Compare commits
10 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 codex-bot
|
3f0ac694a0 | ||
 Zayden-Jung
|
32c7edd0a5 | ||
|
Zayden-Jung
|
658d799334 | ||
|
codex-bot
|
53fbe9c75c | ||
|
codex-bot
|
dac6edbe1e | ||
|
Zayden-Jung
|
7a674ac797 | ||
|
codex-bot
|
eacc1e3292 | ||
|
codex-bot
|
2275bc7530 | ||
|
codex-bot
|
9040649320 | ||
|
codex-bot
|
64ced7af42 |
@@ -48,6 +48,7 @@ jobs:
|
||||
outside.mkdir()
|
||||
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','www-archive','--help'],cwd=outside,check=True)
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','maintain','postgres','--help'],cwd=outside,check=True)
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','maintain','edition-tracks','--help'],cwd=outside,check=True)
|
||||
subprocess.run([python,'-I','-B','-m','paper_atlas','maintain','joint-editions','--help'],cwd=outside,check=True)
|
||||
|
||||
@@ -88,6 +88,7 @@ CI 在已授权的远程 runner 上运行测试、构建 wheel，并从源码目
|
||||
|
||||
开发通过工作分支和 PR 交付，由用户手动合并。
|
||||
|
||||
早期WWW档案的可重放元数据采集、论文/海报分轨与待核查条目见 [WWW档案采集](docs/www-archive.md)。
|
||||
历史联合会议的既有届次归属可通过 [`maintain joint-editions`](docs/joint-editions.md) 先只读规划，再按计划哈希执行；保留论文与投稿决定来源，不重导入。
|
||||
同年多届的 `event_key`、显式迁移、旧文件刷新与查询边界见 [会议事件身份](docs/event-identity.md)。
|
||||
研究类型与自定义标签可通过 [`annotate`](docs/annotations.md) 显式初始化、添加和撤回；两者独立查询，保留证据及完整更正历史，不从会议轨道推断研究类型。
|
||||
|
||||
@@ -190,3 +190,7 @@ WWW早期逐来源核查见 `www-early-proceedings-2026-11-08.json`：1995春季
|
||||
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。
|
||||
|
||||
IJCAI 联办届次的逐条后续核查见 [2018/2022 分区与目录差集](ijcai-sections-2026-11-08.md) 和 [稳定 ID 映射](ijcai-sections-2026-11-08.json)。已定位 345 条非 main 分类及 2022 官方 HTML 缺失但官方文件仍存在的一条记录；生产分类尚未修正，不能把整卷数量作为 main 覆盖率。
|
||||
|
||||
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。
|
||||
|
||||
@@ -0,0 +1,867 @@
|
||||
{
|
||||
"snapshot_at": "2026-11-08 16:34:40.741334+00:00",
|
||||
"scope": "Official first-pass conference-year census vs current populated editions and real aliases. Missing year means no imported attempt in that year, not missing paper count or proof all other years complete. Includes announced/nonarchival exceptions below.",
|
||||
"venues": [
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"expected_years": 40,
|
||||
"observed_expected_years": 39,
|
||||
"missing_years": [
|
||||
2026
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"NeurIPS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICML",
|
||||
"expected_years": 43,
|
||||
"observed_expected_years": 14,
|
||||
"missing_years": [
|
||||
1980,
|
||||
1983,
|
||||
1985,
|
||||
1987,
|
||||
1988,
|
||||
1989,
|
||||
1990,
|
||||
1991,
|
||||
1992,
|
||||
1993,
|
||||
1994,
|
||||
1995,
|
||||
1996,
|
||||
1997,
|
||||
1998,
|
||||
1999,
|
||||
2000,
|
||||
2001,
|
||||
2002,
|
||||
2003,
|
||||
2004,
|
||||
2005,
|
||||
2006,
|
||||
2007,
|
||||
2008,
|
||||
2009,
|
||||
2010,
|
||||
2011,
|
||||
2012
|
||||
],
|
||||
"missing_count": 29,
|
||||
"canonical_matches": [
|
||||
"ICML"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICLR",
|
||||
"expected_years": 14,
|
||||
"observed_expected_years": 11,
|
||||
"missing_years": [
|
||||
2014,
|
||||
2015,
|
||||
2016
|
||||
],
|
||||
"missing_count": 3,
|
||||
"canonical_matches": [
|
||||
"ICLR"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "COLM",
|
||||
"expected_years": 3,
|
||||
"observed_expected_years": 3,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"COLM"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "COLT",
|
||||
"expected_years": 39,
|
||||
"observed_expected_years": 39,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"COLT"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "AISTATS",
|
||||
"expected_years": 29,
|
||||
"observed_expected_years": 25,
|
||||
"missing_years": [
|
||||
1985,
|
||||
1989,
|
||||
1991,
|
||||
1993
|
||||
],
|
||||
"missing_count": 4,
|
||||
"canonical_matches": [
|
||||
"AISTATS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "UAI",
|
||||
"expected_years": 42,
|
||||
"observed_expected_years": 42,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"UAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "CLeaR",
|
||||
"expected_years": 5,
|
||||
"observed_expected_years": 5,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"CLEAR"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ACL",
|
||||
"expected_years": 64,
|
||||
"observed_expected_years": 48,
|
||||
"missing_years": [
|
||||
1963,
|
||||
1964,
|
||||
1965,
|
||||
1966,
|
||||
1967,
|
||||
1968,
|
||||
1969,
|
||||
1970,
|
||||
1971,
|
||||
1972,
|
||||
1973,
|
||||
1974,
|
||||
1975,
|
||||
1976,
|
||||
1977,
|
||||
1978
|
||||
],
|
||||
"missing_count": 16,
|
||||
"canonical_matches": [
|
||||
"ACL",
|
||||
"ACL+COLING",
|
||||
"ACL+EACL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "EMNLP",
|
||||
"expected_years": 31,
|
||||
"observed_expected_years": 31,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"CoNLL+EMNLP",
|
||||
"EMNLP"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "NAACL",
|
||||
"expected_years": 18,
|
||||
"observed_expected_years": 18,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"NAACL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "EACL",
|
||||
"expected_years": 19,
|
||||
"observed_expected_years": 19,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"ACL+EACL",
|
||||
"EACL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "COLING",
|
||||
"expected_years": 31,
|
||||
"observed_expected_years": 28,
|
||||
"missing_years": [
|
||||
1971,
|
||||
1976,
|
||||
1978
|
||||
],
|
||||
"missing_count": 3,
|
||||
"canonical_matches": [
|
||||
"ACL+COLING",
|
||||
"COLING",
|
||||
"COLING+LREC"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "CoNLL",
|
||||
"expected_years": 30,
|
||||
"observed_expected_years": 30,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"CoNLL",
|
||||
"CoNLL+EMNLP"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "CVPR",
|
||||
"expected_years": 39,
|
||||
"observed_expected_years": 14,
|
||||
"missing_years": [
|
||||
1983,
|
||||
1985,
|
||||
1986,
|
||||
1988,
|
||||
1989,
|
||||
1991,
|
||||
1992,
|
||||
1993,
|
||||
1994,
|
||||
1996,
|
||||
1997,
|
||||
1998,
|
||||
1999,
|
||||
2000,
|
||||
2001,
|
||||
2003,
|
||||
2004,
|
||||
2005,
|
||||
2006,
|
||||
2007,
|
||||
2008,
|
||||
2009,
|
||||
2010,
|
||||
2011,
|
||||
2012
|
||||
],
|
||||
"missing_count": 25,
|
||||
"canonical_matches": [
|
||||
"CVPR"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICCV",
|
||||
"expected_years": 20,
|
||||
"observed_expected_years": 7,
|
||||
"missing_years": [
|
||||
1987,
|
||||
1988,
|
||||
1990,
|
||||
1993,
|
||||
1995,
|
||||
1998,
|
||||
1999,
|
||||
2001,
|
||||
2003,
|
||||
2005,
|
||||
2007,
|
||||
2009,
|
||||
2011
|
||||
],
|
||||
"missing_count": 13,
|
||||
"canonical_matches": [
|
||||
"ICCV"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ECCV",
|
||||
"expected_years": 19,
|
||||
"observed_expected_years": 4,
|
||||
"missing_years": [
|
||||
1990,
|
||||
1992,
|
||||
1994,
|
||||
1996,
|
||||
1998,
|
||||
2000,
|
||||
2002,
|
||||
2004,
|
||||
2006,
|
||||
2008,
|
||||
2010,
|
||||
2012,
|
||||
2014,
|
||||
2016,
|
||||
2026
|
||||
],
|
||||
"missing_count": 15,
|
||||
"canonical_matches": [
|
||||
"ECCV"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "AAAI",
|
||||
"expected_years": 40,
|
||||
"observed_expected_years": 40,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"AAAI",
|
||||
"AAAI+IAAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "IJCAI",
|
||||
"expected_years": 35,
|
||||
"observed_expected_years": 35,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"ECAI+IJCAI",
|
||||
"IJCAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ECAI",
|
||||
"expected_years": 29,
|
||||
"observed_expected_years": 27,
|
||||
"missing_years": [
|
||||
1974,
|
||||
1980
|
||||
],
|
||||
"missing_count": 2,
|
||||
"canonical_matches": [
|
||||
"ECAI",
|
||||
"ECAI+IJCAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "KDD",
|
||||
"expected_years": 32,
|
||||
"observed_expected_years": 32,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"KDD"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "SIGIR",
|
||||
"expected_years": 50,
|
||||
"observed_expected_years": 50,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"SIGIR"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "WWW",
|
||||
"expected_years": 33,
|
||||
"observed_expected_years": 27,
|
||||
"missing_years": [
|
||||
1994,
|
||||
1996,
