Compare commits
9 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| c8db6118d4 | |||
| 1c64971a52 | |||
| ac14df0625 | |||
| afb3b939ca | |||
| 8c147f5e6e | |||
| 6961710e96 | |||
| f4be9de547 | |||
| 33bb378369 | |||
| b14193063a |
@@ -46,6 +46,26 @@ jobs:
|
||||
subprocess.run([python,'-B','-m','pip','install','--no-deps',str(wheel)],check=True)
|
||||
outside = root / 'outside-checkout'
|
||||
outside.mkdir()
|
||||
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():
|
||||
path = mm_snapshots/name
|
||||
path.parent.mkdir(parents=True,exist_ok=True)
|
||||
path.write_bytes(body.encode('utf-8'))
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','mm2026-program','--snapshots',str(mm_snapshots),'--out',str(root/'installed-mm2026')],cwd=outside,check=True)
|
||||
mm_report = json.loads((root/'installed-mm2026/collection-report.json').read_text())
|
||||
assert (mm_report['records'],mm_report['program_observations'],mm_report['extra_presentation_observations']) == (2143,4326,2183)
|
||||
assert len(mm_report['files']) == 28 and mm_report['missing_abstract_count'] == 216
|
||||
assert mm_report['session_count'] == 157 and not mm_report['database_written'] and mm_report['network_requests'] == 0 and mm_report['approved_for_import'] == 0
|
||||
mm_rows = {r['paper_id']:r for f in mm_report['files'] for r in map(json.loads,pathlib.Path(f['file']).read_text().splitlines())}
|
||||
import hashlib
|
||||
assert set(mm_rows) == {g['paper_id'] for g in mm_fixture['independent_inventory']['inventory']}
|
||||
for gold in mm_fixture['independent_inventory']['inventory']:
|
||||
row = mm_rows[gold['paper_id']]
|
||||
assert (row['title'],row['authors'],row['affiliations'],row['track']) == (gold['title'],gold['authors'],gold['affiliations'],gold['track_literal'])
|
||||
assert hashlib.sha256(row['abstract'].encode()).hexdigest() == gold['abstract_sha256']
|
||||
assert [c['source_pointer'] for c in row['contexts']] == gold['locations']
|
||||
assert not row['approved_for_import'] and not row['final_decision_verified'] and 'emails' not in row
|
||||
subprocess.run([str(venv/'bin/paper-atlas'),'--help'],cwd=outside,check=True)
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','cvf','--help'],cwd=outside,check=True)
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','rss2026-proceedings','--help'],cwd=outside,check=True)
|
||||
@@ -151,6 +171,36 @@ jobs:
|
||||
(rss_snapshots/'receipts.json').write_text(json.dumps(rss_fixture['receipts']))
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','rss2026-proceedings','--snapshots',str(rss_snapshots),'--out',str(root/'installed-rss2026')],cwd=outside,check=True)
|
||||
assert json.loads((root/'installed-rss2026/collection-report.json').read_text())['records'] == 210
|
||||
recsys_fixture = json.loads(gzip.decompress((src/'tests/fixtures/recsys2026-source.json.gz').read_bytes()))
|
||||
recsys_snapshots = root/'recsys2026-snapshots'
|
||||
recsys_snapshots.mkdir()
|
||||
for name,encoded in recsys_fixture['files'].items():
|
||||
path = recsys_snapshots/name
|
||||
path.parent.mkdir(parents=True,exist_ok=True)
|
||||
path.write_bytes(base64.b64decode(encoded))
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','recsys2026-program','--snapshots',str(recsys_snapshots),'--out',str(root/'installed-recsys2026')],cwd=outside,check=True)
|
||||
recsys_report = json.loads((root/'installed-recsys2026/collection-report.json').read_text())
|
||||
assert (recsys_report['records'],recsys_report['unique_dois'],recsys_report['missing_abstract_count']) == (263,260,0)
|
||||
assert recsys_report['duplicate_doi_observations'] == 6 and len(recsys_report['repeated_dois']) == 3
|
||||
assert not recsys_report['database_written'] and recsys_report['network_requests'] == 0 and recsys_report['approved_for_import'] == 0
|
||||
recsys_rows = [json.loads(line) for manifest in recsys_report['files'] for line in pathlib.Path(manifest['file']).read_text().splitlines()]
|
||||
gold_keys = recsys_fixture['independent_gold'][0].keys()
|
||||
assert [{k:r['metadata']['program_fields'][k] for k in gold_keys} for r in recsys_rows] == recsys_fixture['independent_gold']
|
||||
ismir_fixture = json.loads(gzip.decompress((src/'tests/fixtures/ismir2026-source.json.gz').read_bytes()))
|
||||
ismir_snapshots = root/'ismir2026-snapshots'
|
||||
ismir_snapshots.mkdir()
|
||||
for name,encoded in ismir_fixture['files'].items():
|
||||
target = ismir_snapshots/name
|
||||
target.parent.mkdir(parents=True,exist_ok=True)
|
||||
target.write_bytes(base64.b64decode(encoded))
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','collect','ismir2026-program','--snapshots',str(ismir_snapshots),'--out',str(root/'installed-ismir2026')],cwd=outside,check=True)
|
||||
ismir_report = json.loads((root/'installed-ismir2026/collection-report.json').read_text())
|
||||
assert (ismir_report['records'],ismir_report['missing_abstract_count'],ismir_report['review_optin_yes'],ismir_report['review_optin_no']) == (140,0,101,39)
|
||||
assert ismir_report['literal_title_version_differences'] == 2 and ismir_report['author_sequence_version_differences'] == 3
|
||||
assert not ismir_report['database_written'] and ismir_report['network_requests'] == 0 and ismir_report['approved_for_import'] == 0
|
||||
ismir_rows = [json.loads(line) for line in pathlib.Path(ismir_report['files'][0]['file']).read_text().splitlines()]
|
||||
assert [(r['external_id'],r['title'],r['authors'],r['abstract']) for r in ismir_rows] == [('2026/'+g['program_id'],g['title'],g['authors'],g['abstract']) for g in ismir_fixture['independent_gold']]
|
||||
assert all(not r['identifiers'] and not r['submission_identifiers'] and r['metadata']['paper_type'] is None for r in ismir_rows)
|
||||
corl_fixture = json.loads(gzip.decompress((src/'tests/fixtures/corl2026-source.json.gz').read_bytes()))
|
||||
corl_official = root/'corl2026-official'
|
||||
corl_archive = root/'corl2026-archive'
|
||||
|
||||
@@ -131,8 +131,14 @@ ICAPS 2026 也提供独立的 `collect icaps2026-registry`,保留 Crossref 卷
|
||||
|
||||
ECCV 2026 的[暂定节目采集器](docs/eccv2026-program.md)合并重复节目 ID,并以不可变缓存断点采集公开元数据;保留摘要原文、来源关键词及未分类 track,始终待身份审核,不自动入库。
|
||||
|
||||
`collect ismir2026-program` 核验 140 项 ISMIR 官方录用节目及原始摘要,保留两处标题、三处作者名单差异和 101 组自愿公开评审文本;不推断原始 OpenReview ID 或拒稿。见 [ISMIR 2026 使用与恢复说明](docs/ismir2026-program.md)。
|
||||
|
||||
`collect icassp2026-registry` 从冻结的 10 页 Crossref 元数据核验 4,582 条论文,明确排除 7 条非论文及 56 条其他会议记录;保留摘要缺失和单字段作者姓名,不自动融合节目表。见 [ICASSP 2026 采集与恢复说明](docs/icassp2026-registry.md)。
|
||||
|
||||
`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 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)。
|
||||
|
||||
`collect mm2026-program` 从已冻结官方快照恢复全部 28 个来源 track 的 2,143 个节目 ID,保留 4,326 次展示的来源位置与场次上下文,单列 216 个摘要缺失项;输出供贡献类型、出版及作品身份核查使用,不是可直接导入的论文/决定队列。见 [MM 2026 使用、来源和恢复说明](docs/mm2026-source-status.md)。
|
||||
|
||||
@@ -189,6 +189,8 @@ ICAPS官方共同历史明确列出两个前身系列,现有DBLP映射只覆
|
||||
|
||||
MM 2026 的[官方 CFP](https://2026.acmmm.org/site/cfp-guidelines.html)说明会后公开最终评审及适用的作者回复,但未明确包含全部被拒投稿。2026-11-08 对官方组的匿名 API 查询返回200,对该组 `venueid` 的投稿查询返回403;[证据](mm-editions-2026-11-08.json)保存查询、时间和响应哈希。公开拒稿可用性仍为 unknown,403不能作为零记录或不存在公开拒稿的证据。
|
||||
|
||||
2026-11-17后续:完整节目JSON与按声明的负面venue ID进行的四条匿名403核查已冻结,见 [MM最新来源状态](../mm2026-source-status.md);没有据此关闭公开拒稿缺口。
|
||||
|
||||
WWW早期逐来源核查见 `www-early-proceedings-2026-11-08.json`:1995春季论文三目录均为38个相同条目ID,海报摘要53个条目与作者链接47个条目不齐;1994春季50个Title字段与主页49场报告说法待逐项核对。上述为源目录观察,不是已导入或全部录用数量;主会、海报、教程等继续独立核验。
|
||||
|
||||
WWW事件标识生产迁移已独立验收(报告SHA `f5dbb8a8`):保留1399个原届次字段及IDs、59个Fall投稿和完整全库历史哈希。服务器已缓存46个官方HTML来源(约223KB),只作为后续维护式采集器的输入;尚未补导早期WWW论文,也未启用可选注解表。
|
||||
@@ -198,3 +200,5 @@ IJCAI 联办届次的逐条后续核查见 [2018/2022 分区与目录差集](ijc
|
||||
2026年11月9日的[当前历史年度缺口核对](historical-gaps-2026-11-09.md)单列135个历史会议—年份、14个2026年度及85个经范围修正的初步候选来源年度;它使用当前生产edition/别名快照,保留原固定快照不变。年度有记录不等于逐篇、逐track或公开拒稿历史完整。
|
||||
|
||||
[早期NLP来源范围复核](historical-source-scope-2026-11-09.md)保留3份官方网页的响应哈希,排除4个COLING卷对ACL缺口的误匹配,并区分会议举办记录、目录可获取性与论文级覆盖;尚未导入或关闭这些年度缺口。
|
||||
|
||||
- [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。
|
||||
|
||||
@@ -1,47 +1,48 @@
|
||||
# 2020 起补漏状态:2026-11-17
|
