70,
"status": "tentative",
"confidence": "中",
"judgment_range": [
55,
80
],
"rationale": "给切分、重复和配置；最佳窗口选取程序不足。",
"missing_information": "给切分、重复和配置；最佳窗口选取程序不足。",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5、11—12、14"
},
{
"dimension_id": "B4",
"dimension_name": "比较对象与比较公平性",
"score": 70,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "有直接近邻并搜索窗口，但等调参预算及短时强基线不完整。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5—6、12"
},
{
"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": "经验竞争力成立，理论和全面SOTA主张不成立。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5—6、10"
},
{
"dimension_id": "C2",
"dimension_name": "机制归因与竞争解释区分度",
"score": 60,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "消融丰富但只两数据集且容量混杂，专家归因不足。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 6—7"
},
{
"dimension_id": "C3",
"dimension_name": "结果稳定性与不确定性处理",
"score": 70,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "五种子及六数据集标准差较好，未给全基线配对不确定性。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5、14"
},
{
"dimension_id": "C4",
"dimension_name": "适用范围与边界验证",
"score": 65,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "长短时多数据覆盖，弱相关和数据不足仅讨论未系统验证。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5—7、12—14"
},
{
"dimension_id": "D1",
"dimension_name": "过程透明度",
"score": 60,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "算法配置可读，关键公式与参数定义需要核对。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 4、10—12"
},
{
"dimension_id": "D2",
"dimension_name": "研究资源可获得性",
"score": 65,
"status": "tentative",
"confidence": "中",
"judgment_range": [
50,
80
],
"rationale": "代码数据链接明确，未检查固定依赖与可执行性。",
"missing_information": "代码数据链接明确，未检查固定依赖与可执行性。",
"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": "全面最佳与插件全提升过强，单元格违反MAE/RMSE关系。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 5—7"
},
{
"dimension_id": "D4",
"dimension_name": "表达清晰度",
"score": 65,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "模块结构清楚，理论和TopK公式易误导。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 3—5、10"
},
{
"dimension_id": "E1",
"dimension_name": "复杂度合理性",
"score": 65,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "多模块有针对性，必要性未与等容量模型区分。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 6—7"
},
{
"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": "单配置训练耗时显存有证据，跨设置和插件成本不足。",
"missing_information": "单配置训练耗时显存有证据，跨设置和插件成本不足。",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 7"
},
{
"dimension_id": "E3",
"dimension_name": "可迁移与可复用程度",
"score": 70,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "可接入其他MLP，部分配置下降且公式需修订。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 7、11"
},
{
"dimension_id": "E4",
"dimension_name": "后续研究启发性",
"score": 75,
"status": "rated",
"confidence": "高",
"judgment_range": null,
"rationale": "通道干扰、专家分工和不同尺度权重有具体研究价值。",
"missing_information": "",
"claim_ids": [],
"source_ids": [
"S01"
],
"location": "PDF 6—7、14"
},
{
"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": "关键",
"certainty": "已确认",
"description": "下采样漏因子d及不同权重列被忽略导致理论证明失效；有限数组有界不等同所述有效上界。",
"affected_claim_ids": [
"CL02"
],
"source_ids": [
"S01"
],
"location": "PDF 10式13—24"
},
{
"risk_id": "R02",
"severity": "重要",
"certainty": "已确认文本冲突",
"description": "α=0时式10选中分支为−1、未选中为0，外softmax逆向赋权，与主导模式加权解释冲突。",
"affected_claim_ids": [
"CL03"
],
"source_ids": [
"S01"
],
"location": "PDF 4式10、12表6"
},
{
"risk_id": "R03",
"severity": "局部",
"certainty": "已确认",
"description": "表3 ECL192无selector损失MSE0.156、MAE0.456违反同误差口径MAE≤RMSE，须校正。",
"affected_claim_ids": [
"CL01"
],
"source_ids": [
"S01"
],
"location": "PDF 6表3"
}
],
"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": "定向查阅多尺度专家组合；暂停使用定理1与未校正的TopK机制解释",
"recommended_sections": [
"3—5页结构",
"6—7页消融与插件",
"9—10页证明",
"11—14页设置与种子结果"
],
"sources": [
{
"source_id": "S01",
"source_type": "paper_pdf",
"title": "Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting",
"version_or_date": "2406.03751v2",
"location": "/workspace/scratch/ac01e91af073/candidate_recovery/priority_packet_20261108/papers/ATT-0097/ATT-0097_paper.pdf",
"sha256": "02aad9b5b876e3b53d6c34114d6e658eb557898d57f20402baf512b3e264b05e",
"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-0097/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": 1554
}