Compare commits
11 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 4d97822d9e | |||
| 48f8304517 | |||
| f2b9fe0149 | |||
| 32d99858c1 | |||
| 060d67aba5 | |||
| d0a466977c | |||
| 52f9740d99 | |||
| bcb8b2ad7e | |||
| 95ff77d77f | |||
| 28805462ee | |||
| 2907c3774f |
@@ -47,6 +47,26 @@ jobs:
|
||||
subprocess.run([python,'-B','-m','pip','install','--no-deps',str(wheel)],check=True)
|
||||
outside = root / 'outside-checkout'
|
||||
outside.mkdir()
|
||||
cikm_snapshots = pathlib.Path('/data/paper-index/validation/cikm2026-source-snapshots-v1')
|
||||
if cikm_snapshots.is_dir():
|
||||
cikm_output = root / 'installed-cikm2026'
|
||||
command = [python, '-I', '-B', '-m', 'paper_atlas', 'collect', 'cikm2026-sources']
|
||||
subprocess.run([*command, '--snapshots', str(cikm_snapshots), '--out', str(cikm_output)], cwd=outside, check=True)
|
||||
report = json.loads((cikm_output/'collection-report.json').read_text())
|
||||
assert {name: entry['records'] for name, entry in report['files'].items()} == {
|
||||
'programme.jsonl': 1008, 'alternate-programme.jsonl': 1005,
|
||||
'supplemental-programme.jsonl': 73, 'crossref.jsonl': 1081}
|
||||
assert len(report['registry_outside_doi_programme']) == 73 and not report['database_written']
|
||||
programme = [json.loads(line) for line in (cikm_output/'programme.jsonl').read_text().splitlines()]
|
||||
assert all(row['abstract'] and row['author_display_names'] for row in programme)
|
||||
assert len({row['doi'] for row in programme}) == 1008
|
||||
broken = root/'tampered-cikm2026'
|
||||
broken.mkdir()
|
||||
(broken/'program.html').write_text('tampered')
|
||||
rejected = subprocess.run([*command, '--snapshots', str(broken), '--out', str(root/'rejected-cikm2026')], cwd=outside, capture_output=True, text=True)
|
||||
assert rejected.returncode != 0 and 'Snapshot hash mismatch' in rejected.stderr
|
||||
assert not (root/'rejected-cikm2026').exists()
|
||||
print('CIKM 2026 full frozen-source CLI check passed', flush=True)
|
||||
mm_fixture = json.loads(gzip.decompress((src/'tests/fixtures/mm2026-source.json.gz').read_bytes()))
|
||||
mm_snapshots = root/'mm2026-snapshots'
|
||||
for name, body in mm_fixture['files'].items():
|
||||
|
||||
@@ -141,6 +141,8 @@ ECCV 2026 的[暂定节目采集器](docs/eccv2026-program.md)合并重复节目
|
||||
|
||||
`collect sdm2026-proceedings` 核验 53 个 Crossref 论文章节,并单独保留 53 项日程观察及 52 页摘要。作者差异、取消展示和摘要缺失分别保留,不自动拼接来源或绑定作品;见 [SDM 2026 使用与恢复说明](docs/sdm2026-proceedings.md)。
|
||||
|
||||
`collect cikm2026-sources` 核验并分开导出两份官方节目、附属议程和出版登记。见 [CIKM 2026 来源采集与恢复](docs/cikm2026-sources.md)。
|
||||
|
||||
`collect icdm2026-program` 离线核验 324 条 ICDM2026 官方线下日程,按明确的研究/应用标签输出 241/83 条;展示长短、缺失摘要及未核实出版身份分别保留,不自动入库。见 [ICDM2026 使用与恢复说明](docs/icdm2026-program.md)。
|
||||
|
||||
`collect recsys2026-program` 核验九个 track 的 263 项官方录用贡献观察(260 个不同 DOI),保留摘要、原始作者和重复 DOI 的来源版本。见 [RecSys 2026 使用与恢复说明](docs/recsys2026-program.md)。
|
||||
|
||||
@@ -0,0 +1,22 @@
|
||||
# CIKM 2026 来源采集与恢复
|
||||
|
||||
使用固定节目和登记快照复现 CIKM 2026 来源盘点。采集命令生成四份独立 JSONL,输入逐文件校验 SHA-256。
|
||||
|
||||
```sh
|
||||
paper-atlas collect cikm2026-sources \
|
||||
--snapshots /data/paper-index/validation/cikm2026-source-snapshots-v1 \
|
||||
--out /data/paper-index/collected/cikm2026-sources-v1
|
||||
```
|
||||
|
||||
输入包括两版官方节目 HTML、Crossref 卷登记、五页逐篇登记及分页回执。服务器验证目录保留输入原文。输出目录必须是新目录。先检查 `collection-report.json`,报告在四份 JSONL 写完后发布。
|
||||
|
||||
| 文件 | 内容 |
|
||||
| --- | --- |
|
||||
| `programme.jsonl` | 带 DOI 的 1,008 条节目记录,包括标题、作者显示名、摘要和五类节目标签 |
|
||||
| `alternate-programme.jsonl` | 另一版节目 1,005 条记录及各自的字段 |
|
||||
| `supplemental-programme.jsonl` | 73 条演讲、教程、工作坊及其他附属活动观察 |
|
||||
| `crossref.jsonl` | 1,081 条 ACM 卷内登记,每条保留登记字段及分页文件位置 |
|
||||
|
||||
节目 DOI 指向 Crossref 的出版登记。确认作者和标题差异以及历史投稿绑定后,再为来源观察准备入库队列。报告另列 73 个未出现在带 DOI 节目区的登记,附属活动仍保留各自的活动类型。公开拒稿与撤回决定仍需独立来源核查。
|
||||
|
||||
官方原始来源见[带 DOI 的节目](https://cikm2026.diag.uniroma1.it/cikm-program/program.html)、[另一版节目](https://cikm2026.diag.uniroma1.it/cikm-program/CIKM2026_program.html)和 [Crossref 卷登记](https://api.crossref.org/works/10.1145/3799682)。
|
||||
@@ -204,3 +204,5 @@ IJCAI 联办届次的逐条后续核查见 [2018/2022 分区与目录差集](ijc
|
||||
- [MM 2026 官方节目来源状态](../mm2026-source-status.md):完整官方日程 JSON、重复展示盘点、28 个来源 track、缺失作者/摘要和四条匿名决定路径的 403 证据;这些不是已导入或公开拒稿全集。
|
||||
|
||||
- [2026-11-18 公开负面来源核查](public-negative-source-audit-2026-11-18.md):ResearchArcade 930 条非 ICLR 声明的当前库比对、5 条未绑定声明及原始接口访问证据;不把镜像差集算作新增拒稿。
|
||||
|
||||
- [ECCV 2026 出版目录与节目单对账](eccv2026-publisher-crosswalk-2026-11-18.md)记录 Springer 78 卷的 DOI、节目单差异及 PostgreSQL 只读绑定核查。
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,20 @@
|
||||
# ECCV 2026 出版目录与节目单对账
|
||||
|
||||
2026-11-18 核验了 Springer LNCS 17001–17078 的全部 78 卷。会议索引显示 **2,835 条**,逐卷目录合计也有 **2,835 条带 DOI 的章节**,另有 156 项卷首或卷末资料。出版方卷册简介及大会节目单均为 **2,834 条**。两个来源仍有逐条差异,汇总数量相差一条的原因待核。逐卷数字、目录页哈希和只读数据库回执见[机器可读清单](eccv2026-publisher-crosswalk-2026-11-18.json)。[Springer 会议索引](https://link.springer.com/conference/eccv) · [第一卷](https://link.springer.com/book/10.1007/978-3-032-36984-0) · [大会节目单](https://eccv.ecva.net/Conferences/2026/AcceptedPapers)
|
||||
|
||||
## 逐篇对账
|
||||
|
||||
|核对对象|唯一标题且完整作者顺序一致|唯一标题且目录所显示作者顺序一致|标题对得上、作者有差异|标题待核|
|
||||
|---|---:|---:|---:|---:|
|
||||
|全部 2,834 条节目记录|1,332|709|535|258|
|
||||
|首批已入库的 30 条节目记录|23|3|4|0|
|
||||
|本次只读核验通过的 248 条既有论文候选|173|72|2|1|
|
||||
|20 篇有既往拒稿、桌拒或撤回的优先论文|12|7|1|0|
|
||||
|
||||
目录作者栏有时只显示前六人。作者差异包括缩写、姓名文字变化与排列变化。原始名单、顺序和来源保留,前缀匹配与作者差异需查章节作者页。节目单与出版目录的摘要、分轨及公开负面决定覆盖仍待分别核查。
|
||||
|
||||
## 当前库核对
|
||||
|
||||
只读核对了全部 2,835 个出版 DOI,68 个已有论文绑定。对账后另检查 271 个已知论文关联,涵盖 245 个本次候选和 26 个已入库节目记录。其中 14 个 DOI 已指向同一论文,257 个 DOI 尚未绑定。245 个候选内有 10 篇带既往负面决定。
|
||||
|
||||
下一批准备以出版 DOI、正式分轨和完整作者证据复核关联。首批 30 条节目记录保留原投稿、决定和来源。确认同届同一投稿后,再补充出版证据,避免重复创建 ECCV 投稿。本次核查未写入数据库。