||||
|
||||
**总体仍为 13/17,第 14 步未完成。** 本页补充新的生产结果,不回写 [2026-11-10 恢复清单](backfill-handoff-2026-11-10.md) 或更早快照。用户确定的范围不变:2020 年起主动补漏;43 个更早历史缺口延期而非补齐,2000–2019 已发现的名单和身份线索继续保留。
|
||||
**总体仍为 13/17,第 14 步未完成。** 本页更新当日最新生产结果;[2026-11-10 恢复清单](backfill-handoff-2026-11-10.md)和更早快照继续保留。用户确定的范围不变:2020 年起主动补漏;43 个更早历史缺口延期而非补齐,2000–2019 已发现的名单和身份线索继续保留。
|
||||
|
||||
## 最新数据库盘点
|
||||
|
||||
只读快照 `2026-11-17 09:38:31.677743+00`,固定 43 个目标会议、278 个应有会议年份槽位,其中 270 个至少有一条投稿记录,8 个仍为空,均为 2026 年:**CIKM、ECCV、ICASSP、ICDM、IROS、ISMIR、MM、RecSys**。本次 SDM2026 新增记录使空槽从 9 减到 8。
|
||||
只读快照 `2026-11-17 14:06:28.803415+00`,固定 43 个目标会议、278 个应有会议年份槽位,其中 **272 个至少有一条投稿记录,6 个仍完全为空**,均为 2026 年:**CIKM、ECCV、ICDM、IROS、ISMIR、MM**。SDM25、ICASSP112、RecSys47 三批分别使空槽从 9 降至 8、7、6。
|
||||
|
||||
这只说明有无记录,**不表示 270 个槽位已经逐篇、逐 track、摘要或公开拒稿覆盖完整**;不能据此宣布第 14 步完成。2020–2025 没有整年空槽,仍有逐来源完整性和公开负面决定缺口。SDM2026 仅导入 25/53 条,状态为 partial,同样不能称为整届补齐。
|
||||
这些是会议—年份的存在性统计,**不表示 272 个槽位已逐篇、逐 track、摘要或公开拒稿覆盖完整**。2020–2025 没有整年空槽,仍有来源完整性和公开负面决定缺口。RecSys 九轨、ICASSP 和 SDM 的本批来源均仍为 partial;不能据此宣布第 14 步完成。
|
||||
|
||||
| 生产文件(相对 `/data/paper-index/`) | SHA-256 |
|
||||
| 生产文件(相对 `/data/paper-index/`) | SHA256 |
|
||||
| --- | --- |
|
||||
| collected/active-scope-census-20261117-v17/summary.json | bfb1db8b50619c3756abb91ad0f73fa58ff998c7db58a216661342f12047749f |
|
||||
| collected/active-scope-census-20261117-v17/snapshot.json | b5389205f8b34f7ed57946416f49c253e0aed4a05e45eb818801f18fca6a8cb4 |
|
||||
| collected/active-scope-census-20261117-v19/summary.json | cf0c5a013b6efe7d232187c9c76d9820bc8b33e2dd5674cab53d78cd3369ab4c |
|
||||
| collected/active-scope-census-20261117-v19/snapshot.json | 38d09e3782372edbdd2840f5922d65fb497c425b1eaf2d1fb10342956a7a82f2 |
|
||||
| validation/active-scope-fixed278-v1.json | a835bef5b9c3a0f76069d840cecdb9a6bcf65d3a38796d70dbfdfd4b49242264 |
|
||||
|
||||
## 已推进的两批来源
|
||||
原始快照、范围定义与生成脚本已备份,本机已按固定范围和别名逐条重算 272/278,未用 `max(id)` 推算数量。此前 v17/v18 快照保留,不能将其旧数字当作当前状态。
|
||||
|
||||
- **SDM2026**:53 个正式注册章节、53 个独立日程观察和 52 个公开摘要页已冻结并规范化。25 条发表记录已在 PostgreSQL 独立验收,新增论文实体为 0;28 条待身份/版本核查。完整旧历史和 5,653 篇受保护论文的资料、来源、标签和既有标识保留。见 [生产验收与恢复](../sdm2026-identity-review.md)。这批队列已经消费,禁止重放。
|
||||
- **ECCV2026**:2,834 个唯一初步日程条目及公开摘要已全量采集并独立验收;新的只读身份预检和 1,997 个候选历史证据包已保存,尚未入库。初步日程不等于已核验出版社最终论文集;负面决定元数据仍受匿名访问限制。见 [来源状态](../eccv2026-source-status.md)。
|
||||
## 已独立接受的近期补录
|
||||
|
||||
SDM 新增事件使 SeBA 和 AdamG 同时具有较早 ICLR 拒稿与后来的 SDM 发表事实。旧的两次 ICLR 投稿及四条决定来源观察仍保留,没有被较晚 accepted 覆盖;多个来源观察不直接累加成多次拒稿。
|
||||
- **RecSys2026**:官方九轨 263 项观察、260 个不同 DOI 均已冻结并规范化。47 条现有作品关联通过独立验收,新增论文实体为 0;新增一个来源、九个 edition、47 次投稿/47 条录用观察、47 个发表 DOI 投稿标识及47条来源类型标签证据。原始摘要单独保存,规范摘要不覆盖。5,812 篇受保护旧作品及全部旧投稿/决定历史保持不变,foundry 就绪检查200、SQLite备份只读。216项待审查,包括三组重复 DOI 的六项观察。见 [九轨验收与恢复](../recsys2026-program.md)。
|
||||
- **ICASSP2026**:Crossref 冻结的 4,645 个条目中排除 56 个其他会议条目和 7 个目录/封面等非论文条目,剩余 4,582 条注册论文;全部注册摘要缺失。112 条已有 DOI 的来源/录用历史已独立验收,新增论文实体为 0,coverage 为 partial112/4582;4,470 条仍待身份核查。正式节目标题表与注册元数据保持独立,不自动融合作者或摘要。见 [来源边界与恢复](../icassp2026-registry.md)。
|
||||
- **SDM2026**:53 个注册章节、53 项独立日程观察及 52 页摘要已冻结。25 条来源关联已独立接受,新增论文实体为 0,28 条待审查;见 [生产验收与恢复](../sdm2026-identity-review.md)。
|
||||
|
||||
## 其余七个会议的最新入口核查
|
||||
三批已经消费的输入队列均**禁止重放**。最新已接受生产结果为 RecSys47:论文实体仍为 **3,567,888**,来源记录 **3,814,931**,投稿 **531,620**,决定来源观察 **571,172**。观察数不等于不同论文或不同投稿的数量;后续须使用当前基线和新的增量队列。
|
||||
|
||||
已对下表七个会议的 14 个明确官方 URL 保存原始响应和回执:13 个 HTTP 200,IROS 官方论文索引 HTTP 403。所有请求均匿名,不绕过访问限制,没有下载论文 PDF;保存入口不是完成逐篇采集或负面决定普查。
|
||||
SDM 新增事件使 SeBA 和 AdamG 同时保有较早 ICLR 拒稿与后来 SDM 发表事实。原来的两次 ICLR 投稿及四条决定来源观察均保留,没有被 accepted 覆盖;四条观察不能直接累加成四次拒稿。本批 RecSys47 本身没有既往负面观察,但全部旧全库历史同样通过保护验收。
|
||||
|
||||
| 会议 | 已保存的明确官方入口 | 尚未完成 |
|
||||
## 已采集、尚待关联或规范化的来源
|
||||
|
||||
| 会议 | 已取得的来源与状态 | 下一步 |
|
||||
| --- | --- | --- |
|
||||
| ICDM | [详细日程](https://icdm2026.neu.edu.cn/DetailedSessions/list.htm)、[研究轨道政策](https://icdm2026.neu.edu.cn/CallforResearchTrack/list.htm)、[应用轨道政策](https://icdm2026.neu.edu.cn/CallforAppliedTrack/list.htm) | 官方页面称为线下展示列表;需要核对逐篇范围、研究/应用轨道及演讲长短标签,不能把展示长短自动等同于论文类型;摘要和正式出版身份仍待核查 |
|
||||
| ICASSP | [录用标题清单](https://cmsworkshops.com/ICASSP2026/papers/accepted_papers.php)、[作者指南](https://2026.ieeeicassp.org/author-guidelines/) | 取得逐篇完整作者/摘要/出版记录,区别会议投稿与期刊展示,不能只导入标题或从缺席推断拒稿 |
|
||||
| IROS | [官方论文索引](https://2026.ieee-iros.org/program/paper_index/) | 当前服务器返回 403,保留缺口并停止该入口;第三方浏览器页面不能替代独立核验的官方原文 |
|
||||
| ISMIR | [官网](https://ismir2026.ismir.net/)、[官方虚拟平台](https://ismir2026program.ismir.net/)、[作者指南](https://ismir2026.ismir.net/authors/author-guidelines) | 核查平台公开静态数据与正式开放论文集的逐篇映射;首页可读取不代表论文目录已经取得 |
|
||||
| CIKM | [录用页](https://cikm2026.diag.uniroma1.it/accepted-papers/)、[日程页](https://cikm2026.diag.uniroma1.it/program/) | 网页提取的录用页仍显示 TBD;需要检查原文引用的节目数据与独立正式出版目录,不能当成没有论文 |
|
||||
| RecSys | [官网](https://recsys.acm.org/recsys26/)、[投稿说明](https://recsys.acm.org/recsys26/call/) | 继续取得可核验的逐篇正式记录,并分开主轨、工业、复现、demo、challenge/workshop |
|
||||
| MM | [官网](https://2026.acmmm.org/) | 继续核对官方完整日程和出版目录,分开研究论文与 grand challenge、workshop 等;首页响应不证明覆盖完整 |
|
||||
| ECCV | 2,834 个不同初步节目 ID 及公开摘要已独立采集;1,997 个只读候选历史证据包已保存,尚未入库 | 初步日程不等于 Springer 最终论文集;继续作品/版本和出版核查。见 [来源状态](../eccv2026-source-status.md) |
|
||||
| ICDM | 324 项线下节目观察,明确研究241/应用83;演讲长168/短156,摘要均缺失;规范化和80个候选历史包已核验 | 展示长短不能当成论文类型;需审查作品与正式出版版本,尚未导入主库。见 [采集器说明](../icdm2026-program.md) |
|
||||
| ISMIR | 140 项节目和正式名单均已核验,140份摘要,101组自愿公开评审;两处标题、三处作者名单差异保留,78个候选历史包已核验 | 数字 miniconf ID 不是原始 OpenReview ID;评审意见不转成最终拒稿。继续作品身份/历史关联,尚未入库。采集器见 [PR #63](https://gitea.entroia.com/Zayden-Jung/paper-atlas/pulls/63) |
|
||||
| MM | 官方10.8MB日程JSON已冻结,4,326次观察对应2,143个节目ID、28个来源track;重复展示核心字段一致,216个ID缺摘要,其中两项主轨同时缺作者 | 不是2,143篇已核验科研论文。先区分各轨贡献与活动、保留全部上下文并单列缺失;尚未规范化/入库。见 [来源与访问证据](../mm2026-source-status.md) |
|
||||
| CIKM | 官方录用/日程入口与五个分轨页面已保存;五个分轨链接实际是CFP/政策,不是逐篇录用名单 | 查找实际节目或出版社完整目录;TBD和没有静态表不能当作没有论文 |
|
||||
| IROS | 官方论文索引入口的原始HTTP403已保存 | 保留访问限制,不重试绕过;寻找可合法读取、能独立核验的出版元数据 |
|
||||
|
||||
冻结目录:`/data/paper-index/collected/remaining2026-official-leads-v1`。manifest SHA-256:`0e13313d94e3bff17f071d3a1384f6ed83ece156239fe5bc4633cc7a34fb8e04`。恢复包:`/data/paper-index/validation/remaining2026-official-leads-v1-recovery.tar.gz`,SHA-256:`0be8c84bb5c591e5afaaa5f95dd5334bf13a9be1671cb942e46e998f502495bb`。HTTP 成功仅是入口可读性,不能作为可导入记录数量。
|
||||
早期 14 个入口快照保持在 `/data/paper-index/collected/remaining2026-official-leads-v1`,后续新增原文另建冻结目录,不覆盖早期回执。HTTP200只证明入口可读,不直接作为可导入记录或全部论文数量。
|
||||
|
||||
## 第 14 步仍需做什么
|
||||
## 公开拒稿与后续工作
|
||||
|
||||
1. 取得并规范化其余可公开取得的完整逐篇来源,记录应有范围、排除项和版本;对缺失、受限或尚未公开的入口保存明确证据,不能伪造“已补齐”。优先推进当前可读的 ICDM 详细日程、ICASSP 清单及其他会议的正式目录。
|
||||
2. 完成来源与年度、track、摘要完整性的对应核查;已经有若干记录的年份也要看目录差集,不能只消除空槽。
|
||||
3. 继续近期和历史年度实际公开的 rejected、desk_rejected、withdrawn 来源核查,特别是 UAI2024–2026 的 opt-in 拒稿、EMNLP2023 的实际公开范围以及其他会议的逐年限定政策。公开评审和公开决定不同;没有找到不等于零条或未曾拒稿。
|
||||
4. 通过身份核查的记录再执行新快照守护、恢复备份和增量导入,保留较早决定。深层作品版本、跨会历史及类型/标签协调继续列为第 15 步;不能为减少空槽创建重复论文,也不能只盯住少量身份疑难项而停止其他来源采集。
|
||||
MM 官方群组元数据可匿名读取,但根据其给出的 submission invitation 和 rejected/withdrawn/desk-rejected venue ID,四次限1条的匿名 notes 核查均为403。查询、时间、原文和哈希已保留,没有认证重试或绕过权限。访问限制不等于零条负面记录;详见 [MM来源证据](../mm2026-source-status.md)。ISMIR公开的101组评审来自录用节目,不能记成101条拒稿。
|
||||
|
||||
第 16 步仍是所有导入结束后的独立全库去重与完整审计,第 17 步是最终长期运行/恢复和交付整理。上述任务均未因单批验收或 CI 成功而完成;总体 goal 继续保持 active。
|
||||
第14步仍需逐会议、年份、track完成公开拒稿/desk-reject/withdrawn来源核查和可得数据采集;继续核查UAI近年自愿公开范围、EMNLP实际覆盖范围及其余已列明缺口。不能从未见录用、评分、评审推荐、缺少摘要或接口不可访问制造负面决定。
|
||||
|
||||
之后仍需完成跨会作品/历次投稿与类型标签关联(第15步),所有导入结束后的独立全库去重、标识冲突、近似标题作者、摘要/约束/查询及覆盖审计(第16步),以及长期运行与恢复文档最终整理(第17步)。阶段性来源入库、测试通过、某年度有记录均不能替代这些验收。
|
||||
|
||||
@@ -0,0 +1,50 @@
|
||||
# ISMIR 2026 官方节目与摘要采集
|
||||
|
||||
这是长期维护项目中的离线采集器,按需处理冻结的官方元数据,不联网、不执行网页脚本、不下载论文 PDF、不连接数据库。输出仍须经过作品身份与投稿历史审查。
|
||||
|
||||
## 使用
|
||||
|
||||
```sh
|
||||
paper-atlas collect ismir2026-program \
|
||||
--snapshots /data/paper-index/collected \
|
||||
--out /data/paper-index/collected/ismir2026-normalized-<new-run>
|
||||
```
|
||||
|
||||
输入父目录需要三个冻结目录:
|
||||
|
||||
- `remaining2026-listings-research-v2`:清单、`ismir-accepted.html`、`ismir-call.html`。
|
||||
- `ismir2026-script-research-v1`:清单及 `papers.js`,用于证明官方程序明确加载的数据文件和 poster 链接模板;只读取脚本原文。
|
||||
- `ismir2026-json-research-v1`:清单及 `papers.json`,提供 140 项完整元数据和公开摘要。
