Compare commits
4 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 codex-bot
|
7c6f4c9f1d | ||
 Zayden-Jung
|
32c7edd0a5 | ||
|
Zayden-Jung
|
658d799334 | ||
|
codex-bot
|
53fbe9c75c |
@@ -60,6 +60,8 @@ paper-atlas collect colm --cache /data/paper-index/raw/http-cache \
|
||||
--out /data/paper-index/collected
|
||||
```
|
||||
|
||||
早期主系列的Workshop名称按[ICML/IROS精确届次证据](docs/coverage/historical-primary-series-2026-11-09.md)识别，保留原名与范围证据；代码支持不代表已补齐生产数据。
|
||||
|
||||
`paper-atlas collect --help` 查看来源；`paper-atlas import --help` 查看导入方式。完整批次步骤见[使用指南](docs/usage.md)。
|
||||
|
||||
共享实例名为 `foundry-postgres`，数据位于 `foundry_data` 库的 `research` schema；其他项目可按权限复用同一组表。库名通过 libpq service 配置、schema 通过 search_path 或 `--pg-schema` 指定，不写死在查询中。PostgreSQL 凭据放在服务器权限为 `0600` 的 libpq service 文件中；命令行只使用服务名称。`paper-atlas maintain postgres --help` 提供迁移入口：先完整核验 21 张业务表，再发布目标 schema。SQLite FTS5 内部表由 PostgreSQL GIN 索引替代。切换后 SQLite 为只读备份；`import records`、`import arxiv` 和 `maintain backfill` 使用 `--pg-service foundry-research` 写入主库，整个写入会话只允许一个协调写入者，会议文件失败时整体回滚并保留失败批次记录。
|
||||
|
||||
@@ -190,3 +190,5 @@ 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89个初步候选来源年度；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。
|
||||
|
||||
@@ -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 +1,56 @@
|
||||
# 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**89个**匹配到初步候选论文集，另**46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。匹配只使用同family的四位卷key年份或卷标题唯一显式年份；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**。
|
||||
|
||||
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。
|
||||
@@ -0,0 +1,33 @@
|
||||
# ICML 与 IROS 早期主系列的来源范围
|
||||
|
||||
本轮修正采集阶段的届次识别，不修改任何现有生产投稿轨道或历史。正式主系列曾以Workshop命名，不等于附属workshop；也不能反过来把所有旧workshop升为主会。
|
||||
|
||||
## 已核实的精确范围
|
||||
|
||||
| 会议 | 论文集键 | 依据与行为 |
|
||||
| --- | --- | --- |
|
||||
| ICML | `conf/icml/1988`、`1989`、`1990`、`1991`、`1992` | [官方历史](https://icml.cc/Conferences/2008/past_icmls.shtml.html)将其列为第5–9届，年份与举办地对应固定目录中的完整标题。1989/1991/1992的Workshop名称不再导致主系列被默认排除；1988/1990保留main并增加来源范围证据 |
|
||||
| IROS | `conf/iros/1988`、`1989`、`1990` | [IEEE RAS官方历届目录](https://www.ieee-ras.org/conferences-workshops/financially-co-sponsored/iros/iros-past-and-future-venues/)列出三届与论文集链接，地点及日期对应固定目录标题；这些是IROS主系列 |
|
||||
|
||||
规则同时要求family、booktitle基础别名（ML或IROS）、空轨道后缀、完整精确论文集键、匹配的事件年份及固定完整标题。仍执行原有书目年份核查：与事件年不同且标题无明确事件年时拒绝推断。ML91原始标题没有四位年份，使用精确1991卷键、完整标题、逐篇书目年和官方第8届记录，不从两位标题代码猜世纪。
|
||||
|
||||
`1991w`/`1988w`等卷键、booktitle中的Workshops后缀、不同届次/地点/完整标题、未列入的年份均不会获得上述主系列豁免。AISTATS/COLT既有精确规则保留；真正的附属workshop仍受默认不采集workshop的边界约束。
|
||||
|
||||
## 原始字段、决定与后续导入
|
||||
|
||||
采集器仍保存原始proceedings标题（包括Workshop）、书目年、原始作者名、完整来源书目字段及稳定标识；新增 `track_scope_note` 与官方 `track_scope_evidence_url`。接受状态仍只源自该论文的inproceedings书目证据；不从历史目录生成占位论文或拒稿，也不重新导入已经存在的记录。
|
||||
|
||||
新规则的输出必须重新做原始来源/标题/作者/稳定标识与现有库冲突预检，再按增量导入。此前被隔离的ICML1988/1990记录不能仅凭代码规则而直接解除全部冲突。当前正在运行的历史批次使用原固定版本和文件，不能在运行中替换其源码或输入。
|
||||
|
||||
## 验证与证据
|
||||
|
||||
新增回归覆盖：ICML三届Workshop名称、IROS最初三届、ICML原Conference名称的两届、错误卷键/后缀/标题/未知年份，以及归一化记录经过原生文件导入后保留轨道证据。构建与测试仅在已授权的ces-control远程runner执行，本机仅做语法和文本/JSON一致性检查；结果以相应commit的CI回执为准。
|
||||
|
||||
官方HTML在工作证据目录 `paper-index/historical-primary-series-evidence-v1/`，附响应状态、字节数、时间与SHA256；仅取元数据网页，没有下载论文全文。
|
||||
|
||||
| 来源 | UTC采样时间 | HTTP | 字节数 | SHA256 |
|
||||
| --- | --- | ---: | ---: | --- |
|
||||
