diff --git a/README.md b/README.md index 603aca2..ce7b7f9 100644 --- a/README.md +++ b/README.md @@ -6,6 +6,8 @@ Paper Atlas 将 arXiv、AI 会议论文集及公开投稿决定整理到可追 项目仍在建设中。候选范围包含 43 个会议（含 ACM MM、MLSys），尚未完成全部历史数据和最终去重复核。实际进度以数据库、来源清单和覆盖报告为准，而不是仓库文件数量。 +当前主动补漏从 **2020 年**起；2000 年起已发现的名单、缺口与待办保存在[补漏恢复清单](docs/coverage/backfill-handoff-2026-11-10.md)，下次从这里接续。已有旧数据保留，范围排除不算补齐。 + 历史 ICLR 2014–2016 官方录用页由 `collect iclr-archive` 适配，保留主会/workshop及重复展示证据；运行和身份核验边界见 [历史档案说明](docs/coverage/iclr-archive-2014-2016.md)。 ## 项目结构 diff --git a/docs/coverage/README.md b/docs/coverage/README.md index b8652a3..ce5bbc6 100644 --- a/docs/coverage/README.md +++ b/docs/coverage/README.md @@ -1,5 +1,7 @@ # 会议覆盖与公开决定核查 +**当前工作范围：2020 年起主动补漏。** 2000 年起已发现资料保留，恢复工作从 [补漏范围与恢复清单（2026-11-10）](backfill-handoff-2026-11-10.md) 开始；下文旧日期快照不改写，较早年份排除不算补齐。 + 这是 2026-11-08 的首份核查基线，**完整逐年政策普查和最终去重仍未完成**。收录 43 个目标，不能把“有记录”当作“完整覆盖”。结构化清单见 [inventory-2026-11-08.json](inventory-2026-11-08.json)。清单中的 `policy_checks` 均限定所列年份和轨道；空数组表示尚未核实，绝不表示没有公开拒稿。 ## 快照与复核 diff --git a/docs/coverage/backfill-handoff-2026-11-10.json b/docs/coverage/backfill-handoff-2026-11-10.json new file mode 100644 index 0000000..ccacde9 --- /dev/null +++ b/docs/coverage/backfill-handoff-2026-11-10.json @@ -0,0 +1,1519 @@ +{ + "version": 1, + "recorded_at": "2026-11-10", + "user_instruction": "后续补漏从2020年起；2000年起已发现名单、缺口、记录留在项目中，供下次恢复。", + "active_backfill_from_year": 2020, + "preserve_discovered_from_year": 2000, + "delete_existing_older_data": false, + "scope_exclusions_are_completed": false, + "snapshot_at": "2026-11-09 16:26:41.688509+00:00", + "snapshot_scope": "At least one observed submission per target venue-year; not complete papers/tracks/abstracts/public decisions. Missing publication may be not yet available.", + "source_summary_sha256": "336701d09575f252e189451384a013498fe09ec106a32f01c200ecd26fe056e2", + "source_raw_sha256": "647a35a1ba4d9e91d54561978f0fa354f5467e98b4e5180bfa90049c66230cd6", + "legacy_comparison": { + "target_slots": 1266, + "observed_slots": 1208, + "historical_gaps": 43, + "historical_gaps_before_2000": 41, + "deferred_2000_2019_year_gaps": [ + { + "venue": "WWW", + "year": 2000 + }, + { + "venue": "ICAPS", + "year": 2001 + } + ], + "nonarchival_exception": { + "venue": "MLSys", + "year": 2018, + "note": "SysML first edition nonarchival; do not manufacture a proceedings gap or accepted publication." + }, + "current_2026_gaps": 14, + "historical_baseline_135_resolved_by_data": 92 + }, + "venues": [ + { + "venue": "NeurIPS", + "official_year_census_file": "neurips-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "ICML", + "official_year_census_file": "icml-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "ICLR", + "official_year_census_file": "iclr-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "COLM", + "official_year_census_file": "colm-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "COLT", + "official_year_census_file": "colt-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "AISTATS", + "official_year_census_file": "aistats-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2001, + 2003, + 2005, + 