|
||||
|
||||
固定清单和全部输入原始字节均校验 SHA256、HTTP 回执、官方 URL 及带时区的采集时间。已有输出目录不能覆盖;先检查原任务是否已结束,再选择新目录。失败保留 `failed.json`,只有全批成功才发布 `collection-report.json`。
|
||||
|
||||
## 来源与版本
|
||||
|
||||
[正式录用名单](https://ismir2026.ismir.net/accepted-papers)和[官方虚拟平台](https://ismir2026program.ismir.net/papers.html)各有 140 项,经来源内标题对应核查一致;其中 2 处标题有直引号/弯引号文字差异,3 处作者名单有差异,两个来源的原始写法分别保留并标记,不静默修正或拼接作者。
|
||||
|
||||
作者差异涉及节目 ID `60`、`126`、`433`,包含大小写和姓名完整度问题。正式名单的作者机构可能含括号和分号,采集器只在括号外拆分作者;作者原始字符串也保留。来源内名单对应不代表数据库作品身份已经获准关联。
|
||||
|
||||
- 原始 JSON 摘要全文保留,包括数学符号、换行和 Unicode,不作扁平化提取。
|
||||
- 数字 `id`、`forum` 是 miniconf 节目定位符,不视为原始 OpenReview 投稿 ID;不推断 DOI 或 arXiv ID,投稿标识列表保持空。
|
||||
- `accepted` 来自正式录用名单与节目平台,不是原始签名决定。`track=program_unclassified`,不从主题、session 或远程展示方式推断研究方法、workshop 或论文类型。
|
||||
- `ismir_program:keyword` 保存来源非空关键词,规范空白并去除同条记录内完全重复值;原始关键词列表(含空项)保留在元数据。
|
||||
- `ismir_program:presentation` 保存来源展示方式。Remote/In-person 是展示方式,不是研究类型。
|
||||
- poster URL 严格依据冻结的官方 JS 模板生成;本命令不请求 poster 页面。
|
||||
|
||||
## 公开评审与拒稿边界
|
||||
|
||||
原始来源中有 **101 组明确选择公开的评审材料**;其余 39 项 `publish_reviews=No`,评审正文为空。采集器验证此偏好和正文的一致性,原文保存在来源元数据,不把评审意见或 meta-review 中的推荐转换成额外的最终决定。
|
||||
|
||||
这些记录来自录用节目,不能据此当作 101 条公开拒稿记录。公开拒稿导出是否可得仍记为 unknown,需要单独核查。[征稿与评审流程](https://ismir2026.ismir.net/authors/call-for-papers)中的评审规则也不等于具体投稿决定。
|
||||
|
||||
输出包含一份 140 条 JSONL、部分覆盖清单、七个原始来源文件及报告,批准导入数为零。采集成功不等于会议论文/track/公开负面决定覆盖完整,也不替代最后的全库去重审计。
|
||||
|
||||
## 恢复与验证
|
||||
|
||||
`papers.json` SHA256:`864d384cbc928554504e1b39849137bb380143e247a48f2d71563a698cb8e62d`。
|
||||
|
||||
原始 JSON 和 JS 恢复包:服务器 `/data/paper-index/validation/ismir2026-json-research-recovery-v1.tar.gz`,本地 `/Users/zzyang/Documents/Codex/2026-11-06/paper-index/` 同名文件;SHA256 为 `bba7b236cfe4d8b259d6c1230b3fe09a3e9071f5203884c92b016ca0718fb095`。
|
||||
|
||||
正式名单与政策恢复包:同目录 `remaining2026-listings-research-v2-recovery.tar.gz`,SHA256 为 `f5ef7c2e73d46712146e4d6711ad5ad562e16b8b55c0cd75d1041cd0b81142cb`。安全恢复三个源目录、核验文件后可重跑上述命令。
|
||||
|
||||
完整来源和独立 140 项清单在测试夹具中冻结。测试、构建、打包、安装及实际隔离目录 CLI 验证只在用户指定 `ces-control:host` runner 执行。生产规范化后还需独立核验全部记录,并用 PostgreSQL 只读预检检查候选作品和既往投稿;不自动合并来源差异或人物身份。
|
||||
@@ -0,0 +1,92 @@
|
||||
# ACM MM 2026 官方节目来源状态
|
||||
|
||||
2026-11-17 已冻结官网正式日程、技术日程、征稿/评审政策、两个日程脚本和脚本明确引用的 `program-data.json`。本页记录可恢复的来源证据,不宣称这些节目贡献全部都是已发表科研论文;总体仍为 13/17,第 14 步未完成。
|
||||
|
||||
## 已取得的数据
|
||||
|
||||
[官方技术日程](https://2026.acmmm.org/site/technical-programme.html)明确加载 `technical-programme.js`,该脚本读取 [program-data.json](https://2026.acmmm.org/site/program-data.json)。原始 JSON 为 10,808,209 字节,生成时间为 `2026-11-14T18:36:26.860677+00:00`,保存了 5 天、20 个房间、157 个日程场次。
|
||||
|
||||
递归盘点得到 **4,326 次论文样式的节目观察,涉及 2,143 个不同节目 ID**。额外 2,183 次是直接列表和子场次/多次展示中重复的观察。相同 ID 的标题、作者、摘要、track 和机构字段一致;所有来源位置均保留,不能把重复展示累加成新论文。
|
||||
|
||||
独立盘点的逐 ID 来源 track 数量如下。它们来自 `paper.track`;157 个外层日程条目的 `entry.track` 均为空,不能用外层空字段覆盖真实来源分类。展示形式和学术 track 也不是同一概念。
|
||||
|
||||
| 来源 track 原文 | 不同节目 ID 数 |
|
||||
| --- | ---: |
|
||||
| MRAC | 35 |
|
||||
| SUMAC | 9 |
|
||||
| NeuroMM | 10 |
|
||||
| IMPACT | 8 |
|
||||
| RichMediaGAI | 10 |
|
||||
| MMSports | 16 |
|
||||
| MUWS | 5 |
|
||||
| EReL-MIR | 7 |
|
||||
| GreenMM | 10 |
|
||||
| DFF | 12 |
|
||||
| Main Track | 1703 |
|
||||
| Grand Challenge | 97 |
|
||||
| Doctoral Symposium | 4 |
|
||||
| Datasets | 50 |
|
||||
| Interactive Art | 23 |
|
||||
| Reproducibility | 1 |
|
||||
| Demo and Video | 27 |
|
||||
| Open Source | 14 |
|
||||
| Industry Talk | 7 |
|
||||
| BNI | 25 |
|
||||
| QoEVMA | 4 |
|
||||
| HUMA | 14 |
|
||||
| WIPAI | 8 |
|
||||
| AMI | 11 |
|
||||
| Mulsemedia | 9 |
|
||||
| UAVM | 11 |
|
||||
| MCHM | 7 |
|
||||
| JAV-CG | 6 |
|
||||
|
||||
共有 1,927 个节目 ID 带摘要,216 个缺少摘要。Main Track 的 1,703 个 ID 中,有两项同时缺少作者与摘要:
|
||||
|
||||
- `mfp4971`:ASDG: MLLM-based Audio Semantics for Dance Generation。
|
||||
- `mfp7801`:Dynamic Late Fusion Multiple Kernel k-means Clustering based on Adaptive Sample Selection and Alignment。
|
||||
|
||||
两项仍有科学标题,原文没有明确撤稿或拒稿标签;因此只能标记字段缺失、暂缓关联,不能推断负面决定。非主轨的 workshop、grand challenge、行业报告、艺术、博士生等项目还需逐轨核对存档与贡献类型,不能把全部 2,143 个节目 ID 都计作已发表科研论文。原始公开联系邮箱不进入独立盘点、人物别名或论文标识。
|
||||
|
||||
## 公开负面决定的访问边界
|
||||
|
||||
[官方 CFP](https://2026.acmmm.org/site/cfp-guidelines.html)链接至 [OpenReview 群组](https://openreview.net/group?id=acmmm.org/ACMMM/2026/Conference)。匿名群组元数据可读,但根据群组给出的原始 submission invitation、rejected/withdrawn/desk-rejected venue ID,进行的四次 `limit=1` 匿名 notes 核查全部返回 **HTTP 403**。
|
||||
|
||||
保存了准确查询、时间、状态、响应原文和哈希;没有认证、重试或绕过权限。403 是已观察接口的访问限制,不代表零条拒稿、从未拒稿,或排除了其他可能公开的来源。评审公开规则也不能替代具体最终决定记录。当前不从评分、评审推荐、节目缺席或空字段制造 rejected/withdrawn 事件。
|
||||
|
||||
## 产物与恢复
|
||||
|
||||
原始目录(均相对 `/data/paper-index/collected/`):
|
||||
|
||||
- `mm2026-program-policy-research-v1`:六页官方日程和分轨/评审政策。
|
||||
- `mm2026-navigation-research-v1`:官网明确加载的导航原文。
|
||||
- `mm2026-program-data-discovery-v1`:两份脚本及公开群组元数据。
|
||||
- `mm2026-program-and-public-probes-v1`:完整节目 JSON 和四个匿名访问限制回执。
|
||||
|
||||
独立盘点:`/data/paper-index/validation/mm2026-independent-program-inventory-v1.json`,包含每个节目 ID 的所有来源位置、track、标题/作者、摘要可用性及核心版本数量。全部响应原文、回执及盘点已在本机备份,并独立核验了原始字节哈希。
|
||||
|
||||
| 证据 | SHA256 |
|
||||
| --- | --- |
|
||||
| program-data.json | 08e2976ecba2d0d535000b0935f41c85076ec674e518a1df2c5843d9bde4d083 |
|
||||
| 独立逐 ID 盘点 | 375dd975fdff023f2ff591d47066ec616c2bfc3b717b6016ab162d74d587f3e7 |
|
||||
| 完整来源恢复包 | 8247149ed7437a36c13ca2b6128431e2b0f3f8a388a5ddefb62427b0c1ce6f8d |
|
||||
|
||||
服务器恢复包:`/data/paper-index/validation/mm2026-source-discovery-and-inventory-recovery-v1.tar.gz`;本地备份:`/Users/zzyang/Documents/Codex/2026-11-06/paper-index/` 同名文件。先安全解包并核验回执,再做规范化,不能重新抓取 403 入口作为恢复方式。
|
||||
|
||||
## 可复用采集命令
|
||||
|
||||
在已配置的服务器环境中运行,`--snapshots` 是包含 `mm2026-program-and-public-probes-v1/` 的父目录;恢复时先安全解包上述已核验恢复包。命令只读快照,不请求网络、不连接数据库,不重新访问403入口,也不下载PDF:
|
||||
|
||||
```sh
|
||||
paper-atlas collect mm2026-program \
|
||||
--snapshots /data/paper-index/collected \
|
||||
--out /data/paper-index/collected/mm2026-native-v1
|
||||
```
|
||||
|
||||
输出目录必须不存在;已存在、失败或部分输出均不能覆盖重跑,应先查看报告,另选新的目录。`collection-report.json` 仅在全量验证成功后生成;失败保留 `failed.json`,不冒充完成。
|
||||
|
||||
采集器核验固定回执、正文哈希、URL、抓取时间、完整逐轨数量和字段缺失盘点。28个逐轨 JSONL 保留原始标题、作者、机构、逐字摘要以及同一节目ID的全部展示位置、时间、poster/oral号和展示kind;157个场次及子场次/非论文活动另存 `sessions.jsonl`。外层空track不覆盖 `paper.track`,不同核心版本、未知字段或未处理嵌套需要重新审查,不能静默丢弃或取第一条。公开联系邮箱数组只留在原始证据中,不进入规范记录。`evidence/` 保留原始节目JSON、完整回执及四个既有403响应。
|
||||
|
||||
这些文件的格式为 `mm_program_observation_v1_not_ingestion_record`,所有项 `approved_for_import=false`。节目ID仅为 `mm_program:program_id` 来源定位符,track标签使用 `mm_program:track`;不建立科学作品、原始投稿ID或最终决定,不推断 DOI/arXiv/OpenReview 标识、论文类型、拒稿或撤稿。行业报告、艺术、workshop及其他来源贡献均保留,尚需逐轨核对贡献类型与正式出版依据。
|
||||
|
||||
本批尚未形成生产导入队列。后续做贡献类型、作品/出版身份及既往投稿审查,再生成经批准的增量队列。已消费的其他会议导入队列不可重放;最终全库去重和完整审计仍为独立必做阶段。
|
||||
@@ -0,0 +1,83 @@
|
||||
# RecSys 2026 公开录用贡献采集
|
||||
|
||||
这是长期维护项目中的离线采集器,按需处理冻结的官方元数据,不连接数据库、不访问论文链接或下载 PDF。输出须经过作品、DOI 和投稿历史审查才能导入。
|
||||
|
||||
## 使用
|
||||
|
||||
```sh
|
||||
paper-atlas collect recsys2026-program \
|
||||
--snapshots /data/paper-index/collected \
|
||||
--out /data/paper-index/collected/recsys2026-normalized-<new-run>
|
||||
```
|
||||
|
||||
输入父目录应包含 `remaining2026-listings-research-v2/manifest.json` 与 `recsys-contributions.html`。采集器检查固定清单 SHA256、官方 URL、HTTP 200、采集时区、原始字节哈希、九个 track 的菜单及完整条目数。现有输出目录不可覆盖;失败保留 `failed.json`,成功才发布 `collection-report.json`。再次运行前先检查原任务是否结束。
|
||||
|
||||
## 数据范围与重复项
|
||||
|
||||
来源是 [RecSys 官方录用贡献页面](https://recsys.acm.org/recsys26/contributions/),冻结时间为 2026-11-17。九个来源 track:
|
||||
|
||||
| track | 观察数 |
|
||||
| --- | ---: |
|
||||
| long | 65 |
|
||||
| short | 29 |
|
||||
| past_present_future | 13 |
|
||||
| reproducibility | 4 |
|
||||
| resource | 7 |
|
||||
| industry | 83 |
|
||||
| research_practice_notes | 34 |
|
||||
| demo | 18 |
|
||||
| doctoral_symposium | 10 |
|
||||
|
||||
**263 项来源观察对应 260 个不同 DOI,并非 263 篇不同论文。** 每条记录用官方页面中的 accordion locator 标识,分别保留来源标题、作者原文、摘要和位置,不假设 locator 是原始投稿 ID。
|
||||
|
||||
以下 DOI 各出现两次,六个观察均显式标记待审查:
|
||||
|
||||
- `10.1145/3773078.3831839`:Dart 两条来源记录的标题、作者和摘要都有差异;不得静默选一个覆盖另一个。
|
||||
- `10.1145/3773078.3831819`:标题与作者相同、摘要版本不同。