|
||||
@@ -0,0 +1,339 @@
|
||||
{
|
||||
"sources": {
|
||||
"poster.html": {
|
||||
"url": "https://www3.cs.stonybrook.edu/~icdm2026/PosterwDemo/list.htm",
|
||||
"final_url": "https://www3.cs.stonybrook.edu/~icdm2026/PosterwDemo/list.htm",
|
||||
"http_status": 200,
|
||||
"bytes": 132977,
|
||||
"sha256": "b02083ca7574a188fe876851a700a12c131c262353db557bd43a8320fad5f747",
|
||||
"at": "2026-11-18T07:06:11.984184+00:00"
|
||||
},
|
||||
"schedule.html": {
|
||||
"url": "https://icdm2026.neu.edu.cn/DetailedSessions/list.htm",
|
||||
"final_url": "https://icdm2026.neu.edu.cn/DetailedSessions/list.htm",
|
||||
"http_status": 200,
|
||||
"bytes": 213830,
|
||||
"sha256": "c1294b89bae8c2dfcf652d8a25556e733ef42dc3ac3387070abe08419b961b0f",
|
||||
"at": "2026-11-18T07:06:12.349258+00:00"
|
||||
},
|
||||
"deepsync.html": {
|
||||
"url": "https://dm.cs.univie.ac.at/news/story/deepsync-paper-accepted-at-icdm-2026",
|
||||
"final_url": "https://dm.cs.univie.ac.at/news/story/deepsync-paper-accepted-at-icdm-2026",
|
||||
"http_status": 200,
|
||||
"bytes": 90333,
|
||||
"sha256": "e243196943434225acec2841b53c77a2b1459184e7c185e1e1cbb055118fe282",
|
||||
"at": "2026-11-18T07:06:20.561308+00:00"
|
||||
}
|
||||
},
|
||||
"poster_count": 343,
|
||||
"poster_groups": {
|
||||
"long-posters": 177,
|
||||
"short-posters": 166
|
||||
},
|
||||
"oral_count": 324,
|
||||
"shared_count": 324,
|
||||
"poster_only": {
|
||||
"DM1022": {
|
||||
"group": "short-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area C",
|
||||
"slot": "P2-3C-085",
|
||||
"session": "Applied Track: Real-world AI in finance, healthcare and industry II",
|
||||
"title": "Beyond Bidding Agents: A Dual-Role Multi-Agent Framework with Dynamic Reserve Pricing for Auto-Bidding Auctions",
|
||||
"line": 683
|
||||
},
|
||||
"DM1189": {
|
||||
"group": "long-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area A",
|
||||
"slot": "P1-3A-032",
|
||||
"session": "Heterogeneous data mining: spatiotemporal and representation learning",
|
||||
"title": "Traj-Transformer: Diffusion Models with Transformer for GPS Trajectory Generation",
|
||||
"line": 456
|
||||
},
|
||||
"DM1234": {
|
||||
"group": "long-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area A",
|
||||
"slot": "P1-2A-007",
|
||||
"session": "Foundations, causality and learning theory",
|
||||
"title": "Prediction-Powered Corpus Mining: Coverage-Valid Statistics from Scarce Labels",
|
||||
"line": 354
|
||||
},
|
||||
"DM1246": {
|
||||
"group": "short-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area B",
|
||||
"slot": "P2-3B-074",
|
||||
"session": "LLM-driven data mining and novel applications II",
|
||||
"title": "Feature Selection for Trajectory Inference",
|
||||
"line": 672
|
||||
},
|
||||
"DM1345": {
|
||||
"group": "short-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area B",
|
||||
"slot": "P2-3B-060",
|
||||
"session": "LLM-driven data mining and heterogeneous learning",
|
||||
"title": "TRACER: An LLM-based Coarse-to-Fine Framework for Adaptive Network Traffic Classification",
|
||||
"line": 658
|
||||
},
|
||||
"DM1408": {
|
||||
"group": "long-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area B",
|
||||
"slot": "P1-2B-043",
|
||||
"session": "Applied Track: Industrial, financial and decision intelligence",
|
||||
"title": "A Generation-to-Application Framework for Semantic ID Collision in Industrial Generative Recommendation",
|
||||
"line": 390
|
||||
},
|
||||
"DM1644": {
|
||||
"group": "long-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area B",
|
||||
"slot": "P1-2B-072",
|
||||
"session": "Recommendation, adaptation and spatiotemporal modeling II",
|
||||
"title": "LQ-Rec: Late Quantization for Sequential Recommendation",
|
||||
"line": 419
|
||||
},
|
||||
"DM1751": {
|
||||
"group": "short-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area A",
|
||||
"slot": "P2-3A-014",
|
||||
"session": "ML/DL and statistical methods",
|
||||
"title": "MissGNN: Missingness-Guided Graph Neural Network for Feature- and Sample-Aware Imputation",
|
||||
"line": 612
|
||||
},
|
||||
"DM1995": {
|
||||
"group": "long-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area B",
|
||||
"slot": "P1-2B-053",
|
||||
"session": "Applied Track: Recommendation, security and operational intelligence II",
|
||||
"title": "Multi-Modal Causal Disentanglement for Multi-Domain Sequential Audio Recommendation",
|
||||
"line": 400
|
||||
},
|
||||
"DM2002": {
|
||||
"group": "long-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area B",
|
||||
"slot": "P1-3B-048",
|
||||
"session": "Heterogeneous data mining and systems",
|
||||
"title": "HiMamba: A Hierarchical State Space Framework for Asymmetric Multimodal Data Mining in Clinical Assessment",
|
||||
"line": 472
|
||||
},
|
||||
"DM2055": {
|
||||
"group": "short-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area A",
|
||||
"slot": "P2-3A-038",
|
||||
"session": "Applied Track: Real-world AI in finance, healthcare and industry I",
|
||||
"title": "CGSBR: Adaptive Cross-Source Gating for Cold-Start Sequential Bundle Recommendation",
|
||||
"line": 636
|
||||
},
|
||||
"DM2140": {
|
||||
"group": "long-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area A",
|
||||
"slot": "P1-3A-008",
|
||||
"session": "Machine learning and statistical methods",
|
||||
"title": "Reliability-Guided Pseudo-Label Learning and Prototype Alignment for Domain-Adaptive Colorectal Segmentation",
|
||||
"line": 432
|
||||
},
|
||||
"DM252": {
|
||||
"group": "short-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area B",
|
||||
"slot": "P2-2B-046",
|
||||
