Compare commits
1 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 28805462ee |
@@ -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():
|
||||
|
||||
@@ -137,6 +137,8 @@ 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)。
|
||||
@@ -202,5 +202,3 @@ IJCAI 联办届次的逐条后续核查见 [2018/2022 分区与目录差集](ijc
|
||||
[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。
|
||||
|
||||
- [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。
|
||||
|
||||
@@ -1493,7 +1493,7 @@
|
||||
},
|
||||
"TMLR_current20261108": {
|
||||
"url": "https://www.jmlr.org/tmlr/faq.html",
|
||||
"finding": "Additionalnonconferencepolicyreference; TMLR is not in the current 43-conference registry:accepted/rejected/withdrawn/retractedallpublic; deskrejectedneverpublic. Authorshiddenonnotyetacceptedpapers; donotinferanonymousidentities. Continuousjournal; eventcertification/journal-to-conferencepresentationnotanotherindependentreviewacceptance."
|
||||
"finding": "Additionalnonconferencevenuealreadyinregistry:accepted/rejected/withdrawn/retractedallpublic; deskrejectedneverpublic. Authorshiddenonnotyetacceptedpapers; donotinferanonymousidentities. Continuousjournal; eventcertification/journal-to-conferencepresentationnotanotherindependentreviewacceptance."
|
||||
}
|
||||
},
|
||||
"public_negative_recovery_notes": {
|
||||
@@ -1507,12 +1507,6 @@
|
||||
"original_rejection_notes_obtained": false,
|
||||
"prior_decisions_inserted": 0,
|
||||
"requires": "Per-paper primary original identifiers/decisions or an explicitly distinguished policy-supported relation; never manufacture an original note."
|
||||
},
|
||||
"researcharcade_20261118": {
|
||||
"audit": "public-negative-source-audit-2026-11-18.json",
|
||||
"summary": "930 non-ICLR 2020+ mirror claims:925 scoped ID matches all have rejected status;5 held,3 with equal title+source abstract but distinct unverified note IDs. No writes or new rejections approved.",
|
||||
"access": "NeurIPS2021 and EMNLP2023 original note queries403; stopped, no bypass.",
|
||||
"next": "Seek independent primary evidence for note.id/forum relationships and final decisions; no title-only merge or duplicate-rejection import. No full-public-set coverage claim."
|
||||
}
|
||||
},
|
||||
"restore_rules": [
|
||||
|
||||
@@ -1,320 +0,0 @@
|
||||
{
|
||||
"version": 1,
|
||||
"as_of": "2026-11-18",
|
||||
"scope": "930 cached ResearchArcade non-ICLR negative claims, NeurIPS 2021–2025 and EMNLP 2023; not a conference-completeness audit",
|
||||
"database_snapshot": {
|
||||
"database": "foundry_data",
|
||||
"schema": "research",
|
||||
"at": "2026-11-18 03:48:34.65659+00",
|
||||
"snapshot": "1048885:1048885:"
|
||||
},
|
||||
"database_written": false,
|
||||
"approved_for_import": 0,
|
||||
"claims": 930,
|
||||
"known_same_scope_attempt_claims": 925,
|
||||
"all_925_have_rejected_status": true,
|
||||
"without_same_scope_attempt_claims": 5,
|
||||
"by_venue_year": [
|
||||
{
|
||||
"venue": "EMNLP",
|
||||
"year": 2023,
|
||||
"claims": 10
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"claims": 136
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2022,
|
||||
"claims": 153
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2023,
|
||||
"claims": 176
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2024,
|
||||
"claims": 201
|
||||
},
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2025,
|
||||
"claims": 254
|
||||
}
|
||||
],
|
||||
"evidence": {
|
||||
"diff_report_sha256": "d49361a8622f3b3f59e824690ceb8bf1c878be35c3e3758366d3b46a407673f5",
|
||||
"candidate_packets_sha256": "3b21df27e0f30e56b81086d16d3943c4563bbe382200e866b15de14510e07472",
|
||||
"dataset_revision": "c61bb99b0452429c32f85b1e392f3afdb65731c4",
|
||||
"dataset_parquet_sha256": "bb6e165ee152a95d91a7ffa16abc9d4a6effbdfcf59183b3bb819d09171689d1",
|
||||
"candidate_jsonl_sha256": "848e646596e8c747e0c636c2381a139978aff8f2c19f01ad49c98e7f4270c5e6",
|
||||
"collector_repository": "https://github.com/ulab-uiuc/research-arcade",
|
||||
"collector_revision": "ecf9c7c2490840b029bd2add4f02d04aca1d014e",
|
||||
"collector_openreview_crawler_sha256": "4539d951ca05b20785169638eab3884148aa6c354a34c5ecc04e15c84a5910fe",
|
||||
"collector_revision_proven_to_generate_dataset": false
|
||||
},
|
||||
"collector_semantics": {
|
||||
"legacy_2020_2022": "Reads Blind_Submission note.id; first reply with content.decision, no invitation/signature verification. Not a verified final-decision note.",
|
||||
"legacy_2019": "Reads first recommendation, which must not be promoted to a final decision. Outside active 2020+ backfill.",
|
||||
"modern_branch": "Reads Submission note.id and last venueid component; Conference replaced by venue literal. Withdrawn_Submission skipped.",
|
||||
"identity": "The exported field paper_openreview_id is note.id; forum equality or equivalence to another mirror ID is not independently proved.",
|
||||
"coverage": "Six-field table has no authors or decision signatures; no completeness inference for public withdrawn/rejected records."