|
||||
- `10.1145/3773078.3831861`:重复展示的文字相同,保留两个来源位置。
|
||||
|
||||
所有观察都有公开摘要。正文只转换为 HTML 展示文字并规范空白,原始页面完整保留;遇到未审查的数学或图片结构会停止,不把上标扁平化成数字。作者按来源的逗号和最后一个 and 分隔,原始名单同时保留;这不是已验证的作者人物身份或别名。
|
||||
|
||||
`accepted` 仅指官方页面明示录用,不是原始签名评审决定。DOI 来自官方超链接,尚未独立核查实时出版商版本;归入 `publication_doi`,不复制其他会议的投稿 ID。track 明确来自页面区块;`recsys_program:contribution_type` 仅保存页面原始类型标签(Research、PastPresentFuture、Doctoral Symposium),各 track 的 RES/IND/RPN 等缩写同时保留在来源字段,不统一推断研究方法类型。
|
||||
|
||||
本页只含录用贡献,不能据此推断未出现的稿件被拒。公开拒稿导出仍为 unknown,征稿页的 desk rejection 政策不等于具体拒稿记录。不得将本批采集成功当成会议全部来源、负面决定或全库去重完成。
|
||||
|
||||
## 输出与恢复
|
||||
|
||||
输出九份 JSONL、对应部分覆盖清单、原始 HTML 和清单证据,以及记录观察数和不同 DOI 数的报告;批准导入数为零。
|
||||
|
||||
清单 SHA256:`fea7b710587636db06794ee195cd083634c41e9054a217859d9dd0ccdd1afab9`。
|
||||
|
||||
服务器恢复包 `/data/paper-index/validation/remaining2026-listings-research-v2-recovery.tar.gz`,本地备份 `/Users/zzyang/Documents/Codex/2026-11-06/paper-index/remaining2026-listings-research-v2-recovery.tar.gz`,SHA256 为 `f5ef7c2e73d46712146e4d6711ad5ad562e16b8b55c0cd75d1041cd0b81142cb`。安全恢复原始目录、核对哈希后重跑上述命令。
|
||||
|
||||
完整来源与独立 263 项基准已保存在测试夹具,所有测试、构建和安装验证交给指定的 `ces-control:host` runner。生产导入前还需独立核验规范化结果,并检查当前数据库已有 DOI 绑定及历次投稿。最终全库去重审计仍是独立必做阶段。
|
||||
|
||||
## 2026-11-17 PostgreSQL 补录验收
|
||||
|
||||
采集器仍只生成待审查文件;本节记录随后单独完成的生产补录。47 条来源记录已关联到 47 篇既有作品,依据是已绑定的同一发表 DOI、规范化标题、完整作者集合,以及原始 arXiv 来源明确引用的同一 DOI。逐条当前资料和历史包已与只读预检核对;没有新增论文实体、人物别名、arXiv 标识或原始 OpenReview ID。
|
||||
|
||||
| track | 已导入观察 / 来源应有观察 |
|
||||
| --- | ---: |
|
||||
| demo | 1 / 18 |
|
||||
| doctoral_symposium | 2 / 10 |
|
||||
| industry | 18 / 83 |
|
||||
| long | 13 / 65 |
|
||||
| past_present_future | 2 / 13 |
|
||||
| reproducibility | 1 / 4 |
|
||||
| research_practice_notes | 4 / 34 |
|
||||
| resource | 2 / 7 |
|
||||
| short | 4 / 29 |
|
||||
|
||||
九个 track 全部保持 **partial**。总计 47/263 个来源观察已导入,216 个待审查,其中包括三组重复 DOI 的六项观察。来源的 263 项观察对应 260 个不同 DOI,不能把观察数量当成不同科学论文数量。
|
||||
|
||||
本批新增一个来源、九个 edition、47 条来源记录、47 次投稿/47 条录用观察、47 个 `publication_doi` 投稿标识及47条来源类型标签证据关联。源摘要分别保存,47 篇既有作品的规范摘要保持不变;原始程序字段、来源链接、时间和类型标签也逐条核验。Research/PastPresentFuture/Doctoral Symposium 仍属于来源 namespace,不强制映射成统一研究方法类别。
|
||||
|
||||
独立验收确认:5,812 篇受保护旧作品及其旧资料、来源、标签、标识不变,全部旧投稿/决定原文与关联历史不变;foundry-core `/readyz` 为 200,受保护 SQLite 备份大小/只读权限不变。论文实体仍为 3,567,888;不能用 `max(id)` 代替行数。
|
||||
|
||||
- 完整验收:`/data/paper-index/collected/recsys2026-import47-v1/postgresql-postcheck-v1.json`,SHA256 `7c7e2dcd06bdbc839666740a989c1f187fa47290800a9055cf4540be64336cf4`。
|
||||
- 保护基线:`/data/paper-index/collected/recsys2026-import47-baseline-v1/baseline.json`,SHA256 `aa86d51ff18774a505b1c59510ad867c6221c152334dc4983d31c5290cb8ac0f`。
|
||||
- 导入前完整队列/基线恢复包:`/data/paper-index/validation/recsys2026-reviewed47-recovery-v1.tar.gz`,SHA256 `ae054a6447e8c2864fd8e365867cd3308dee974f375fafff5653fff2a51044e1`;本地同名备份位于 `/Users/zzyang/Documents/Codex/2026-11-06/paper-index/`,已核验全部 47 个原始身份包、九份输入和基线。
|
||||
|
||||
执行代码固定在提交 `8c147f5e6edda900e2eed19372ab031f661b31c5` 的独立验证目录,85 个包文件校验通过;24 个写入关键文件与此前已验收版本一致。授权 `ces-control:host` runner 的 CI1230/job1327通过525项测试及安装后实际RecSys263项/260DOI验证。没有改变服务器默认运行代码目录或共享数据库配置。
|
||||
|
||||
**九份输入均已消费,禁止重放。** 恢复时先检查实际 PostgreSQL、执行回执和终态验收;不能因日志安静、观测超时或重新启动 Goal 就复跑。后续216条须另建审查与增量队列,并重新取当前基线。本批通过不等于整届 RecSys、公开拒稿覆盖或最终全库去重已完成。
|
||||
@@ -23,6 +23,7 @@ COMMANDS = {
|
||||
('collect','colm'): ('paper_atlas.collectors.proceedings', {'source':'colm'}, 'COLM 官方论文集'),
|
||||
('collect','neurips'): ('paper_atlas.collectors.proceedings', {'source':'neurips'}, 'NeurIPS 官方论文集'),
|
||||
('collect','mlsys'): ('paper_atlas.collectors.proceedings', {'source':'mlsys'}, 'MLSys 官方历年标题与摘要'),
|
||||
('collect','ismir2026-program'): ('paper_atlas.collectors.ismir2026', {}, '核验 ISMIR 2026 公开节目与录用名单并保留原始摘要、来源差异和自愿公开评审'),
|
||||
('collect','icaps2026-registry'): ('paper_atlas.collectors.icaps_registry2026', {}, '核验 ICAPS 2026 Crossref 注册元数据并保留独立版本'),
|
||||
('collect','eccv2026-program'): ('paper_atlas.collectors.eccv2026', {}, '核验ECCV2026暂定节目并断点采集公开元数据'),
|
||||
('collect','icassp2026-registry'): ('paper_atlas.collectors.icassp2026', {}, '核验 ICASSP 2026 冻结注册论文元数据'),
|
||||
@@ -30,6 +31,8 @@ COMMANDS = {
|
||||
('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'),
|
||||
('collect','recsys2026-program'): ('paper_atlas.collectors.recsys2026', {}, '核验 RecSys 2026 公开录用贡献并保留 DOI 来源版本'),
|
||||
('collect','mm2026-program'): ('paper_atlas.collectors.mm2026', {}, '恢复 MM 2026 全部来源 track 与重复展示上下文,待贡献和身份核查'),
|
||||
('collect','cvf'): ('paper_atlas.collectors.vision', {'source':'cvf'}, 'CVPR / ICCV 官方开放目录'),
|
||||
('collect','ecva'): ('paper_atlas.collectors.vision', {'source':'ecva'}, 'ECCV 官方开放目录'),
|
||||
('collect','aamas-proceedings'): ('paper_atlas.collectors.aamas', {}, '按官方目录区分 AAMAS 发表形式和摘要'),
|
||||
|
||||
@@ -0,0 +1,208 @@
|
||||
"""Frozen ISMIR 2026 accepted program, abstracts and opt-in review provenance."""
|
||||
import argparse
|
||||
from collections import Counter
|
||||
from datetime import datetime
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
import unicodedata
|
||||
|
||||
from paper_atlas.io.html import Document, Node, clean
|
||||
|
||||
SOURCE = 'ismir_program'
|
||||
TRACK = 'program_unclassified'
|
||||
PAPERS = 'https://ismir2026program.ismir.net/papers.html'
|
||||
ACCEPTED = 'https://ismir2026.ismir.net/accepted-papers'
|
||||
SNAPSHOTS = {
|
||||
'remaining2026-listings-research-v2': ('fea7b710587636db06794ee195cd083634c41e9054a217859d9dd0ccdd1afab9',
|
||||
'research_completed_not_coverage_or_import_approval', {
|
||||
'ismir-accepted.html': ACCEPTED,
|
||||
'ismir-call.html': 'https://ismir2026.ismir.net/authors/call-for-papers'}),
|
||||
'ismir2026-script-research-v1': ('5885b4bcfc2fc65374e5dc7a0d74f4eb86a0a36b8689f9fe8edbd10d49a08794',
|
||||
'public_script_research_only', {'papers.js': 'https://ismir2026program.ismir.net/static/js/papers.js'}),
|
||||
'ismir2026-json-research-v1': ('8be3e23277c199720264d940917118572655d18c0f9ac6db1b9cd30a6561b34d',
|
||||
'public_metadata_json_research_only', {'papers.json': 'https://ismir2026program.ismir.net/papers.json'}),
|
||||
}
|
||||
REVIEW_KEYS = {'meta_review','publish_reviews','review1','review2','review3','review4'}
|
||||
|
||||
|
||||
def digest(raw):
|
||||
return hashlib.sha256(raw).hexdigest()
|
||||
|
||||
|
||||
def one(items):
|
||||
if len(items) != 1:
|
||||
raise ValueError('Expected exactly one reviewed source field')
|
||||
return items[0]
|
||||
|
||||
|
||||
def title_key(text):
|
||||
return ''.join(c for c in unicodedata.normalize('NFKD', text).casefold() if c.isalnum())
|
||||
|
||||
|
||||
def load_snapshots(root):
|
||||
root = Path(root)
|
||||
if root.is_symlink():
|
||||
raise ValueError('Unsafe snapshot root')
|
||||
result = {}
|
||||
for name, (expected, status, urls) in SNAPSHOTS.items():
|
||||
directory = root/name; path = directory/'manifest.json'
|
||||
if directory.is_symlink() or path.is_symlink() or path.stat().st_size > 128*1024:
|
||||
raise ValueError('Unsafe snapshot manifest')
|
||||
raw = path.read_bytes()
|
||||
if digest(raw) != expected:
|
||||
raise ValueError('Reviewed manifest hash changed')
|
||||
manifest = json.loads(raw)
|
||||
if manifest['status'] != status or manifest['database_written'] is not False:
|
||||
raise ValueError('Unreviewed snapshot scope')
|
||||
files = {'manifest.json': raw}; receipts = {}
|
||||
for filename, url in urls.items():
|
||||
receipt = one([r for r in manifest['entries'] if r.get('file') == filename])
|
||||
path = directory/filename
|
||||
if path.is_symlink() or path.stat().st_size > 8*1024**2:
|
||||
raise ValueError('Unsafe snapshot source file')
|
||||
body = path.read_bytes()
|
||||
if (receipt['url'] != url or receipt['final_url'] != url or receipt['http_status'] != 200
|
||||
or receipt['bytes'] != len(body) or receipt['sha256'] != digest(body)
|
||||
or datetime.fromisoformat(receipt['at']).utcoffset() is None):
|
||||
raise ValueError('Source receipt/body disagree')
|
||||
files[filename] = body; receipts[filename] = receipt
|
||||
result[name] = (files, receipts)
|
||||
return result
|
||||
|
||||
|
||||
def author_names(literal):