|
||||
1997,
|
||||
1998,
|
||||
1999,
|
||||
2000
|
||||
],
|
||||
"missing_count": 6,
|
||||
"canonical_matches": [
|
||||
"WWW"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "WSDM",
|
||||
"expected_years": 19,
|
||||
"observed_expected_years": 19,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"WSDM"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "RecSys",
|
||||
"expected_years": 20,
|
||||
"observed_expected_years": 19,
|
||||
"missing_years": [
|
||||
2026
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"RecSys"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "CIKM",
|
||||
"expected_years": 35,
|
||||
"observed_expected_years": 34,
|
||||
"missing_years": [
|
||||
2026
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"CIKM"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICDM",
|
||||
"expected_years": 26,
|
||||
"observed_expected_years": 25,
|
||||
"missing_years": [
|
||||
2026
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"ICDM"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "SDM",
|
||||
"expected_years": 26,
|
||||
"observed_expected_years": 25,
|
||||
"missing_years": [
|
||||
2026
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"SDM"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ECML-PKDD",
|
||||
"expected_years": 38,
|
||||
"observed_expected_years": 33,
|
||||
"missing_years": [
|
||||
1986,
|
||||
1987,
|
||||
1988,
|
||||
1989,
|
||||
1991
|
||||
],
|
||||
"missing_count": 5,
|
||||
"canonical_matches": [
|
||||
"ECML",
|
||||
"ECML-PKDD",
|
||||
"PKDD"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICRA",
|
||||
"expected_years": 43,
|
||||
"observed_expected_years": 43,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"ICRA"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "IROS",
|
||||
"expected_years": 39,
|
||||
"observed_expected_years": 35,
|
||||
"missing_years": [
|
||||
1988,
|
||||
1989,
|
||||
1990,
|
||||
2026
|
||||
],
|
||||
"missing_count": 4,
|
||||
"canonical_matches": [
|
||||
"IROS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "RSS",
|
||||
"expected_years": 22,
|
||||
"observed_expected_years": 20,
|
||||
"missing_years": [
|
||||
2025,
|
||||
2026
|
||||
],
|
||||
"missing_count": 2,
|
||||
"canonical_matches": [
|
||||
"RSS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "CoRL",
|
||||
"expected_years": 10,
|
||||
"observed_expected_years": 9,
|
||||
"missing_years": [
|
||||
2026
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"CORL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICAPS",
|
||||
"expected_years": 37,
|
||||
"observed_expected_years": 28,
|
||||
"missing_years": [
|
||||
1990,
|
||||
1991,
|
||||
1992,
|
||||
1993,
|
||||
1995,
|
||||
1997,
|
||||
1999,
|
||||
2001,
|
||||
2026
|
||||
],
|
||||
"missing_count": 9,
|
||||
"canonical_matches": [
|
||||
"AIPS",
|
||||
"ICAPS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "KR",
|
||||
"expected_years": 23,
|
||||
"observed_expected_years": 23,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"KR"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "AAMAS",
|
||||
"expected_years": 25,
|
||||
"observed_expected_years": 22,
|
||||
"missing_years": [
|
||||
2012,
|
||||
2025,
|
||||
2026
|
||||
],
|
||||
"missing_count": 3,
|
||||
"canonical_matches": [
|
||||
"AAMAS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICASSP",
|
||||
"expected_years": 51,
|
||||
"observed_expected_years": 49,
|
||||
"missing_years": [
|
||||
1977,
|
||||
2026
|
||||
],
|
||||
"missing_count": 2,
|
||||
"canonical_matches": [
|
||||
"ICASSP"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "INTERSPEECH",
|
||||
"expected_years": 39,
|
||||
"observed_expected_years": 39,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"ECST",
|
||||
"EUROSPEECH",
|
||||
"ICSLP",
|
||||
"INTERSPEECH"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ISMIR",
|
||||
"expected_years": 27,
|
||||
"observed_expected_years": 26,
|
||||
"missing_years": [
|
||||
2026
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"ISMIR"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "MICCAI",
|
||||
"expected_years": 29,
|
||||
"observed_expected_years": 29,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"MICCAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "FAccT",
|
||||
"expected_years": 9,
|
||||
"observed_expected_years": 9,
|
||||
"missing_years": [],
|
||||
"missing_count": 0,
|
||||
"canonical_matches": [
|
||||
"FAccT"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "MLSys",
|
||||
"expected_years": 9,
|
||||
"observed_expected_years": 8,
|
||||
"missing_years": [
|
||||
2018
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"MLSys"
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "MM",
|
||||
"expected_years": 34,
|
||||
"observed_expected_years": 33,
|
||||
"missing_years": [
|
||||
2026
|
||||
],
|
||||
"missing_count": 1,
|
||||
"canonical_matches": [
|
||||
"MM"
|
||||
]
|
||||
}
|
||||
],
|
||||
"expected_venue_years": 1266,
|
||||
"missing_venue_years": 150,
|
||||
"venues_with_missing_years": 25,
|
||||
"known_nonpublication_exceptions": [
|
||||
{
|
||||
"venue": "NeurIPS",
|
||||
"year": 2026,
|
||||
"reason": "announced;not in proceedings index at census"
|
||||
},
|
||||
{
|
||||
"venue": "CoRL",
|
||||
"year": 2026,
|
||||
"reason": "not in publisher proceedings index at census"
|
||||
},
|
||||
{
|
||||
"venue": "MLSys",
|
||||
"year": 2018,
|
||||
"reason": "first non-archival SysML meeting; not a missing formal publication volume"
|
||||
}
|
||||
],
|
||||
"historical_missing_years_excluding_nonarchival_2018": 135,
|
||||
"historical_venues_with_missing_years": 16,
|
||||
"historical_gaps": [
|
||||
{
|
||||
"venue": "ICML",
|
||||
"years": [
|
||||
1980,
|
||||
1983,
|
||||
1985,
|
||||
1987,
|
||||
1988,
|
||||
1989,
|
||||
1990,
|
||||
1991,
|
||||
1992,
|
||||
1993,
|
||||
1994,
|
||||
1995,
|
||||
1996,
|
||||
1997,
|
||||
1998,
|
||||
1999,
|
||||
2000,
|
||||
2001,
|
||||
2002,
|
||||
2003,
|
||||
2004,
|
||||
2005,
|
||||
2006,
|
||||
2007,
|
||||
2008,
|
||||
2009,
|
||||
2010,
|
||||
2011,
|
||||
2012
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICLR",
|
||||
"years": [
|
||||
2014,
|
||||
2015,
|
||||
2016
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "AISTATS",
|
||||
"years": [
|
||||
1985,
|
||||
1989,
|
||||
1991,
|
||||
1993
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ACL",
|
||||
"years": [
|
||||
1963,
|
||||
1964,
|
||||
1965,
|
||||
1966,
|
||||
1967,
|
||||
1968,
|
||||
1969,
|
||||
1970,
|
||||
1971,
|
||||
1972,
|
||||
1973,
|
||||
1974,
|
||||
1975,
|
||||
1976,
|
||||
1977,
|
||||
1978
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "COLING",
|
||||
"years": [
|
||||
1971,
|
||||
1976,
|
||||
1978
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "CVPR",
|
||||
"years": [
|
||||
1983,
|
||||
1985,
|
||||
1986,
|
||||
1988,
|
||||
1989,
|
||||
1991,
|
||||
1992,
|
||||
1993,
|
||||
1994,
|
||||
1996,
|
||||
1997,
|
||||
1998,
|
||||
1999,
|
||||
2000,
|
||||
2001,
|
||||
2003,
|
||||
2004,
|
||||
2005,
|
||||
2006,
|
||||
2007,
|
||||
2008,
|
||||
2009,
|
||||
2010,
|
||||
2011,
|
||||
2012
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICCV",
|
||||
"years": [
|
||||
1987,
|
||||
1988,
|
||||
1990,
|
||||
1993,
|
||||
1995,
|
||||
1998,
|
||||
1999,
|
||||
2001,
|
||||
2003,
|
||||
2005,
|
||||
2007,
|
||||
2009,
|
||||
2011
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ECCV",
|
||||
"years": [
|
||||
1990,
|
||||
1992,
|
||||
1994,
|
||||
1996,
|
||||
1998,
|
||||
2000,
|
||||
2002,
|
||||
2004,
|
||||
2006,
|
||||
2008,
|
||||
2010,
|
||||
2012,
|
||||
2014,
|
||||
2016
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ECAI",
|
||||
"years": [
|
||||
1974,
|
||||
1980
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "WWW",
|
||||
"years": [
|
||||
1994,
|
||||
1996,
|
||||
1997,
|
||||
1998,
|
||||
1999,
|
||||
2000
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ECML-PKDD",
|
||||
"years": [
|
||||
1986,
|
||||
1987,
|
||||
1988,
|
||||
1989,
|
||||
1991
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "IROS",
|
||||
"years": [
|
||||
1988,
|
||||
1989,
|
||||
1990
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "RSS",
|
||||
"years": [
|
||||
2025
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICAPS",
|
||||
"years": [
|
||||
1990,
|
||||
1991,
|
||||
1992,
|
||||
1993,
|
||||
1995,
|
||||
1997,
|
||||
1999,
|
||||
2001
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "AAMAS",