"session": "LLM-driven data mining and novel applications I",
|
||||
"title": "Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols",
|
||||
"line": 572
|
||||
},
|
||||
"DM383": {
|
||||
"group": "long-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area A",
|
||||
"slot": "P1-2A-022",
|
||||
"session": "Heterogeneous graphs and multimodal intelligence",
|
||||
"title": "Subgraph Meta-Learning for Direction and Time Aware Transaction Anomaly Detection",
|
||||
"line": 369
|
||||
},
|
||||
"DM463": {
|
||||
"group": "short-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area B",
|
||||
"slot": "P2-2B-050",
|
||||
"session": "Modeling, recommendation and LLM methods",
|
||||
"title": "CaST-POI: Candidate-Conditioned Spatiotemporal Ranking for Next POI Recommendation",
|
||||
"line": 576
|
||||
},
|
||||
"DM483": {
|
||||
"group": "short-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area B",
|
||||
"slot": "P2-2B-051",
|
||||
"session": "Modeling, recommendation and LLM methods",
|
||||
"title": "Causal Masking Lowers Intrinsic Dimension in Full-Vocabulary Sequential Recommendation: Evidence from a Single-Variable Attention Ablation",
|
||||
"line": 577
|
||||
},
|
||||
"DM713": {
|
||||
"group": "short-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area B",
|
||||
"slot": "P2-2B-060",
|
||||
"session": "Modeling, recommendation and LLM methods",
|
||||
"title": "Hint-Conditioned Knowledge Tracing: A Causal-Inspired View of Context-Dependent Hint Usage",
|
||||
"line": 586
|
||||
},
|
||||
"DM736": {
|
||||
"group": "long-posters",
|
||||
"floor": "3F",
|
||||
"area": "Area B",
|
||||
"slot": "P1-3B-050",
|
||||
"session": "LLM-driven data mining and retrieval I",
|
||||
"title": "From Natural-Language Hypotheses to Verified Data-Mining Discoveries",
|
||||
"line": 474
|
||||
},
|
||||
"DM803": {
|
||||
"group": "short-posters",
|
||||
"floor": "2F",
|
||||
"area": "Area B",
|
||||
"slot": "P2-2B-032",
|
||||
"session": "Heterogeneous data mining and multimodal learning I",
|
||||
"title": "Graph-Guided LLM Reasoning for Incident Prediction Over Multi-Source Data Streams",
|
||||
"line": 558
|
||||
}
|
||||
},
|
||||
"oral_only": [],
|
||||
"title_differences": [
|
||||
{
|
||||
"paper_id": "DM1319",
|
||||
"poster_title": "FFE-FRCN: A Frequency Feature Enhanced Few-shot Learning Approach for Object Detection in Microscopic Images",
|
||||
"oral_title": "An FFE-FRCN-Based Data Platform for Environmental Microorganism Image Retrieval and Knowledge Platform"
|
||||
}
|
||||
],
|
||||
"nonpaper_table_rows": [],
|
||||
"database_written": false,
|
||||
"scope": "Official presentation metadata. Shared programme IDs identify repeated appearances within this event. Poster-only IDs are scheduling observations pending identity and publication review.",
|
||||
"pg_readonly": {
|
||||
"snapshot": {
|
||||
"at": "2026-11-18 07:08:21.138511+00",
|
||||
"snapshot": "1095530:1095530:"
|
||||
},
|
||||
"report_sha256": "04ad5547342d7e3c2939046f290ecff647878c202c867e47acbdc438d4e10ad4",
|
||||
"existing_icdm2026_editions": [],
|
||||
"existing_icdm_program_source": false,
|
||||
"reviewed_links": [
|
||||
{
|
||||
"external_id": "2026/DM1125",
|
||||
"paper_id": 2783475,
|
||||
"track": "research",
|
||||
"source_row_sha256": "4e981605cf471a5ea29bb3ba3a676784cea55f7777a681eb5fe267ff9c83fa4a",
|
||||
"source_abstract": null,
|
||||
"work_anchor": {
|
||||
"scheme": "arxiv",
|
||||
"value": "2608.29635"
|
||||
},
|
||||
"independent_source": "https://arxiv.org/abs/2608.29635",
|
||||
"existing_history": [
|
||||
{
|
||||
"id": 132984,
|
||||
"venue": "ICLR",
|
||||
"year": 2026,
|
||||
"observations": [
|
||||
{
|
||||
"id": 134279,
|
||||
"status": "rejected"
|
||||
},
|
||||
{
|
||||
"id": 539402,
|
||||
"status": "rejected"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"original_icdm_decision_verified": false,
|
||||
"imported": false
|
||||
},
|
||||
{
|
||||
"external_id": "2026/DM790",
|
||||
"paper_id": 2485633,
|
||||
"track": "applied",
|
||||
"source_row_sha256": "14e03ca3833b267d6f677325f4e4b9295d1fa42cc77be6707b9bca745444888b",
|
||||
"source_abstract": null,
|
||||
"work_anchor": {
|
||||
"scheme": "arxiv",
|
||||
"value": "2509.19774"
|
||||
},
|
||||
"independent_source": "https://arxiv.org/abs/2509.19774",
|
||||
"existing_history": [
|
||||
{
|
||||
"id": 138980,
|
||||
"venue": "ICLR",
|
||||
"year": 2026,
|
||||
"observations": [
|
||||
{
|
||||
"id": 545219,
|
||||
"status": "withdrawn"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"original_icdm_decision_verified": false,
|
||||
"imported": false
|
||||
},
|
||||
{
|
||||
"external_id": "2026/DM1157",
|
||||
"paper_id": 3286364,
|
||||
"track": "research",
|
||||
"source_row_sha256": "22ed027f29a161bc978b3c33e921b42c67d999d520eed49ec46ce5935a6f2f2a",
|
||||
"source_abstract": null,
|
||||
"work_anchor": {
|
||||
"scheme": "openreview_snapshot",
|
||||
"value": "2026/1dGzRTSLqL"
|
||||
},
|
||||
"independent_source": "https://dm.cs.univie.ac.at/news/story/deepsync-paper-accepted-at-icdm-2026",
|
||||
"existing_history": [
|
||||
{
|
||||
"id": 127709,
|
||||
"venue": "ICLR",
|
||||
"year": 2026,
|
||||
"observations": [
|
||||
{
|
||||
"id": 129094,
|
||||
"status": "rejected"
|
||||
},
|
||||
{
|
||||
"id": 534293,
|
||||
"status": "rejected"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"original_icdm_decision_verified": false,
|
||||
"imported": false
|
||||
}
|
||||
],
|
||||
"held": [
|
||||
{
|
||||
"external_id": "2026/DM1791",
|
||||
"paper_id": 3288747,
|
||||
"reason": "DomainBridging has name-order/format differences and no arxiv self-accepted link; token-bag retrieval is not author or work identity approval."