|
||||
# Institution names can contain semicolons; split only outside parentheses.
|
||||
parts = []; depth = 0; start = 0
|
||||
for index, char in enumerate(literal):
|
||||
if char == '(': depth += 1
|
||||
elif char == ')':
|
||||
depth -= 1
|
||||
if depth < 0: raise ValueError('Unbalanced author affiliation')
|
||||
elif char == ';' and depth == 0:
|
||||
parts.append(literal[start:index]); start = index+1
|
||||
if depth:
|
||||
raise ValueError('Unbalanced author affiliation')
|
||||
parts.append(literal[start:])
|
||||
names = [clean(p.split('(', 1)[0]) for p in parts]
|
||||
if any(not name for name in names):
|
||||
raise ValueError('Missing accepted-list author')
|
||||
return names
|
||||
|
||||
|
||||
def accepted_listing(raw):
|
||||
doc = Document(raw.decode('utf-8')); tables = []
|
||||
for table in doc.root.walk():
|
||||
if table.tag != 'table': continue
|
||||
rows = []
|
||||
for row in table.walk():
|
||||
if row.tag == 'tr':
|
||||
rows.append([clean(n.text()) for n in row.children if isinstance(n, Node) and n.tag in ('th','td')])
|
||||
if rows and rows[0] == ['Paper Title', 'Authors']:
|
||||
tables.append(rows)
|
||||
rows = one(tables)[1:]; result = {}
|
||||
if len(rows) != 140:
|
||||
raise ValueError('Incomplete official accepted-list census')
|
||||
for row in rows:
|
||||
if len(row) != 2 or not row[0] or not row[1] or title_key(row[0]) in result:
|
||||
raise ValueError('Missing or ambiguous accepted-list title')
|
||||
result[title_key(row[0])] = {'title': row[0], 'authors_literal': row[1], 'author_names': author_names(row[1])}
|
||||
return result
|
||||
|
||||
|
||||
def program_observations(rows, listing):
|
||||
if not isinstance(rows, list) or len(rows) != 140:
|
||||
raise ValueError('Incomplete public program census')
|
||||
observations = []; seen = set(); used = set()
|
||||
for original in rows:
|
||||
if not isinstance(original, dict) or not isinstance(original.get('content'), dict):
|
||||
raise ValueError('Invalid public program record')
|
||||
pid = original.get('id'); content = original.get('content', {})
|
||||
if not isinstance(pid, str) or not re.fullmatch(r'[1-9][0-9]*', pid) or pid in seen or original.get('forum') != pid:
|
||||
raise ValueError('Missing/repeated numeric program locator, not an OpenReview ID')
|
||||
seen.add(pid); title = content.get('title'); authors = content.get('authors'); abstract = content.get('abstract')
|
||||
if (not isinstance(title, str) or not clean(title) or not isinstance(abstract, str) or not abstract.strip()
|
||||
or not isinstance(authors, list) or not authors or any(not isinstance(a, str) or not clean(a) for a in authors)):
|
||||
raise ValueError('Missing program title, author sequence or abstract')
|
||||
key = title_key(title)
|
||||
if key not in listing or key in used:
|
||||
raise ValueError('Program/accepted-list title membership mismatch')
|
||||
used.add(key); accepted = listing[key]
|
||||
keywords = content.get('keywords'); presentation = content.get('paper_presentation')
|
||||
session = content.get('session'); reviews = original.get('reviews')
|
||||
if (not isinstance(keywords, list) or any(not isinstance(k, str) for k in keywords)
|
||||
or presentation not in ('Remote','In-person','Remote during oral, In-person during nominee')
|
||||
or not isinstance(session, list) or len(session) != 1 or not isinstance(session[0], str) or session[0] != original.get('session')
|
||||
or not re.fullmatch(r'(?:[1-9]|1[0-4])', session[0])):
|
||||
raise ValueError('Unreviewed source keywords, presentation or session')
|
||||
if (not isinstance(reviews, dict) or set(reviews) != REVIEW_KEYS
|
||||
or any(not isinstance(v, str) for v in reviews.values())
|
||||
or reviews['publish_reviews'] not in ('Yes','No')):
|
||||
raise ValueError('Unreviewed opt-in review structure')
|
||||
review_text = [reviews[k] for k in REVIEW_KEYS-{'publish_reviews'}]
|
||||
if (reviews['publish_reviews'] == 'No' and any(review_text)) or (reviews['publish_reviews'] == 'Yes' and not any(review_text)):
|
||||
raise ValueError('Review publication preference/body disagree')
|
||||
flags = []
|
||||
if title != accepted['title']: flags.append('program_and_accepted_title_literal_versions_differ')
|
||||
if authors != accepted['author_names']: flags.append('program_and_accepted_author_sequence_versions_differ')
|
||||
observations.append({'original': original, 'accepted_listing': accepted, 'review_flags': flags})
|
||||
if (used != listing.keys() or sum('program_and_accepted_title_literal_versions_differ' in o['review_flags'] for o in observations) != 2
|
||||
or {o['original']['id'] for o in observations if 'program_and_accepted_author_sequence_versions_differ' in o['review_flags']} != {'60','126','433'}
|
||||
or Counter(o['original']['reviews']['publish_reviews'] for o in observations) != {'Yes':101,'No':39}):
|
||||
raise ValueError('Unreviewed source-version or opt-in census')
|
||||
return observations
|
||||
|
||||
|
||||
def collect(out, *, snapshots):
|
||||
out = Path(out)
|
||||
if out.exists(): raise ValueError('Output exists; inspect previous operation before retrying')
|
||||
out.mkdir(parents=True)
|
||||
try:
|
||||
sources = load_snapshots(snapshots)
|
||||
official, _ = sources['remaining2026-listings-research-v2']; script, _ = sources['ismir2026-script-research-v1']
|
||||
program, receipts = sources['ismir2026-json-research-v1']; receipt = receipts['papers.json']
|
||||
if b"d3.json('papers.json')" not in script['papers.js'] or b'href="poster_${openreview.id}.html"' not in script['papers.js']:
|
||||
raise ValueError('Unreviewed public program data path or poster link template')
|
||||
observations = program_observations(json.loads(program['papers.json']), accepted_listing(official['ismir-accepted.html']))
|
||||
evidence = out/'evidence'; evidence.mkdir()
|
||||
for name, (files, _) in sources.items():
|
||||
directory = evidence/name; directory.mkdir()
|
||||
for filename, body in files.items(): (directory/filename).write_bytes(body)
|
||||
rows = []
|
||||
for observation in observations:
|
||||
original = observation['original']; content = original['content']; pid = original['id']
|
||||
tags = [{'namespace':SOURCE+':presentation','value':content['paper_presentation']}]
|
||||
tags += [{'namespace':SOURCE+':keyword','value':value} for value in dict.fromkeys(clean(k) for k in content['keywords'] if clean(k))]
|
||||
rows.append({'source':SOURCE,'external_id':'2026/'+pid,'url':'https://ismir2026program.ismir.net/poster_'+pid+'.html',
|
||||
'title':content['title'],'authors':content['authors'],'abstract':content['abstract'],
|
||||
'identifiers':{},'submission_identifiers':[],'venue':'ISMIR','year':2026,'track':TRACK,'status':'accepted',
|
||||
'raw_decision':'Present in official ISMIR2026 accepted list and public virtual program; not an original signed decision.',
|
||||
'evidence_url':ACCEPTED,'observed_at':receipt['at'],'tags':tags,
|
||||
'metadata':{'program_entry':original,'accepted_listing':observation['accepted_listing'],'review_flags':observation['review_flags'],
|
||||
'program_receipt':receipt,'source_evidence':{'file':'evidence/ismir2026-json-research-v1/papers.json','sha256':receipt['sha256'],'url':receipt['url']},
|
||||
'original_decision_signature_verified':False,'paper_type':None,
|
||||
'id_scope':'Numeric miniconf id/forum fields are program locators, not original OpenReview submission IDs; no inferred DOI or arxiv ID.',
|
||||
'track_scope':'Unclassified regular accepted-list program; no workshop or research-method class inferred from topic/session/remote presentation.',
|
||||
'review_scope':'101 source-opt-in review sets retained as raw public text;39No contain no review text. Reviewer recommendations/meta-review prose are not separately inferred final negative decisions.',
|
||||
'abstract_transform':'Original JSON abstract string retained verbatim, including math, newlines and Unicode; no markup flattening or PDF extraction.',
|
||||
'program_listing_scope':'Source versions remain separate.2title literal differences and3author-list differences flagged, not silently fused or resolved.',
|
||||
'scope':'Pending work/history review. Poster URL follows frozen official JS template; poster pages not downloaded. No work merge, aliases, negative decision or final coverage/dedup claim.'}})
|
||||
path = out/'ismir-program-2026-unclassified.jsonl';raw=''.join(json.dumps(r,ensure_ascii=False)+'\n' for r in rows).encode();path.write_bytes(raw)
|
||||
manifest={'source':SOURCE,'parser_version':1,'venue':'ISMIR','year':2026,'track':TRACK,'count':140,'file':str(path),
|
||||
'file_sha256':digest(raw),'list_url':ACCEPTED,'status':'partial','missing_abstract_count':0,'source_expected_count':140}
|
||||
path.with_suffix('.manifest.json').write_text(json.dumps(manifest,indent=2)+'\n')
|
||||
report={'status':'collected_pending_identity_review','records':140,'files':[manifest],'missing_abstract_count':0,
|
||||
'literal_title_version_differences':2,'author_sequence_version_differences':3,'review_optin_yes':101,'review_optin_no':39,
|
||||
'database_written':False,'network_requests':0,'pdfs_downloaded':False,'approved_for_import':0,
|
||||
'public_rejected_availability':'unknown_accepted_program_reviews_are_not_a_rejected_export',
|
||||
'scope':'140accepted observations;101opt-in review sets, not101rejected records. Source keyword/presentation tags are namespace-scoped; no original OpenReview ID assumption or source-version fusion.'}
|
||||
part=out/'collection-report.json.part';part.write_text(json.dumps(report,ensure_ascii=False,indent=2)+'\n');part.replace(out/'collection-report.json');return report
|
||||
except Exception as error:
|
||||
(out/'failed.json').write_text(json.dumps({'status':'failed_not_complete','error_type':type(error).__name__,'database_written':False})+'\n')
|
||||
raise
|
||||
|
||||
|
||||
def main(argv=None, *, prog=None):
|
||||
parser=argparse.ArgumentParser(prog=prog,description=__doc__);parser.add_argument('--snapshots',required=True);parser.add_argument('--out',required=True)
|
||||
args=parser.parse_args(argv);print(json.dumps(collect(args.out,snapshots=args.snapshots),ensure_ascii=False))
|
||||
@@ -0,0 +1,202 @@
|
||||
"""Restore frozen ACM MM 2026 program observations, not publication decisions."""
|
||||
import argparse
|
||||
from collections import Counter
|
||||
from datetime import datetime
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
SOURCE = 'mm_program'
|
||||
SNAPSHOT = 'mm2026-program-and-public-probes-v1'
|
||||
URL = 'https://2026.acmmm.org/site/program-data.json'
|
||||
BODY_SHA = '08e2976ecba2d0d535000b0935f41c85076ec674e518a1df2c5843d9bde4d083'
|
||||
MANIFEST_SHA = 'e43ac6cdfc86bac61305553a044dd6148800b5aa41a5d1bf06c486e90d0ed7b8'
|
||||
TRACK_COUNTS = {'MRAC':35,'SUMAC':9,'NeuroMM':10,'IMPACT':8,'RichMediaGAI':10,
|
||||
'MMSports':16,'MUWS':5,'EReL-MIR':7,'GreenMM':10,'DFF':12,'Main Track':1703,
|
||||
'Grand Challenge':97,'Doctoral Symposium':4,'Datasets':50,'Interactive Art':23,
|
||||
'Reproducibility':1,'Demo and Video':27,'Open Source':14,'Industry Talk':7,
|
||||
'BNI':25,'QoEVMA':4,'HUMA':14,'WIPAI':8,'AMI':11,'Mulsemedia':9,
|
||||
'UAVM':11,'MCHM':7,'JAV-CG':6}
|
||||
CORE = ('paper_id','title','authors','affiliations','abstract','track')
|
||||
PRESENTATION = ('kind','start_time','end_time','poster_id','oral_id')
|
||||
|
||||
|
||||
def digest(raw):
|
||||
return hashlib.sha256(raw).hexdigest()
|
||||
|
||||
|
||||
def safe_read(path, limit):
|
||||
if any(p.is_symlink() for p in (path, *path.parents)) or not path.is_file() or path.stat().st_size > limit:
|
||||
raise ValueError('Unsafe snapshot path or size')
|
||||
return path.read_bytes()
|
||||
|
||||
|
||||
def load_snapshot(root):
|
||||
directory = Path(root)/SNAPSHOT
|
||||
raw = safe_read(directory/'manifest.json', 128*1024)
|
||||
if digest(raw) != MANIFEST_SHA:
|
||||
raise ValueError('Reviewed manifest hash changed')
|
||||
manifest = json.loads(raw)
|
||||
if manifest.get('database_written') is not False or len(manifest['entries']) != 5:
|
||||
raise ValueError('Unreviewed manifest scope')
|
||||
evidence = {'manifest.json':raw}
|
||||
for receipt in manifest['entries']:
|
||||
name = receipt['file']
|
||||
if Path(name).name != name or name in evidence:
|
||||
raise ValueError('Unsafe or duplicate receipt name')
|
||||
body = safe_read(directory/name, 12*1024**2)
|
||||
if (receipt['bytes'] != len(body) or receipt['sha256'] != digest(body)
|
||||
or receipt['url'] != receipt['final_url']
|
||||
or not receipt['content_type'].startswith('application/json')
|
||||
or datetime.fromisoformat(receipt['at']).utcoffset() is None):
|
||||
raise ValueError('Snapshot receipt/body disagree')
|
||||
if name == 'program-data.json':
|
||||
if receipt['url'] != URL or receipt['http_status'] != 200 or digest(body) != BODY_SHA:
|
||||
raise ValueError('Wrong program source')
|
||||
elif receipt['http_status'] != 403:
|
||||
raise ValueError('Unreviewed public-access result')
|
||||
evidence[name] = body
|
||||
if 'program-data.json' not in evidence:
|
||||
raise ValueError('Missing program source')
|
||||
return evidence
|
||||
|
||||
|
||||
def without_emails(value):
|
||||
"""Keep public session structure; contact arrays remain in raw evidence only."""
|
||||
if isinstance(value, dict):
|
||||
return {k:without_emails(v) for k,v in value.items() if k != 'emails'}
|
||||
if isinstance(value, list):
|
||||
return [without_emails(v) for v in value]
|
||||
return value
|
||||
|
||||
|
||||
def program_locations(node, pointer=''):
|
||||
"""Independent structural guard against silently skipping a new nesting form."""