|
||||
"years": [
|
||||
2012,
|
||||
2025
|
||||
]
|
||||
},
|
||||
{
|
||||
"venue": "ICASSP",
|
||||
"years": [
|
||||
1977
|
||||
]
|
||||
}
|
||||
],
|
||||
"current_2026_gaps": 14
|
||||
}
|
||||
@@ -0,0 +1,58 @@
|
||||
# 历史年度缺口的当前核对
|
||||
|
||||
生产只读快照：2026-11-08 16:34:40.741334 UTC（北京时间11月9日00:34），foundry_data/research。对比已核实的43份首轮官方会议年度清单，使用当前有投稿记录的edition及真实venue_aliases，不沿用旧固定快照的missing_years。
|
||||
|
||||
- 清单共1266个会议—年份位置，当前有150个位置尚无投稿记录，涉及25个目标会议。
|
||||
- 其中2025年及以前136个；排除已明确非存档的SysML2018首届，剩**135个历史年度待补采或核实，涉及16个会议**。
|
||||
- 另有14个2026年度待核实。已知NeurIPS2026和CoRL2026在首轮核查时尚未进入论文集索引，不能一律当已公开论文遗漏；其他年度也需逐个核实发布时间。
|
||||
|
||||
这些是“整年没有任何投稿记录”的数量，不是缺论文篇数，也不是完整性百分比。一个年份只有少数记录、只有公开拒稿或缺了某个track，仍会被计作“已有年度”；这些更细缺口及公开拒稿的逐年可获得性尚须继续核验。会议别名共享的联合届次不能当成两批独立论文，未见录用也不能推断拒稿。
|
||||
|
||||
| 会议 | 历史缺口年份数 |
|
||||
| --- | ---: |
|
||||
| ICML | 29 |
|
||||
| CVPR | 25 |
|
||||
| ACL | 16 |
|
||||
| ECCV | 14 |
|
||||
| ICCV | 13 |
|
||||
| ICAPS | 8 |
|
||||
| WWW | 6 |
|
||||
| ECML-PKDD | 5 |
|
||||
| AISTATS | 4 |
|
||||
| ICLR、COLING、IROS | 各3 |
|
||||
| ECAI、AAMAS | 各2 |
|
||||
| RSS、ICASSP | 各1 |
|
||||
|
||||
[完整逐年结果](historical-gaps-2026-11-09.json) 保留43目标的官方预期、现有年份数、缺失年份与规范会议匹配。原始只读生产导出保存在 `/data/paper-index/collected/historical-gap-current-20261109-v1.json`。 导出SHA256 `580cdea6dd9869adafe9bc28fb75cf3854bb290ad65aa5a600d9bc368a528b93`。年度对照清单为 `docs/coverage/inventory-2026-11-08.json`；候选来源文件绑定的输入哈希与本目录缺口JSON逐字节一致。来源清单的年份和哈希沿用相应 `*-editions-2026-11-08.json`，不是本轮重新访问所有会议网站；2026发布状态需要后续更新。
|
||||
|
||||
## 候选来源与下一步
|
||||
|
||||
另一次只读目录核查在现有、已校验的DBLP快照中，为135个历史年度中的**85个**匹配到初步候选论文集，另**50个**尚未按本轮规则匹配到，需要继续识别目录键或寻找官方来源。未匹配不等于会议没举办、未出版或没有公开来源。
|
||||
|
||||
[候选卷清单](historical-source-candidates-2026-11-09.json) 保留卷key、标题、出版年份、原始bibliographic counts和出版者链接。初筛使用目标family映射内的四位卷key年份或卷标题唯一显式年份，再按具体会议身份复核；两位键、出版年份与会议年份差异、前身系列及其他目录命名可能漏匹配。原始计数可能含workshop、前言、索引或多个卷，**不能当可直接导入的录用论文数量**。
|
||||
|
||||
后续[来源范围复核](historical-source-scope-2026-11-09.md)排除了4个误归ACL的COLING卷，因此候选年度由89修正为85、未匹配年度由46增至50。原卷及排除理由保留在JSON中；135个历史年度缺口不因此改变。ACL1963–1978与COLING1971/1976/1978在当前Anthology目录未列出，继续记为来源待核实，不能一律称作已公开但漏采的论文集。
|
||||
|
||||
优先核查已有候选卷较集中的CVPR22年、ICCV12年、ECCV14年和ICML25年。其中ICML早期workshop名称可能属于官方主系列前身，也可能是附属workshop，须对照官方届次证据逐卷区分，不能靠标题包含workshop一刀切。所有候选须经过范围、稳定标识、重复/冲突、原始字段和覆盖预检；这一步没有导入候选卷。
|
||||
|
||||
## 复核方法
|
||||
|
||||
只读获取当前有记录的edition，不连接papers大文本或标签表：
|
||||
|
||||
```sql
|
||||
WITH counts AS (
|
||||
SELECT edition_id,count(*) AS submissions
|
||||
FROM submissions GROUP BY edition_id
|
||||
)
|
||||
SELECT e.id,e.venue_id,v.acronym,e.year,e.track,e.event_key,counts.submissions
|
||||
FROM editions e JOIN venues v ON v.id=e.venue_id
|
||||
JOIN counts ON counts.edition_id=e.id ORDER BY e.id;
|
||||
|
||||
SELECT venue_id,alias FROM venue_aliases ORDER BY venue_id,alias;
|
||||
```
|
||||
|
||||
逐目标取规范会议名或别名相等的edition年份集合，与该目标edition_census.expected_years做集合差；再把2026与明确非存档的SysML2018单列。保留原始导出与校验哈希，不把每个matched year误当逐篇/逐track完整。
|
||||
|
||||
与本清单同一阶段的WWW补采只补1995年现有poster轨道，不新增缺失年度，所以即使其15条增量已验收，135这个年度计数也不会随之下降。早期1994年的50条正式展示候选、307条混合节目候选共357条仍需核实；其中并非每条都是论文。
|
||||
|
||||
本清单用于明确第14步剩余范围，不代表第14步完成，也不替代所有导入结束后的第16步全库去重、摘要、约束和实际查询验收。
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,32 @@
|
||||
# 早期 NLP 来源范围复核
|
||||
|
||||
核查时间：2026-11-08 18:27 UTC（北京时间11月9日）。本轮只修正来源候选和记录可获得性，没有操作生产数据库。
|
||||
|
||||
## 跨会议候选修正
|
||||
|
||||
先前候选清单将 `conf/coling/1965`、`1967`、`1969`、`1973` 匹配到 ACL 年会缺口。这四卷标题明确属于 COLING；[COLING 官方 Anthology 目录](https://aclanthology.org/venues/coling/)将它们列在 COLING 下。出版者写作 ACL 或目标映射包含 COLING，不足以证明某一年是 ACL 联办届次。
|
||||
|
||||
从 ACL 候选中排除上述四卷，原始卷字段和排除理由保留在[候选JSON](historical-source-candidates-2026-11-09.json)的 `excluded_cross_venue_candidates` 中。135个历史会议—年份位置仍未关闭；有初步候选来源的年度由89修正为85，尚未匹配的由46增至50。这些数字是目录初筛结果，不是已验证可导入的论文数。
|
||||
|
||||
联合届次仍按具体年度的明确会议身份处理，例如有官方联办证据的卷可以属于多个会议。不能一律排除跨family卷，也不能把联合卷重复导入为两批论文。
|
||||
|
||||
## 来源待核实的早期年份
|
||||
|
||||
| 范围 | 本轮官方来源观察 | 处理 |
|
||||
| --- | --- | --- |
|
||||
| ACL 1963–1978，共16年 | [ACL 官方 Anthology 目录](https://aclanthology.org/venues/acl/)目前从1979年列起 | 保留历史举办清单；逐年核实是否有可索引发表材料，不能据会议举办就断言漏采正式论文集，也不据目录缺失断言未出版 |
|
||||
| COLING 1971、1976、1978 | [主办委员会历史](https://ufal.mff.cuni.cz/iccl-old)列出这三届；当前Anthology COLING目录未列出 | 来源缺口继续开放，需要主办方或出版者逐篇索引；不生成占位论文或录用/拒稿记录 |
|
||||
|
||||
这19个位置不能用其他会议的卷补齐，也不能因本轮未找到目录而删除。公开拒稿可获得性是独立核查，不从论文集或录用清单缺失推断。
|
||||
|
||||
## 证据与复核
|
||||
|
||||
三份原始HTML及 `receipts.json` 保存在工作证据目录 `paper-index/nlp-history-source-review-v1/`；结构化响应URL、时间、状态、字节数和完整SHA256收录于候选JSON的 `scope_review.evidence`。三次响应均为HTTP200；未获取论文全文。
|
||||
|
||||
| 官方来源 | 响应SHA256 |
|
||||
| --- | --- |
|
||||
| [acl-venue](https://aclanthology.org/venues/acl/) | `d04c188c0769e065f18ca9c0246f70086e2f7027ce3efe5ea0f2cdc641796b72` |
|
||||
| [coling-venue](https://aclanthology.org/venues/coling/) | `8e7ec0a2915bfbccaa26b7a7558a9cf977c4aadc119794516ecebb826f61623f` |
|
||||
| [iccl-history](https://ufal.mff.cuni.cz/iccl-old) | `c5286dc51236c90685d22543ff1f7b209adcb3eedb82a7b1ac2115c8dd0169fc` |
|
||||
|
||||
复核时先校验保存的原始响应哈希，再读取目录中的会议身份和年度。实时网页若已变化，应另存新响应和时间，不能把新内容套用旧哈希。本次不改最初会议年度清单或生产年度快照，不代表第14步覆盖验收或第16步最终全库审计完成。
|
||||
@@ -0,0 +1,201 @@
|
||||
{
|
||||
"format": 1,
|
||||
"source_cache_sha256": "8a65562f3490497cada2919ec77827134beabd5ec9c3690dec3625e2318aa54e",
|
||||
"records": [
|
||||
{
|
||||
"entry_id": "45",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/45/index.html",
|
||||
"individual_sha256": "83bede6afc9a7039fae2dd1f28274a394418b34f5d5632590b913617580bda1a",
|
||||
"title": "WISE - World Wide Information System for R&D; Efforts",
|
||||
"authors": [
|
||||
"Fritz Loseries",
|
||||
"Veronika Samara",
|
||||
"Bodo Urban"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "16",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/16/index.html",
|
||||
"individual_sha256": "cf76da903eaeaa27d19857fdaa13220f6821559bf4ac22844fae10abbaa6f3f3",
|
||||
"title": "The World Wide Web as a Tool for Collaborative Inter-Agency Projects: Creation of an Environmental Metadata Database for the Analysis of the Venice Lagoon Ecosystem.",
|
||||
"authors": [
|
||||
"Mirko Labbri"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "17",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/17/index.html",
|
||||
"individual_sha256": "0578fec9c82e8f2f98c4de0f1bcc44011ebb84c53353fdcc423a69cf70673bc2",
|
||||
"title": "NetRepreneur",
|
||||
"authors": [
|
||||
"Kari-Pekka Turtiainen",
|
||||
"Antti Auer"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "29",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/29/index.html",
|
||||
"individual_sha256": "624ad3f685de1163411e33e90488975d848a63243fd7ffbed0862c6fb58c4140",
|
||||
"title": "Mosaic TueV 2.4.3: Multilingual GUI and Improvements towards User Friendliness",
|
||||
"authors": [
|
||||
"Mike Bretz",
|
||||
"Uwe Koch",
|
||||
"Paul de Bra"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "13",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/13/index.html",
|
||||
"individual_sha256": "02409321a3403a94d8362a9862f4960386ea9c344fb47f4bcdf9eae128e8b46e",
|
||||
"title": "Using a WWW Browser as an Alternative User Interface for Interactive Applications",
|
||||
"authors": [
|
||||
"Frank Lonczewski"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "36",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/36/index.html",
|
||||
"individual_sha256": "ed9dada4ea5903cb8f0a4e75f2958416a6e32647fbf3530e58edd9abf26070ce",
|
||||
"title": "HyperSource: A Hypermedia Program Development And Documentation System",
|
||||
"authors": [
|
||||
"Jan Oliver Borchers"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "57",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/57/index.html",
|
||||
"individual_sha256": "3ad4206ad28a19823172cd2845f636fe7a461c251940e9a93deb8f6484b8a984",
|
||||
"title": "Progressive Image Transmission Capability (PROTRAC) on the World Wide Web",
|
||||
"authors": [
|
||||
"Vojislav Lalich-Petrich",
|
||||
"Gaurav Bhatia",
|
||||
"Larry Davis"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "38",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/38/index.html",
|
||||
"individual_sha256": "940370acc5e6a954b197053fe451e466a904d1f0ac82c8fe4e6ca455faf2c927",
|
||||
"title": "Measuring the Web with Lycos",
|
||||
"authors": [
|
||||
"Michael L. Mauldin"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": "Official abstract listing has no abstract. Canonical HTML has body sections but no explicit abstract; body is not substituted as a summary."