|
||||
},
|
||||
{
|
||||
"external_id": "2026/DM1801",
|
||||
"paper_id": 3288866,
|
||||
"reason": "LightGFC author lists substantially differ; hold version/work review, no automatic author aliases or merge."
|
||||
},
|
||||
{
|
||||
"external_id": "2026/DM1413",
|
||||
"paper_id": 3292171,
|
||||
"reason": "OFS author lists differ including JianchengLv vs JindiLv; not treated as aliases; hold independent version/work verification."
|
||||
}
|
||||
]
|
||||
},
|
||||
"publisher_catalog_status": "No 2026 IEEE publisher catalogue verified in this check",
|
||||
"public_negative_availability": "unverified",
|
||||
"next": "Use the existing oral source denominator by track. Compare the three reviewed candidates with the fresh import baseline and preserve their earlier attempts. Keep the poster-only rows as a separate source inventory, and resolve the title disagreement before linking that poster."
|
||||
}
|
||||
@@ -0,0 +1,204 @@
|
||||
{
|
||||
"checked_on": "2026-11-18",
|
||||
"venue": "IROS",
|
||||
"year": 2026,
|
||||
"conference_program": {
|
||||
"url": "https://2026.ieee-iros.org/program/paper_index/",
|
||||
"status": "unavailable_in_checked_environment",
|
||||
"paper_level_full_index_verified": false
|
||||
},
|
||||
"publisher_registration_check": {
|
||||
"status": "no_target_container_in_first_25_relevance_results",
|
||||
"rows_checked": 25,
|
||||
"observed_container": "2026 IEEE 13th International Conference on Intelligent Systems (IS)",
|
||||
"complete_registry_search": false
|
||||
},
|
||||
"journal_presentations": {
|
||||
"journal": "IEEE Transactions on Robotics",
|
||||
"scope": "IROS 2026 conference presentation of journal papers",
|
||||
"rendered_index_and_embedded_entries_match": true,
|
||||
"count": 30,
|
||||
"xplore_document_ids": [
|
||||
"10989573",
|
||||
"11251175",
|
||||
"11488837",
|
||||
"11268969",
|
||||
"11098164",
|
||||
"11219220",
|
||||
"11304178",
|
||||
"11267071",
|
||||
"11304172",
|
||||
"11455384",
|
||||
"11397863",
|
||||
"11288096",
|
||||
"11544114",
|
||||
"11534108",
|
||||
"11488912",
|
||||
"11535315",
|
||||
"11342351",
|
||||
"11353077",
|
||||
"11429535",
|
||||
"11364144",
|
||||
"11427341",
|
||||
"11427344",
|
||||
"11455389",
|
||||
"11488904",
|
||||
"11535317",
|
||||
"11554436",
|
||||
"11495270",
|
||||
"11575122",
|
||||
"11488843",
|
||||
"11581355"
|
||||
],
|
||||
"conference_submission_decision_verified": false,
|
||||
"publication_dois_verified": false
|
||||
},
|
||||
"author_reported_conference_acceptance_candidates": [
|
||||
{
|
||||
"arxiv": "2607.06499",
|
||||
"acceptance_evidence": [
|
||||
"uw-roundup.html",
|
||||
"uw-faculty.html"
|
||||
],
|
||||
"author_count_current": 3,
|
||||
"work_identity_status": "existing_work_binding_verified_read_only",
|
||||
"database_paper_id": 2731624,
|
||||
"ordered_authors_match": true,
|
||||
"arxiv_versions_stored": [
|
||||
"v1"
|
||||
]
|
||||
},
|
||||
{
|
||||
"arxiv": "2505.04999",
|
||||
"acceptance_evidence": [
|
||||
"usc-acceptance.html"
|
||||
],
|
||||
"author_list_evidence": "usc-clam-project.html",
|
||||
"author_count_current": 7,
|
||||
"work_identity_status": "existing_work_binding_verified_read_only",
|
||||
"database_paper_id": 2381843,
|
||||
"ordered_authors_match": true,
|
||||
"arxiv_versions_stored": [
|
||||
"v1",
|
||||
"v2"
|
||||
]
|
||||
},
|
||||
{
|
||||
"acceptance_evidence": [
|
||||
"ntt-contributed.html"
|
||||
],
|
||||
"author_count_current": 6,
|
||||
"work_identity_status": "stable_identifier_and_track_pending"
|
||||
}
|
||||
],
|
||||
"purdue_scope_note": {
|
||||
"evidence": "purdue-mars.html",
|
||||
"reported_combined_count": 10,
|
||||
"reported_tro_subset": 2
|
||||
},
|
||||
"public_rejected_desk_rejected_withdrawn": "not_located_in_checked_public_sources",
|
||||
"coverage_status": "partial_source_audit",
|
||||
"database_written": false,
|
||||
"receipts": [
|
||||
{
|
||||
"name": "ieee-tro-list.html",
|
||||
"url": "https://www.ieee-ras.org/publications/t-ro/t-ro-list-of-conference-papers/",
|
||||
"final_url": "https://www.ieee-ras.org/publications/t-ro/t-ro-list-of-conference-papers/",
|
||||
"status": 200,
|
||||
"bytes": 610713,
|
||||
"sha256": "2f2bb466446c62c37dc0927f8df45b161a096cbf8ab1aeffc4f43fa5d27e6358"
|
||||
},
|
||||
{
|
||||
"name": "ieee-tro-policy.html",
|
||||
"url": "https://www.ieee-ras.org/publications/t-ro/",
|
||||
"final_url": "https://www.ieee-ras.org/publications/t-ro/",
|
||||
"status": 200,
|