| [icml-history](https://icml.cc/Conferences/2008/past_icmls.shtml.html) | 2026-11-08T18:36:43.043135+00:00 | 200 | 11993 | `80cce886fe985551339a52b13c4077acf827e8fcc01555f854dc24077bdebdf0` |
|
||||
| [iros-history](https://www.ieee-ras.org/conferences-workshops/financially-co-sponsored/iros/iros-past-and-future-venues/) | 2026-11-08T18:36:45.687171+00:00 | 200 | 466059 | `fdb4594621e68567e1099f5c88aae53de835b7b8146025148c3b1968df990697` |
|
||||
|
||||
本次不关闭历史年度缺口，也不替代全部导入后的全库去重、来源/年度/track覆盖、摘要和实际查询验收。
|
||||
File diff suppressed because it is too large
Load Diff
@@ -54,7 +54,34 @@ HISTORICAL_WORKSHOP_TITLES = {
|
||||
}
|
||||
|
||||
|
||||
# Exact pinned volume titles corroborated by official series histories. The
|
||||
# original title (including Workshop) remains in source metadata. In particular
|
||||
# ML91 has no four-digit year in its title; its exact key/title and bibliographic
|
||||
# year are checked independently, rather than guessing a title year.
|
||||
HISTORICAL_PRIMARY_EVIDENCE = {
|
||||
'icml': ('ML', 'https://icml.cc/Conferences/2008/past_icmls.shtml.html'),
|
||||
'iros': ('IROS', 'https://www.ieee-ras.org/conferences-workshops/financially-co-sponsored/iros/iros-past-and-future-venues/'),
|
||||
}
|
||||
HISTORICAL_PRIMARY_TITLES = {
|
||||
('icml', 1988): 'Machine Learning, Proceedings of the Fifth International Conference on Machine Learning, Ann Arbor, Michigan, USA, June 12-14, 1988',
|
||||
('icml', 1989): 'Proceedings of the Sixth International Workshop on Machine Learning (ML 1989), Cornell University, Ithaca, New York, USA, June 26-27, 1989',
|
||||
('icml', 1990): 'Machine Learning, Proceedings of the Seventh International Conference on Machine Learning, Austin, Texas, USA, June 21-23, 1990',
|
||||
('icml', 1991): 'Proceedings of the Eighth International Workshop (ML91), Northwestern University, Evanston, Illinois, USA',
|
||||
('icml', 1992): 'Proceedings of the Ninth International Workshop on Machine Learning (ML 1992), Aberdeen, Scotland, UK, July 1-3, 1992',
|
||||
('iros', 1988): "IEEE International Workshop on Intelligent Robots and Systems '88, Proceedings. IROS 1988, Tokyo, Japan, October 31 - November 2, 1988",
|
||||
('iros', 1989): "IEEE International Workshop on Intelligent Robots and Systems '89, Proceedings. IROS 1989, September 4-6, 1989, Tsukuba, Japan",
|
||||
('iros', 1990): "IEEE International Workshop on Intelligent Robots and Systems '90, Towards a New Frontier of Applications, Proceedings. IROS 1990, July 3-6, 1990, Ibaraki, Japan",
|
||||
}
|
||||
|
||||
|
||||
def historical_track(family, base, suffix, volume_key, year, title):
|
||||
primary = HISTORICAL_PRIMARY_EVIDENCE.get(family)
|
||||
if (primary and not suffix and base.casefold() == primary[0].casefold()
|
||||
and volume_key == f'conf/{family}/{year}'
|
||||
and title == HISTORICAL_PRIMARY_TITLES.get((family, year))):
|
||||
return ('main',
|
||||
'Historical primary series; exact proceedings key, complete title and bibliographic/event year corroborated by official series history. Workshop in this original title is not an affiliated track.',
|
||||
primary[1])
|
||||
if suffix or base.casefold() != family or volume_key != f'conf/{family}/{year}':
|
||||
return None
|
||||
prefix = HISTORICAL_WORKSHOP_TITLES.get((family, year))
|
||||
|
||||
@@ -0,0 +1,115 @@
|
||||
"""Regression coverage for primary series once named Workshop, with strict scope boundaries."""