2007, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "UAI", + "official_year_census_file": "uai-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "CLeaR", + "official_year_census_file": "clear-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "ACL", + "official_year_census_file": "acl-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "EMNLP", + "official_year_census_file": "emnlp-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "NAACL", + "official_year_census_file": "naacl-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2003, + 2004, + 2006, + 2007, + 2009, + 2010, + 2012, + 2013, + 2015, + 2016, + 2018, + 2019, + 2021, + 2022, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "EACL", + "official_year_census_file": "eacl-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2003, + 2006, + 2009, + 2012, + 2014, + 2017, + 2021, + 2023, + 2024, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "COLING", + "official_year_census_file": "coling-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2002, + 2004, + 2006, + 2008, + 2010, + 2012, + 2014, + 2016, + 2018, + 2020, + 2022, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "CoNLL", + "official_year_census_file": "conll-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "CVPR", + "official_year_census_file": "cvpr-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "ICCV", + "official_year_census_file": "iccv-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2001, + 2003, + 2005, + 2007, + 2009, + 2011, + 2013, + 2015, + 2017, + 2019, + 2021, + 2023, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "ECCV", + "official_year_census_file": "eccv-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2002, + 2004, + 2006, + 2008, + 2010, + 2012, + 2014, + 2016, + 2018, + 2020, + 2022, + 2024 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "AAAI", + "official_year_census_file": "aaai-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2002, + 2004, + 2005, + 2006, + 2007, + 2008, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "IJCAI", + "official_year_census_file": "ijcai-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2001, + 2003, + 2005, + 2007, + 2009, + 2011, + 2013, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "ECAI", + "official_year_census_file": "ecai-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2002, + 2004, + 2006, + 2008, + 2010, + 2012, + 2014, + 2016, + 2018, + 2020, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "KDD", + "official_year_census_file": "kdd-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "SIGIR", + "official_year_census_file": "sigir-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "WWW", + "official_year_census_file": "www-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [ + 2000 + ], + "missing_target_years_2020_2026": [] + }, + { + "venue": "WSDM", + "official_year_census_file": "wsdm-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "RecSys", + "official_year_census_file": "recsys-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "CIKM", + "official_year_census_file": "cikm-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "ICDM", + "official_year_census_file": "icdm-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "SDM", + "official_year_census_file": "sdm-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "ECML-PKDD", + "official_year_census_file": "ecml-pkdd-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "ICRA", + "official_year_census_file": "icra-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "IROS", + "official_year_census_file": "iros-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "RSS", + "official_year_census_file": "rss-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "CoRL", + "official_year_census_file": "corl-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "ICAPS", + "official_year_census_file": "icaps-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [ + 2001 + ], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "KR", + "official_year_census_file": "kr-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2002, + 2004, + 2006, + 2008, + 2010, + 2012, + 2014, + 2016, + 2018, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "AAMAS", + "official_year_census_file": "aamas-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "ICASSP", + "official_year_census_file": "icassp-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "INTERSPEECH", + "official_year_census_file": "interspeech-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "ISMIR", + "official_year_census_file": "ismir-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + }, + { + "venue": "MICCAI", + "official_year_census_file": "miccai-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "FAccT", + "official_year_census_file": "facct-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [] + }, + { + "venue": "MLSys", + "official_year_census_file": "mlsys-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025, + 2026 + ], + "missing_target_years_2000_2019": [ + 2018 + ], + "missing_target_years_2020_2026": [] + }, + { + "venue": "MM", + "official_year_census_file": "mm-editions-2026-11-08.json", + "observed_years_2000_2026": [ + 2000, + 2001, + 2002, + 2003, + 2004, + 2005, + 2006, + 2007, + 2008, + 2009, + 2010, + 2011, + 2012, + 2013, + 2014, + 2015, + 2016, + 2017, + 2018, + 2019, + 2020, + 2021, + 2022, + 2023, + 2024, + 2025 + ], + "missing_target_years_2000_2019": [], + "missing_target_years_2020_2026": [ + 2026 + ] + } + ], + "recent_pending": [ + { + "id": "aamas2026", + "state": "frozen_primary_inventory_not_imported", + "official_contents_url": "https://www.ifaamas.org/Proceedings/aamas2026/forms/contents.htm", + "server_directory": "/data/paper-index/collected/aamas2026-primary-evidence-v1", + "checksums_sha256": "18431ba5f9ef3578d7cd32cb290833b4b3a1615cf62f1d3362065b763446bc6b", + "official_entries": 643, + "excluded_keynotes": 3, + "explicit_retracted": 1, + "section_counts": { + "Keynote Talks": 3, + "Research Paper Track": 338, + "Extended Abstracts": 185, + "AAAI Track": 19, + "Blue Sky Ideas Track": 17, + "Doctoral Consortium": 34, + "Demonstration Track": 44, + "JAAMAS Track": 3 + }, + "held_title_differences": 8, + "next": "Formal collector and remote CI, then fresh PostgreSQL identity review; raw643 not all accepted." + }, + { + "id": "cvpr2026-findings", + "state": "collected_941_abstracts_verified_not_imported", + "server_report": "/data/paper-index/collected/cvf-2026-verified/recovery-audit.json", + "next": "Recheck source/track manifests and current identities; incremental import only after preflight.", + "report_sha256": "8ba863ca70cf67d06068b50c5165d1b1311abfbd53da921510b4baadbbb7be34" + }, + { + "id": "aamas2025", + "state": "240_of_476_source_entries_accepted_236_held", + "consumed_queues": [ + 225, + 15 + ], + "last_acceptance_report": "/data/paper-index/collected/aamas2025-import15-v1/postgresql-postcheck-v1.json", + "last_acceptance_sha256": "4ab474e510965da09403729e892726c7072341f3df634114c83b28d1838742d0", + "next": "Review236held, including