||||
"bytes": 566001,
|
||||
"sha256": "37b8877babb62e69d61e8b32193378afad4372117025a139cf70ffc26fcada5c"
|
||||
},
|
||||
{
|
||||
"name": "ntt-contributed.html",
|
||||
"url": "https://group.ntt/en/topics/2026/09/28/iros2026.html",
|
||||
"final_url": "https://group.ntt/en/topics/2026/09/28/iros2026.html",
|
||||
"status": 200,
|
||||
"bytes": 221293,
|
||||
"sha256": "ade0a0320a83e1d4504ff5da24c9f495aed581cffa01aa38b1e4cbec331f6dbc"
|
||||
},
|
||||
{
|
||||
"name": "crossref-proceedings-query.json",
|
||||
"url": "https://api.crossref.org/works?query.container-title=2026+IEEE%2FRSJ+International+Conference+on+Intelligent+Robots+and+Systems+%28IROS%29&filter=prefix%3A10.1109%2Ctype%3Aproceedings-article%2Cfrom-pub-date%3A2026-01-01%2Cuntil-pub-date%3A2026-12-31&rows=25&select=DOI%2Ctitle%2Cevent%2Ccontainer-title%2Cpublisher%2Cpublished%2CURL",
|
||||
"final_url": "https://api.crossref.org/works?query.container-title=2026+IEEE%2FRSJ+International+Conference+on+Intelligent+Robots+and+Systems+%28IROS%29&filter=prefix%3A10.1109%2Ctype%3Aproceedings-article%2Cfrom-pub-date%3A2026-01-01%2Cuntil-pub-date%3A2026-12-31&rows=25&select=DOI%2Ctitle%2Cevent%2Ccontainer-title%2Cpublisher%2Cpublished%2CURL",
|
||||
"status": 200,
|
||||
"bytes": 13634,
|
||||
"sha256": "415bf105de8006a42d3f2f8e6eb0078eb54c51bd65315296c0735e853431b228"
|
||||
},
|
||||
{
|
||||
"name": "purdue-mars.html",
|
||||
"url": "https://engineering.purdue.edu/IE/news/2026/she-iros-mars-lab",
|
||||
"final_url": "https://engineering.purdue.edu/IE/news/2026/she-iros-mars-lab",
|
||||
"status": 200,
|
||||
"bytes": 60386,
|
||||
"sha256": "fae6ba9637ea141ff3fda93643b97ddfb65d6ea3689f1bca3580956272b2d373"
|
||||
},
|
||||
{
|
||||
"name": "uw-acceptance.html",
|
||||
"url": "https://faculty.washington.edu/chx/post/2026-06-17-iros-mppi/",
|
||||
"status": 404,
|
||||
"error": "HTTP Error 404: "
|
||||
},
|
||||
{
|
||||
"name": "usc-acceptance.html",
|
||||
"url": "https://liralab.usc.edu/news/",
|
||||
"final_url": "https://liralab.usc.edu/news/",
|
||||
"status": 200,
|
||||
"bytes": 25381,
|
||||
"sha256": "9fa6b272b7995448a4318dd91cc94b93eeb514ddaa92d7df6880b3d93d91fceb"
|
||||
},
|
||||
{
|
||||
"name": "arxiv-2607.06499.html",
|
||||
"url": "https://arxiv.org/abs/2607.06499",
|
||||
"final_url": "https://arxiv.org/abs/2607.06499",
|
||||
"status": 200,
|
||||
"bytes": 43362,
|
||||
"sha256": "98fcbcaf39832f3002fa2910f69ca650481bb473cdb450290e5f9ca9245646a2"
|
||||
},
|
||||
{
|
||||
"name": "arxiv-2505.04999.html",
|
||||
"url": "https://arxiv.org/abs/2505.04999",
|
||||
"final_url": "https://arxiv.org/abs/2505.04999",
|
||||
"status": 200,
|
||||
"bytes": 42506,
|
||||
"sha256": "26ea0fd9ac8753b911ff97f1aaf29ea495f50b5c1e106b33c1336ea87c03b0df"
|
||||
},
|
||||
{
|
||||
"name": "uw-faculty.html",
|
||||
"url": "https://www.me.washington.edu/facultyfinder/xu-chen",
|
||||
"final_url": "https://www.me.washington.edu/facultyfinder/xu-chen",
|
||||
"status": 200,
|
||||
"bytes": 99274,
|
||||
"sha256": "877af368b564ba26a62b1ce4f947b439cceada2490dfb446b8730ba132c72c78"
|
||||
},
|
||||
{
|
||||
"name": "uw-roundup.html",
|
||||
"url": "https://faculty.washington.edu/chx/post/2026-09-07-new-papers-2026/",
|
||||
"final_url": "https://faculty.washington.edu/chx/post/2026-09-07-new-papers-2026/",
|
||||
"status": 200,
|
||||
"bytes": 180954,
|
||||
"sha256": "bc9ef19a07ea2875f8cfffe9afd62bcc2998fbe7c4bc8a4440c1bc87bae3856b"
|
||||
},
|
||||
{
|
||||
"name": "usc-clam-project.html",
|
||||
"url": "https://clamrobot.github.io/",
|
||||
"final_url": "https://clamrobot.github.io/",
|
||||
"status": 200,
|
||||
"bytes": 20098,
|
||||
"sha256": "3b3ea3f817ce6483807ace9b5a42ccf9835b811837346b63411190316fe2819c"
|
||||
}
|
||||
],
|
||||
"work_identity_review": {
|
||||
"snapshot_at": "2026-11-18 09:26:04.582744+00",
|
||||
"evidence_sha256": "5e5cfb57525a369e8c81e1a9ea6edeb4f5e83a33e1961eeead8a014e3d59ad6d",
|
||||
"existing_work_matches": 2,
|
||||
"database_written": false
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,21 @@
|
||||
# IROS 2026 来源核查
|
||||
|
||||
2026-11-18 核查了会议节目、期刊报告名单、作者机构公布的录用信息和 DOI 登记线索。逐项来源、响应哈希与文献定位符见[机器可读清单](iros2026-source-audit-2026-11-18.json)。本次来源核查未写入数据库。
|
||||
|
||||
## 期刊论文在会上报告
|
||||
|
||||
IEEE RAS 的 T-RO 名单在 IROS 2026 一节列出 30 个不同的 IEEE Xplore 文献编号。页面渲染内容和内嵌数据的编号及顺序完全一致。T-RO 政策允许已录用的期刊文章到 IROS 报告。后续应保留期刊出版与会议报告两种关系,并在确认期刊 DOI 后核对现有论文身份。本清单没有逐条验证 DOI 或会议投稿决定。[T-RO 报告名单](https://www.ieee-ras.org/publications/t-ro/t-ro-list-of-conference-papers/) · [T-RO 报告政策](https://www.ieee-ras.org/publications/t-ro/)
