{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3VKZBUIGMAHOM4ZNT4QNQ2Q2F7","short_pith_number":"pith:3VKZBUIG","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"},"canonical_sha256":"dd5590d106600ee6732d9f20d86a1a2ff328eb0a6a0527ef2f6d502fb6f5fe89","source":{"kind":"arxiv","id":"2004.04906","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.04906","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2004.04906v3","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04906","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"3VKZBUIGMAHO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"3VKZBUIGMAHOM4ZN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"3VKZBUIG","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3VKZBUIGMAHOM4ZNT4QNQ2Q2F7","target":"record","payload":{"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"},"canonical_sha256":"dd5590d106600ee6732d9f20d86a1a2ff328eb0a6a0527ef2f6d502fb6f5fe89","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"},"source_kind":"arxiv","source_id":"2004.04906","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+K9HFb3aKGUKn5ulRYXUfsCakazaUYEhe/5BuHtUvmuy+lrHMRVY3U0sazLK1mITT9TKogLuS5WDRBg8WBikCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:50:24.572256Z"},"content_sha256":"b63d77014eb2910b646d8476d487621f20facca91476c55aa0b1345e76cffaa9","schema_version":"1.0","event_id":"sha256:b63d77014eb2910b646d8476d487621f20facca91476c55aa0b1345e76cffaa9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3VKZBUIGMAHOM4ZNT4QNQ2Q2F7","target":"graph","payload":{"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"},"verdict_id":"69d8be53-25bf-49ce-b023-2ebe61463f0e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U8qa1c2iIHRYyW9KUW27emY8zZkzhW2GyDGRMNl2OrW5yRVJYf8aMUf4V5VNDRGpSvhZ4CG028M6OADolathBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:50:24.573379Z"},"content_sha256":"0fd4a0e0108254f59a9acb3b8cd6e27b582453648b9a1b70a698e6d64d6ff262","schema_version":"1.0","event_id":"sha256:0fd4a0e0108254f59a9acb3b8cd6e27b582453648b9a1b70a698e6d64d6ff262"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/bundle.json","state_url":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T17:50:24Z","links":{"resolver":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7","bundle":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/bundle.json","state":"https://pith.science/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3VKZBUIGMAHOM4ZNT4QNQ2Q2F7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3VKZBUIGMAHOM4ZNT4QNQ2Q2F7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"179520b17eb7655f708fa8cc17a2d0a7759f710681cf9166587ba099b951d8e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-10T04:53:17Z","title_canon_sha256":"c96f5bf3536a0d3e14c11ae7bba5d82215542e366aca2579cd67c8304bdd8f71"},"schema_version":"1.0","source":{"id":"2004.04906","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.04906","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2004.04906v3","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.04906","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"3VKZBUIGMAHO","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"3VKZBUIGMAHOM4ZN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"3VKZBUIG","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:0fd4a0e0108254f59a9acb3b8cd6e27b582453648b9a1b70a698e6d64d6ff262","target":"graph","created_at":"2026-05-17T23:38:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"34dcd6909a322924e26601d22cc89a2bb69a0ba33e8f2a386e0f66604458ec05"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"916c72306ca4ee458b29fbf2bcdfea177e7ae5eff4f5bf83c2cdeee0ce2dae6b"},"paper":{"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,","authors_text":"Barlas O\\u{g}uz, Danqi Chen, Ledell Wu, Patrick Lewis, Sergey Edunov, Sewon Min, Vladimir Karpukhin, Wen-tau Yih","cross_cats":[],"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.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-10T04:53:17Z","title":"Dense Passage Retrieval for Open-Domain Question Answering"},"references":{"count":113,"internal_anchors":8,"resolved_work":113,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Passage Re-ranking with","work_id":"fc2ddd97-10e7-40a7-933c-840da1cd2f01","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"2020 , booktitle =","work_id":"55e9beb5-adc8-4a04-8159-ea1fa498a605","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Relevance-guided Supervision for OpenQA with","work_id":"e109b3e7-d675-41ce-a9e1-1ef8465f9881","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"The probabilistic relevance framework:","work_id":"8fc0aab3-8cc7-4e70-9dc4-066311e5527d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Learning to Retrieve Reasoning Paths over","work_id":"e513a414-13b7-4924-8112-988c627f3aea","year":null}],"snapshot_sha256":"bcf46dcd452c8eedc2f350ab9bd78dfcfcbaa00730946212898e387189d96408"},"source":{"id":"2004.04906","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T21:21:33.779649Z","id":"69d8be53-25bf-49ce-b023-2ebe61463f0e","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"69d8be53-25bf-49ce-b023-2ebe61463f0e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b63d77014eb2910b646d8476d487621f20facca91476c55aa0b1345e76cffaa9","target":"record","created_at":"2026-05-17T23:38:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"179520b17eb7655f708fa8cc17a2d0a7759f710681cf9166587ba099b951d8e4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-10T04:53:17Z","title_canon_sha256":"c96f5bf3536a0d3e14c11ae7bba5d82215542e366aca2579cd67c8304bdd8f71"},"schema_version":"1.0","source":{"id":"2004.04906","kind":"arxiv","version":3}},"canonical_sha256":"dd5590d106600ee6732d9f20d86a1a2ff328eb0a6a0527ef2f6d502fb6f5fe89","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd5590d106600ee6732d9f20d86a1a2ff328eb0a6a0527ef2f6d502fb6f5fe89","first_computed_at":"2026-05-17T23:38:50.118168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.118168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iGwZX/TrpiD42rdA6yOprs2dFkWm8m72oeDSSQiSlwDcOuLaus0ZW1+DL/QEteF4OFNizgqpuJ+pI+lob0GACA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.118744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.04906","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b63d77014eb2910b646d8476d487621f20facca91476c55aa0b1345e76cffaa9","sha256:0fd4a0e0108254f59a9acb3b8cd6e27b582453648b9a1b70a698e6d64d6ff262"],"state_sha256":"e066a747668f7934dce7510cdfd131061b54377b6df65cd56cedeab8e8ff36c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rPMyHOPqb5OcFczbhRkTIu7k/uvvG6yCixFxyLFvkaNoC1Te/2G7WFuxZlmsgzE5e5RG9RXBiUwduhlGjvAtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:50:24.578121Z","bundle_sha256":"1843bfee57e75e968134332353c14a672f2453575c2b51967bb0ba64a3f3ac2b"}}