distinguish competition years and journal presentations; do not replay consumed225/15." + }, + { + "id": "rss2025", + "state": "162_of_163_accepted_one_identity_case_held", + "held_external_id": "2025/p117", + "evidence_state_key": "rss2025_held7_primary_evidence_v1", + "next": "Resolve spinal/RMCC publication relation; do not replay accepted6/88/54/14 queues." + }, + { + "id": "public-negative-first-batch", + "state": "1625_rows_accepted_not_a_full_public_negative_census", + "report": "/data/paper-index/collected/public-negative-postgresql-import-postcheck-v1.json", + "status_counts": { + "rejected": 1624, + "withdrawn": 1 + }, + "next": "Do not replay; continue per-year public-source availability checks and source overlap audits." + } + ], + "deferred_identity_work": [ + { + "id": "aamas2012", + "state": "319_of_334_accepted_15_held", + "report": "/data/paper-index/collected/aamas2012-import-v1/postgresql-postcheck-v1.json", + "report_sha256": "149d8f748eaad6f69feb69eda451a2341e4cd1288aa7d03635ae2ef224a032b3", + "next": "Deferred by2020cutoff. Preserve15held; never replay319accepted." + }, + { + "id": "uai2008", + "state": "original_DBLP_identity_conflicts_unresolved_no_corrections_applied", + "official_programme": "https://www.auai.org/uai2008/programme.shtml", + "archive_report": "/data/paper-index/collected/historical-dblp-missing-years-v1/uai2008-page-archive-evidence-v2.json", + "archive_sha256": "39d3c5bf38521ca607f8a3145768f7ad7326d05b4351e3468be4a2d930941402", + "candidates": [ + { + "dblp": "conf/uai/CaiK08", + "pages": "62-69", + "arxiv": "1206.3239", + "official_title": "On Identifying Total Effects in the Presence of Latent Variables and Selection bias", + "correction": "none;correctprimarypublication" + }, + { + "dblp": "conf/uai/KurokiC08", + "pages": "333-340", + "arxiv": "1206.3267", + "official_title": "The Evaluation of Causal Effects in Studies with an Unobserved Exposure/Outcome Variable: Bounds and Identification", + "correction": "NOTAPPROVED:primaryprogramme/archiveproveadifferentpaperatthesereportedpages,butrawDBLPkeyidentity/title/author/page/publisherlinkrequirechecking.Donotrewritetitle/authorsbasedonpagesalone." + }, + { + "dblp": "conf/uai/GanchevGBT08a", + "pages": "204-211", + "arxiv": "1206.3256", + "official_title": "Multi-View Learning over Structured and Non-Identical Outputs", + "correction": "none;correctprimarypublication" + }, + { + "dblp": "conf/uai/GanchevGBT08", + "pages": "88-96", + "arxiv": "1206.3242", + "official_title": "Multi-View Learning in the Presence of View Disagreement", + "official_authors": [ + "C. Mario Christoudias", + "Raquel Urtasun", + "Trevor Darrell" + ], + "correction": "NOTAPPROVED:primaryprogramme/archiveproveadifferentpaperatthesereportedpages,butrawDBLPkeyidentity/title/author/page/publisherlinkrequirechecking.Donotrewritetitle/authorsbasedonpagesalone." + } + ], + "next": "Do not rewrite title/authors or merge works solely from year/page match; raw DBLP identity field evidence required." + } + ], + "public_negative_policy_research": { + "status": "Primaryresearchprogress, notcomplete43venuepolicycensus", + "AISTATS2026": { + "urls": [ + "https://virtual.aistats.org/Conferences/2026/SubmissionFAQ", + "https://virtual.aistats.org/Conferences/2026/CallForPapers" + ], + "finding": "FAQ6 counts withdrawals AFTERreviews as rejected