|
||||
|
||||
普渡大学的通告将团队的 10 项成果一同介绍,其中 2 项属于 T-RO。这个团队样本可以帮助核查来源口径,暂不用于生成逐篇录用记录。[普渡大学通告](https://engineering.purdue.edu/IE/news/2026/she-iros-mars-lab)
|
||||
|
||||
## 作者机构公布的录用线索
|
||||
|
||||
- 华盛顿大学的作者通告列出 IROS 2026 待出版论文,标题与 arXiv 2607.06499 对应,三位作者一致。只读查询确认对应论文 2731624,库内标题与三位作者的顺序一致。[作者通告](https://faculty.washington.edu/chx/post/2026-09-07-new-papers-2026/) · [arXiv](https://arxiv.org/abs/2607.06499)
|
||||
- USC 实验室确认 CLAM 在 IROS 2026 录用。项目页指向 arXiv 2505.04999,当前作者名单为七人。库内 arXiv 保留 v1、v2,现有论文 2381843 的标题和七位作者顺序与当前详情页一致。[实验室通告](https://liralab.usc.edu/news/) · [作者项目页](https://clamrobot.github.io/) · [arXiv](https://arxiv.org/abs/2505.04999)
|
||||
- NTT 公布一条题名及六位作者,待核实稳定标识和会议 track。[NTT 通告](https://group.ntt/en/topics/2026/09/28/iros2026.html)
|
||||
|
||||
这两条工作身份已核实,尚未录入 IROS 录用证据。
|
||||
|
||||
## 待补证据
|
||||
|
||||
[会议论文索引](https://2026.ieee-iros.org/program/paper_index/)在受检环境未能读取。一次限定 IEEE、2026 年及会议论文类型的 Crossref 相关性查询返回的前 25 条属于另一会议。实际会议论文集 DOI、完整出版清单、正式分轨和逐篇覆盖仍待核查。已检查的公开来源中未找到逐篇拒稿、桌拒或撤回清单,继续保持这些决定的公开可得性待查。
|
||||
@@ -11,6 +11,6 @@ paper-atlas collect eccv2026-publications \
|
||||
|
||||
目录归档含 `receipts.jsonl`、`volume-checkpoint.json`、`summary.json` 及 156 页 HTML。摘要在章节详情页读取,章节归档沿用 `springer-selected` 的 `receipts.json` 格式。两类归档都按响应大小和 SHA-256 校验。目录卷号、分页、章节 DOI 归属、标题及 2026 年出处需要一致。已有输出目录需另查回执或换新空目录后运行。
|
||||
|
||||
输出含规范化 JSONL、manifest、采集回执以及所选章节的内容寻址存证。每条保留出版 DOI、卷号、页码、按顺序的完整作者及公开摘要。目录证据用 URL 和哈希连接到输入归档,保存归档以便复核。主会出版观察依据 Springer 正式论文集,原始投稿号、决定日期及签名仍未知。工具仅处理已归档的公开 HTML。
|
||||
输出含规范化 JSONL、manifest、采集回执以及所选章节的内容寻址存证。每条保留出版 DOI、卷号、页码、按顺序的完整作者及公开摘要。单名署名须由同页的结构化作者列表按顺序确认,确认后按原名保存为字符串,引用元数据仍保留原文。目录证据用 URL 和哈希连接到输入归档,保存归档以便复核。主会出版观察依据 Springer 正式论文集,原始投稿号、决定日期及签名仍未知。工具仅处理已归档的公开 HTML。
|
||||
|
||||
生成的文件待做论文身份复核后方可导入。准备生产批次时核实每个 DOI 与现有 arXiv 标识的绑定,保持两者的来源证据。对已存在的同届节目投稿需先核对投稿身份及轨道,再附加出版来源,避免因直接导入创建重复投稿。具有 ICLR 等既往决定的论文须保留原记录。新的增量导入 manifest 需以当前实际来源覆盖为父版本,留存待核差集和独立验收回执。
|
||||
|
||||
@@ -44,3 +44,13 @@ paper-atlas collect icdm2026-program \
|
||||
原始来源恢复包为 `/data/paper-index/validation/remaining2026-official-leads-v1-recovery.tar.gz`,SHA-256 为 `0be8c84bb5c591e5afaaa5f95dd5334bf13a9be1671cb942e46e998f502495bb`。独立盘点为 `/data/paper-index/validation/icdm2026-independent-program-inventory-v1.json`,SHA-256 为 `e13eaea0a158dcaafdf5dfb4af7948e4793b0e98041ec87d42b52513acfdc5f6`;本机工作记录目录也保留同名备份。
|
||||
|
||||
下次继续先验证源码版本、原始证据和实际输出,再寻找可公开取得的摘要与正式出版记录,核查逐篇版本、稳定标识及旧投稿历史,准备新的只读预检和可审阅入库队列。完成日程规范化不意味着 ICDM2026 整届出版覆盖、公开负面决定普查或最终全库去重完成。
|
||||
|
||||
## 2026-11-18 官方展示来源核查
|
||||
|
||||
口头日程的 324 个节目编号全部出现在官方海报排期。海报表有 343 个不同编号,其中长演讲组安排 177 项海报,短演讲组安排 166 项。19 个只见于海报表的编号作为独立来源线索登记。两份排期的覆盖范围各自保留,正式出版目录仍待核验。[官方详细日程](https://icdm2026.neu.edu.cn/DetailedSessions/list.htm) · [官方海报表](https://www3.cs.stonybrook.edu/~icdm2026/PosterwDemo/list.htm)
|
||||
|
||||
共同编号 DM1319 的标题在两个来源中实质不同。详细日程描述基于 FFE-FRCN 的数据平台,海报表描述 FFE-FRCN 的少样本检测方法。两份标题及来源位置均已留存,该编号的跨来源作品关联待核验。
|
||||
|
||||
生产只读快照确认 ICDM 2026 仍无入库届次。节目、作者和独立录用证据支持继续处理 DM1125、DM790、DM1157 三项既有作品关联。DM1125 和 DM1157 各有一次 ICLR 拒稿投稿及两条来源观察,DM790 有一次 ICLR 撤回投稿。三项均尚未导入,节目原始摘要字段缺失。另有三个候选存在作者名称顺序或名单差异,继续暂缓作品关联。[FALCON 作者记录](https://arxiv.org/abs/2608.29635) · [PPGFlowECG 作者记录](https://arxiv.org/abs/2509.19774) · [DeepSynC 大学录用说明](https://dm.cs.univie.ac.at/news/story/deepsync-paper-accepted-at-icdm-2026)
|
||||
|
||||
本轮仍未核实公开的 ICDM 2026 拒稿或撤回决定导出。[逐条差集、标题冲突、快照和后续入口](coverage/icdm2026-presentation-scope-2026-11-18.json)
|
||||
|
||||
@@ -30,6 +30,7 @@ COMMANDS = {
|
||||
('collect','eccv2026-publications'): ('paper_atlas.collectors.eccv2026_publications', {}, '核验ECCV2026 Springer 正式出版章节'),
|
||||
('collect','icassp2026-registry'): ('paper_atlas.collectors.icassp2026', {}, '核验 ICASSP 2026 冻结注册论文元数据'),
|
||||
('collect','icdm2026-program'): ('paper_atlas.collectors.icdm2026', {}, '核验 ICDM2026 冻结日程及明确的研究/应用轨道'),
|
||||
('collect','cikm2026-sources'): ('paper_atlas.collectors.cikm2026', {}, '核对 CIKM 2026 节目、附属议程与 Crossref 出版登记'),
|
||||
('collect','sdm2026-proceedings'): ('paper_atlas.collectors.sdm2026', {}, '核验 SDM 2026 注册论文并单独保留公开日程版本'),
|
||||
('collect','icaps2026-program'): ('paper_atlas.collectors.icaps2026', {}, '核验 ICAPS 2026 官方录用名单并分开既有论文展示'),
|
||||
('collect','rss2026-proceedings'): ('paper_atlas.collectors.rss2026', {}, '核验 RSS 2026 官方论文集与独立录用表'),
|
||||
|
||||
@@ -0,0 +1,164 @@
|
||||
"""Collect CIKM 2026 programme and Crossref metadata from frozen snapshots."""