|
||||
},
|
||||
{
|
||||
"entry_id": "05",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/05/index.html",
|
||||
"individual_sha256": "1858be87d6e7f47476e1cb8fb4793c0fce3b8a6ff653bcfd4a35089e0520f177",
|
||||
"title": "Virtual Places - Adding people to the web",
|
||||
"authors": [
|
||||
"Yosi Mass"
|
||||
],
|
||||
"author_source": "author_index",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": "Official abstract listing and canonical HTML have no abstract. Canonical page identifies a contact and links PostScript; no full-text download. Author identity comes from author index, not inferred from contact role."
|
||||
},
|
||||
{
|
||||
"entry_id": "37",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/37/index.html",
|
||||
"individual_sha256": "b700a0a51b7a82a5f88373ae0283bb369d1cf6f455acff7d91cd7313fa8b3adf",
|
||||
"title": "The Internet Public Library: Serving a Global Community",
|
||||
"authors": [
|
||||
"Susan Schweitzer"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "41",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/41/index.html",
|
||||
"individual_sha256": "397b474109f9c1240a77d0f490f2b02dd35fae93febbb7397d1b2a31759a8ec1",
|
||||
"title": "Graphical Browsing in the WorldWideWeb and the MultiMedia Forum",
|
||||
"authors": [
|
||||
"Rainer Pagé",
|
||||
"Klaus Süllow"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "47",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/47/index.html",
|
||||
"individual_sha256": "52eb4bfdd658730a222c98170b72dabf9cbcc5ffd2ada1e900b826baf2b02833",
|
||||
"title": "Interoperating Advanced Hypermedia Systems with WWW",
|
||||
"authors": [
|
||||
"Jian Zhang",
|
||||
"Martin Fruehauf",
|
||||
"Thomas Kirste"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "50",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/50/index.html",
|
||||
"individual_sha256": "8dc8b0561bd8b1b106c5b209a973c695c3cc9df5288450d4a01fe32541476b7e",
|
||||
"title": "Web Enabled Agile Manufacturing",
|
||||
"authors": [
|
||||
"S. V. Iyer",
|
||||
"T. Singh",
|
||||
"U. Ravaioli",
|
||||
"R. E. DeVor",
|
||||
"S. G. Kapoor",
|
||||
"G. Veknatasubramian"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "55",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/55/index.html",
|
||||
"individual_sha256": "21780cd4047f513e8c9aeced5247002e27cf71719f08de85c6531b57a9e5058d",
|
||||
"title": "Weblets: Fundamental Building Blocks for WWW Tools",
|
||||
"authors": [
|
||||
"Thomas J. Watt Jr."
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
},
|
||||
{
|
||||
"entry_id": "59",
|
||||
"individual_url": "https://archives.iw3c2.org/www3/proceedings/posters/59/index.html",
|
||||
"individual_sha256": "fed4cc9dcaee350a12c5e4b6fa9c99be9bead25a81632512d31566400d3d0fad",
|
||||
"title": "Usenet and the World-Wide Web",
|
||||
"authors": [
|
||||
"M. L. Grant"
|
||||
],
|
||||
"author_source": "canonical_byline",
|
||||
"reason": "Reviewed canonical H1 and explicit authorship for this exact linked poster entry; retain abstract-heading and author-index title variants without fuzzy matching.",
|
||||
"missing_abstract_reason": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,111 @@
|
||||
# Early WWW archive collector
|
||||
|
||||
`paper-atlas collect www-archive` is a maintained metadata adapter. It reads official
|
||||
IW3C2 archive HTML, keeps exact source hashes, and separates importable rows from
|
||||
program entries that still need review. It fetches no PDF, follows no paper-body or
|
||||
reference link, and makes no database connection.
|
||||
|
||||
For a fresh source snapshot on the server:
|
||||
|
||||
```sh
|
||||
paper-atlas collect www-archive \
|
||||
--http-cache /data/paper-index/cache/www-archive \
|
||||
--source-cache /data/paper-index/collected/www-archive-source-v2 \
|
||||
--out /data/paper-index/collected/www-archive-normalized-v2
|
||||
```
|
||||
|
||||
For reproducible offline replay of the already verified snapshot:
|
||||
|
||||
```sh
|
||||
paper-atlas collect www-archive \
|
||||
--source-cache /data/paper-index/collected/www-early-archive-source-v1 \
|
||||
--source-cache-sha256 c9388ccef44486e0684c9ee9e8620a465cdc4574e6bc9ea9391d743e01a3312c \
|
||||
--out /data/paper-index/collected/www-archive-normalized-v1
|
||||
```
|
||||
|
||||
Use a new output directory for another batch. Existing snapshots and normalized
|
||||
batches are never overwritten. The manifest hash binds every source URL, byte count,
|
||||
response hash and cache filename. Plain files must remain directly within the cache;
|
||||
symlinks, escaping paths, duplicate URLs, non-200 responses and altered bytes fail.
|
||||
The command uses UTF-8 where valid and explicitly records an ISO-8859-1 fallback for
|
||||
older pages; original bytes remain authoritative for encoding corrections.
|
||||
|
||||
## Evidence and outputs
|
||||
|
||||
- WWW3 Spring 1995 papers use `event_key=www-1995-spring`, `track=main`. The author,
|
||||
session and abstract indexes must have the same nonempty entry-ID set. The ID is
|
||||
local to this exact event and proceedings section, never a DOI or OpenReview ID.
|
||||
- Posters remain `track=poster`. An abstract without a linked author-index entry
|
||||
stays in review even when another index has a placeholder `#` link for it.
|
||||
- Paper URLs must agree between author and session indexes. A malformed whitespace
|
||||
URL in the abstract list may use the exact event/entry-ID match only when both
|
||||
independent indexes corroborate the same clean URL. The original href is retained.
|
||||
- Canonical names come from the explicitly labeled author index. The source lists
|
||||
them alphabetically; this is **not** original byline order. Both the raw index names
|
||||
and the full abstract-page byline/affiliation text remain in metadata. No person ID
|
||||
or cross-source identity is inferred from a name. Conflicting titles or missing
|
||||
abstracts stay in review. Topic keywords are not treated as an abstract.
|
||||
- WWW1 1994 formal presentations and WWW2 1994 mixed categories remain review
|
||||
candidates. The first list contains uncertain business-track annotations and a
|
||||
count discrepancy; the second contains panels, tutorials, products and other
|
||||
activities. Neither presentation listing nor a missing full-text link establishes
|
||||
a regular-paper acceptance or a rejection. Raw category/title/name claims are kept.
|
||||
|
||||
The main and poster JSONL files have independent manifests with explicit event key,
|
||||
track, count and SHA256. `source_listing_count` records the full recognized abstract
|
||||
listing, while `held_entry_count` records excluded entries; neither is a ready-row
|
||||
count. Their status stays `partial`: a verified linked subset does
|
||||
not prove complete event coverage. `review-candidates.jsonl` contains nested
|
||||
candidates and reasons, with no importable decision status. It is excluded from
|
||||
`import-queue.json`. `report.json` accounts for ready/held records and every source
|
||||
used. Newlines delimit JSONL; Unicode U+2028/U+2029 inside metadata are not line breaks.
|
||||
The output is published only after all required source and scope checks pass.
|
||||
|
||||
## Before importing
|
||||
|
||||
This independent collector branch starts from main; it does not include or silently
|
||||
install the event-aware writer. Its output requires the reviewed integrated runtime
|
||||
from PR31 (or a main revision containing that implementation). The production event
|
||||
schema migration has been independently accepted, preserving existing edition1212
|
||||
and its 59 Fall submissions; that is not an import of the Spring proceedings.
|
||||
|
||||
Inspect held entries and original author names, preflight every ready row against
|
||||
current PostgreSQL stable identifiers and candidate identities, and verify the
|
||||
source/year/track/event coverage before running `import records`. When a ready subset
|
||||
excludes held entries, preserve the independently known listing total in the existing
|
||||
incremental-coverage protocol: bind a freshly checked parent count and expected count,
|
||||
and set the full expected count from this manifest. A new source uses previous count
|
||||
0 and previous expected count null; an existing source requires its actual current
|
||||
values. These live parent values are not guessed by the offline collector. Do not automatically
|
||||
run this queue against an older writer. Preserve extended versions and independent
|
||||
submission/decision evidence, and keep unresolved identities held. A normalization
|
||||
report or passing tests alone do not establish production import, complete historical
|
||||
coverage or final global deduplication.
|
||||
|
||||
Initial fixed-cache replay (64ced7a, CI1057): 38 main papers and38 posters ready;
|
||||
372 entries held (50 first-conference fields,307 mixed program entries,15 posters).
|
||||
Independent report44dfd070 verified source hashes,counts and author evidence, finding
|
||||
one existing exact-title candidate. That publication is explicitly linked to
|
||||
arXiv1811.12161 by its WWW1995/journal-reference declaration; arXiv1810.07232 is a
|
||||
different1997 invited chapter and remains separate despite the overlap note. This
|
||||
is a preparation observation, not evidence of completed production import or final
|
||||
global deduplication.
|
||||
|
||||
## 以单篇官方页面核实待处理 poster
|
||||
|
||||
作者索引漏链接、摘要目录使用短标题或标题存在拼写差异时，不放宽全局标题匹配。可以先取得单篇官方 HTML，人工核对 H1、署名区与原目录同一 entry URL，再提供带 SHA256 的逐条核查文件：
|
||||
|
||||
```sh
|
||||
paper-atlas collect www-archive \
|
||||
--source-cache /data/paper-index/collected/www-poster-reviewed-source-v2 \
|
||||
--source-cache-sha256 8a65562f3490497cada2919ec77827134beabd5ec9c3690dec3625e2318aa54e \
|
||||
--reviewed-posters docs/coverage/www-1995-posters-reviewed-2026-11-09.json \
|
||||
--reviewed-posters-sha256 <核查文件的SHA256> \
|
||||
--out <新的输出目录>
|
||||
```
|
||||
|
||||
[1995 年15条poster的核查输入](coverage/www-1995-posters-reviewed-2026-11-09.json) 绑定61页来源快照：原46页和补取的15页单篇HTML。程序验证输入文件及快照哈希、单篇页面哈希、完全一致的 canonical H1、原摘要目录中的同一URL/entry ID及作者证据，不通过相似标题猜身份。规范标题采用单篇H1，摘要目录标题及作者索引标题均在 metadata 中保留。
|
||||
|
||||
`author_source=canonical_byline` 表示名字出现在H1之后、摘要/关键词或下一节标题之前的署名区域，由逐条核查明确选出，不从全文引用或机构猜作者；保留原始缩写、顺序、重音和拼写。只有 `author_source=author_index` 时使用原作者索引顺序并逐项核对；05的单篇页面写的是联系人，作者身份使用原作者索引证据，不由联系人角色推断。核查输入是审阅后的数据声明，程序的字符串/哈希检查不代替人工识别署名语义。
|
||||
|
||||
38和05的来源没有可明确引用的摘要。保留 `abstract=null` 和逐条缺失原因，manifest准确报告 missing_abstract_count，继续标partial；正文、联系方式及PostScript链接不当作摘要，也不下载正文。缺摘要不等于拒稿或未发表。本批输出仍包含原先已验收记录，正式导入前必须只取新增external ID，检查实时覆盖父记录并按incremental模式准备，不能直接重导入全部输出。
|
||||
@@ -23,6 +23,7 @@ COMMANDS = {
|
||||
('collect','mlsys'): ('paper_atlas.collectors.proceedings', {'source':'mlsys'}, 'MLSys 官方历年标题与摘要'),
|
||||
('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','www-archive'): ('paper_atlas.collectors.www_archive', {}, '核验早期WWW官方档案并分开待核查条目'),
|
||||
('collect','dblp'): ('paper_atlas.collectors.dblp_records', {}, '核对并整理 DBLP 历史发表记录'),
|
||||
('catalogue','dblp'): ('paper_atlas.collectors.dblp', {}, '盘点 DBLP 历史会议目录'),
|
||||
('import','arxiv'): ('paper_atlas.ingestion.arxiv', {}, '导入 arXiv 元数据 ZIP'),
|
||||
|
||||
@@ -0,0 +1,340 @@
|
||||
"""Reproducible early WWW metadata; unresolved program entries stay outside imports."""