|
||||
from contextlib import closing
|
||||
import hashlib
|
||||
import json
|
||||
from pathlib import Path
|
||||
import sqlite3
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
from paper_atlas.collectors.dblp_records import normalize_row
|
||||
from paper_atlas.collectors.dblp_scope import scope
|
||||
from paper_atlas.ingestion.records import ingest_file
|
||||
|
||||
ICML_HISTORY = 'https://icml.cc/Conferences/2008/past_icmls.shtml.html'
|
||||
IROS_HISTORY = 'https://www.ieee-ras.org/conferences-workshops/financially-co-sponsored/iros/iros-past-and-future-venues/'
|
||||
|
||||
|
||||
class HistoricalPrimarySeriesTests(unittest.TestCase):
|
||||
def example(self, family, year, title, book=None, key=None):
|
||||
key = key or f'conf/{family}/{year}'
|
||||
book = book or ('ML' if family == 'icml' else 'IROS')
|
||||
row = {'record_type':'inproceedings', 'key':f'conf/{family}/Paper{year}', 'publtype':None,
|
||||
'fields':{'title':['An independently identified historical research paper'],
|
||||
'author':['Jane Doe'], 'booktitle':[book], 'year':[str(year)],
|
||||
'crossref':[key], 'ee':[f'https://doi.org/10.1234/{family}.{year}']}}
|
||||
volume = {'record_type':'proceedings', 'key':key,
|
||||
'fields':{'title':[title], 'year':[str(year)]}}
|
||||
return row, volume
|
||||
|
||||
def test_icml_workshop_primary_editions_are_not_silently_filtered(self):
|
||||
examples = {
|
||||
1989:'Proceedings of the Sixth International Workshop on Machine Learning (ML 1989), Cornell University, Ithaca, New York, USA, June 26-27, 1989',
|
||||
1991:'Proceedings of the Eighth International Workshop (ML91), Northwestern University, Evanston, Illinois, USA',
|
||||
1992:'Proceedings of the Ninth International Workshop on Machine Learning (ML 1992), Aberdeen, Scotland, UK, July 1-3, 1992',
|
||||
}
|
||||
for year, title in examples.items():
|
||||
with self.subTest(year=year):
|
||||
row, volume = self.example('icml', year, title)
|
||||
record, reason = normalize_row(row, {volume['key']:volume}, {'ICML'})
|
||||
self.assertIsNone(reason)
|
||||
self.assertEqual((record['venue'],record['year'],record['track'],record['status']), ('ICML',year,'main','accepted'))
|
||||
self.assertEqual(record['metadata']['proceedings_title'], title)
|
||||
self.assertEqual(record['metadata']['track_scope_evidence_url'], ICML_HISTORY)
|
||||
self.assertEqual(record['metadata']['bibliographic_year'], year)
|
||||
|
||||
def test_iros_first_three_editions_are_primary_series(self):
|
||||
examples = {
|
||||
1988:"IEEE International Workshop on Intelligent Robots and Systems '88, Proceedings. IROS 1988, Tokyo, Japan, October 31 - November 2, 1988",
|
||||
1989:"IEEE International Workshop on Intelligent Robots and Systems '89, Proceedings. IROS 1989, September 4-6, 1989, Tsukuba, Japan",
|
||||
1990:"IEEE International Workshop on Intelligent Robots and Systems '90, Towards a New Frontier of Applications, Proceedings. IROS 1990, July 3-6, 1990, Ibaraki, Japan",
|
||||
}
|
||||
for year, title in examples.items():
|
||||
with self.subTest(year=year):
|
||||
row, volume = self.example('iros', year, title)
|
||||
record, reason = normalize_row(row, {volume['key']:volume}, {'IROS'})
|
||||
self.assertIsNone(reason)
|
||||
self.assertEqual((record['venue'],record['year'],record['track']), ('IROS',year,'main'))
|
||||
self.assertEqual(record['metadata']['proceedings_title'], title)
|
||||
self.assertEqual(record['metadata']['track_scope_evidence_url'], IROS_HISTORY)
|
||||
|
||||