|
||||
|
||||
import argparse
|
||||
from collections import Counter
|
||||
from hashlib import sha256
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
from paper_atlas.io.html import Document, clean
|
||||
|
||||
PROGRAM = 'https://cikm2026.diag.uniroma1.it/cikm-program/program.html'
|
||||
VOLUME = '10.1145/3799682'
|
||||
CONTAINER = 'Proceedings of the 35th ACM International Conference on Information and Knowledge Management'
|
||||
TRACKS = {'FULL': 596, 'SHORT': 234, 'APPLIED': 86, 'RESOURCE': 46, 'DEMO': 46}
|
||||
SUPPLEMENTAL = {'KEYNOTE', 'TUTORIAL', 'INDUSTRY', 'POSTER', 'PHD', 'PHD · REMOTE', 'WORKSHOP', 'ANALYTICUP'}
|
||||
PAGE_COUNTS = (250, 250, 250, 250, 81)
|
||||
HASHES = {
|
||||
'program.html': '3eaa668b6aaf09a671d8a3e19a2889b9ab21afaa7ded013794afa94bf35281d6',
|
||||
'CIKM2026_program.html': 'e3630bd1247df713b8b618f1d3cd9709e7020b2524bb677f82a10f83badd1732',
|
||||
'crossref-parent.json': 'f3370418d86ccfcfaeb972073bc5fcd1c1c737caed96570fc83f99db0f7d204a',
|
||||
'crossref-page-1.json': '16bed29f8ee82d668b124c369b632c5c1de0753bdbec7eb72ecb22ffdda5c710',
|
||||
'crossref-page-2.json': '54424ca31d99462394c9fde5fecfd7dd16337351d21ede3169f19af54d4f49c5',
|
||||
'crossref-page-3.json': '2dc31d89f41966614ed66a11d1ebaa4b2a6904dcf92945b7185e72e7e65382dd',
|
||||
'crossref-page-4.json': 'fbbec2b52650dc99a0251c743f035a6fd95be263b04c55c12134cf8473bdde76',
|
||||
'crossref-page-5.json': '06151c5f770c1e37e8ea9dabe5210be9c969a14fa3bf9925a2d7730ced47d6e5',
|
||||
'crossref-pages.json': '8be1f8f05139f7a1231b73ad6430f28d2f625809f1530cd9de654f8b3c68c1ae',
|
||||
}
|
||||
|
||||
|
||||
def fields(node, css_class):
|
||||
return [child for child in node.walk() if css_class in child.attrs.get('class', '').split()]
|
||||
|
||||
|
||||
def parse_program(raw, *, require_doi):
|
||||
document = Document(raw.decode('utf-8'))
|
||||
papers = {}
|
||||
for card in fields(document.root, 'paper'):
|
||||
pid = card.attrs.get('data-pid')
|
||||
if not pid:
|
||||
continue
|
||||
titles = fields(card, 'ptitle')
|
||||
labels = fields(card, 'badge')
|
||||
abstracts = fields(card, 'abstxt')
|
||||
if pid in papers or len(titles) != 1 or len(labels) != 1 or len(abstracts) > 1:
|
||||
raise ValueError(f'Invalid or repeated programme card {pid}')
|
||||
title = clean(titles[0].text())
|
||||
label = clean(labels[0].text())
|
||||
authors = [clean(author.text()) for author in fields(card, 'au')]
|
||||
abstract = clean(abstracts[0].text()) if abstracts else None
|
||||
doi_url = titles[0].attrs.get('href')
|
||||
doi = doi_url.removeprefix('https://doi.org/') if doi_url else None
|
||||
if label not in TRACKS or not title or not authors or not all(authors):
|
||||
raise ValueError(f'Incomplete programme metadata {pid}')
|
||||
if require_doi and (not doi or not re.fullmatch(re.escape(VOLUME) + r'\.\d+', doi) or not abstract):
|
||||
raise ValueError(f'Missing programme DOI or abstract {pid}')
|
||||
papers[pid] = {'programme_id': pid, 'title': title, 'author_display_names': authors,
|
||||
'abstract': abstract, 'programme_label': label, 'programme_doi_link': doi_url,
|
||||
'doi': doi if require_doi else None}
|
||||
return papers
|
||||
|
||||
|
||||
def parse_supplemental(raw):
|
||||
document = Document(raw.decode('utf-8'))
|
||||
events = {}
|
||||
for session in fields(document.root, 'sessblock'):
|
||||
section = session.attrs.get('id', '')
|
||||
if not section.startswith(('pre-', 'kn-')):
|
||||
continue
|
||||
for card in fields(session, 'paper'):
|
||||
labels = fields(card, 'badge')
|
||||
if len(labels) != 1:
|
||||
raise ValueError(f'Ambiguous supplemental label in {section}')
|
||||
label = clean(labels[0].text())
|
||||
if label not in SUPPLEMENTAL:
|
||||
continue
|
||||
titles = fields(card, 'ptitle')
|
||||
abstracts = fields(card, 'abstxt')
|
||||
locator = card.attrs.get('id') or section
|
||||
if locator in events or len(titles) != 1 or len(abstracts) > 1:
|
||||
raise ValueError(f'Ambiguous supplemental entry {locator}')
|
||||
events[locator] = {'programme_locator': locator, 'programme_section': section,
|
||||
'programme_label': label, 'title': clean(titles[0].text()),
|
||||
'author_display_names': [clean(a.text()) for a in fields(card, 'au')],
|
||||
'abstract': clean(abstracts[0].text()) if abstracts else None}
|
||||
return events
|
||||
|
||||
|
||||
def parse_registry(snapshots):
|
||||
volume = json.loads(snapshots['crossref-parent.json'])['message']
|
||||
if (volume['DOI'], volume['title'], volume['ISBN']) != (VOLUME, [CONTAINER], ['9798400725395']):
|
||||
raise ValueError('Unexpected Crossref volume')
|
||||
records = {}
|
||||
for number, count in enumerate(PAGE_COUNTS, 1):
|
||||
name = f'crossref-page-{number}.json'
|
||||
message = json.loads(snapshots[name])['message']
|
||||
if message['total-results'] != 1081 or len(message['items']) != count:
|
||||
raise ValueError(f'Unexpected Crossref pagination in {name}')
|
||||
for item in message['items']:
|
||||
doi = item['DOI'].lower()
|
||||
if (doi in records or not re.fullmatch(re.escape(VOLUME) + r'\.\d+', doi)
|
||||
or item.get('container-title') != [CONTAINER] or item.get('type') != 'proceedings-article'
|
||||
or item.get('published', {}).get('date-parts') != [[2026, 11, 6]]):
|
||||
raise ValueError(f'Unexpected Crossref record {doi}')
|
||||
records[doi] = {'registry': item, 'source_file': name}
|
||||
return records
|
||||
|
||||
|
||||
def collect(snapshots, output):
|
||||
snapshots = Path(snapshots)
|
||||
output = Path(output)
|
||||
if output.exists() or output.is_symlink():
|
||||
raise FileExistsError(output)
|
||||
bodies = {}
|
||||
for name, expected in HASHES.items():
|
||||
path = snapshots / name
|
||||
if path.is_symlink() or not path.is_file() or path.stat().st_size > 8 * 1024**2:
|
||||
raise ValueError(f'Invalid snapshot file {name}')
|
||||
raw = path.read_bytes()
|
||||
if sha256(raw).hexdigest() != expected:
|
||||
raise ValueError(f'Snapshot hash mismatch for {name}')
|
||||
bodies[name] = raw
|
||||
|
||||
programme = parse_program(bodies['program.html'], require_doi=True)
|
||||
alternate = parse_program(bodies['CIKM2026_program.html'], require_doi=False)
|
||||
supplemental = parse_supplemental(bodies['program.html'])
|
||||
registry = parse_registry(bodies)
|
||||
programme_dois = {r['doi'] for r in programme.values()}
|
||||
tracks = Counter(r['programme_label'] for r in programme.values())
|
||||
if (tracks != TRACKS or len(programme_dois) != len(programme) or programme_dois - registry.keys()
