{"work":{"id":"083391f8-812d-430f-8d08-89a03031ce6c","openalex_id":"https://openalex.org/W3015883388","doi":"10.18653/v1/2020.emnlp-main.550","arxiv_id":null,"raw_key":null,"title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) , month = nov, year =","authors":[{"given":"Vladimir","family":"Karpukhin","sequence":"first","affiliation":[]},{"given":"Barlas","family":"Oguz","sequence":"additional","affiliation":[]},{"given":"Sewon","family":"Min","sequence":"additional","affiliation":[]},{"given":"Patrick","family":"Lewis","sequence":"additional","affiliation":[]},{"given":"Ledell","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Sergey","family":"Edunov","sequence":"additional","affiliation":[]},{"given":"Danqi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Wen-tau","family":"Yih","sequence":"additional","affiliation":[]}],"authors_text":"doi: 10","year":2020,"venue":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","abstract":null,"external_url":"https://doi.org/10.18653/v1/2020.emnlp-main.550","cited_by_count":1724,"metadata_source":"doi_reference","metadata_fetched_at":"2026-07-08T20:05:33.949387+00:00","pith_arxiv_id":null,"created_at":"2026-05-08T16:53:30.205051+00:00","updated_at":"2026-07-08T20:05:33.949387+00:00","title_quality_ok":false,"display_title":"Dense Passage Retrieval for Open-Domain Question Answering","render_title":"Dense Passage Retrieval for Open-Domain Question Answering"},"hub":{"state":{"work_id":"083391f8-812d-430f-8d08-89a03031ce6c","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":94,"external_cited_by_count":1724,"distinct_field_count":8,"first_pith_cited_at":"2021-04-18T11:27:08+00:00","last_pith_cited_at":"2026-07-07T08:04:05+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T03:09:30.768261+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":9},{"context_role":"dataset","n":3},{"context_role":"baseline","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":9},{"context_polarity":"use_dataset","n":3},{"context_polarity":"baseline","n":1},{"context_polarity":"use_method","n":1}],"runs":{"context_extract":{"job_type":"context_extract","status":"succeeded","result":{"enqueued_papers":25},"error":null,"updated_at":"2026-05-14T18:09:38.887924+00:00"},"graph_features":{"job_type":"graph_features","status":"succeeded","result":{"co_cited":[{"title":"booktitle =","work_id":"3c5a795a-85bd-45a1-8e65-06a9c5641111","shared_citers":9},{"title":"Sentence- BERT : Sentence embeddings using S iamese BERT -networks","work_id":"cf07889b-1f35-4d81-9514-4ad3ed223c57","shared_citers":9},{"title":"BERT : Pre-training of deep bidirectional transformers for language understanding","work_id":"3e3c8ac8-b858-4b22-af32-393d98c883e0","shared_citers":7},{"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","shared_citers":7},{"title":"ColBERT: Efficient and effective passage search via con- textualized late interaction over bert","work_id":"a0aa64b7-2891-458f-a5ef-35ff6fa77f18","shared_citers":6},{"title":"Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov","work_id":"45551929-96dc-40f3-9f89-10e76731cc24","shared_citers":6},{"title":"doi: 10.18653/v1/2022.naacl-main.272","work_id":"bfa57bc7-9275-4c55-a608-477c2f68ca23","shared_citers":6},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":6},{"title":"FEVER: a large-scale dataset for Fact Extraction and VERification","work_id":"b696f75f-e5ad-4555-9c12-e292e77c388f","shared_citers":5},{"title":"Joshi, E","work_id":"d05a9c57-9d88-473a-aa65-efb13f9dee25","shared_citers":5},{"title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","work_id":"bab684a8-d933-426c-a19e-2c855a0d1f59","shared_citers":5},{"title":"Representation Learning with Contrastive Predictive Coding","work_id":"7b08a1d4-d565-424e-9c86-6ef244b7b90a","shared_citers":5},{"title":"SimCSE: Simple contrastive learning of sentence embeddings","work_id":"f9c0d9b5-c569-4f54-bdc7-6ff3cdd316db","shared_citers":5},{"title":"The Faiss library","work_id":"41b4c732-3a63-4106-9e7c-50d61cfb2126","shared_citers":5},{"title":"Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus","work_id":"aa2fb99f-beb8-463c-8cd4-c575e96e2512","shared_citers":4},{"title":"Constructing A Multi-hop","work_id":"fd3a2c44-aeea-48a7-b162-d3f0c6d43f35","shared_citers":4},{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":4},{"title":"Lost in the Middle: How Language Models Use Long Contexts","work_id":"37c05e13-4a24-44f8-a1c4-da1bbe7223aa","shared_citers":4},{"title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","work_id":"78d498ce-11db-4f88-8eb0-40e0f86af615","shared_citers":4},{"title":"MTEB: Massive text embedding benchmark","work_id":"5c5a0bda-f984-4ea2-8938-cab73425e1b6","shared_citers":4},{"title":"MuSiQue: Multihop questions via single-hop question composition.Transactions of the Association for Computational Linguistics, 