|
||||
if isinstance(node, dict):
|
||||
if 'paper_id' in node:
|
||||
yield pointer
|
||||
for key,value in node.items():
|
||||
escaped = key.replace('~','~0').replace('/','~1')
|
||||
yield from program_locations(value, pointer+'/'+escaped)
|
||||
elif isinstance(node, list):
|
||||
for i,value in enumerate(node):
|
||||
yield from program_locations(value, pointer+'/'+str(i))
|
||||
|
||||
|
||||
def parse_program(raw):
|
||||
data = json.loads(raw)
|
||||
if (data.get('generated_at') != '2026-11-14T18:36:26.860677+00:00'
|
||||
or data.get('days') != [1,2,3,4,5] or len(data.get('rooms',[])) != 20
|
||||
or len(data.get('entries',[])) != 157):
|
||||
raise ValueError('Unreviewed program edition or census')
|
||||
records = {}; sessions = []; seen = []
|
||||
|
||||
def observe(paper, pointer, session_pointer, subsession_pointer=None):
|
||||
if not set(CORE) <= paper.keys() or set(paper)-set(CORE)-set(PRESENTATION)-{'emails'}:
|
||||
raise ValueError('Unreviewed program fields')
|
||||
for key in ('paper_id','title','abstract','track'):
|
||||
if not isinstance(paper[key],str):
|
||||
raise ValueError('Wrong program field type')
|
||||
for key in ('authors','affiliations'):
|
||||
if not isinstance(paper[key],list) or any(not isinstance(v,str) for v in paper[key]):
|
||||
raise ValueError('Wrong author or affiliation list')
|
||||
if not paper['paper_id'].strip() or not paper['title'].strip() or paper['track'] not in TRACK_COUNTS:
|
||||
raise ValueError('Missing identity/title or unreviewed source track')
|
||||
core = {k:paper[k] for k in CORE}
|
||||
pid = paper['paper_id']; seen.append(pointer)
|
||||
if pid not in records:
|
||||
missing = [k for k in ('authors','abstract') if not paper[k]]
|
||||
records[pid] = {**core,'source':SOURCE,'year':2026,'venue':'MM',
|
||||
'source_locator':{'namespace':'mm_program:program_id','value':pid},
|
||||
'observed_status':'listed_in_official_program',
|
||||
'publication_identity_verified':False,'final_decision_verified':False,
|
||||
'approved_for_import':False,'missing_fields':missing,
|
||||
'tags':[{'namespace':'mm_program:track','value':paper['track']}],
|
||||
'contexts':[]}
|
||||
elif {k:records[pid][k] for k in CORE} != core:
|
||||
raise ValueError('Conflicting core versions for one program ID; review required')
|
||||
records[pid]['contexts'].append({'source_pointer':pointer,'session_pointer':session_pointer,
|
||||
'subsession_pointer':subsession_pointer,
|
||||
'presentation':{k:paper[k] for k in PRESENTATION if k in paper}})
|
||||
|
||||
for i,entry in enumerate(data['entries']):
|
||||
pointer = '/entries/'+str(i)
|
||||
if entry['track'] != '':
|
||||
raise ValueError('Unreviewed outer track; do not override paper.track')
|
||||
session = without_emails({k:v for k,v in entry.items() if k not in ('papers','subsessions')})
|
||||
session.update(source_pointer=pointer,subsessions=[])
|
||||
for j,paper in enumerate(entry.get('papers') or []):
|
||||
observe(paper,pointer+'/papers/'+str(j),pointer)
|
||||
for j,sub in enumerate(entry.get('subsessions') or []):
|
||||
sp = pointer+'/subsessions/'+str(j)
|
||||
saved = without_emails({k:v for k,v in sub.items() if k != 'items'})
|
||||
saved.update(source_pointer=sp,nonpaper_items=[])
|
||||
for k,item in enumerate(sub.get('items') or []):
|
||||
ip = sp+'/items/'+str(k)
|
||||
if 'paper_id' in item:
|
||||
observe(item,ip,pointer,sp)
|
||||
else:
|
||||
saved['nonpaper_items'].append({'source_pointer':ip,'fields':without_emails(item)})
|
||||
session['subsessions'].append(saved)
|
||||
sessions.append(session)
|
||||
if set(seen) != set(program_locations(data)) or len(set(seen)) != len(seen):
|
||||
raise ValueError('Unhandled or duplicated program location')
|
||||
items = list(records.values())
|
||||
if (len(seen) != 4326 or len(items) != 2143
|
||||
or Counter(r['track'] for r in items) != TRACK_COUNTS
|
||||
or sum(not r['abstract'] for r in items) != 216
|
||||
or {r['paper_id'] for r in items if not r['authors']} != {'mfp4971','mfp7801'}):
|
||||
raise ValueError('Program count or missing-field census changed')
|
||||
return items,sessions
|
||||
|
||||
|
||||
def collect(out, *, snapshots):
|
||||
out = Path(out)
|
||||
if out.exists() or out.is_symlink():
|
||||
raise ValueError('Output exists; use a fresh directory')
|
||||
if any(p.is_symlink() for p in out.parents):
|
||||
raise ValueError('Unsafe output parent')
|
||||
out.mkdir(parents=True)
|
||||
try:
|
||||
evidence = load_snapshot(snapshots)
|
||||
rows,sessions = parse_program(evidence['program-data.json'])
|
||||
(out/'evidence').mkdir()
|
||||
for name,body in evidence.items():
|
||||
(out/'evidence'/name).write_bytes(body)
|
||||
outputs = []
|
||||
for track,count in TRACK_COUNTS.items():
|
||||
slug = re.sub('[^a-z0-9]+','_',track.lower()).strip('_')
|
||||
path = out/('mm-program-2026-'+slug+'.jsonl')
|
||||
raw = ''.join(json.dumps(r,ensure_ascii=False)+'\n' for r in rows if r['track']==track).encode()
|
||||
path.write_bytes(raw)
|
||||
outputs.append({'file':str(path),'file_sha256':digest(raw),'count':count,
|
||||
'track_literal':track,'format':'mm_program_observation_v1_not_ingestion_record',
|
||||
'status':'pending_contribution_and_identity_review','approved_for_import':0})
|
||||
session_raw = ''.join(json.dumps(r,ensure_ascii=False)+'\n' for r in sessions).encode()
|
||||
(out/'sessions.jsonl').write_bytes(session_raw)
|
||||
report = {'status':'collected_pending_contribution_and_identity_review','source':SOURCE,
|
||||
'records':2143,'program_observations':4326,'extra_presentation_observations':2183,
|
||||
'track_counts':TRACK_COUNTS,'files':outputs,'session_count':157,
|
||||
'sessions_file_sha256':digest(session_raw),'missing_abstract_count':216,
|
||||
'missing_author_program_ids':['mfp4971','mfp7801'],
|
||||
'source_body_sha256':BODY_SHA,'source_manifest_sha256':MANIFEST_SHA,
|
||||
'database_written':False,'pdfs_downloaded':False,'network_requests':0,'approved_for_import':0,
|
||||
'public_negative_access':{'anonymous_notes_probes':4,'http_statuses':[403]*4,
|
||||
'negative_decisions_inferred':0,'scope':'Observed endpoints only; not proof of zero public negative decisions.'},
|
||||
'scope':'Program IDs are source locators, not scientific-work or original submission IDs. All28source tracks retained; presentation times/kinds/locators and session context kept separately. No publication status, paper type, DOI, arxiv/OpenReview ID, rejection or withdrawal inferred. Blank fields are not negative decisions. Contribution/publication/work/history review and final whole-database audit remain.'}
|
||||
part = out/'collection-report.json.part'
|
||||
part.write_text(json.dumps(report,ensure_ascii=False,indent=2)+'\n')
|
||||
part.replace(out/'collection-report.json')
|
||||
return report
|
||||
except Exception as error:
|
||||
(out/'failed.json').write_text(json.dumps({'status':'failed_not_complete','error_type':type(error).__name__,'database_written':False})+'\n')
|
||||
raise
|
||||
|
||||
|
||||
def main(argv=None, *, prog=None):
|
||||
parser = argparse.ArgumentParser(prog=prog,description=__doc__)
|
||||
parser.add_argument('--snapshots',required=True)
|
||||
parser.add_argument('--out',required=True)
|
||||
args = parser.parse_args(argv)
|
||||
print(json.dumps(collect(args.out,snapshots=args.snapshots),ensure_ascii=False))
|
||||
@@ -0,0 +1,172 @@
|
||||
"""Frozen RecSys 2026 accepted-contribution observations, preserving source variants."""
|
||||
import argparse
|
||||
from collections import Counter
|
||||
from datetime import datetime
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
|
||||
from paper_atlas.io.html import Document, Node, clean
|
||||
|
||||
SOURCE = 'recsys_program'
|
||||
SNAPSHOT = 'remaining2026-listings-research-v2'
|
||||
MANIFEST_SHA = 'fea7b710587636db06794ee195cd083634c41e9054a217859d9dd0ccdd1afab9'
|
||||
URL = 'https://recsys.acm.org/recsys26/contributions/'
|
||||
TRACKS = [('long', 'Long Papers', 65), ('short', 'Short Papers', 29),
|
||||
('past_present_future', 'PPF Papers', 13), ('reproducibility', 'Reproducibility', 4),
|
||||
('resource', 'Resource', 7), ('industry', 'Industry', 83),
|
||||
('research_practice_notes', 'R&P Notes', 34), ('demo', 'Demos', 18),
|
||||
('doctoral_symposium', 'Doctoral', 10)]
|
||||
|
||||
|
||||
def digest(raw):
|
||||
return hashlib.sha256(raw).hexdigest()
|
||||
|
||||
|
||||
def one(items):
|
||||
if len(items) != 1:
|
||||
raise ValueError('Expected exactly one reviewed source field')
|
||||
return items[0]
|
||||
|
||||
|
||||
def load_snapshot(root):
|
||||
root = Path(root); directory = root/SNAPSHOT; path = directory/'manifest.json'
|
||||
if root.is_symlink() or directory.is_symlink() or path.is_symlink() or path.stat().st_size > 128*1024:
|
||||
raise ValueError('Unsafe snapshot manifest')
|
||||
raw = path.read_bytes()
|
||||
if digest(raw) != MANIFEST_SHA:
|
||||
raise ValueError('Reviewed manifest hash changed')
|
||||
manifest = json.loads(raw)
|
||||
if manifest['status'] != 'research_completed_not_coverage_or_import_approval' or manifest['database_written'] is not False:
|
||||
raise ValueError('Unreviewed snapshot scope')
|
||||
receipt = one([e for e in manifest['entries'] if e['venue'] == 'RecSys' and e['label'] == 'contributions'])
|
||||
name = receipt['file']; path = directory/name
|
||||
if Path(name).name != name or path.is_symlink() or path.stat().st_size > 4*1024**2:
|
||||
raise ValueError('Unsafe snapshot body')
|
||||
body = path.read_bytes()
|
||||
if (receipt['url'] != URL or receipt['final_url'] != URL or receipt['http_status'] != 200
|
||||
or not receipt['content_type'].startswith('text/html') or receipt['bytes'] != len(body)
|
||||
or receipt['sha256'] != digest(body) or datetime.fromisoformat(receipt['at']).utcoffset() is None):
|
||||
raise ValueError('Snapshot receipt/body disagree')
|
||||
return receipt, {'manifest.json': raw, name: body}, body
|
||||
|
||||
|
||||
def body_text(node, doi_url):
|
||||
if not isinstance(node, Node):
|
||||
return node
|
||||
if node.tag in ('script', 'style') or (node.tag == 'a' and node.attrs.get('href') == doi_url):
|
||||
return ''
|
||||
text = ''.join(body_text(c, doi_url) for c in node.children)
|
||||
return ' '+text+' ' if node.tag in ('p','div','li','br','section') else text
|
||||
|
||||
|
||||
def parse_program(raw):
|
||||
doc = Document(raw.decode('utf-8')); nodes = list(doc.root.walk())
|
||||
if not any(n.tag == 'title' and 'RecSys 26 - Accepted Contributions' in n.text() for n in nodes):
|
||||
raise ValueError('Wrong conference edition')
|
||||
menu = one([n for n in nodes if n.tag == 'ul' and n.attrs.get('id') == 'tab-1'])
|
||||
labels = [(n.attrs.get('href'), clean(n.text())) for n in menu.walk() if n.tag == 'a']
|
||||
if labels != [(f'#content-tab-1-{i}', label) for i, (_,label,_) in enumerate(TRACKS)]:
|
||||
raise ValueError('Unreviewed track menu')
|
||||
observations = []; seen = set()
|
||||
for tab, (track, label, count) in enumerate(TRACKS):
|
||||
section = one([n for n in nodes if n.tag == 'div' and n.attrs.get('id') == f'content-tab-1-{tab}'])
|
||||
listing = one([n for n in section.walk() if n.tag == 'ul' and n.attrs.get('id') == f'accordion-{tab+1}'])
|
||||
rows = [n for n in listing.children if isinstance(n, Node) and n.tag == 'li']
|
||||
if len(rows) != count:
|
||||
raise ValueError('Incomplete reviewed track census')
|
||||
for position, row in enumerate(rows, 1):
|
||||
anchor = one([n for n in row.children if isinstance(n, Node) and n.tag == 'a'])
|
||||
locator = anchor.attrs.get('rel', '').removeprefix('#')
|
||||
if not re.fullmatch(f'accordion-{tab+1}-slide-[0-9]+', locator) or locator in seen:
|
||||
raise ValueError('Missing or repeated program locator')
|
||||
seen.add(locator)
|
||||
types = [n for n in anchor.walk() if n.tag == 'span' and n.attrs.get('class') == 'paper-type']
|
||||
type_node = one(types); type_literal = type_node.attrs.get('title'); abbreviation = clean(type_node.text())
|
||||
expected_type = [('Research','RES'),('Research','RES'),('PastPresentFuture','PPF'),
|
||||
('Research','REPR'),('Research','RSC'),('Research','IND'),('Research','RPN'),('Research','DEMO'),('Doctoral Symposium','DS')][tab]
|
||||
if (type_literal,abbreviation) != expected_type:
|
||||
raise ValueError('Unreviewed source contribution type')
|
||||
title = clean(''.join(c.text() if isinstance(c, Node) else c for c in anchor.children
|
||||
if not isinstance(c, Node) or c.tag not in ('span','em','br')))
|
||||
authors_literal = clean(one([n for n in anchor.walk() if n.tag == 'em']).text())
|
||||
if not authors_literal.startswith('by '):
|
||||
raise ValueError('Missing program author prefix')
|
||||
authors_literal = authors_literal[3:]
|
||||
authors = [n.strip() for n in re.split(r',\s+|\s+and\s+', authors_literal)]
|
||||
if not title or any(not n or '@' in n for n in authors):
|
||||
raise ValueError('Missing title or program author')
|
||||
body = one([n for n in row.children if isinstance(n, Node) and n.tag == 'div'])
|
||||
doi_url = one([n.attrs.get('href') for n in body.walk() if n.tag == 'a'
|
||||
and n.attrs.get('href', '').startswith('https://doi.org/')])
|
||||
if not re.fullmatch(r'https://doi.org/10\.1145/3773078\.[0-9]+', doi_url):
|
||||
raise ValueError('Wrong publication DOI family')
|
||||
abstract = clean(body_text(body, doi_url))
|
||||
if len(abstract) < 100 or any(n.tag in ('math','sup','sub','img','svg') for n in body.walk()):
|
||||
raise ValueError('Missing abstract or unreviewed structured markup')
|
||||
observations.append({'doi': doi_url.removeprefix('https://doi.org/'), 'tab': tab, 'position': position,
|
||||
'locator': locator, 'title': title, 'authors': authors, 'authors_literal': authors_literal,
|
||||
'abstract': abstract, 'type_labels': [type_literal], 'source_type_abbreviation': abbreviation,
|
||||
'track': track, 'track_label': label})
|
||||
counts = Counter(r['doi'] for r in observations)
|
||||
if len(observations) != 263 or len(counts) != 260 or {d:n for d,n in counts.items() if n>1} != {
|
||||
'10.1145/3773078.3831839':2,'10.1145/3773078.3831819':2,'10.1145/3773078.3831861':2}:
|
||||
raise ValueError('Unreviewed DOI observation census')
|
||||
for item in observations:
|
||||
item['review_flags'] = ['repeated_program_doi_preserve_versions_requires_review'] if counts[item['doi']] > 1 else []
|
||||
return observations
|
||||
|
||||
|
||||
def collect(out, *, snapshots):
|
||||
out = Path(out)
|
||||
if out.exists():
|
||||
raise ValueError('Output exists; inspect previous operation before retrying')
|
||||
out.mkdir(parents=True)
|
||||
try:
|
||||
receipt, files, body = load_snapshot(snapshots); observations = parse_program(body)
|
||||
evidence = out/'evidence'; evidence.mkdir()
|
||||
for name, raw in files.items():
|
||||
(evidence/name).write_bytes(raw)
|
||||
outputs = []
|
||||
for track,label,count in TRACKS:
|
||||
rows = []
|
||||
for item in observations:
|
||||
if item['track'] != track:
|
||||
continue
|
||||
doi = item['doi']; url = URL+'#'+item['locator']
|
||||
rows.append({'source': SOURCE, 'external_id': '2026/'+item['locator'], 'url': url,
|
||||
'title': item['title'], 'authors': item['authors'], 'abstract': item['abstract'],
|
||||
'identifiers': {'doi': doi}, 'submission_identifiers': [{'scheme':'publication_doi','value':doi}],
|
||||
'venue':'RecSys', 'year':2026, 'track':track, 'status':'accepted', 'observed_at':receipt['at'],
|
||||
'evidence_url':URL, 'raw_decision':'Listed as an accepted contribution in the official RecSys2026 '+label+' section; not a signed review decision.',
|
||||
'tags':[{'namespace':SOURCE+':contribution_type','value':item['type_labels'][0]}],
|
||||
'metadata':{'program_fields':item, 'program_receipt':receipt,
|
||||
'source_evidence':{'file':'evidence/'+receipt['file'],'sha256':receipt['sha256'],'url':URL},
|
||||
'source_manifest':{'file':'evidence/manifest.json','sha256':MANIFEST_SHA},
|
||||
'original_decision_signature_verified':False,
|
||||
'author_scope':'Source-reported comma/and-delimited names; original literal retained. Not verified publisher person identities or aliases.',
|
||||
'doi_scope':'DOI asserted by official program hyperlink, not independently verified live publisher metadata.',
|
||||
'abstract_transform':'HTML display text and whitespace normalization; source retained. No PDF or cross-source fusion.',
|
||||
'scope':'Program observation keyed by source locator. Repeated DOI variants retained separately and flagged, not counted as distinct scientific works. Requires DOI/work/history review before import.'}})
|
||||
path = out/f'recsys-program-2026-{track}.jsonl';raw=''.join(json.dumps(r,ensure_ascii=False)+'\n' for r in rows).encode();path.write_bytes(raw)
|
||||
manifest={'source':SOURCE,'parser_version':1,'venue':'RecSys','year':2026,'track':track,'count':len(rows),
|
||||
'file':str(path),'file_sha256':digest(raw),'list_url':URL,'status':'partial','missing_abstract_count':0,
|
||||
'scope':'Official accepted-contribution observations; unique DOI counts differ from observation counts.'}
|
||||
path.with_suffix('.manifest.json').write_text(json.dumps(manifest,indent=2)+'\n');outputs.append(manifest)
|
||||
report={'status':'collected_pending_identity_review','records':263,'unique_dois':260,'files':outputs,
|
||||
'track_counts':{track:count for track,_,count in TRACKS},'missing_abstract_count':0,
|
||||
'duplicate_doi_observations':6,'repeated_dois':{d:n for d,n in Counter(r['doi'] for r in observations).items() if n>1},
|
||||
'source_manifest_sha256':MANIFEST_SHA,'database_written':False,'network_requests':0,'pdfs_downloaded':False,
|
||||
'approved_for_import':0,'public_rejected_availability':'unknown_no_public_export_verified',
|
||||
'scope':'263 program observations for260 DOIs, not263 unique papers or final work identities. Track/type labels are source scoped. Not complete public-negative coverage or a final whole-database audit.'}
|
||||
part=out/'collection-report.json.part';part.write_text(json.dumps(report,ensure_ascii=False,indent=2)+'\n');part.replace(out/'collection-report.json');return report
|
||||
except Exception as error:
|
||||
(out/'failed.json').write_text(json.dumps({'status':'failed_not_complete','error_type':type(error).__name__,'database_written':False})+'\n')
|
||||
raise
|
||||
|
||||
|
||||
def main(argv=None, *, prog=None):
|
||||
parser=argparse.ArgumentParser(prog=prog,description=__doc__)
|
||||
parser.add_argument('--snapshots',required=True);parser.add_argument('--out',required=True)
|
||||
args=parser.parse_args(argv);print(json.dumps(collect(args.out,snapshots=args.snapshots),ensure_ascii=False))
|
||||
BIN
Binary file not shown.