FORSTATISTICS; preservewithdrawn/rejecteddecisionsemantics separately, do notinferreject fromaggregates. AcceptedpaperPDFpublicationdescribed; no explicitpostdecisionrejectedpublicpolicyincheckedpages." + }, + "CoRL2026": { + "url": "https://2026.corl.org/contributions/instruction-for-authors", + "finding": "Explicitacceptedpapers+reviews publicdeanonymized afterdecisions; checkedtextdoesnotestablishrejectedavailability. Do not extrapolate2021removalpolicyto2026." + }, + "COLM2026": { + "urls": [ + "https://github.com/COLM-org/colm-org.github.io/blob/main/cfp.md", + "https://colm.cc/Conferences/2026/AuthorGuide", + "https://colm.eventhosts.cc/Conferences/2026/CallForPapers" + ], + "finding": "Verifiedyearqualified2026CFPfixedGitHubcommit explicitlyRejected/Withdrawnmetadata notpublished; liveAuthorGuidestale2024references do notoverridepinned2026CFP. Notextrapolatedtoothereditions.", + "pinned_commit": "f1718e86fd16ed9b10b4e010c9098c1b6223c2a8", + "pinned_url": "https://raw.githubusercontent.com/COLM-org/colm-org.github.io/f1718e86fd16ed9b10b4e010c9098c1b6223c2a8/cfp.md", + "sha256": "f2d93319226aebc28bfe163cc1e634adca0e7679f07bd65634844c25bf3a7399" + }, + "CLeaR2026": { + "url": "https://www.cclear.cc/2026/CallforPapers", + "finding": "SearchindexedCFP saysnoPUBLICdiscussionsduringreview. DirectwebopenJSshell only, cannotinferpostdecisionrejectedpolicy; rendered/staticprimarycontentneedsinspection.", + "browser_attempt": "CUAcreateTab andgetState both30sec transporttimeouts; completedCUApart asunavailable, notwebsitepolicyfailure.", + "static_primary": { + "url": "https://www.cclear.cc/static/js/main.901abbee.chunk.js", + "bytes": 483927, + "sha256": "d5b9a0cda61581da679b1de7180da74dcc4d70625c984a401b10820083719a76", + "finding": "DownloadedviaURLdeclaredbyofficialHTML; read-onlytextanalysis,noJSexecution. Bundlecontains6sameOpenReviewreviewperiodprivacyparagraphs and2026dataset-tracktext. No verifiedexplicitpostdecisionRejectpublicationpolicyyet; maintainunknown/notnopublicReject." + } + }, + "RSS2026": { + "url": "https://roboticsconference.org/2026/information/cfp/", + "finding": "Year-qualifiedofficialCFP statespaperspubliconlyafteracceptance andreviewsnotpublic. UnqualifiedrootURL now2027; do notapplycurrentrootto2026." + }, + "COLT2026": { + "url": "https://learningtheory.org/colt2026/cfp.html", + "finding": "CMTsubmission; acceptedpapersPMLRmayoptforonepageextendedabstract. NoexplicitpostdecisionRejectedpublicpolicyincheckedCFP; missingabstracttextnotonlycompletenessissue." + }, + "MM2026": { + "urls": [ + "https://2026.acmmm.org/site/author-instructions.html", + "https://2026.acmmm.org/site/cfp-guidelines.html", + "https://2026.acmmm.org/site/review-process-guidelines.html" + ], + "finding": "OpenReviewandmultipleexplicittracks+deskcriteria, butcheckedpagesdoNOTestablishpostdecisionpublicRejectedpolicy. Platformuse≠publicReject." + }, + "KDD2026": { + "url": "https://kdd2026.kdd.org/research-track-call-for-papers/", + "finding": "ResearchtrackCFPpublishesacceptedpapers+reviews. DoesnotestablishRejectedpublicpolicy. Resubmit isexplicitseparatedecision fromReject andWithdrawn across2cycles; future ingestionmustpreserverawdecision/cycle identity, notcollapseResubmittoReject. Notyetaddedtocommittedbaseline15venues20checks." + }, + "ICAPS2024": { + "url": "https://icaps24.icaps-conference.org/calls/main_track/", + "finding": "FAQonlyacceptedreviews+finalrebuttalpublic; committee