def test_main_named_icml_predecessors_also_carry_primary_scope_provenance(self):
|
||||
examples = {
|
||||
1988:'Machine Learning, Proceedings of the Fifth International Conference on Machine Learning, Ann Arbor, Michigan, USA, June 12-14, 1988',
|
||||
1990:'Machine Learning, Proceedings of the Seventh International Conference on Machine Learning, Austin, Texas, USA, June 21-23, 1990',
|
||||
}
|
||||
for year, title in examples.items():
|
||||
row, volume = self.example('icml', year, title)
|
||||
edition, reason = scope(row, volume)
|
||||
self.assertIsNone(reason)
|
||||
self.assertEqual(edition['track'], 'main')
|
||||
self.assertEqual(edition['track_scope_evidence_url'], ICML_HISTORY)
|
||||
|
||||
def test_wrong_keys_titles_suffixes_and_unknown_years_keep_workshop_boundary(self):
|
||||
title = 'Proceedings of the Eighth International Workshop (ML91), Northwestern University, Evanston, Illinois, USA'
|
||||
for year, changed, book, key in [
|
||||
(1991,title,'ML','conf/icml/1991w'),
|
||||
(1991,title,'ML (Workshops)','conf/icml/1991'),
|
||||
(1991,title.replace('Eighth','Ninth'),'ML','conf/icml/1991'),
|
||||
(1991,title + ', Affiliated Workshop','ML','conf/icml/1991'),
|
||||
(1987,'Machine Learning Workshop 1987, Irvine','ML','conf/icml/1987'),
|
||||
]:
|
||||
with self.subTest(year=year, book=book, key=key, title=changed):
|
||||
row, volume = self.example('icml',year,changed,book,key)
|
||||
record, reason = normalize_row(row,{volume['key']:volume},{'ICML'})
|
||||
self.assertIsNone(record)
|
||||
self.assertEqual(reason,'separate_workshop')
|
||||
self.assertNotIn('track_scope_evidence_url',scope(row,volume)[0])
|
||||
title = "IEEE International Workshop on Intelligent Robots and Systems '88, Proceedings. IROS 1988, Tokyo, Japan, October 31 - November 2, 1988"
|
||||
for changed, book, key in [
|
||||
(title,'IROS','conf/iros/1988w'),
|
||||
(title,'IROS (Workshops)','conf/iros/1988'),
|
||||
(title.replace('Tokyo','Another city'),'IROS','conf/iros/1988'),
|
||||
]:
|
||||
row, volume = self.example('iros',1988,changed,book,key)
|
||||
self.assertEqual(normalize_row(row,{volume['key']:volume},{'IROS'})[1],'separate_workshop')
|
||||
|
||||
def test_primary_scope_proof_survives_native_file_ingestion(self):
|
||||
title = 'Proceedings of the Eighth International Workshop (ML91), Northwestern University, Evanston, Illinois, USA'
|
||||
row, volume = self.example('icml',1991,title)
|
||||
record, reason = normalize_row(row,{volume['key']:volume},{'ICML'})
|
||||
self.assertIsNone(reason)
|
||||
with tempfile.TemporaryDirectory() as temporary:
|
||||
root=Path(temporary);path=root/'records.jsonl';path.write_text(json.dumps(record)+'\n')
|
||||
path.with_suffix('.manifest.json').write_text(json.dumps({'source':'dblp','count':1,'list_url':ICML_HISTORY,'file_sha256':hashlib.sha256(path.read_bytes()).hexdigest()}))
|
||||
ingest_file(root/'test.sqlite',path)
|
||||
with closing(sqlite3.connect(root/'test.sqlite')) as connection:
|
||||
self.assertEqual(connection.execute('SELECT track FROM editions').fetchone()[0],'main')
|
||||
self.assertEqual(connection.execute('SELECT status FROM decisions').fetchone()[0],'accepted')
|
||||
metadata=json.loads(connection.execute('SELECT metadata_json FROM source_records').fetchone()[0])
|
||||
self.assertEqual(metadata['proceedings_title'],title)
|
||||
self.assertEqual(metadata['track_scope_evidence_url'],ICML_HISTORY)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
Reference in New Issue
Block a user