diff --git a/docs/coverage/acl-hcinlp-codi-workshops-2026-11-20.json b/docs/coverage/acl-hcinlp-codi-workshops-2026-11-20.json new file mode 100644 index 0000000..50e02f1 --- /dev/null +++ b/docs/coverage/acl-hcinlp-codi-workshops-2026-11-20.json @@ -0,0 +1,379 @@ +{ + "status": "committed_and_readonly_verified", + "snapshot_at": "2026-11-19 18:16:33.907457+00", + "scopes": [ + { + "workshop": "hcinlp", + "host": "NAACL", + "year": 2024, + "official_roster": "https://aclanthology.org/volumes/2024.hcinlp-1/", + "xml_source": "https://raw.githubusercontent.com/acl-org/acl-anthology/master/data/xml/2024.hcinlp.xml", + "xml_sha256": "2fc6ebbab546c68f9775c5c9873a12a22e20133f06335b4c9f092c2d20eb6fd4", + "booktitle": "Proceedings of the Third Workshop on Bridging Human--Computer Interaction and Natural Language Processing", + "roster_html_sha256": "67d48903c47fe2efb2eb27f6dff90b47299efb872a0ba01fa4f8294222e25663", + "edition_id": 104136, + "count": 9, + "source_id": 4, + "frontmatter_excluded": 1 + }, + { + "workshop": "codi", + "host": "EMNLP", + "year": 2025, + "official_roster": "https://aclanthology.org/volumes/2025.codi-1/", + "xml_source": "https://raw.githubusercontent.com/acl-org/acl-anthology/master/data/xml/2025.codi.xml", + "xml_sha256": "679d28bb94514e6b1e9de23cbfbed4a2f1bfa35b9a331d9255d528a136e05c23", + "booktitle": "Proceedings of the 6th Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences (CODI 2025)", + "roster_html_sha256": "47aebd4e448d771938a430deaa1db7d015c1c42d55531ddaf1b95ad1f7906809", + "edition_id": 104137, + "count": 18, + "source_id": 4, + "frontmatter_excluded": 1 + } + ], + "records": [ + { + "external_id": "2024.hcinlp-1.1", + "paper_id": 3572585, + "source_record_id": 3824638, + "submission_id": 541181, + "decision_id": 580763, + "link": "new_publication_identity", + "title": "Examining Prosody in Spoken Navigation Instructions for People with Disabilities", + "doi": "10.18653/v1/2024.hcinlp-1.1", + "abstract_sha256": "5809222659f95206cda995853694add1d153573427202b2175775564f91edf51" + }, + { + "external_id": "2024.hcinlp-1.2", + "paper_id": 2010033, + "source_record_id": 3824639, + "submission_id": 541182, + "decision_id": 580764, + "link": "existing_preprint", + "title": "Properties and Challenges of LLM-Generated Explanations", + "doi": "10.18653/v1/2024.hcinlp-1.2", + "abstract_sha256": "cf0ac114fe49c332b0b7bb705beedd035b1af7f3931420619db81e557dbbb4eb" + }, + { + "external_id": "2024.hcinlp-1.3", + "paper_id": 3572586, + "source_record_id": 3824640, + "submission_id": 541183, + "decision_id": 580765, + "link": "new_publication_identity", + "title": "This Reference Does Not Exist: An Exploration of LLM Citation Accuracy and Relevance", + "doi": "10.18653/v1/2024.hcinlp-1.3", + "abstract_sha256": "9f597f509bda83775059b55d3613d30d1d417842363499efe2313d4ca79f708c" + }, + { + "external_id": "2024.hcinlp-1.4", + "paper_id": 3572587, + "source_record_id": 3824641, + "submission_id": 541184, + "decision_id": 580766, + "link": "new_publication_identity", + "title": "Combining Multiple Metrics for Evaluating Retrieval-Augmented