Vendored
BIN
Binary file not shown.
BIN
Binary file not shown.
@@ -0,0 +1,92 @@
|
||||
import base64
|
||||
import copy
|
||||
import gzip
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors import ismir2026 as c
|
||||
|
||||
|
||||
class ISMIR2026Test(unittest.TestCase):
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.fixture=json.loads(gzip.decompress((Path(__file__).parent/'fixtures/ismir2026-source.json.gz').read_bytes()))
|
||||
cls.files={name:base64.b64decode(raw) for name,raw in cls.fixture['files'].items()}
|
||||
cls.program=json.loads(cls.files['ismir2026-json-research-v1/papers.json'])
|
||||
cls.accepted=cls.files['remaining2026-listings-research-v2/ismir-accepted.html']
|
||||
|
||||
def materialize(self,root):
|
||||
for name,raw in self.files.items():
|
||||
p=root/name;p.parent.mkdir(parents=True,exist_ok=True);p.write_bytes(raw)
|
||||
|
||||
def test140_source_versions_and_review_optins_against_independent_gold(self):
|
||||
listing=c.accepted_listing(self.accepted);observations=c.program_observations(self.program,listing)
|
||||
self.assertEqual(len(observations),140)
|
||||
for observation,gold in zip(observations,self.fixture['independent_gold']):
|
||||
r=observation['original'];v=r['content'];official=observation['accepted_listing']
|
||||
self.assertEqual((r['id'],r['forum'],v['title'],v['authors'],v['abstract']),(gold['program_id'],gold['forum_literal'],gold['title'],gold['authors'],gold['abstract']))
|
||||
self.assertEqual(official,{'title':gold['official_title'],'authors_literal':gold['official_authors_literal'],'author_names':gold['official_author_names']})
|
||||
self.assertEqual(v['session'],gold['session_literal']);self.assertEqual(v['paper_presentation'],gold['presentation_literal']);self.assertEqual(v['keywords'],gold['keywords'])
|
||||
self.assertEqual(sum('program_and_accepted_title_literal_versions_differ' in r['review_flags'] for r in observations),2)
|
||||
self.assertEqual({r['original']['id'] for r in observations if 'program_and_accepted_author_sequence_versions_differ' in r['review_flags']},{'60','126','433'})
|
||||
self.assertEqual(sum(r['original']['reviews']['publish_reviews']=='Yes' for r in observations),101)
|
||||
|
||||
def test_full_collection_keeps_abstract_bytes_review_text_tags_and_no_inferred_ids(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp);src=root/'src';self.materialize(src);out=root/'out';report=c.collect(out,snapshots=src)
|
||||
self.assertEqual((report['records'],report['missing_abstract_count'],report['review_optin_yes'],report['review_optin_no']),(140,0,101,39))
|
||||
self.assertFalse(report['database_written']);self.assertFalse(report['pdfs_downloaded']);self.assertEqual(report['network_requests'],0);self.assertEqual(report['approved_for_import'],0)
|
||||
self.assertEqual(report['public_rejected_availability'],'unknown_accepted_program_reviews_are_not_a_rejected_export')
|
||||
manifest,=report['files'];raw=Path(manifest['file']).read_bytes();self.assertEqual(hashlib.sha256(raw).hexdigest(),manifest['file_sha256']);self.assertEqual(manifest['status'],'partial')
|
||||
rows=[json.loads(l) for l in raw.splitlines()];self.assertEqual(len(rows),140)
|
||||
for row,original,gold in zip(rows,self.program,self.fixture['independent_gold']):
|
||||
self.assertEqual(row['metadata']['program_entry'],original);self.assertEqual(row['abstract'],gold['abstract']);self.assertEqual(row['title'],gold['title']);self.assertEqual(row['authors'],gold['authors'])
|
||||
self.assertEqual(row['external_id'],'2026/'+gold['program_id']);self.assertEqual(row['identifiers'],{});self.assertEqual(row['submission_identifiers'],[])
|
||||
self.assertEqual(row['status'],'accepted');self.assertEqual(row['track'],'program_unclassified');self.assertIsNone(row['metadata']['paper_type']);self.assertFalse(row['metadata']['original_decision_signature_verified'])
|
||||
tags=[{'namespace':'ismir_program:presentation','value':gold['presentation_literal']}]+[{'namespace':'ismir_program:keyword','value':v} for v in dict.fromkeys(' '.join(k.split()) for k in gold['keywords'] if k.strip())]
|
||||
self.assertEqual(row['tags'],tags);self.assertTrue(all(t['value'] for t in row['tags']))
|
||||
if original['reviews']['publish_reviews']=='No':self.assertFalse(any(v for k,v in row['metadata']['program_entry']['reviews'].items() if k!='publish_reviews'))
|
||||
for name,body in self.files.items():self.assertEqual((out/'evidence'/name).read_bytes(),body)
|
||||
with self.assertRaisesRegex(ValueError,'Output exists'):c.collect(out,snapshots=src)
|
||||
|
||||
def test_duplicate_and_malformed_locator_or_incomplete_census_rejected(self):
|
||||
listing=c.accepted_listing(self.accepted)
|
||||
for kind in ('repeat','forum','non_numeric','missing_row'):
|
||||
rows=copy.deepcopy(self.program)
|
||||
if kind=='repeat':rows[1]['id']=rows[0]['id'];rows[1]['forum']=rows[0]['forum']
|
||||
if kind=='forum':rows[0]['forum']='OriginalOpenReviewID'
|
||||
if kind=='non_numeric':rows[0]['id']='abc';rows[0]['forum']='abc'
|
||||
if kind=='missing_row':rows.pop()
|
||||
with self.subTest(kind=kind),self.assertRaises(ValueError):c.program_observations(rows,listing)
|
||||
|
||||
def test_empty_fields_foreign_title_and_session_disagree_rejected(self):
|
||||
listing=c.accepted_listing(self.accepted)
|
||||
for field,value in [('authors',[]),('abstract',''),('title','A foreign paper'),('session',['99']),('keywords',[42])]:
|
||||
rows=copy.deepcopy(self.program);rows[0]['content'][field]=value
|
||||
with self.subTest(field=field),self.assertRaises(ValueError):c.program_observations(rows,listing)
|
||||
|
||||
def test_source_optin_no_cannot_publish_review_text(self):
|
||||
rows=copy.deepcopy(self.program);r=next(r for r in rows if r['reviews']['publish_reviews']=='No');r['reviews']['meta_review']='Do not infer a negative decision'
|
||||
with self.assertRaisesRegex(ValueError,'preference'):c.program_observations(rows,c.accepted_listing(self.accepted))
|
||||
|
||||
def test_parenthesized_affiliation_semicolons_do_not_split_people(self):
|
||||
self.assertEqual(c.author_names('A Person (University A; Lab (X)); B Person (Institute B)'),['A Person','B Person'])
|
||||
for raw in ['A Person (Broken','; A Person (Lab)','A Person )']:
|
||||
with self.assertRaises(ValueError):c.author_names(raw)
|
||||
|
||||
def test_ambiguous_official_title_is_not_fused(self):
|
||||
source=self.accepted.replace(b'FusID: Modality-Fused Semantic IDs for Generative Music Recommendation',b'Off-Manifold Robustness in Synthesizer Inversion with Joint Distribution Flow Matching',1)
|
||||
with self.assertRaisesRegex(ValueError,'ambiguous'):c.accepted_listing(source)
|
||||
|
||||
def test_tamper_missing_file_and_symlink_fail_without_success_report(self):
|
||||
for kind in ('manifest','body','missing','symlink'):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp);src=root/'src';self.materialize(src);path=src/'ismir2026-json-research-v1'/('manifest.json' if kind=='manifest' else 'papers.json')
|
||||
if kind=='missing':path.unlink()
|
||||
elif kind=='symlink':other=root/'actual.json';path.rename(other);path.symlink_to(other)
|
||||
else:path.write_bytes(path.read_bytes()+b' ')
|
||||
with self.subTest(kind=kind),self.assertRaises((ValueError,FileNotFoundError)):c.collect(root/'out',snapshots=src)
|
||||
self.assertTrue((root/'out/failed.json').exists());self.assertFalse((root/'out/collection-report.json').exists())
|
||||
@@ -0,0 +1,146 @@
|
||||
import copy
|
||||
import gzip
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors import mm2026 as c
|
||||
|
||||
|
||||
class MM2026Test(unittest.TestCase):
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.fixture = json.loads(gzip.decompress((Path(__file__).parent/'fixtures/mm2026-source.json.gz').read_bytes()))
|
||||
cls.files = {name:body.encode('utf-8') for name,body in cls.fixture['files'].items()}
|
||||
cls.raw = cls.files[c.SNAPSHOT+'/program-data.json']
|
||||
cls.data = json.loads(cls.raw)
|
||||
cls.gold = cls.fixture['independent_inventory']
|
||||
|
||||
def materialize(self, root):
|
||||
for name,body in self.files.items():
|
||||
path = root/name; path.parent.mkdir(parents=True,exist_ok=True); path.write_bytes(body)
|
||||
|
||||
def parse_changed(self, data):
|
||||
return c.parse_program(json.dumps(data,ensure_ascii=False).encode())
|
||||
|
||||
def test_all2143_ids_and4326_locations_against_independent_inventory(self):
|
||||
rows,sessions = c.parse_program(self.raw)
|
||||
self.assertEqual(len(rows),2143); self.assertEqual(len(sessions),157)
|
||||
self.assertEqual(sum(len(r['contexts']) for r in rows),4326)
|
||||
actual = {r['paper_id']:r for r in rows}
|
||||
self.assertEqual(set(actual),{g['paper_id'] for g in self.gold['inventory']})
|
||||
for gold in self.gold['inventory']:
|
||||
r = actual[gold['paper_id']]
|
||||
self.assertEqual((r['title'],r['authors'],r['track'],r['affiliations']),
|
||||
(gold['title'],gold['authors'],gold['track_literal'],gold['affiliations']))
|
||||
self.assertEqual(hashlib.sha256(r['abstract'].encode()).hexdigest(),gold['abstract_sha256'])
|
||||
self.assertEqual([x['source_pointer'] for x in r['contexts']],gold['locations'])
|
||||
|
||||
def test_every_presentation_and_session_context_is_preserved(self):
|
||||
rows,sessions = c.parse_program(self.raw)
|
||||
for r in rows:
|
||||
for context in r['contexts']:
|
||||
node = self.data
|
||||
for key in context['source_pointer'].split('/')[1:]:
|
||||
node = node[int(key)] if isinstance(node,list) else node[key]
|
||||
self.assertEqual(context['presentation'],{k:node[k] for k in c.PRESENTATION if k in node})
|
||||
self.assertEqual(r['paper_id'],node['paper_id'])
|
||||
for i,session in enumerate(sessions):
|
||||
original = self.data['entries'][i]
|
||||
self.assertEqual(session['source_pointer'],'/entries/'+str(i))
|
||||
self.assertEqual(session['track'],'')
|
||||
for key in original.keys()-{'papers','subsessions'}:
|
||||
self.assertEqual(session[key],original[key])
|
||||
for j,sub in enumerate(original.get('subsessions') or []):
|
||||
saved = session['subsessions'][j]
|
||||
self.assertEqual(saved['title'],sub['title'])
|
||||
expected = [x for x in sub.get('items') or [] if 'paper_id' not in x]
|
||||
self.assertEqual([x['fields'] for x in saved['nonpaper_items']],expected)
|
||||
|
||||
def test_all_tracks_retained_without_publication_or_negative_inference(self):
|
||||
rows,_ = c.parse_program(self.raw)
|
||||
self.assertEqual({r['track'] for r in rows},set(self.gold['unique_id_track_counts']))
|
||||
for r in rows:
|
||||
self.assertFalse(r['approved_for_import']); self.assertFalse(r['final_decision_verified'])
|
||||
self.assertFalse(r['publication_identity_verified'])
|
||||
self.assertEqual(r['source_locator'],{'namespace':'mm_program:program_id','value':r['paper_id']})
|
||||
