{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3VKZBUIGMAHOM4ZNT4QNQ2Q2F7","short_pith_number":"pith:3VKZBUIG","schema_version":"1.0","canonical_sha256":"dd5590d106600ee6732d9f20d86a1a2ff328eb0a6a0527ef2f6d502fb6f5fe89","source":{"kind":"arxiv","id":"2004.04906","version":3},"attestation_state":"computed","paper":{"title":"Dense Passage Retrieval for Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Dense vector embeddings from a dual-encoder model outperform BM25 by 9-19 percent in top-20 passage retrieval for open-domain question answering.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barlas O\\u{g}uz, Danqi Chen, Ledell Wu, Patrick Lewis, Sergey Edunov, Sewon Min, Vladimir Karpukhin, Wen-tau Yih","submitted_at":"2020-04-10T04:53:17Z","abstract_excerpt":"Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2004.04906","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-10T04:53:17Z","cross_cats_sorted":[],"title_canon_sha256":"c96f5bf3536a0d3e14c11ae7bba5d82215542e366aca2579cd67c8304bdd8f71","abstract_canon_sha256":"179520b17eb7655f708fa8cc17a2d0a7759f710681cf9166587ba099b951d8e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.118744Z","signature_b64":"iGwZX/TrpiD42rdA6yOprs2dFkWm8m72oeDSSQiSlwDcOuLaus0ZW1+DL/QEteF4OFNizgqpuJ+pI+lob0GACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd5590d106600ee6732d9f20d86a1a2ff328eb0a6a0527ef2f6d502fb6f5fe89","last_reissued_at":"2026-05-17T23:38:50.118168Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.118168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dense Passage Retrieval for Open-Domain Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Dense vector embeddings from a dual-encoder model outperform BM25 by 9-19 percent in top-20 passage retrieval for open-domain question answering.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barlas O\\u{g}uz, Danqi Chen, Ledell Wu, Patrick Lewis, Sergey Edunov, Sewon Min, Vladimir Karpukhin, Wen-tau Yih","submitted_at":"2020-04-10T04:53:17Z","abstract_excerpt":"Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy,"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That embeddings learned from a small number of questions and passages will generalize to the full distribution of queries and documents encountered at test time without additional adaptation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Dense dual-encoder retrievers outperform BM25 by 9-19% absolute in top-20 passage retrieval accuracy across open-domain QA datasets and enable new state-of-the-art end-to-end QA results.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Dense vector embeddings from a dual-encoder model outperform BM25 by 9-19 percent in top-20 passage retrieval for open-domain question answering.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"34dcd6909a322924e26601d22cc89a2bb69a0ba33e8f2a386e0f66604458ec05"},"source":{"id":"2004.04906","kind":"arxiv","version":3},"verdict":{"id":"69d8be53-25bf-49ce-b023-2ebe61463f0e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T21:21:33.779649Z","strongest_claim":"our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.","one_line_summary":"Dense dual-encoder retrievers outperform BM25 by 9-19% absolute in top-20 passage retrieval accuracy across open-domain QA datasets and enable new state-of-the-art end-to-end QA results.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That embeddings learned from a small number of questions and passages will generalize to the full distribution of queries and documents encountered at test time without additional adaptation.","pith_extraction_headline":"Dense vector embeddings from a dual-encoder model outperform BM25 by 9-19 percent in top-20 passage retrieval for open-domain question answering."},"references":{"count":113,"sample":[{"doi":"","year":null,"title":"Passage Re-ranking with","work_id":"fc2ddd97-10e7-40a7-933c-840da1cd2f01","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"2020 , booktitle =","work_id":"55e9beb5-adc8-4a04-8159-ea1fa498a605","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Relevance-guided Supervision for OpenQA with","work_id":"e109b3e7-d675-41ce-a9e1-1ef8465f9881","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The probabilistic relevance framework:","work_id":"8fc0aab3-8cc7-4e70-9dc4-066311e5527d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Learning to Retrieve Reasoning Paths over","work_id":"e513a414-13b7-4924-8112-988c627f3aea","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":113,"snapshot_sha256":"bcf46dcd452c8eedc2f350ab9bd78dfcfcbaa00730946212898e387189d96408","internal_anchors":8},"formal_canon":{"evidence_count":1,"snapshot_sha256":"916c72306ca4ee458b29fbf2bcdfea177e7ae5eff4f5bf83c2cdeee0ce2dae6b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.04906","created_at":"2026-05-17T23:38:50.118253+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.04906v3","created_at":"2026-05-17T23:38:50.118253+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04906","created_at":"2026-05-17T23:38:50.118253+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VKZBUIGMAHO","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VKZBUIGMAHOM4ZN","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VKZBUIG","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":32,"sample":[{"citing_arxiv_id":"2605.23067","citing_title":"What Training Data Teaches RL Memory Agents: An Empirical Study of Curriculum Effects in Memory-Augmented QA","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2409.01579","citing_title":"AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2504.09775","citing_title":"MIST: A Co-Design Framework for Heterogeneous, Multi-Stage LLM Inference","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2310.10631","citing_title":"Llemma: An Open Language Model For Mathematics","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2506.20821","citing_title":"MultiFinRAG: An Optimized Multimodal Retrieval-Augmented Generation (RAG) Framework for Financial Question Answering","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2510.11954","citing_title":"VizCopilot: Fostering Appropriate Reliance on Enterprise Chatbots with Context Visualization","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":196,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04936","citing_title":"Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2208.03299","citing_title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","ref_index":210,"is_internal_anchor":true},{"citing_arxiv_id":"2601.17617","citing_title":"Agentic Search in the Wild: Intents and Trajectory Dynamics from 14M+ Real Search Requests","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2305.10250","citing_title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20844","citing_title":"AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2404.18796","citing_title":"Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14169","citing_title":"BOOKMARKS: Efficient Active Storyline Memory for Role-playing","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2002.08910","citing_title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14503","citing_title":"Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2405.17428","citing_title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","ref_index":135,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09666","citing_title":"Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2309.07597","citing_title":"C-Pack: Packed Resources For General Chinese Embeddings","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12487","citing_title":"Task-Adaptive Embedding Refinement via Test-time LLM Guidance","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2112.09118","citing_title":"Unsupervised Dense Information Retrieval with Contrastive Learning","ref_index":146,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27906","citing_title":"From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2201.08239","citing_title":"LaMDA: Language Models for Dialog Applications","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7","json":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7.json","graph_json":"https://pith.science/api/pith-number/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/graph.json","events_json":"https://pith.science/api/pith-number/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/events.json","paper":"https://pith.science/paper/3VKZBUIG"},"agent_actions":{"view_html":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7","download_json":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7.json","view_paper":"https://pith.science/paper/3VKZBUIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.04906&json=true","fetch_graph":"https://pith.science/api/pith-number/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/graph.json","fetch_events":"https://pith.science/api/pith-number/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/action/storage_attestation","attest_author":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/action/author_attestation","sign_citation":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/action/citation_signature","submit_replication":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/action/replication_record"}},"created_at":"2026-05-17T23:38:50.118253+00:00","updated_at":"2026-05-17T23:38:50.118253+00:00"}