|
||||
or len(alternate) != 1005 or alternate.keys() - programme.keys()
|
||||
or len(supplemental) != 73 or len(registry) - len(programme_dois) != 73):
|
||||
raise ValueError('Unexpected programme or registry coverage')
|
||||
groups = {
|
||||
'programme': programme,
|
||||
'alternate-programme': alternate,
|
||||
'supplemental-programme': supplemental,
|
||||
'crossref': registry,
|
||||
}
|
||||
output.mkdir(parents=True, exist_ok=False)
|
||||
files = {}
|
||||
for name, rows in groups.items():
|
||||
filename = name + '.jsonl'
|
||||
payload = ''.join(json.dumps({'source_key': key, **row}, ensure_ascii=False) + '\n'
|
||||
for key, row in sorted(rows.items())).encode()
|
||||
(output / filename).write_bytes(payload)
|
||||
files[filename] = {'records': len(rows), 'sha256': sha256(payload).hexdigest()}
|
||||
report = {'status': 'collected_pending_identity_review', 'files': files, 'input_sha256': HASHES,
|
||||
'programme_by_label': dict(tracks), 'programme_dois_in_registry': len(programme_dois),
|
||||
'registry_outside_doi_programme': sorted(registry.keys() - programme_dois),
|
||||
'programme_ids_missing_from_alternate': sorted(programme.keys() - alternate.keys()),
|
||||
'database_written': False, 'public_negative_decisions_verified': False}
|
||||
partial = output / 'collection-report.json.part'
|
||||
partial.write_text(json.dumps(report, ensure_ascii=False, indent=2) + '\n', encoding='utf-8')
|
||||
partial.replace(output / 'collection-report.json')
|
||||
return report
|
||||
|
||||
|
||||
def main(argv=None, *, prog=None):
|
||||
parser = argparse.ArgumentParser(prog=prog, description=__doc__)
|
||||
parser.add_argument('--snapshots', type=Path, required=True)
|
||||
parser.add_argument('--out', type=Path, required=True)
|
||||
options = parser.parse_args(argv)
|
||||
print(json.dumps(collect(options.snapshots, options.out), ensure_ascii=False))
|
||||
@@ -54,6 +54,27 @@ def read_page(index, url):
|
||||
return raw, evidence
|
||||
|
||||
|
||||
def require_display_authors(nodes, authors):
|
||||
matching_article_lists = []
|
||||
for node in nodes:
|
||||
if node.tag != 'script' or node.attrs.get('type') != 'application/ld+json':
|
||||
continue
|
||||
try:
|
||||
article = json.loads(''.join(node.children))
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
if not isinstance(article, dict) or article.get('@type') != 'ScholarlyArticle':
|
||||
continue
|
||||
entries = article.get('author')
|
||||
if not isinstance(entries, list) or not all(
|
||||
isinstance(entry, dict) and isinstance(entry.get('name'), str) for entry in entries
|
||||
):
|
||||
raise ValueError('Unreviewed Springer article author list')
|
||||
matching_article_lists.append([clean(entry['name']) for entry in entries])
|
||||
if matching_article_lists != [authors]:
|
||||
raise ValueError('Single-name author requires matching Springer display author list')
|
||||
|
||||
|
||||
def parse_chapter(html, doi, *, book_title, publication_year):
|
||||
nodes = list(Document(html).root.walk())
|
||||
meta = defaultdict(list)
|
||||
@@ -73,12 +94,22 @@ def parse_chapter(html, doi, *, book_title, publication_year):
|
||||
raise ValueError('Missing named chapter authors')
|
||||
authors = []
|
||||
for raw in raw_authors:
|
||||
if ',' not in raw:
|
||||
name = clean(raw)
|
||||
if len(name.split()) != 1 or not any(character.isalpha() for character in name):
|
||||
raise ValueError('Unreviewed citation author format')
|
||||
authors.append(name)
|
||||
continue
|
||||
if raw.count(',') != 1:
|
||||
raise ValueError('Unreviewed citation author format')
|
||||
family, given = [clean(s) for s in raw.split(',', 1)]
|
||||
if not family or not given:
|
||||
raise ValueError('Incomplete citation author')
|
||||
authors.append({'given':given, 'family':family})
|
||||
if any(isinstance(author, str) for author in authors):
|
||||
display_names = [author if isinstance(author, str) else author['given']+' '+author['family']
|
||||
for author in authors]
|
||||
require_display_authors(nodes, display_names)
|
||||
abstract_nodes = [n for n in nodes if n.attrs.get('id') == 'Abs1-content']
|
||||
if len(abstract_nodes) > 1:
|
||||
raise ValueError('Ambiguous abstract section')
|
||||
|
||||
@@ -9,7 +9,7 @@ import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors.springer_selected import (
|
||||
BOOK, SOURCE, collect, parse_chapter, parse_toc, read_page, snapshot_index,
|
||||
BOOK, SCOPE, SOURCE, collect, parse_chapter, parse_toc, read_page, snapshot_index,
|
||||
)
|
||||
from paper_atlas.db.store import Store
|
||||
from paper_atlas.ingestion.records import ingest_file
|
||||
@@ -153,6 +153,28 @@ class SpringerSelectedTests(unittest.TestCase):
|
||||
html = self.fixture['chapters']['chapter-01.html'].replace('id="Abs1-content"','id="not-an-abstract"')
|
||||
self.assertIsNone(parse_chapter(html, BOOK+'_1')['abstract'])
|
||||
|
||||
def test_single_name_preserves_literal_and_requires_ordered_display_confirmation(self):
|
||||
html = f"""
|
||||
<meta name="citation_doi" content="{BOOK}_1">
|
||||
<meta name="citation_inbook_title" content="{SCOPE['book_title']}">
|
||||
<meta name="citation_publication_date" content="{SCOPE['publication_year']}">
|
||||
<meta name="citation_title" content="Example">
|
||||
<meta name="citation_author" content="Rajkumar">
|
||||
<meta name="citation_author" content="Doe, Jane">
|
||||
<meta name="citation_firstpage" content="1">
|
||||
<meta name="citation_lastpage" content="5">
|
||||
"""
|
||||
article = {'@type':'ScholarlyArticle', 'author':[{'name':'Rajkumar'}, {'name':'Jane Doe'}]}
|
||||
script = '<script type="application/ld+json">{}</script>'
|
||||
chapter = parse_chapter(html+script.format(json.dumps(article)), BOOK+'_1')
|
||||
self.assertEqual(chapter['authors'], ['Rajkumar', {'family':'Doe', 'given':'Jane'}])
|
||||
self.assertEqual(chapter['authors_citation_raw'], ['Rajkumar','Doe, Jane'])
|
||||
with self.assertRaisesRegex(ValueError, 'matching Springer display author list'):
|
||||
parse_chapter(html, BOOK+'_1')
|
||||
article['author'].reverse()
|
||||
with self.assertRaisesRegex(ValueError, 'matching Springer display author list'):
|
||||
parse_chapter(html+script.format(json.dumps(article)), BOOK+'_1')
|
||||
|
||||
def test_toc_ignores_frontmatter_but_rejects_duplicate_publications(self):
|
||||
html = self.fixture['toc']['springer-toc1.html']
|
||||
self.assertEqual(len(parse_toc(html)), 17)
|
||||
|
||||
Reference in New Issue
Block a user