discussionsprivate. DoesnotbyitselfestablishallRejectedmetadataprivate. Thisyearsinglemaintrack;formerApplications/Learning/RoboticsetcareoptionalprimarykeywordsNOTseparatetracks. Technical/positionandlong/shortindependentpaperattributes." + }, + "ICCV2025": { + "url": "https://iccv.thecvf.com/Conferences/2025/AuthorGuidelines", + "finding": "Underreviewsubmissionsonlyassignedcommittee; reviewsandresponsesneverpublic. DoNOTinferallpostdecisionRejectedmetadataprivate. PageTOCcontainsstaleCVPR2026heading; actualbodyICCV2025policyexplicit." + }, + "TMLR_current20261108": { + "url": "https://www.jmlr.org/tmlr/faq.html", + "finding": "Additionalnonconferencevenuealreadyinregistry:accepted/rejected/withdrawn/retractedallpublic; deskrejectedneverpublic. Authorshiddenonnotyetacceptedpapers; donotinferanonymousidentities. Continuousjournal; eventcertification/journal-to-conferencepresentationnotanotherindependentreviewacceptance." + } + }, + "public_negative_recovery_notes": { + "uai_2024_2026": "Official opt-in rejected-publication policy known; usable public per-paper source remains unverified. Challenge restriction must not be bypassed.", + "emnlp_2023": "Published opt-in rejected metadata known; existing9records do not prove full public set. Distinguish ARR reviews and conference commitment/decision.", + "aamas2026_aaai": { + "detailed_policy_year": "AAAI-26", + "overview_policy_year": "AAAI-25", + "source_conflict_retained": true, + "detailed_policy_sha256": "f3d0b52ad66fe243e99d09577b36043e1d2a4f5d5c184a5cd4c50da543eb3a4d", + "original_rejection_notes_obtained": false, + "prior_decisions_inserted": 0, + "requires": "Per-paper primary original identifiers/decisions or an explicitly distinguished policy-supported relation; never manufacture an original note." + } + }, + "restore_rules": [ + "Verify live PostgreSQL state and specific task handle before writing. Old work-state fields may be superseded.", + "Use accepted postcheck and current source bindings to distinguish consumed queues from pending materials.", + "Do not replay a whole batch because a count or observation times out.", + "Keep each submission/decision and source history when another venue accepts the same work.", + "Final whole-database identity, coverage, abstract, integrity and actual-query audit still required." + ] +} diff --git a/docs/coverage/backfill-handoff-2026-11-10.md b/docs/coverage/backfill-handoff-2026-11-10.md new file mode 100644 index 0000000..b0efda6 --- /dev/null +++ b/docs/coverage/backfill-handoff-2026-11-10.md @@ -0,0 +1,52 @@ +# 补漏范围与恢复清单（2026-11-10） + +用户确定：**后续主动补漏从 2020 年起**。2000 年起已经发现的名单、缺口、资料组合和身份核查记录保留在项目中，供下次接着做；已有旧数据继续保留。停止补采的年份标为范围外或延期，不算作已补齐。 + +本页是下一次工作的入口，结构化记录见 [backfill-handoff-2026-11-10.json](backfill-handoff-2026-11-10.json)。它保存 43 个会议的 2000–2026 已观察年份、缺年、官方目录文件入口、近期待办与恢复证据。旧的日期快照不改写，也不能当实时数据库。 + +## 当前范围和年份差集 + +依据生产只读快照 `2026-11-09 16:26:41.688509+00:00`，原全历史口径为 1266 个目标年份槽位：1208 已观察、43 个历史缺年、14 个 2026 缺年，以及 1 个 SysML 2018 非存档例外。原 135 个历史缺口中有 92 个通过数据补入解决；其余 43 个现在停止补采，不能因此宣称全部解决。 + +- **2020–2025**：没有整年完全缺记录的目标槽位，但逐篇、track、摘要、公开负面决定仍不完整。 +- **2026**：NeurIPS、ECCV、RecSys、CIKM、ICDM、SDM、IROS、RSS、CoRL、ICAPS、AAMAS、ICASSP、ISMIR、ACM MM，共 14 个槽位。须逐个核查是否已经公开出版；不能将尚未发布的资料说成漏采。 +- **2000–2019 延期线索**：WWW 2000、ICAPS 2001 两个整年缺口；官方历届记录分别见 [WWW](www-editions-2026-11-08.json)、[ICAPS](icaps-editions-2026-11-08.json)。