|
||||
import argparse
|
||||
from collections import defaultdict
|
||||
import hashlib
|
||||
from html.parser import HTMLParser
|
||||
import json
|
||||
from pathlib import Path
|
||||
import re
|
||||
import tempfile
|
||||
from urllib.parse import urljoin, urlsplit
|
||||
|
||||
from paper_atlas.io.html import Document, clean
|
||||
from paper_atlas.io.http import fetch
|
||||
|
||||
ROOT = 'https://archives.iw3c2.org/'
|
||||
SPRING = ROOT+'www3/proceedings/'
|
||||
FALL = ROOT+'www2/Proceedings/WWW2_Proceedings.html'
|
||||
SEEDS = [ROOT+'www1/PrelimProcs.html', ROOT+'www1/Proceedings.html', FALL,
|
||||
SPRING+'proceedings.html', *[SPRING+'papers/'+x+'.html' for x in ('author','session','abstract')],
|
||||
*[SPRING+'posters/'+x+'.html' for x in ('author','abstract')]]
|
||||
|
||||
|
||||
def decode(raw):
|
||||
try:
|
||||
return raw.decode('utf-8-sig'), 'utf-8'
|
||||
except UnicodeDecodeError:
|
||||
return raw.decode('iso-8859-1'), 'iso-8859-1 fallback; original bytes retained'
|
||||
|
||||
|
||||
def text(html):
|
||||
return re.sub(r'[ \t\r\n\f\v]+',' ',Document(html).root.text()).strip(' \t\r\n\f\v')
|
||||
|
||||
|
||||
def anchors(html):
|
||||
return [(n.attrs.get('href',''),clean(n.text())) for n in Document(html).root.walk() if n.tag=='a']
|
||||
|
||||
|
||||
def source_url(url):
|
||||
p=urlsplit(url)
|
||||
if p.scheme!='https' or p.netloc!='archives.iw3c2.org' or p.query or p.fragment or not p.path.endswith('.html'):
|
||||
raise ValueError('Only exact official archive HTML source URLs are allowed')
|
||||
return url
|
||||
|
||||
|
||||
class Sources:
|
||||
def __init__(self, directory, expected_sha256):
|
||||
self.root=Path(directory).resolve();manifest=self.root/'manifest.json';raw=manifest.read_bytes()
|
||||
if hashlib.sha256(raw).hexdigest()!=expected_sha256:
|
||||
raise ValueError('Source cache manifest checksum mismatch')
|
||||
self.rows={};self.used=set()
|
||||
for row in json.loads(raw)['sources']:
|
||||
url=source_url(row['url'])
|
||||
if url in self.rows or row.get('status')!=200:
|
||||
raise ValueError('Duplicate or incomplete source response')
|
||||
p=self.root/row['file']
|
||||
if p.is_symlink() or p.parent!=self.root or not p.is_file():
|
||||
raise ValueError('Source cache paths must be plain files directly within the cache')
|
||||
data=p.read_bytes()
|
||||
if len(data)>2*1024**2 or len(data)!=row['bytes'] or hashlib.sha256(data).hexdigest()!=row['sha256']:
|
||||
raise ValueError('Source response checksum or size mismatch')
|
||||
self.rows[url]={'raw':data,'receipt':row}
|
||||
|
||||
def read(self,url):
|
||||
source_url(url)
|
||||
if url not in self.rows:
|
||||
raise ValueError('Required source missing from cache: '+url)
|
||||
self.used.add(url)
|
||||
return decode(self.rows[url]['raw'])[0]
|
||||
|
||||
def proof(self,urls):
|
||||
return [{'url':url,'sha256':self.rows[url]['receipt']['sha256'],
|
||||
'encoding':decode(self.rows[url]['raw'])[1]} for url in sorted(set(urls))]
|
||||
|
||||
|
||||
def download_sources(http_cache, directory):
|
||||
directory=Path(directory)
|
||||
if directory.exists():
|
||||
raise ValueError('Refusing to overwrite a source snapshot')
|
||||
directory.mkdir(parents=True)
|
||||
responses={url:fetch(url,http_cache,2*1024**2) for url in SEEDS}
|
||||
html=decode(responses[FALL])[0]
|
||||
for href,label in anchors(html):
|
||||
if href!='Author_Inst.html' and href.endswith('.html'):
|
||||
url=source_url(urljoin(FALL,href))
|
||||
if not url.startswith(ROOT+'www2/Proceedings/'):
|
||||
raise ValueError('Unexpected fall category source')
|
||||
responses[url]=fetch(url,http_cache,2*1024**2)
|
||||
receipts=[]
|
||||
for i,(url,raw) in enumerate(sorted(responses.items())):
|
||||
name='source-'+str(i).zfill(2)+'.html';(directory/name).write_bytes(raw)
|
||||
receipts.append({'url':url,'status':200,'file':name,'bytes':len(raw),'sha256':hashlib.sha256(raw).hexdigest()})
|
||||
manifest=directory/'manifest.json';manifest.write_text(json.dumps({'sources':receipts},indent=2)+'\n')
|
||||
return hashlib.sha256(manifest.read_bytes()).hexdigest()
|
||||
|
||||
|
||||
def identity(href,track):
|
||||
url=urljoin(SPRING+track+'/',href);p=urlsplit(url)
|
||||
match=re.fullmatch(r'/www3/proceedings/'+track+r'/(\d+)/[^?#]+',p.path)
|
||||
if p.scheme=='https' and p.netloc=='archives.iw3c2.org' and not p.query and not p.fragment and match:
|
||||
return match[1],url
|
||||
return None
|
||||
|
||||
|
||||
class AuthorIndex(HTMLParser):
|
||||
def __init__(self,html,track):
|
||||
super().__init__(convert_charrefs=True);self.track=track;self.name='';self.bold=None;self.link=None;self.link_text=[]
|
||||
self.entries=defaultdict(lambda:{'authors':[],'urls':set(),'titles':set()});self.feed(html)
|
||||
|
||||
def handle_starttag(self,tag,attrs):
|
||||
if tag=='b':self.bold=[]
|
||||
if tag=='a':self.link=dict(attrs).get('href');self.link_text=[]
|
||||
|
||||
def handle_data(self,data):
|
||||
if self.bold is not None:self.bold.append(data)
|
||||
if self.link is not None:self.link_text.append(data)
|
||||
|
||||
def handle_endtag(self,tag):
|
||||
if tag=='b' and self.bold is not None:
|
||||
self.name=clean(''.join(self.bold));self.bold=None
|
||||
if tag=='a' and self.link is not None:
|
||||
own=identity(self.link,self.track)
|
||||
if own:
|
||||
key,url=own;entry=self.entries[key];entry['urls'].add(url);entry['titles'].add(clean(''.join(self.link_text)))
|
||||
if not self.name:raise ValueError('Paper link has no archive author context')
|
||||
if self.name not in entry['authors']:entry['authors'].append(self.name)
|
||||
self.link=None
|
||||
|
||||
|
||||
def sections(html):
|
||||
"""Use explicit h3 boundaries; old HTML omits many p/li closing tags."""