Conversations", + "doi": "10.18653/v1/2024.hcinlp-1.4", + "abstract_sha256": "25bd40698db8726eca267c38885eddb797646311f058d0110aa8eebfcd9ce9b5" + }, + { + "external_id": "2024.hcinlp-1.5", + "paper_id": 2018250, + "source_record_id": 3824642, + "submission_id": 541185, + "decision_id": 580767, + "link": "existing_preprint", + "title": "How Much Annotation is Needed to Compare Summarization Models?", + "doi": "10.18653/v1/2024.hcinlp-1.5", + "abstract_sha256": "201bbbca3ef6e3773771174bc301cf0df5df88e7430abd574f458834389198b9" + }, + { + "external_id": "2024.hcinlp-1.6", + "paper_id": 3572588, + "source_record_id": 3824643, + "submission_id": 541186, + "decision_id": 580768, + "link": "new_publication_identity", + "title": "An Interactive Co-Pilot for Accelerated Research Ideation", + "doi": "10.18653/v1/2024.hcinlp-1.6", + "abstract_sha256": "9bcd406a8331e1dd27fd04b20d1b25c0ad812e5fa9e99fd989d32190b464d722" + }, + { + "external_id": "2024.hcinlp-1.7", + "paper_id": 3572589, + "source_record_id": 3824644, + "submission_id": 541187, + "decision_id": 580769, + "link": "new_publication_identity", + "title": "Sensemaking of Socially-Mediated Crisis Information", + "doi": "10.18653/v1/2024.hcinlp-1.7", + "abstract_sha256": "9e10b91d147ada74e0175a86a8a88bd914f007abb6ec6a97829e7b56349c1ca5" + }, + { + "external_id": "2024.hcinlp-1.8", + "paper_id": 2058339, + "source_record_id": 3824645, + "submission_id": 541188, + "decision_id": 580770, + "link": "existing_preprint", + "title": "Blind Spots and Biases: Exploring the Role of Annotator Cognitive Biases in NLP", + "doi": "10.18653/v1/2024.hcinlp-1.8", + "abstract_sha256": "89d785fbb8257a47db1cb8af287287108a6b0e370a6487495e178ecf1bb6f8cf" + }, + { + "external_id": "2024.hcinlp-1.9", + "paper_id": 1994009, + "source_record_id": 3824631, + "submission_id": 541174, + "decision_id": 580756, + "link": "previously_linked", + "title": "LLMCheckup: Conversational Examination of Large Language Models via Interpretability Tools and Self-Explanations", + "doi": "10.18653/v1/2024.hcinlp-1.9", + "abstract_sha256": "0fef8318671702bc132fd04c3979c252f850fca5842f5a148e4503d75fdb5f62" + }, + { + "external_id": "2025.codi-1.1", + "paper_id": 3572590, + "source_record_id": 3824646, + "submission_id": 541189, + "decision_id": 580771, + "link": "new_publication_identity", + "title": "Long Context Benchmark for the Russian Language", + "doi": "10.18653/v1/2025.codi-1.1", + "abstract_sha256": "9d2f0645720220131b1215761f8cb50f5ddcbd44fc778dd03ce989fe7a155be3" + }, + { + "external_id": "2025.codi-1.2", + "paper_id": 2438682, + "source_record_id": 3824647, + "submission_id": 541190, + "decision_id": 580772, + "link": "existing_preprint", + "title": "Unpacking Ambiguity: The Interaction of Polysemous Discourse Markers and Non-DM Signals", + "doi": "10.18653/v1/2025.codi-1.2", + "abstract_sha256": "f1d0804a758fbf4e4b56e5519132be4f2352f819ed86f5c9e0fcdb1c77bdf881" + }, + { + "external_id": "2025.codi-1.3", + "paper_id": 3572591, + "source_record_id": 3824648, + "submission_id": 541191, + "decision_id": 