SysML 2018 是非存档首届，见 [MLSys](mlsys-editions-2026-11-08.json)，不能制造正式出版记录。 +- **2000 年前**：剩余 41 个历史缺年停止补采。旧来源文件继续保留作证据，不再作为当前工作队列。 + +以上只判断目标会议年份是否至少有一条投稿记录，绝不等于目录完整、独立论文数量或最终去重验收。 + +## 近期资料与恢复位置 + +服务器采集根目录为 `/data/paper-index/collected`，本地证据备份为 `/Users/zzyang/Documents/Codex/2026-11-06/paper-index`。这些目录提供大体积原始文件，仓库 JSON 提供路径、状态和可用哈希；恢复前先验证文件存在、哈希和生产实际状态。 + +| 资料 | 当前状态 | 下一步与证据入口 | +| --- | --- | --- | +| AAMAS 2026 | 官方目录 643 条，3 个 keynote 排除；640 个非 keynote 中含 1 个明确撤稿。尚未导入 | `aamas2026-primary-evidence-v1/` 保存官方 HTML、回执、逐项目录、审计和校验清单。八个标题差异/撤稿前缀条目需核查。先扩展正式 collector 并远程验证，再做新 PostgreSQL 身份预检。 | +| CVPR 2026 Findings | 941 条摘要已核验，尚未导入 | `cvf-2026-verified/recovery-audit.json`；原 404 与 RVLF/FVLF 路径更正证据保留。先核对 manifests、track 和实体关系。 | +| AAMAS 2025 | 476 个非 keynote 来源中，240 已验收、236 待身份核查 | `aamas2025-import225-v1/` 与 `aamas2025-import15-v1/` 是已消费批次，禁止重放。15 条最近验收报告哈希见 JSON。余下资料从当前身份候选与新只读基线继续。 | +| RSS 2025 | 163 条目录中 162 已验收，`2025/p117` 待核查 | 保留 spinal/RMCC 关系问题；查看工作状态键 `rss2025_held7_primary_evidence_v1`，不能重跑已消费的 6/88/54/14 批次。 | +| 近期公开负面决定首批 | 1625 条已验收：1624 rejected、1 withdrawn | `public-negative-postgresql-import-postcheck-v1.json`；仅该批次验收，不是公开拒稿全集，不要重放。 | + +AAMAS 2026 官方目录分区：research 338、extended abstracts 185、AAAI 19、Blue Sky 17、doctoral 34、demo 44、JAAMAS 3，另有 keynote 3。JAAMAS 是期刊展示关系，不能凭目录再造一次独立审稿录用。官方撤稿条目在 research 分区，不能把全目录都标为当前 accepted。 + +AAAI 转投政策有年份冲突：[详细征稿页](https://cyprusconferences.org/aamas2026/call-for-papers-aaai-track/) 指 AAAI-26 rejected，[总览](https://cyprusconferences.org/aamas2026/calls/) 写 AAAI-25。保留两份证据；19 个 AAAI track 条目不能直接转成 19 条有原始 note 的拒稿决定。原投稿 ID、逐篇决定和版本关系仍需核实。 + +## 2000–2019 已发现但延期的身份与名单工作 + +- **AAMAS 2012**：官方 334 条，319 已独立验收、15 个身份条目保留待查。验收报告 `aamas2012-import-v1/postgresql-postcheck-v1.json`，哈希在 JSON；已验收 319 条及被替代的 316 条计划均不得重放。来源布局与用法见 [AAMAS 适配说明](../aamas-proceedings.md)。 +- **UAI 2008**：官方 programme 与归档资料确认了四篇独立论文，但部分原始 DBLP 键的标题、作者、页码、出版链接对应仍有冲突。JSON 保留四组候选、arXiv ID、官方题名及归档报告哈希。之前仅根据页码推断题名/作者错误的结论已撤回，未应用纠正；恢复时不得据此覆盖或合并。 +- **其他名单**：本目录全部 `*-editions-2026-11-08.json` 保留各会议官方年份及来源；[历史缺口](historical-gaps-2026-11-09.md)、[来源候选](historical-source-candidates-2026-11-09.json)、[来源范围](historical-source-scope-2026-11-09.md)、[主系列](historical-primary-series-2026-11-09.md)、[前身会议](historical-predecessors-2026-11-09.md)、[ICLR 档案](iclr-archive-2014-2016.md)继续留档。这些旧报告的“缺失”可能已被后续导入解决，恢复时必须对照当前状态，不能直接当可执行队列。 + +## 公开拒稿资料不能遗漏 + +结构化清单保留最近已查的政策 URL、限定年份和可用性结论。优先继续 UAI 2024–2026 的 opt-in 公开拒稿来源、EMNLP 2023 的公开集合范围及其他目标的逐年核查；平台使用 OpenReview 不能证明 rejected 公开。访问受限如实记录，不绕过 Challenge。 + +保留 rejected、desk rejected、withdrawn、retracted、resubmit 的区别；评审建议不等于最终决定。COLM 2026 的不公开政策只适用于已核实年份，不能推广到其他会议。PaperCopilot 与原 OpenReview、镜像间有重叠，候选计数不能相加。论文先被 A 拒绝再被 B 录用时，两次投稿、决定、来源与证据全部保留。 + +## 下次启动顺序 + +1. 读取本页和 JSON，再核实服务器工作状态、明确的 systemd invocation 与终态报告。权威工作状态 `/Users/zzyang/Documents/Codex/2026-11-06/paper-index/work-state.json` 中部分旧字段会过期；以最新验收和实际查询为准。 +2. 当前主动范围为 2020 起，2000–2019 只恢复线索，不自动启动其采集。先检查新来源是否已导入，验收过的队列禁止重放。 +3. 使用现有 `foundry-postgres` 的 `foundry_data.research`。当前已验证 writer 为提交 `714f745bd5c3fbc742be1efae0b31ab37a55e21f` 的固定 release；恢复时重新确认，不使用旧 `/data/paper-index/code` 替代。服务配置仅由服务器受保护文件读取，不复制密码。 +4. 对待导入资料做新只读身份预检，处理稳定标识、短标题、作者/版本差异、track 与跨会历史，再生成小范围增量队列。每批独立验收，SQLite 只读备份保持保护。 +5. 编译、测试或 wheel 构建仅在已确认 `ces-control:host` runner 执行。代码按工作分支交付 PR，等待用户手动合并。范围内导入结束后仍须全库去重、近似标题/作者冲突、来源-年份-track、摘要、约束、实际全文查询验收；不能用单批导入或 CI 成功替代。