10:539–554","work_id":"dd4f6eb0-477f-42c4-8d8a-8c8637815f98","shared_citers":4},{"title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","work_id":"41fe12c4-e538-4890-a244-480650ed3078","shared_citers":4},{"title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models , url =","work_id":"c0499b0c-2d17-4e0b-80e9-7ee4ea48e6c2","shared_citers":4},{"title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","work_id":"789cc674-467e-4f23-bb50-05c79fe8c4c2","shared_citers":4}],"time_series":[{"n":2,"year":2023},{"n":3,"year":2024},{"n":28,"year":2026}],"dependency_candidates":[]},"error":null,"updated_at":"2026-05-14T18:09:19.842706+00:00"},"identity_refresh":{"job_type":"identity_refresh","status":"succeeded","result":{"items":[{"title":"Qwen3 Technical Report","outcome":"unchanged","work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e","resolver":"local_arxiv","confidence":0.98,"old_work_id":"25a4e30c-1232-48e7-9925-02fa12ba7c9e"}],"counts":{"fixed":0,"merged":0,"unchanged":1,"quarantined":0,"needs_external_resolution":0},"errors":[],"attempted":1},"error":null,"updated_at":"2026-05-14T18:10:18.259731+00:00"},"summary_claims":{"job_type":"summary_claims","status":"succeeded","result":{"title":"Dense passage retrieval for open-domain question answering","claims":[],"why_cited":"Pith tracks Dense passage retrieval for open-domain question answering because it crossed a citation-hub threshold.","role_counts":[]},"error":null,"updated_at":"2026-05-14T18:09:42.583093+00:00"}},"summary":{"title":"Dense passage retrieval for open-domain question answering","claims":[],"why_cited":"Pith tracks Dense passage retrieval for open-domain question answering because it crossed a citation-hub threshold.","role_counts":[]},"graph":{"co_cited":[{"title":"booktitle =","work_id":"3c5a795a-85bd-45a1-8e65-06a9c5641111","shared_citers":9},{"title":"Sentence- BERT : Sentence embeddings using S iamese BERT -networks","work_id":"cf07889b-1f35-4d81-9514-4ad3ed223c57","shared_citers":9},{"title":"BERT : Pre-training of deep bidirectional transformers for language understanding","work_id":"3e3c8ac8-b858-4b22-af32-393d98c883e0","shared_citers":7},{"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","shared_citers":7},{"title":"ColBERT: Efficient and effective passage search via con- textualized late interaction over bert","work_id":"a0aa64b7-2891-458f-a5ef-35ff6fa77f18","shared_citers":6},{"title":"Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov","work_id":"45551929-96dc-40f3-9f89-10e76731cc24","shared_citers":6},{"title":"doi: 10.18653/v1/2022.naacl-main.272","work_id":"bfa57bc7-9275-4c55-a608-477c2f68ca23","shared_citers":6},{"title":"Retrieval-Augmented Generation for Large Language Models: A Survey","work_id":"b80d2790-6cd9-4c87-b3c4-de404f99a80e","shared_citers":6},{"title":"FEVER: a large-scale dataset for Fact Extraction and VERification","work_id":"b696f75f-e5ad-4555-9c12-e292e77c388f","shared_citers":5},{"title":"Joshi, E","work_id":"d05a9c57-9d88-473a-aa65-efb13f9dee25","shared_citers":5},{"title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","work_id":"bab684a8-d933-426c-a19e-2c855a0d1f59","shared_citers":5},{"title":"Representation Learning with Contrastive Predictive Coding","work_id":"7b08a1d4-d565-424e-9c86-6ef244b7b90a","shared_citers":5},{"title":"SimCSE: Simple contrastive learning of sentence embeddings","work_id":"f9c0d9b5-c569-4f54-bdc7-6ff3cdd316db","shared_citers":5},{"title":"The Faiss library","work_id":"41b4c732-3a63-4106-9e7c-50d61cfb2126","shared_citers":5},{"title":"Barret Zoph, Irwan Bello, Sameer Kumar, Nan Du, Yanping Huang, Jeff Dean, Noam Shazeer, and William Fedus","work_id":"aa2fb99f-beb8-463c-8cd4-c575e96e2512","shared_citers":4},{"title":"Constructing A Multi-hop","work_id":"fd3a2c44-aeea-48a7-b162-d3f0c6d43f35","shared_citers":4},{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","work_id":"588618d7-fd41-4053-b34d-a981f8793039","shared_citers":4},{"title":"Lost in the Middle: How Language Models Use Long Contexts","work_id":"37c05e13-4a24-44f8-a1c4-da1bbe7223aa","shared_citers":4},{"title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","work_id":"78d498ce-11db-4f88-8eb0-40e0f86af615","shared_citers":4},{"title":"MTEB: Massive text embedding benchmark","work_id":"5c5a0bda-f984-4ea2-8938-cab73425e1b6","shared_citers":4},{"title":"MuSiQue: Multihop questions via single-hop question composition.Transactions of the Association for Computational Linguistics, 10:539–554","work_id":"dd4f6eb0-477f-42c4-8d8a-8c8637815f98","shared_citers":4},{"title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","work_id":"41fe12c4-e538-4890-a244-480650ed3078","shared_citers":4},{"title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models , url =","work_id":"c0499b0c-2d17-4e0b-80e9-7ee4ea48e6c2","shared_citers":4},{"title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","work_id":"789cc674-467e-4f23-bb50-05c79fe8c4c2","shared_citers":4}],"time_series":[{"n":2,"year":2023},{"n":3,"year":2024},{"n":28,"year":2026}],"dependency_candidates":[]},"authors":[]}}