580773, + "link": "new_publication_identity", + "title": "Enhancing the Automatic Classification of Metadiscourse in Low-Proficiency Learners’ Spoken and Written English Texts Using XLNet", + "doi": "10.18653/v1/2025.codi-1.3", + "abstract_sha256": "d18821e96c47db0e50b158b505cb227fe5a14f20a3440946b4faced7fce8f5b1" + }, + { + "external_id": "2025.codi-1.4", + "paper_id": 3572592, + "source_record_id": 3824649, + "submission_id": 541192, + "decision_id": 580774, + "link": "new_publication_identity", + "title": "Entity Tracking in Small Language Models: An Attention-Based Study of Parameter-Efficient Fine-Tuning", + "doi": "10.18653/v1/2025.codi-1.4", + "abstract_sha256": "7caf38bace2f786f36f8ab7897fdd715b27e9bc5d5c8a1856485e6e1a66e9cbe" + }, + { + "external_id": "2025.codi-1.5", + "paper_id": 3572593, + "source_record_id": 3824650, + "submission_id": 541193, + "decision_id": 580775, + "link": "new_publication_identity", + "title": "Stance Detection on Nigerian 2023 Election Tweets Using BERT: A Low-Resource Transformer-Based Approach", + "doi": "10.18653/v1/2025.codi-1.5", + "abstract_sha256": "58c859043771c242f978e512485400172e680e472de36b388a31ab543b8bede0" + }, + { + "external_id": "2025.codi-1.6", + "paper_id": 3572594, + "source_record_id": 3824651, + "submission_id": 541194, + "decision_id": 580776, + "link": "new_publication_identity", + "title": "Code-switching in Context: Investigating the Role of Discourse Topic in Bilingual Speech Production", + "doi": "10.18653/v1/2025.codi-1.6", + "abstract_sha256": "54425322122f3c0b724fbea775ab32aea2d2524b486799b827552302e1e75735" + }, + { + "external_id": "2025.codi-1.7", + "paper_id": 3572595, + "source_record_id": 3824652, + "submission_id": 541195, + "decision_id": 580777, + "link": "new_publication_identity", + "title": "“Otherwise” in Context: Exploring Discourse Functions with Language Models", + "doi": "10.18653/v1/2025.codi-1.7", + "abstract_sha256": "a0f79178ff047597c60375a89c41b8aa8f295b601307286bf83af857de43f42c" + }, + { + "external_id": "2025.codi-1.8", + "paper_id": 2516229, + "source_record_id": 3824653, + "submission_id": 541196, + "decision_id": 580778, + "link": "existing_preprint", + "title": "On the Role of Context for Discourse Relation Classification in Scientific Writing", + "doi": "10.18653/v1/2025.codi-1.8", + "abstract_sha256": "20cb1b0b81b4fbfcd2063a00bfbceb985592c4599d8401e6c52f5545874bfa81" + }, + { + "external_id": "2025.codi-1.10", + "paper_id": 2321303, + "source_record_id": 3824654, + "submission_id": 541197, + "decision_id": 580779, + "link": "existing_preprint", + "title": "Zero-Shot Belief: A Hard Problem for LLMs", + "doi": "10.18653/v1/2025.codi-1.10", + "abstract_sha256": "c4051c4c96c72c409aad0f14e852755606f436b1a6dd9df502cc314cfd6b4da5" + }, + { + "external_id": "2025.codi-1.11", + "paper_id": 3572596, + "source_record_id": 3824655, + "submission_id": 541198, + "decision_id": 580780, + "link": "new_publication_identity", + "title": "Probing the Limits of Multilingual Language Understanding: Low-Resource Language Proverbs as LLM Benchmark for AI