|
||||
},
|
||||
"held_claims": [
|
||||
{
|
||||
"source_row": 33219,
|
||||
"note_id_claim": "FSf9h6t152",
|
||||
"venue": "NeurIPS",
|
||||
"year": 2025,
|
||||
"raw_decision": "Rejected_Submission",
|
||||
"title": "Hierarchical Restructuring of Graph Neural Networks for Robust Learning under Edge Perturbations",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_no_exact_title_candidate_not_proof_of_novelty"
|
||||
},
|
||||
{
|
||||
"source_row": 44669,
|
||||
"note_id_claim": "Pk972F7J8Um",
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"raw_decision": "Reject",
|
||||
"title": "Differential Privacy of Dirichlet Posterior Sampling",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [
|
||||
{
|
||||
"paper_id": 3527429,
|
||||
"existing_identifiers": [
|
||||
{
|
||||
"scheme": "openreview",
|
||||
"value": "fgBxcKcz9ea",
|
||||
"paper_id": 3527429
|
||||
},
|
||||
{
|
||||
"scheme": "papercopilot_openreview",
|
||||
"value": "nips/2021/fgBxcKcz9ea",
|
||||
"paper_id": 3527429
|
||||
}
|
||||
],
|
||||
"source_abstract_exact_equal": true,
|
||||
"existing_attempts": [
|
||||
{
|
||||
"id": 444666,
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"source_submission_id": "nips/2021/fgBxcKcz9ea",
|
||||
"statuses": [
|
||||
"rejected"
|
||||
]
|
||||
}
|
||||
],
|
||||
"attempts_truncated": false,
|
||||
"identity_approved": false,
|
||||
"id_alias_approved": false
|
||||
}
|
||||
],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_distinct_note_ids_even_with_equal_title_and_abstract"
|
||||
},
|
||||
{
|
||||
"source_row": 44696,
|
||||
"note_id_claim": "ki4eJ1fSJNq",
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"raw_decision": "Reject",
|
||||
"title": "Fitting large mixture models using stochastic component selection",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [
|
||||
{
|
||||
"paper_id": 1545058,
|
||||
"existing_identifiers": [
|
||||
{
|
||||
"scheme": "arxiv",
|
||||
"value": "2110.04776",
|
||||
"paper_id": 1545058
|
||||
},
|
||||
{
|
||||
"scheme": "openreview",
|
||||
"value": "ZS394D3djsg",
|
||||
"paper_id": 1545058
|
||||
},
|
||||
{
|
||||
"scheme": "papercopilot_openreview",
|
||||
"value": "nips/2021/ZS394D3djsg",
|
||||
"paper_id": 1545058
|
||||
}
|
||||
],
|
||||
"source_abstract_exact_equal": true,
|
||||
"existing_attempts": [
|
||||
{
|
||||
"id": 444652,
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"source_submission_id": "nips/2021/ZS394D3djsg",
|
||||
"statuses": [
|
||||
"rejected"
|
||||
]
|
||||
}
|
||||
],
|
||||
"attempts_truncated": false,
|
||||
"identity_approved": false,
|
||||
"id_alias_approved": false
|
||||
}
|
||||
],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_distinct_note_ids_even_with_equal_title_and_abstract"
|
||||
},
|
||||
{
|
||||
"source_row": 45757,
|
||||
"note_id_claim": "bDP7I2fYwLj",
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"raw_decision": "Reject",
|
||||
"title": "WeaveNet for Approximating Assignment Problems",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [
|
||||
{
|
||||
"paper_id": 3527390,
|
||||
"existing_identifiers": [
|
||||
{
|
||||
"scheme": "openreview",
|
||||
"value": "2rAiDBJgR_",
|
||||
"paper_id": 3527390
|
||||
},
|
||||
{
|
||||
"scheme": "papercopilot_openreview",
|
||||
"value": "nips/2021/2rAiDBJgR_",
|
||||
"paper_id": 3527390
|
||||
}
|
||||
],
|
||||
"source_abstract_exact_equal": true,
|
||||
"existing_attempts": [
|
||||
{
|
||||
"id": 444580,
|
||||
"venue": "NeurIPS",
|
||||
"year": 2021,
|
||||
"source_submission_id": "nips/2021/2rAiDBJgR_",
|
||||
"statuses": [
|
||||
"rejected"
|
||||
]
|
||||
}
|
||||
],
|
||||
"attempts_truncated": false,
|
||||
"identity_approved": false,
|
||||
"id_alias_approved": false
|
||||
}
|
||||
],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_distinct_note_ids_even_with_equal_title_and_abstract"
|
||||
},
|
||||
{
|
||||
"source_row": 49327,
|
||||
"note_id_claim": "yB8cQIICqe",
|
||||
"venue": "EMNLP",
|
||||
"year": 2023,
|
||||
"raw_decision": "Desk_Rejected_Submission",
|
||||
"title": "EZ-STANCE: A Large Dataset for Zero-Shot Stance Detection",
|
||||
"same_scope_identifier_match": false,
|
||||
"exact_title_candidates": [],
|
||||
"approved_for_import": false,
|
||||
"disposition": "hold_possible_later_publication_with_changed_title_and_dataset_size_no_identity_or_author_transfer",
|
||||
"later_publication_retrieval_lead": {
|
||||
"url": "https://aclanthology.org/2024.acl-long.838/",
|
||||
"http_status": 200,
|
||||
"bytes": 40557,
|
||||
"response_sha256": "b50dd55c48e31e4c10e97927ce01679369735834aa2c0f8d9f41f8e8e02fc776",
|
||||
"checked_at": "2026-11-18T04:07:03.699767+00:00",
|
||||
"anthology_id": "2024.acl-long.838",
|
||||
"doi": "10.18653/v1/2024.acl-long.838",
|
||||
"title": "EZ-STANCE: A Large Dataset for English Zero-Shot Stance Detection",
|
||||
"venue": "ACL",
|
||||
"year": 2024,
|
||||
"publication_verified": true,
|
||||
"link_to_anonymous_rejection_verified": false,
|
||||
"authors_transferred_to_anonymous_claim": false,
|
||||
"dataset_pairs_published_version": 47316,
|
||||
"dataset_pairs_rejection_mirror_version": 30606,
|
||||
"database_written": false,
|
||||
"current_database_evidence": {
|
||||
"snapshot": {
|
||||
"at": "2026-11-18 04:09:23.720956+00",
|
||||
"snapshot": "1051887:1051887:"
|
||||
},
|
||||
"paper_id": 2131805,
|
||||
"verified_identifiers": [
|
||||
{
|
||||
"scheme": "acl",
|
||||
"value": "2024.acl-long.838",
|
||||
"paper_id": 2131805
|
||||
},
|
||||
{
|
||||
"scheme": "acl_anthology",
|
||||
"value": "2024.acl-long.838",
|
||||
"paper_id": 2131805
|
||||
},
|
||||
{
|
||||
"scheme": "doi",
|
||||
"value": "10.18653/v1/2024.acl-long.838",
|
||||
"paper_id": 2131805
|
||||
}
|
||||
],
|
||||
"existing_attempts": [
|
||||
{
|
||||
"venue": "ACL",
|
||||
"year": 2024,
|
||||
"track": "main",
|
||||
"statuses": [
|
||||
"accepted"
|
||||
]
|
||||
}
|
||||
],
|
||||
"packet_file_sha256": "de5dfa658177adef87134cf7723afc086bd7395405a31166ff9597b03b3c8af3",