|
||||
result=[]
|
||||
for chunk in re.split(r'<h3\b[^>]*>',html,flags=re.I)[1:]:
|
||||
parts=re.split(r'</h3\s*>',chunk,maxsplit=1,flags=re.I)
|
||||
if len(parts)!=2:raise ValueError('Unclosed archive entry heading')
|
||||
heading,body=parts
|
||||
body=re.split(r'<(?:hr|h2|address)\b',body,maxsplit=1,flags=re.I)[0]
|
||||
author=re.search(r'<i\b[^>]*>(.*?)</i\s*>',body,re.I|re.S)
|
||||
paragraphs=[]
|
||||
for paragraph in re.findall(r'<p\b[^>]*>(.*?)(?=</p\s*>|<p\b|$)',body,re.I|re.S):
|
||||
value=text(paragraph)
|
||||
if value and not value.casefold().startswith('keywords:'):paragraphs.append(value)
|
||||
result.append({'heading':heading,'title':text(heading),'abstract':'\n\n'.join(paragraphs)or None,
|
||||
'author_byline_raw':text(author[1])if author else None})
|
||||
if not result:raise ValueError('No explicit archive entry headings')
|
||||
return result
|
||||
|
||||
|
||||
def reviewed_posters(sources, path, expected_sha256, cache_sha256):
|
||||
if path is None:
|
||||
if expected_sha256:raise ValueError('Reviewed poster path required')
|
||||
return {},None
|
||||
raw=Path(path).read_bytes()
|
||||
if hashlib.sha256(raw).hexdigest()!=expected_sha256:raise ValueError('Reviewed poster checksum mismatch')
|
||||
review=json.loads(raw)
|
||||
if set(review)!={'format','source_cache_sha256','records'} or review['format']!=1 or review['source_cache_sha256']!=cache_sha256:
|
||||
raise ValueError('Reviewed poster snapshot binding differs')
|
||||
if not isinstance(review['records'],list) or not 0<len(review['records'])<=100:
|
||||
raise ValueError('Bounded nonempty poster review required')
|
||||
result={}
|
||||
for row in review['records']:
|
||||
if set(row)!={'entry_id','individual_url','individual_sha256','title','authors','author_source','reason','missing_abstract_reason'}:
|
||||
raise ValueError('Unexpected reviewed poster fields')
|
||||
key=row['entry_id'];own=identity(row['individual_url'],'posters')
|
||||
if not isinstance(key,str) or not own or own[0]!=key or key in result:
|
||||
raise ValueError('Reviewed poster identity duplicated or outside canonical entry')
|
||||
if row['author_source'] not in ('canonical_byline','author_index') or not isinstance(row['authors'],list) or not row['authors'] or any(not isinstance(a,str) or not a.strip()for a in row['authors']):
|
||||
raise ValueError('Explicit author evidence required')
|
||||
if len(set(row['authors']))!=len(row['authors']) or not isinstance(row['reason'],str) or not row['reason'].strip():
|
||||
raise ValueError('Reviewed author order/reason invalid')
|
||||
if sources.rows.get(own[1],{}).get('receipt',{}).get('sha256')!=row['individual_sha256']:
|
||||
raise ValueError('Individual poster page checksum differs')
|
||||
page=sources.read(own[1]);headings=re.findall(r'<h1\b[^>]*>(.*?)</h1\s*>',page,re.I|re.S)
|
||||
if len(headings)!=1 or text(headings[0])!=row['title']:
|
||||
raise ValueError('Reviewed title differs from exact canonical H1')
|
||||
header=re.split(r'</h1\s*>',page,maxsplit=1,flags=re.I)[1]
|
||||
header=re.split(r'<h[23]\b',header,maxsplit=1,flags=re.I)[0]
|
||||
header=re.split(r'\b(?:keywords|abstract)\s*:',text(header),maxsplit=1,flags=re.I)[0]
|
||||
if row['author_source']=='canonical_byline' and any(a.casefold() not in header.casefold()for a in row['authors']):
|
||||
raise ValueError('Reviewed author absent from canonical byline region')
|
||||
result[key]={**row,'canonical_byline_region_raw':header}
|
||||
return result,hashlib.sha256(raw).hexdigest()
|
||||
|
||||
|
||||
def reviewed_row(sources,key,url,item,authors,review):
|
||||
if url!=review['individual_url']:
|
||||
raise ValueError('Reviewed canonical page differs from abstract-entry URL')
|
||||
if authors and authors['urls']!={url}:
|
||||
raise ValueError('Reviewed poster author-index URL disagrees')
|
||||
if review['author_source']=='author_index':
|
||||
names=[]
|
||||
for name in authors['authors']if authors else []:
|
||||
parts=name.split(',');names.append(clean(parts[1]+' '+parts[0])if len(parts)==2 else name)
|
||||
if names!=review['authors']:raise ValueError('Reviewed author-index evidence differs')
|
||||
missing=review['missing_abstract_reason']
|
||||
if not isinstance(missing,str) or bool(missing.strip())==bool(item['abstract']):
|
||||
raise ValueError('Missing abstract requires explicit reason; never invent a summary')
|
||||
urls=[SPRING+'posters/author.html',SPRING+'posters/abstract.html',url]
|
||||
return {'source':'www_archive','external_id':'www3:posters:'+key,'url':url,'title':review['title'],
|
||||
'abstract':item['abstract'],'authors':review['authors'],'identifiers':{},'venue':'WWW','year':1995,
|
||||
'track':'poster','event_key':'www-1995-spring','status':'accepted','raw_decision':'listed in official posters proceedings',
|
||||
'metadata':{'entry_id':key,'source_evidence':sources.proof(urls),'abstract_heading_title_raw':item['title'],
|
||||
'author_byline_raw':item['author_byline_raw'],'author_index_raw':authors['authors']if authors else [],
|
||||
'author_index_titles_raw':sorted(authors['titles'])if authors else [],'abstract_href_raw':url,
|
||||
'author_order':review['author_source'],'reviewed_poster_identity':review,
|
||||
'missing_abstract_reason':missing or None},
|
||||
'tags':[{'namespace':'www_archive:proceedings_section','value':'posters'}]}
|
||||
|
||||
|
||||
def spring_rows(sources,track,reviews=None):
|
||||
base=SPRING+track+'/';author_url=base+'author.html';abstract_url=base+'abstract.html'
|
||||
authors=AuthorIndex(sources.read(author_url),track).entries
|
||||
listing=sections(sources.read(abstract_url));by_id={};held=[];session={}
|
||||
if track=='papers':
|
||||
session_url=base+'session.html'
|
||||
for href,title in anchors(sources.read(session_url)):
|
||||
own=identity(href,track)
|
||||
if own:
|
||||
key,url=own
|
||||
if key in session:raise ValueError('Duplicate main session entry ID')
|
||||
session[key]=url
|
||||
for item in listing:
|
||||
links=[identity(h,track)for h,t in anchors(item['heading'])if identity(h,track)]
|
||||
if len(links)!=1:
|
||||
held.append({'reason':'unverified_heading_identity','evidence':abstract_url,'candidate':item});continue
|
||||
key,url=links[0]
|
||||
if key in by_id:raise ValueError('Duplicate abstract entry ID')
|
||||
by_id[key]=(url,item)
|
||||
if not by_id:raise ValueError('No stable abstract entry IDs')
|
||||
if track=='papers' and (set(authors)!=set(by_id) or set(session)!=set(by_id)):
|
||||
raise ValueError('Main author/session/abstract entry ID sets disagree')
|
||||
if set(authors)-set(by_id):raise ValueError('Author index has entries outside the abstract listing')
|
||||
reviews=reviews or {}
|
||||
if set(reviews)-set(by_id):raise ValueError('Reviewed poster outside abstract listing')
|
||||
rows=[]
|
||||
for key,(url,item) in by_id.items():
|
||||
if key in reviews:
|
||||
if track!='posters':raise ValueError('Reviews only apply to poster entries')
|
||||
rows.append(reviewed_row(sources,key,url,item,authors.get(key),reviews[key]));continue
|
||||
if key not in authors:
|
||||
held.append({'reason':'abstract_entry_missing_linked_author_index','entry_id':key,'evidence':abstract_url,'candidate':item});continue
|
||||
alternatives=authors[key]['urls']
|
||||
if len(alternatives)!=1:raise ValueError('Ambiguous author-index paper URL')
|
||||
canonical=next(iter(alternatives))
|
||||
if track=='papers' and session[key]!=canonical:raise ValueError('Main author/session paper URLs disagree')
|
||||
if url!=canonical and (track!='papers' or not re.search(r'\s',url)):
|
||||
raise ValueError('Uncorroborated archive URL discrepancy')
|
||||
if not item['abstract']:
|
||||
held.append({'reason':'missing_abstract','entry_id':key,'evidence':abstract_url,'candidate':item});continue
|
||||
if item['title'].casefold() not in {t.casefold() for t in authors[key]['titles']}:
|
||||
held.append({'reason':'abstract_and_author_index_titles_disagree','entry_id':key,'evidence':abstract_url,'candidate':item,'author_index_titles':sorted(authors[key]['titles'])});continue
|
||||
names=[]
|
||||
for name in authors[key]['authors']:
|
||||
parts=name.split(',')
|
||||
names.append(clean(parts[1]+' '+parts[0])if len(parts)==2 else name)
|
||||
proof_urls=[author_url,abstract_url]+([session_url]if track=='papers'else[])
|
||||
rows.append({'source':'www_archive','external_id':'www3:'+track+':'+key,'url':canonical,
|
||||
'title':item['title'],'abstract':item['abstract'],'authors':names,'identifiers':{},
|
||||
'venue':'WWW','year':1995,'track':'main'if track=='papers'else'poster','event_key':'www-1995-spring',
|
||||
'status':'accepted','raw_decision':'listed in official '+track+' proceedings',
|
||||
'metadata':{'entry_id':key,'source_evidence':sources.proof(proof_urls),
|
||||
'author_index_raw':authors[key]['authors'],'author_index_titles_raw':sorted(authors[key]['titles']),'author_order':'archive author-index order, not original byline rank',
|
||||
'author_byline_raw':item['author_byline_raw'],'abstract_href_raw':url,
|
||||
'url_corroborated_by_author_and_session':url!=canonical},
|
||||
'tags':[{'namespace':'www_archive:proceedings_section','value':track}]})
|
||||
return rows,held,{'abstract_entries':len(by_id),'linked_author_entries':len(authors),'ready':len(rows),'held':len(held)}
|
||||
|
||||
|
||||
def early_review(sources):
|
||||
held=[];url=ROOT+'www1/PrelimProcs.html';html=sources.read(url)
|
||||
for ordinal,chunk in enumerate(re.split(r'<li\b[^>]*>',html,flags=re.I)[1:],1):
|
||||
title=re.search(r'<em>Title:</em>\s*<b>(.*?)</b>',chunk,re.I|re.S)
|
||||
if not title:raise ValueError('Unclassified first-conference entry')
|
||||
names=re.findall(r'<em>Author:</em>(.*?)(?=<br\b)',chunk,re.I|re.S)
|
||||