Wisdom", + "doi": "10.18653/v1/2025.codi-1.11", + "abstract_sha256": "dc71db0164b811bbf859f0d8f29672cc30afaaafebb7654f689e83f47a3a44b8" + }, + { + "external_id": "2025.codi-1.12", + "paper_id": 3572597, + "source_record_id": 3824656, + "submission_id": 541199, + "decision_id": 580781, + "link": "new_publication_identity", + "title": "Measuring Sexism in US Elections: A Comparative Analysis of X Discourse from 2020 to 2024", + "doi": "10.18653/v1/2025.codi-1.12", + "abstract_sha256": "3817cb511e1dafa9643965b81458d924403be043eb442e886e582a70d915376e" + }, + { + "external_id": "2025.codi-1.13", + "paper_id": 3572598, + "source_record_id": 3824657, + "submission_id": 541200, + "decision_id": 580782, + "link": "new_publication_identity", + "title": "Discourse Relation Recognition with Language Models Under Different Data Availability", + "doi": "10.18653/v1/2025.codi-1.13", + "abstract_sha256": "ba737b732d58a99082fedf480f161daa83cff7cbc0cd3f1f8188b579c5667235" + }, + { + "external_id": "2025.codi-1.14", + "paper_id": 3572599, + "source_record_id": 3824658, + "submission_id": 541201, + "decision_id": 580783, + "link": "new_publication_identity", + "title": "EmbiText: Embracing Ambiguity by Annotation, Recognition and Generation of Pronominal Reference with Event-Entity Ambiguity", + "doi": "10.18653/v1/2025.codi-1.14", + "abstract_sha256": "9fe0bd078512a376677fbf7e762f13f624bfb2ad260b065f44b6ba6a54aa1d0e" + }, + { + "external_id": "2025.codi-1.15", + "paper_id": 3572583, + "source_record_id": 3824633, + "submission_id": 541176, + "decision_id": 580758, + "link": "previously_linked", + "title": "Human and LLM-based Assessment of Teaching Acts in Expert-led Explanatory Dialogues", + "doi": "10.18653/v1/2025.codi-1.15", + "abstract_sha256": "c5225b1cc7d688ccdf1ea7bd869b09df12d251838ffe2c8de0a8ac08760b5cbf" + }, + { + "external_id": "2025.codi-1.16", + "paper_id": 3572600, + "source_record_id": 3824659, + "submission_id": 541202, + "decision_id": 580784, + "link": "new_publication_identity", + "title": "Where Frameworks (Dis)agree: A Study of Discourse Segmentation", + "doi": "10.18653/v1/2025.codi-1.16", + "abstract_sha256": "736403c3f5bcd4050928ce2dc9d842d842e9426d950d84c3aa2ed5e0384909ab" + }, + { + "external_id": "2025.codi-1.17", + "paper_id": 2497633, + "source_record_id": 3824660, + "submission_id": 541203, + "decision_id": 580785, + "link": "existing_preprint", + "title": "Bridging Discourse Treebanks with a Unified Rhetorical Structure Parser", + "doi": "10.18653/v1/2025.codi-1.17", + "abstract_sha256": "200b3731bda2a925ba7aba35e3e1a726c811473caaa24c38b1d0d3063b4e683f" + }, + { + "external_id": "2025.codi-1.18", + "paper_id": 3572601, + "source_record_id": 3824661, + "submission_id": 541204, + "decision_id": 580786, + "link": "new_publication_identity", + "title": "Corpus-Oriented Stance Target Extraction", + "doi": "10.18653/v1/2025.codi-1.18", + "abstract_sha256": "d00b6fa7f9d692987eea391942a14a3f354f2ed6867ab0964ae3621e45f32a68" + }, + { + "external_id": "2025.codi-1.19", + "paper_id": 3572602, + "source_record_id": 3824662, + "submission_id": 541205, + "decision_id": 