|
||||
"original_rejection_link_verified": false
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"access_probes": [
|
||||
{
|
||||
"local_evidence": "researcharcade-neurips2021-original-note-check-v1/report.json",
|
||||
"sha256": "746d752535b516abba43b0e8e6ad901bf39c07da532188dfa97ff911869084ae",
|
||||
"receipt_summary": {},
|
||||
"results": [
|
||||
{
|
||||
"requested_note_id": "Pk972F7J8Um",
|
||||
"status": 403,
|
||||
"url": "https://api.openreview.net/notes?id=Pk972F7J8Um&select=id%2Cforum%2Cinvitation%2Creaders%2Csignatures%2Ccontent.title%2Ccontent.abstract%2Ccontent.venue%2Ccontent.venueid",
|
||||
"sha256": "b0113384cebc9d724284062f776b45044d22450219112342721d8f9683571c08",
|
||||
"checked_at": "2026-11-18T04:01:58.643552+00:00"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"local_evidence": "emnlp2023-primary-public-metadata-probe-v1/notes-probe.json",
|
||||
"sha256": "47799dc4520e113d6a2e7c9ea2f362577bb21e3ad583ee02149a36c21cf6ea9d",
|
||||
"receipt_summary": {
|
||||
"url": "https://api.openreview.net/notes?invitation=EMNLP%2F2023%2FConference%2F-%2FSubmission&limit=1&select=id%2Cnumber%2Cforum%2Cinvitation%2Creaders%2Csignatures%2Ccdate%2Ctcdate%2Cmdate%2Ctmdate%2Ccontent.title%2Ccontent.abstract%2Ccontent.authors%2Ccontent.venue%2Ccontent.venueid%2Ccontent.keywords",
|
||||
"http_status": 403,
|
||||
"response_sha256": "798e964735eb1eff1e4954d5c9e79aad2afd40c3f88dcb82f8ef5bbc55cc0a61",
|
||||
"response_bytes": 546,
|
||||
"at": "2026-11-18T03:38:50.112624+00:00"
|
||||
}
|
||||
},
|
||||
{
|
||||
"local_evidence": "emnlp2023-primary-public-metadata-probe-v1/group-access.json",
|
||||
"sha256": "8fcb9ccd5615a737c17ef0eeedc9121e85a84ebd63667e83df0bda9ffb83d792",
|
||||
"receipt_summary": {
|
||||
"url": "https://api.openreview.net/groups?id=EMNLP%2F2023%2FConference",
|
||||
"http_status": 200,
|
||||
"response_sha256": "7c0cc75e2e8be1c18dffc96a9ceabea34f0f7810139c0a990a6bb117d66f6456",
|
||||
"response_bytes": 13143,
|
||||
"at": "2026-11-18T03:38:49.929085+00:00"
|
||||
}
|
||||
}
|
||||
],
|
||||
"access_limit": "NeurIPS 2021 first original note request and EMNLP 2023 source-declared Submission query returned 403. Requests stopped. No alternate API version, endpoint, authentication, or challenge bypass. 403 does not prove zero public records."
|
||||
}
|
||||
@@ -1,50 +0,0 @@
|
||||
# 公开负面来源核查:2026-11-18
|
||||
|
||||
本次检查 ResearchArcade 缓存中 NeurIPS 2021–2025、EMNLP 2023 的 930 条负面声明,不包括 ICLR 或 2020 年以前的补漏。原始候选文件未重新下载,PostgreSQL 查询为只读。逐条待办、来源哈希与数据库快照见[机器可读记录](public-negative-source-audit-2026-11-18.json)。没有新增论文、决定、ID 别名或合并。
|
||||
|
||||
## 当前库比对
|
||||
|
||||
925 条声明通过同会议、同年份的 OpenReview 标识匹配到投稿,且每条都有 rejected 决定。这里只证明对应拒稿已记录,未核验这些论文的所有后续录用历史,也未证明会议公开拒稿全集完整。
|
||||
|
||||
另 5 条没有同届标识匹配:
|
||||
|
||||
|来源 note.id 声明|会议|标题或识别信息|处置|
|
||||
|---|---|---|---|
|
||||
|FSf9h6t152|NeurIPS 2025|Hierarchical Restructuring of Graph Neural Networks for Robust Learning under Edge Perturbations|无精确标题候选;不是已证明的新论文|