held.append({'reason':'formal_presentation_scope_and_count_need_review','event_key':'www-1994-spring',
|
||||
'ordinal':ordinal,'evidence':url,'candidate':{'title':text(title[1]),
|
||||
'authors_raw':[re.sub(r'\s*<[^>]+>','',text(n)).strip()for n in names],
|
||||
'keywords_raw':text(re.search(r'<em>Keywords:</em>(.*?)(?=<br\b)',chunk,re.I|re.S)[1]) if re.search(r'<em>Keywords:</em>(.*?)(?=<br\b)',chunk,re.I|re.S)else None},
|
||||
'source_evidence':sources.proof([url])})
|
||||
if not held:raise ValueError('First-conference presentation listing empty')
|
||||
category_urls={}
|
||||
for href,label in anchors(sources.read(FALL)):
|
||||
if href!='Author_Inst.html' and href.endswith('.html'):
|
||||
category_url=source_url(urljoin(FALL,href))
|
||||
if not category_url.startswith(ROOT+'www2/Proceedings/'):raise ValueError('Unexpected fall category')
|
||||
category_urls[category_url]=label
|
||||
if not category_urls:raise ValueError('Fall archive category listing empty')
|
||||
for url,label in sorted(category_urls.items()):
|
||||
html=sources.read(url)
|
||||
for ordinal,chunk in enumerate(re.split(r'<dt\b[^>]*>',html,flags=re.I)[1:],1):
|
||||
fields=re.split(r'<dd\b[^>]*>',chunk,maxsplit=1,flags=re.I)
|
||||
title=text(fields[0]);raw_byline=text(re.split(r'</dl\b',fields[1],maxsplit=1,flags=re.I)[0]) if len(fields)==2 else None
|
||||
if title:
|
||||
held.append({'reason':'mixed_program_category_not_verified_paper_acceptance','event_key':'www-1994-fall',
|
||||
'category':label,'ordinal':ordinal,'evidence':url,'candidate':{'title':title,'authors_raw':raw_byline},
|
||||
'source_evidence':sources.proof([FALL,url])})
|
||||
return held,{'first_conference_fields':sum(r['event_key']=='www-1994-spring'for r in held),'fall_categories':len(category_urls),
|
||||
'fall_program_entries':sum(r['event_key']=='www-1994-fall'for r in held)}
|
||||
|
||||
|
||||
def collect(source_cache,cache_sha256,out,*,reviewed=None,reviewed_sha256=None):
|
||||
out=Path(out)
|
||||
if out.exists():raise ValueError('Refusing to overwrite an existing normalized batch')
|
||||
sources=Sources(source_cache,cache_sha256);groups={};held=[];counts={}
|
||||
reviews,review_sha=reviewed_posters(sources,reviewed,reviewed_sha256,cache_sha256)
|
||||
for track in ('papers','posters'):
|
||||
rows,review,counts[track]=spring_rows(sources,track,reviews if track=='posters'else None);groups[track]=rows;held.extend(review)
|
||||
review,counts['earlier']=early_review(sources);held.extend(review)
|
||||
for item in held:
|
||||
if 'source_evidence' not in item:item['source_evidence']=sources.proof([item['evidence']])
|
||||
out.parent.mkdir(parents=True,exist_ok=True)
|
||||
with tempfile.TemporaryDirectory(prefix='.www-archive-',dir=out.parent)as tmp:
|
||||
stage=Path(tmp);queue=[]
|
||||
for track,rows in groups.items():
|
||||
if not rows:continue
|
||||
filename='www-1995-spring-'+('main'if track=='papers'else'poster')+'.jsonl';raw=''.join(json.dumps(r,ensure_ascii=False)+'\n'for r in rows).encode();(stage/filename).write_bytes(raw)
|
||||
manifest={'source':'www_archive','parser_version':2 if review_sha else 1,'venue':'WWW','year':1995,'track':rows[0]['track'],'event_key':'www-1995-spring',
|
||||
'list_url':SPRING+track+'/abstract.html','count':len(rows),'status':'partial','file_sha256':hashlib.sha256(raw).hexdigest(),
|
||||
'missing_abstract_count':sum(not bool((r['abstract']or '').strip())for r in rows),'source_listing_count':counts[track]['abstract_entries'],'held_entry_count':counts[track]['held'],'source_cache_sha256':cache_sha256,'scope':'Verified linked archive entries; held entries and other event tracks excluded, not complete event coverage.'}
|
||||
(stage/filename).with_suffix('.manifest.json').write_text(json.dumps(manifest,indent=2)+'\n');queue.append(str(out/filename))
|
||||
(stage/'review-candidates.jsonl').write_text(''.join(json.dumps(r,ensure_ascii=False)+'\n'for r in held))
|
||||
report={'status':'normalized_not_imported','source_cache_sha256':cache_sha256,'counts':counts,'ready':sum(len(r)for r in groups.values()),'held':len(held),
|
||||
'source_evidence':sources.proof(sources.used),'files':queue,'scope':'Early WWW archive only; no PDF fetching, no rejected/withdrawn inference, no database access. Event-aware importer required.'}
|
||||
if review_sha:report['reviewed_posters_sha256']=review_sha
|
||||
(stage/'report.json').write_text(json.dumps(report,ensure_ascii=False,indent=2)+'\n')
|
||||
(stage/'import-queue.json').write_text(json.dumps({'files':queue},indent=2)+'\n')
|
||||
stage.rename(out)
|
||||
return report
|
||||
|
||||
|
||||
def main(argv=None,*,prog=None):
|
||||
p=argparse.ArgumentParser(prog=prog);p.add_argument('--source-cache',required=True);p.add_argument('--source-cache-sha256');p.add_argument('--http-cache');p.add_argument('--out',required=True)
|
||||
p.add_argument('--reviewed-posters');p.add_argument('--reviewed-posters-sha256')
|
||||
args=p.parse_args(argv)
|
||||
if bool(args.http_cache)==bool(args.source_cache_sha256):p.error('Choose a fresh --http-cache download or an existing --source-cache-sha256 snapshot')
|
||||
sha=download_sources(args.http_cache,args.source_cache)if args.http_cache else args.source_cache_sha256
|
||||
if bool(args.reviewed_posters)!=bool(args.reviewed_posters_sha256):p.error('Reviewed poster file and SHA256 must be supplied together')
|
||||
print(json.dumps(collect(args.source_cache,sha,args.out,reviewed=args.reviewed_posters,reviewed_sha256=args.reviewed_posters_sha256),ensure_ascii=False),flush=True)
|
||||
|
||||
|
||||
if __name__=='__main__':main()
|
||||
@@ -0,0 +1,155 @@
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors.www_archive import (ROOT, SPRING, FALL, Sources, collect, decode,
|
||||
early_review, spring_rows)
|
||||
|
||||
|
||||
class ArchiveTests(unittest.TestCase):
|
||||
def setUp(self):
|
||||
t=tempfile.TemporaryDirectory();self.addCleanup(t.cleanup);self.root=Path(t.name);self.cache=self.root/'cache';self.cache.mkdir()
|
||||
self.pages={ROOT+'www1/PrelimProcs.html':'''<h1>Formal presentations</h1><ol><li><em>Keywords:</em> BUSINESS TRACK?<br><em>Title:</em><b> First contribution</b><br><em>Author:</em>Jane Doe <jane@example.org><br><li><em>Title:</em><b>Unlinked contribution</b><br><em>Author:</em>John Roe<br></ol>''',
|
||||
FALL:'<h1>Conference Tracks</h1><ol><li><a href="Agents.html">Agents</a><li><a href="Tutor.html">Tutorials</a></ol>',
|
||||
ROOT+'www2/Proceedings/Agents.html':'<h3>Panel</h3><dl><dt><a href="a.html">Linked talk</a><dd>Jane Doe<dt>Unlinked talk</a><dd>John Roe</dl>',
|
||||
ROOT+'www2/Proceedings/Tutor.html':'<h1>Tutorials</h1><dl><dt>Training session<dd>Teacher</dl>'}
|
||||
for track in ['papers','posters']:
|
||||
self.pages[SPRING+track+'/author.html']='<b>Doe, Jane</b><ul><li><a href="01/paper.html">Same contribution</a></li></ul><b>Roe, John</b><a href="01/paper.html">Same contribution</a>'
|
||||
self.pages[SPRING+track+'/abstract.html']='''<h1>Abstracts</h1><a href="#one">Same contribution</a><h3><a href="01/paper.html">Same contribution</a></h3><i>Author: Jane Doe, John Roe<br>Institute</i><p>Actual abstract with <i>inline emphasis</i> and a separator\u2028 preserved.</p><hr><h2>Another session</h2>'''
|
||||
self.pages[SPRING+'papers/session.html']='<a href="01/paper.html">Same contribution</a>'
|
||||
|
||||
def sources(self):
|
||||
rows=[]
|
||||
for i,(url,html) in enumerate(sorted(self.pages.items())):
|
||||
raw=html.encode()if isinstance(html,str)else html;name='source-'+str(i)+'.html';(self.cache/name).write_bytes(raw)
|
||||
rows.append(dict(url=url,status=200,file=name,bytes=len(raw),sha256=hashlib.sha256(raw).hexdigest()))
|
||||
p=self.cache/'manifest.json';p.write_text(json.dumps({'sources':rows}));sha=hashlib.sha256(p.read_bytes()).hexdigest()
|
||||
return Sources(self.cache,sha),sha
|
||||
|
||||
def test_offline_batch_separates_tracks_review_and_importable_rows(self):
|
||||
_,sha=self.sources();out=self.root/'batch';report=collect(self.cache,sha,out)
|
||||
self.assertEqual(report['ready'],2);self.assertEqual(report['held'],5)
|
||||
queue=json.loads((out/'import-queue.json').read_text())['files'];self.assertEqual(len(queue),2)
|
||||
for name in queue:
|
||||
p=Path(name);rows=[json.loads(l)for l in p.read_text().split('\n') if l];self.assertEqual(len(rows),1)
|
||||
row=rows[0];self.assertEqual(row['event_key'],'www-1995-spring');self.assertEqual(row['authors'],['Jane Doe','John Roe'])
|
||||
self.assertIn(row['track'],['main','poster']);self.assertIn('inline emphasis',row['abstract']);self.assertNotIn('Another session',row['abstract'])
|
||||
self.assertIn('\u2028',row['abstract']);manifest=json.loads(p.with_suffix('.manifest.json').read_text());self.assertEqual(manifest['file_sha256'],hashlib.sha256(p.read_bytes()).hexdigest());self.assertEqual(manifest['status'],'partial')
|
||||
held=[json.loads(l)for l in(out/'review-candidates.jsonl').read_text().split('\n') if l]
|
||||
self.assertTrue(all('status'not in r and 'source_evidence'in r for r in held))
|
||||
self.assertFalse(any('review-candidates'in p for p in queue))
|
||||
|
||||
def test_partial_manifest_preserves_full_listing_size_separately_from_ready_count(self):
|
||||
self.pages[SPRING+'posters/abstract.html']+='<h3><a href="02/other.html">Unlinked poster</a></h3><i>Author: Other Person</i><p>Actual abstract</p>'
|
||||
_,sha=self.sources();out=self.root/'batch';collect(self.cache,sha,out)
|
||||
manifest=json.loads((out/'www-1995-spring-poster.manifest.json').read_text())
|
||||
self.assertEqual((manifest['count'],manifest['source_listing_count'],manifest['held_entry_count']),(1,2,1))
|
||||
self.assertNotIn('coverage_previous_count',manifest) # Live parent must be independently preflighted.