self.assertEqual(r['tags'],[{'namespace':'mm_program:track','value':r['track']}])
|
||||
self.assertEqual(r['observed_status'],'listed_in_official_program')
|
||||
self.assertTrue({'status','identifiers','submission_identifiers','paper_type','emails'}.isdisjoint(r))
|
||||
missing = [r for r in rows if not r['authors']]
|
||||
self.assertEqual({r['paper_id'] for r in missing},{'mfp4971','mfp7801'})
|
||||
self.assertTrue(all(r['missing_fields']==['authors','abstract'] for r in missing))
|
||||
self.assertEqual(sum(not r['abstract'] for r in rows),216)
|
||||
|
||||
def test_collect_evidence_hashes_and_no_contact_arrays_in_normalized_output(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp);self.materialize(root/'src')
|
||||
report=c.collect(root/'out',snapshots=root/'src')
|
||||
self.assertEqual((report['records'],report['program_observations'],report['extra_presentation_observations']),(2143,4326,2183))
|
||||
self.assertFalse(report['database_written']);self.assertFalse(report['pdfs_downloaded'])
|
||||
self.assertEqual(report['network_requests'],0);self.assertEqual(report['approved_for_import'],0)
|
||||
self.assertEqual(report['public_negative_access']['http_statuses'],[403]*4)
|
||||
self.assertEqual(report['track_counts'],self.gold['unique_id_track_counts'])
|
||||
for name,body in self.files.items():
|
||||
self.assertEqual((root/'out/evidence'/Path(name).name).read_bytes(),body)
|
||||
n=0
|
||||
for item in report['files']:
|
||||
raw=Path(item['file']).read_bytes();self.assertEqual(hashlib.sha256(raw).hexdigest(),item['file_sha256'])
|
||||
self.assertNotIn(b'"emails"',raw);self.assertEqual(len(raw.splitlines()),item['count']);n+=item['count']
|
||||
self.assertEqual(item['format'],'mm_program_observation_v1_not_ingestion_record')
|
||||
self.assertEqual(n,2143)
|
||||
raw=(root/'out/sessions.jsonl').read_bytes()
|
||||
self.assertEqual(hashlib.sha256(raw).hexdigest(),report['sessions_file_sha256']);self.assertNotIn(b'"emails"',raw)
|
||||
with self.assertRaisesRegex(ValueError,'Output exists'):c.collect(root/'out',snapshots=root/'src')
|
||||
|
||||
def test_conflicting_core_version_is_not_silently_merged(self):
|
||||
data=copy.deepcopy(self.data)
|
||||
first=data['entries'][0]['papers'][0]
|
||||
data['entries'][0]['papers'].append({**first,'abstract':'conflicting abstract'})
|
||||
with self.assertRaisesRegex(ValueError,'Conflicting core'):self.parse_changed(data)
|
||||
|
||||
def test_unknown_nesting_cannot_silently_lose_observations(self):
|
||||
data=copy.deepcopy(self.data)
|
||||
moved=data['entries'][0]['papers'].pop()
|
||||
data['entries'][0]['unreviewed_bucket']=[moved]
|
||||
with self.assertRaisesRegex(ValueError,'Unhandled'):self.parse_changed(data)
|
||||
|
||||
def test_track_drift_unknown_fields_or_missing_title_require_review(self):
|
||||
for kind in ('outer_track','paper_track','field','title','authors'):
|
||||
data=copy.deepcopy(self.data);paper=data['entries'][0]['papers'][0]
|
||||
if kind=='outer_track':data['entries'][0]['track']='Main Track'
|
||||
elif kind=='paper_track':paper['track']='New Track'
|
||||
elif kind=='field':paper['doi']='unreviewed'
|
||||
elif kind=='title':paper['title']=''
|
||||
else:paper['authors']='Unparsed author string'
|
||||
with self.subTest(kind=kind),self.assertRaises(ValueError):self.parse_changed(data)
|
||||
|
||||
def test_edition_or_census_change_requires_review(self):
|
||||
for kind in ('edition','count'):
|
||||
data=copy.deepcopy(self.data)
|
||||
if kind=='edition':data['generated_at']='2025-11-14T18:36:26.860677+00:00'
|
||||
else:data['entries'][0]['papers'].pop()
|
||||
with self.subTest(kind=kind),self.assertRaises(ValueError):self.parse_changed(data)
|
||||
|
||||
def test_corruption_missing_evidence_and_symlink_fail_without_completed_report(self):
|
||||
for kind in ('manifest','program','probe','missing','symlink'):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp);self.materialize(root/'src');directory=root/'src'/c.SNAPSHOT
|
||||
name='manifest.json' if kind=='manifest' else 'openreview-rejected-probe.json' if kind=='probe' else 'program-data.json'
|
||||
path=directory/name
|
||||
if kind=='missing':path.unlink()
|
||||
elif kind=='symlink':
|
||||
original=directory/'original.json';path.rename(original);path.symlink_to(original)
|
||||
else:path.write_bytes(path.read_bytes()+b' ')
|
||||
with self.subTest(kind=kind),self.assertRaises((ValueError,FileNotFoundError)):c.collect(root/'out',snapshots=root/'src')
|
||||
self.assertTrue((root/'out/failed.json').exists());self.assertFalse((root/'out/collection-report.json').exists())
|
||||
|
||||
def test_literal_abstract_math_and_nonpaper_session_events_retained(self):
|
||||
rows,sessions=c.parse_program(self.raw)
|
||||
self.assertTrue(any('\\' in r['abstract'] for r in rows))
|
||||
self.assertTrue(any('\n' in r['abstract'] for r in rows))
|
||||
self.assertTrue(any(s['type']=='coffee_break' for s in sessions))
|
||||
self.assertTrue(any(s['type']=='industry_talk' for s in sessions))
|
||||
self.assertEqual(c.without_emails({'emails':['contact'],'items':[{'emails':['contact'],'title':'talk'}]}),{'items':[{'title':'talk'}]})
|
||||
@@ -0,0 +1,79 @@
|
||||
import base64
|
||||
import gzip
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors import recsys2026 as c
|
||||
|
||||
|
||||
class RecSys2026Test(unittest.TestCase):
|
||||
@classmethod
|
||||
def setUpClass(cls):
|
||||
cls.fixture=json.loads(gzip.decompress((Path(__file__).parent/'fixtures/recsys2026-source.json.gz').read_bytes()))
|
||||
cls.files={n:base64.b64decode(raw) for n,raw in cls.fixture['files'].items()}
|
||||
cls.body=cls.files[c.SNAPSHOT+'/recsys-contributions.html']
|
||||
|
||||
def materialize(self,root):
|
||||
for name,raw in self.files.items():
|
||||
path=root/name;path.parent.mkdir(parents=True,exist_ok=True);path.write_bytes(raw)
|
||||
|
||||
def test_all263_observations_against_independent_gold(self):
|
||||
items=c.parse_program(self.body)
|
||||
keys=self.fixture['independent_gold'][0].keys()
|
||||
self.assertEqual([{k:r[k] for k in keys} for r in items],self.fixture['independent_gold'])
|
||||
self.assertEqual(len(items),263);self.assertEqual(len({r['doi'] for r in items}),260)
|
||||
self.assertEqual(sum(bool(r['review_flags']) for r in items),6)
|
||||
variants=[r for r in items if r['doi']=='10.1145/3773078.3831839']
|
||||
self.assertNotEqual(variants[0]['title'],variants[1]['title']);self.assertNotEqual(variants[0]['authors'],variants[1]['authors'])
|
||||
self.assertNotEqual(variants[0]['abstract'],variants[1]['abstract'])
|
||||
|
||||
def test_installed_format_tracks_evidence_and_original_fields(self):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp);src=root/'src';self.materialize(src);out=root/'out'
|
||||
report=c.collect(out,snapshots=src)
|
||||
self.assertEqual((report['records'],report['unique_dois'],report['missing_abstract_count']),(263,260,0))
|
||||
self.assertFalse(report['database_written']);self.assertFalse(report['pdfs_downloaded']);self.assertEqual(report['network_requests'],0);self.assertEqual(report['approved_for_import'],0)
|
||||
self.assertEqual(report['track_counts'],{k:n for k,_,n in c.TRACKS});self.assertEqual(report['duplicate_doi_observations'],6)
|
||||
gold={r['locator']:r for r in self.fixture['independent_gold']};seen=set()
|
||||
for manifest in report['files']:
|
||||
path=Path(manifest['file']);raw=path.read_bytes();self.assertEqual(hashlib.sha256(raw).hexdigest(),manifest['file_sha256'])
|
||||
rows=[json.loads(l) for l in raw.splitlines()];self.assertEqual(len(rows),manifest['count']);self.assertEqual(manifest['status'],'partial')
|
||||
for r in rows:
|
||||
item=r['metadata']['program_fields'];locator=item['locator'];seen.add(locator);expected=gold[locator]
|
||||
for key in expected:self.assertEqual(item[key],expected[key])
|
||||
self.assertEqual(r['external_id'],'2026/'+locator);self.assertEqual(r['title'],expected['title']);self.assertEqual(r['authors'],expected['authors']);self.assertEqual(r['abstract'],expected['abstract'])
|
||||
self.assertEqual(r['track'],manifest['track']);self.assertEqual(r['identifiers'],{'doi':expected['doi']});self.assertEqual(r['submission_identifiers'],[{'scheme':'publication_doi','value':expected['doi']}])
|
||||
self.assertEqual(r['tags'],[{'namespace':'recsys_program:contribution_type','value':expected['type_labels'][0]}]);self.assertFalse(r['metadata']['original_decision_signature_verified'])
|
||||
self.assertEqual(seen,set(gold));self.assertEqual((out/'evidence/recsys-contributions.html').read_bytes(),self.body)
|
||||
with self.assertRaisesRegex(ValueError,'Output exists'):c.collect(out,snapshots=src)
|
||||
|
||||
def test_edition_and_track_label_drift_rejected(self):
|
||||
for old,new in [(b'RecSys 26 - Accepted Contributions',b'RecSys 25 - Accepted Contributions'),(b'>Long Papers</a>',b'>Workshops</a>'),(b"title='Research'",b"title='Unreviewed'")]:
|
||||
with self.subTest(old=old),self.assertRaises(ValueError):c.parse_program(self.body.replace(old,new,1))
|
||||
|
||||
def test_duplicate_locator_missing_author_and_foreign_doi_rejected(self):
|
||||
for old,new in [(b'accordion-1-slide-2"',b'accordion-1-slide-1"'),(b'by Md Aminul Islam, Kathryn Vasilaky and Elena Zheleva',b'by '),(b'https://doi.org/10.1145/3773078.3831824',b'https://doi.org/10.1145/9999999.3831824')]:
|
||||
with self.subTest(old=old),self.assertRaises(ValueError):c.parse_program(self.body.replace(old,new,1))
|
||||
|
||||
def test_math_markup_requires_review_and_is_not_flattened(self):
|
||||
changed=self.body.replace(b'Learning-to-rank (LTR)',b'Learning-to-rank <sup>2</sup> (LTR)',1)
|
||||
with self.assertRaisesRegex(ValueError,'markup'):c.parse_program(changed)
|
||||
|
||||
def test_corruption_and_missing_receipt_body_preserve_failure(self):
|
||||
for kind in ('manifest','body','missing'):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp);src=root/'src';self.materialize(src);path=src/c.SNAPSHOT/('manifest.json' if kind=='manifest' else 'recsys-contributions.html')
|
||||
if kind=='missing':path.unlink()
|
||||
else:path.write_bytes(path.read_bytes()+b' ')
|
||||
with self.assertRaises((ValueError,FileNotFoundError)):c.collect(root/'out',snapshots=src)
|
||||
self.assertTrue((root/'out/failed.json').exists());self.assertFalse((root/'out/collection-report.json').exists())
|
||||
|
||||
def test_symlink_source_and_root_rejected(self):
|
||||
for kind in ('source','root'):
|
||||
with tempfile.TemporaryDirectory() as tmp:
|
||||
root=Path(tmp);src=root/'src';self.materialize(src);path=src/c.SNAPSHOT/'recsys-contributions.html' if kind=='source' else src
|
||||
original=path.with_name(path.name+'-original');path.rename(original);path.symlink_to(original,target_is_directory=kind=='root')
|
||||
with self.assertRaisesRegex(ValueError,'Unsafe'):c.collect(root/'out',snapshots=src)
|
||||
Reference in New Issue
Block a user