580787, + "link": "new_publication_identity", + "title": "Information-Theoretic and Prompt-Based Evaluation of Discourse Connective Edits in Instructional Text Revisions", + "doi": "10.18653/v1/2025.codi-1.19", + "abstract_sha256": "ed89c03f19c384d298803bb0da7f3b0594fcbb919bf75a274ecf22a7a5e61e6b" + } + ], + "preflight_sha256": "d042dffdd1627007a6aabc025aced336c04bf42c9a4ba1a3693a5993e1530997", + "run_id": 1973, + "source_records_written": 25, + "normal_query_verified_ids": [ + 1994009, + 2010033, + 2018250, + 2058339, + 3572585, + 3572586, + 3572587, + 3572588, + 3572589, + 2321303, + 2438682, + 2497633, + 2516229, + 3572583, + 3572590, + 3572591, + 3572592, + 3572593, + 3572594, + 3572595, + 3572596, + 3572597, + 3572598, + 3572599, + 3572600, + 3572601, + 3572602 + ], + "negative_scope": "Individual author reports only; completeness of public negative decisions is unknown.", + "counts_by_link": { + "new_publication_identity": 18, + "existing_preprint": 7, + "previously_linked": 2 + }, + "verification": { + "official_html_and_xml_paper_id_sets_match": true, + "official_source_abstracts_verified": 27, + "catalogue_scope": "Two named workshop proceedings volumes only, excluding front matter.", + "preprint_identity_basis": "Unique normalized title plus complete ordered surnames and given names, verified against the existing arXiv anchor; full original entity histories retained.", + "publication_identity_followup": "The 18 new identities are provisional for final cross-source deduplication.", + "negative_coverage": "The proceedings catalogue does not enumerate rejections. Previously linked author-reported decisions were preserved." + } +} diff --git a/docs/coverage/public-decision-source-boundaries-2026-11-18.md b/docs/coverage/public-decision-source-boundaries-2026-11-18.md index 97aaa24..096052b 100644 --- a/docs/coverage/public-decision-source-boundaries-2026-11-18.md +++ b/docs/coverage/public-decision-source-boundaries-2026-11-18.md @@ -138,3 +138,7 @@ Olivier Jeunen 公开说明其关于利用策略重叠降低 A/B 测试方差的 《Human and LLM-based Assessment of Teaching Acts in Expert-led Explanatory Dialogues》保留 ACL 2025 和 SIGDIAL 2025 拒稿,以及 EMNLP 2025 CODI workshop 录用。公开 OpenReview 连接指向 2025 年 2 月 ARR 评审,随版本关系保存。正式条目的作者顺序采用 Anthology 结构化元数据。《Adapters for Resource-Efficient Deployment of NLU Models》保留 COLING 2022 拒稿和 ESSV 2023 正式发表。两篇均以核实的正式出版标识建档。 [CODI 正式稿](https://aclanthology.org/2025.codi-1.15/) · [ARR 评审页面](https://openreview.net/forum?id=JkxMQ4AqnN) · [ESSV 正式稿](https://www.essv.de/paper.php?id=1196) 三条正式出版摘要均按来源校验,并通过正常查询见到各自独立的拒稿和录用。两次广泛检索超时后的验收使用正式标识、精确题名和已知变体。未发现的题名变体仍列入全库去重复查。 [生产验收](nlp-author-public-decisions-followup-2026-11-20.json) + +### HCI+NLP 2024 和 CODI 2025 正式目录 + +两个官方目录的网页与 XML 逐篇一致。本轮核验 NAACL 2024 HCI+NLP 的 9/9 篇与 EMNLP 2025 CODI 的 18/18 篇,均排除单列的前言。此前已核实的两篇及其作者披露的拒稿历史保留,7 篇关联已有 arXiv 论文,18 篇以正式出版标识建档并留待全库去重复查。27 份正式摘要与 workshop 录用均通过生产库验收和按活动的正常查询。此覆盖完成仅适用于两卷正式论文集。作者公开拒稿仍只覆盖已逐篇核实的披露。 [HCI+NLP 目录](https://aclanthology.org/volumes/2024.hcinlp-1/) · [CODI 目录](https://aclanthology.org/volumes/2025.codi-1/) · [逐篇验收](acl-hcinlp-codi-workshops-2026-11-20.json)