|
||||
|
||||
def test_malformed_href_requires_exact_id_and_two_clean_index_anchors(self):
|
||||
self.pages[SPRING+'papers/abstract.html']=self.pages[SPRING+'papers/abstract.html'].replace('01/paper.html','01/ paper.html')
|
||||
sources,_=self.sources();rows,held,_=spring_rows(sources,'papers');self.assertEqual(held,[])
|
||||
self.assertEqual(rows[0]['url'],SPRING+'papers/01/paper.html');self.assertTrue(rows[0]['metadata']['url_corroborated_by_author_and_session'])
|
||||
self.assertIn(' ',rows[0]['metadata']['abstract_href_raw'])
|
||||
|
||||
def test_main_index_disagreement_fails_without_publishing_batch(self):
|
||||
self.pages[SPRING+'papers/session.html']='<a href="02/other.html">Other work</a>';_,sha=self.sources();out=self.root/'batch'
|
||||
with self.assertRaisesRegex(ValueError,'ID sets disagree'):collect(self.cache,sha,out)
|
||||
self.assertFalse(out.exists())
|
||||
|
||||
def test_same_entry_id_with_conflicting_clean_url_is_rejected(self):
|
||||
self.pages[SPRING+'papers/session.html']='<a href="01/other.html">Same contribution</a>';sources,_=self.sources()
|
||||
with self.assertRaisesRegex(ValueError,'URLs disagree'):spring_rows(sources,'papers')
|
||||
|
||||
def test_poster_without_linked_author_entry_is_held_even_with_abstract(self):
|
||||
self.pages[SPRING+'posters/author.html']='<b>Doe, Jane</b><a href="#">Same contribution</a>';sources,_=self.sources();rows,held,counts=spring_rows(sources,'posters')
|
||||
self.assertEqual(rows,[]);self.assertEqual(counts['abstract_entries'],1);self.assertEqual(held[0]['reason'],'abstract_entry_missing_linked_author_index')
|
||||
|
||||
def test_unlinked_and_panel_entries_never_become_acceptance_or_rejection(self):
|
||||
sources,_=self.sources();held,counts=early_review(sources);self.assertEqual(counts,{'first_conference_fields':2,'fall_categories':2,'fall_program_entries':3})
|
||||
self.assertTrue(any(r['candidate']['title']=='Unlinked talk'for r in held));self.assertTrue(all('status'not in r for r in held))
|
||||
self.assertEqual(held[0]['candidate']['authors_raw'],['Jane Doe'])
|
||||
|
||||
def test_title_disagreement_goes_to_review_with_source_claims(self):
|
||||
self.pages[SPRING+'papers/abstract.html']=self.pages[SPRING+'papers/abstract.html'].replace('Same contribution','Different contribution');sources,_=self.sources();rows,held,_=spring_rows(sources,'papers')
|
||||
self.assertEqual(rows,[]);self.assertEqual(held[0]['reason'],'abstract_and_author_index_titles_disagree')
|
||||
|
||||
def test_cache_tampering_and_manifest_hash_mismatch_fail_closed(self):
|
||||
_,sha=self.sources()
|
||||
with self.assertRaisesRegex(ValueError,'manifest checksum'):Sources(self.cache,'0'*64)
|
||||
p=next(self.cache.glob('source-*.html'));p.write_bytes(p.read_bytes()+b'x')
|
||||
with self.assertRaisesRegex(ValueError,'checksum or size'):Sources(self.cache,sha)
|
||||
|
||||
def test_cache_cannot_read_paths_outside_snapshot(self):
|
||||
_,sha=self.sources();p=self.cache/'manifest.json';d=json.loads(p.read_text());d['sources'][0]['file']='../outside.html';p.write_text(json.dumps(d))
|
||||
with self.assertRaisesRegex(ValueError,'plain files'):Sources(self.cache,hashlib.sha256(p.read_bytes()).hexdigest())
|
||||
|
||||
def test_keywords_only_is_missing_abstract_not_invented_summary(self):
|
||||
self.pages[SPRING+'papers/abstract.html']='<h3><a href="01/paper.html">Same contribution</a></h3><i>Author: Jane Doe</i><p>Keywords: networking, hypertext</p>';sources,_=self.sources();rows,held,_=spring_rows(sources,'papers')
|
||||
self.assertEqual(rows,[]);self.assertEqual(held[0]['reason'],'missing_abstract')
|
||||
|
||||
def test_old_encoding_and_duplicate_abstract_identity(self):
|
||||
self.assertEqual(decode(b'M\xfcller')[0],'Müller')
|
||||
self.pages[SPRING+'papers/abstract.html']*=2;sources,_=self.sources()
|
||||
with self.assertRaisesRegex(ValueError,'Duplicate abstract'):spring_rows(sources,'papers')
|
||||
|
||||
def test_existing_output_is_never_overwritten(self):
|
||||
_,sha=self.sources();out=self.root/'batch';out.mkdir();(out/'keep').write_text('original')
|
||||
with self.assertRaisesRegex(ValueError,'overwrite'):collect(self.cache,sha,out)
|
||||
self.assertEqual((out/'keep').read_text(),'original')
|
||||
|
||||
def review(self,*,authors=None,author_source='canonical_byline',missing='',page=None):
|
||||
url=SPRING+'posters/01/paper.html'
|
||||
self.pages[url]=page or '<h1>Canonical full title</h1><p>Jane Doe, John Roe</p><p>Keywords: web</p><h2>Abstract</h2><p>Body</p>'
|
||||
_,sha=self.sources();raw=self.pages[url].encode()if isinstance(self.pages[url],str)else self.pages[url]
|
||||
row=dict(entry_id='01',individual_url=url,individual_sha256=hashlib.sha256(raw).hexdigest(),
|
||||
title='Canonical full title',authors=authors or ['Jane Doe','John Roe'],author_source=author_source,
|
||||
reason='Reviewed exact canonical entry and its explicit authorship; retain original title variants',missing_abstract_reason=missing)
|
||||
p=self.root/'review.json';p.write_text(json.dumps({'format':1,'source_cache_sha256':sha,'records':[row]}));return sha,p,hashlib.sha256(p.read_bytes()).hexdigest()
|
||||
|
||||
def test_reviewed_variant_keeps_primary_title_and_all_old_title_claims(self):
|
||||
sha,p,h=self.review();out=self.root/'reviewed';r=collect(self.cache,sha,out,reviewed=p,reviewed_sha256=h)
|
||||
row=json.loads((out/'www-1995-spring-poster.jsonl').read_text());self.assertEqual(row['title'],'Canonical full title')
|
||||
self.assertEqual(row['metadata']['abstract_heading_title_raw'],'Same contribution');self.assertEqual(row['metadata']['author_index_titles_raw'],['Same contribution'])
|
||||
self.assertEqual(len(row['metadata']['source_evidence']),3);self.assertEqual(r['reviewed_posters_sha256'],h)
|
||||
self.assertEqual(row['external_id'],'www3:posters:01');self.assertEqual(row['status'],'accepted')
|
||||
|
||||
def test_canonical_byline_can_resolve_unlinked_author_index_without_guessing(self):
|
||||
self.pages[SPRING+'posters/author.html']='<b>Doe, Jane</b><a href="#">Broken index link</a>'
|
||||
sha,p,h=self.review();out=self.root/'reviewed';collect(self.cache,sha,out,reviewed=p,reviewed_sha256=h)
|
||||
row=json.loads((out/'www-1995-spring-poster.jsonl').read_text());self.assertEqual(row['authors'],['Jane Doe','John Roe'])
|
||||
self.assertEqual(row['metadata']['author_index_raw'],[]);self.assertEqual(row['metadata']['author_order'],'canonical_byline')
|
||||
|
||||
def test_reviewed_missing_abstract_is_explicit_partial_not_body_summary(self):
|
||||
self.pages[SPRING+'posters/abstract.html']='<h3><a href="01/paper.html">Same contribution</a></h3><i>Author: Jane Doe</i><p>Keywords: web</p>'
|
||||
sha,p,h=self.review(missing='Neither listing nor canonical page supplies an explicit abstract')
|
||||
out=self.root/'reviewed';collect(self.cache,sha,out,reviewed=p,reviewed_sha256=h)
|
||||
row=json.loads((out/'www-1995-spring-poster.jsonl').read_text());m=json.loads((out/'www-1995-spring-poster.manifest.json').read_text())
|
||||
self.assertIsNone(row['abstract']);self.assertEqual((m['missing_abstract_count'],m['status']),(1,'partial'))
|
||||
sha,p,h=self.review()
|
||||
with self.assertRaisesRegex(ValueError,'Missing abstract'):collect(self.cache,sha,self.root/'bad',reviewed=p,reviewed_sha256=h)
|
||||
self.assertFalse((self.root/'bad').exists())
|
||||
|
||||
def test_reviewed_names_must_be_in_byline_region_not_citations_or_contact_guess(self):
|
||||
sha,p,h=self.review(authors=['Unrelated Person'],page='<h1>Canonical full title</h1><p>Jane Doe</p><h2>Abstract</h2><p>Unrelated Person cited here</p>')
|
||||
with self.assertRaisesRegex(ValueError,'byline region'):collect(self.cache,sha,self.root/'bad',reviewed=p,reviewed_sha256=h)
|
||||
sha,p,h=self.review(author_source='author_index',authors=['Contact Person'])
|
||||
with self.assertRaisesRegex(ValueError,'author-index'):collect(self.cache,sha,self.root/'bad',reviewed=p,reviewed_sha256=h)
|
||||
|
||||
def test_review_hash_cache_binding_and_canonical_h1_are_all_required(self):
|
||||
sha,p,h=self.review()
|
||||
with self.assertRaisesRegex(ValueError,'checksum'):collect(self.cache,sha,self.root/'bad',reviewed=p,reviewed_sha256='0'*64)
|
||||
d=json.loads(p.read_text());d['source_cache_sha256']='0'*64;p.write_text(json.dumps(d));h=hashlib.sha256(p.read_bytes()).hexdigest()
|
||||
with self.assertRaisesRegex(ValueError,'binding'):collect(self.cache,sha,self.root/'bad',reviewed=p,reviewed_sha256=h)
|
||||
d['source_cache_sha256']=sha;d['records'][0]['title']='Wrong title';p.write_text(json.dumps(d));h=hashlib.sha256(p.read_bytes()).hexdigest()
|
||||
with self.assertRaisesRegex(ValueError,'canonical H1'):collect(self.cache,sha,self.root/'bad',reviewed=p,reviewed_sha256=h)
|
||||
|
||||
def test_unlisted_review_entry_and_changed_primary_digest_fail_closed(self):
|
||||
sha,p,h=self.review();d=json.loads(p.read_text());d['records'][0]['individual_sha256']='0'*64;p.write_text(json.dumps(d));h=hashlib.sha256(p.read_bytes()).hexdigest()
|
||||
with self.assertRaisesRegex(ValueError,'page checksum'):collect(self.cache,sha,self.root/'bad',reviewed=p,reviewed_sha256=h)
|
||||
self.pages[SPRING+'posters/abstract.html']=self.pages[SPRING+'posters/abstract.html'].replace('01/paper.html','02/other.html')
|
||||
self.pages[SPRING+'posters/author.html']=self.pages[SPRING+'posters/author.html'].replace('01/paper.html','02/other.html')
|
||||
sha,p,h=self.review()
|
||||
with self.assertRaisesRegex(ValueError,'outside abstract'):collect(self.cache,sha,self.root/'bad',reviewed=p,reviewed_sha256=h)
|
||||
Reference in New Issue
Block a user