|
||||
|Pk972F7J8Um|NeurIPS 2021|Differential Privacy of Dirichlet Posterior Sampling|候选 paper 3527429,已有同届 rejected,原 ID fgBxcKcz9ea|
|
||||
|ki4eJ1fSJNq|NeurIPS 2021|Fitting large mixture models using stochastic component selection|候选 paper 1545058,已有同届 rejected,原 ID ZS394D3djsg;另保留 arXiv 2110.04776|
|
||||
|bDP7I2fYwLj|NeurIPS 2021|WeaveNet for Approximating Assignment Problems|候选 paper 3527390,已有同届 rejected,原 ID 2rAiDBJgR_|
|
||||
|yB8cQIICqe|EMNLP 2023|EZ-STANCE: A Large Dataset for Zero-Shot Stance Detection|镜像称 Desk_Rejected_Submission;原始公开范围及身份未核验|
|
||||
|
||||
三个标题候选的镜像摘要都与已有 PaperCopilot 来源摘要逐字相等,但来源 ID 不同。相等文本不能独立证明两个 note.id 指向同一个 forum,也不能据此创建第二次投稿或批准 ID 别名。现有实体包没有截断投稿列表,均只有已记录的 NeurIPS 2021 拒稿;这不代表从未在其他地方录用。
|
||||
|
||||
## 采集器证据与使用限制
|
||||
|
||||
作者仓库 [research-arcade](https://github.com/ulab-uiuc/research-arcade) 固定版本 `ecf9c7c2490840b029bd2add4f02d04aca1d014e` 的 `openreview_crawler.py` 显示:
|
||||
|
||||
- 2020–2022 的旧接口路径读取 Blind_Submission 的 `note.id`,从 replies 中取第一个带 `decision` 字段的值,未验证决定 invitation 或签名。
|
||||
- 2019 路径取第一个 `recommendation`,不能将其升级为正式决定。该年度属于保留线索的范围,本轮不补导。
|
||||
- 新接口路径读取 Submission 的 `note.id`,用 `venueid` 尾段作为标签;遇 Conference 再取 `venue`,并跳过 Withdrawn_Submission。
|
||||
|
||||
三个源码文件均核对 Git blob SHA-1 和完整文件 SHA-256;没有执行第三方采集器。源码版本早于数据集版本,但未证明该提交实际生成了此数据集。数据集仅有六个元数据字段,缺少作者和决定签名,因此既不能证明完整 withdrawn 覆盖,也不能将导出的 ID 无条件认作已验证 forum。
|
||||
|
||||
## 原始来源访问结果
|
||||
|
||||
EMNLP 2023 官方分组元数据返回 200,其声明的 Submission invitation 与既有配置一致;对该 invitation 的匿名元数据查询返回 403。NeurIPS 2021 对第一条候选 note `Pk972F7J8Um` 的匿名元数据查询同样返回 403,余下五个 ID 未发请求。均已停止对应来源查询,没有换接口版本、登录或绕过访问限制。403 不能说明没有公开投稿;未保留完整错误正文,也不将具体拒绝原因猜测为已知。
|
||||
|
||||
[EMNLP 2023 官方政策](https://2023.emnlp.org/blog/EMNLP-2023-openreview/)说明公开录用稿件与选择公开的拒稿,现有 9 条 rejected 或本镜像的 1 条 desk-rejected 均不能证明完整公开集合。
|
||||
|
||||
## EZ-STANCE 后续发表线索
|
||||
|
||||
独立的 [ACL Anthology 官方条目](https://aclanthology.org/2024.acl-long.838/)确认相近标题的 EZ-STANCE 在 ACL 2024 Long Papers 发表,DOI `10.18653/v1/2024.acl-long.838`。正式标题多了 English,数据集由拒稿镜像中的 30,606 对变为 47,316 对。已保存官方 HTML 的完整哈希,登记为版本关系核查线索;尚未证明与匿名 EMNLP 2023 声明属于同一投稿或同一科学工作,没有把已发表作者转填到匿名记录,也没有写入关联或第二份论文。后续必须核验版本关系并保留各自的投稿决定证据。
|
||||
|
||||
当前 PostgreSQL 的正式标题变体查询命中已有 paper `2131805`,其 ACL/DOI 标识与官方条目一致,已有 `ACL / 2024 / main / accepted` 投稿历史。该实体无需重复新建。匿名 EMNLP 声明与该实体的关系仍未批准,不能把这条线索表述为已经确认的“先拒后录”。快照、标识及完整实体包哈希已记入机器记录。
|
||||
|
||||
## 下次从哪里继续
|
||||
|
||||
1. 保留五条候选及旧 ID,等待可验证的原始公开元数据或独立可靠来源;不要反复重放已拒绝的原始接口请求。
|
||||
2. 对三对 ID 分歧先取得 note/forum 关系证据,再独立审核科学工作身份与逐次投稿关系;保留已有拒稿及以后发现的录用。
|
||||
3. 两条没有精确标题候选的记录仍需标题变体、作者及摘要交叉核查;匿名元数据不能用于推断作者身份。
|
||||
4. 继续其余会议与年度的公开负面可用性核查,不将这 930 条当作全会、全年份覆盖,也不将 accepted-only 镜像算作拒稿补全。
|
||||
|
||||
另修正交接记录:TMLR 是额外的期刊政策线索,当前 43 个会议的 registry 中没有 TMLR;没有因此更改会议分母。2000–2019 已发现线索仍保留。
|
||||
@@ -28,6 +28,7 @@ COMMANDS = {
|
||||
('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'),
|
||||
('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))
|
||||
Reference in New Issue
Block a user