{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:H6ZBTEASHDQD5SUHCMZZWJSZHV","short_pith_number":"pith:H6ZBTEAS","schema_version":"1.0","canonical_sha256":"3fb219901238e03eca8713339b26593d603b9f0a5b63e7dc5d4a12f32a236379","source":{"kind":"arxiv","id":"2206.10658","version":4},"attestation_state":"computed","paper":{"title":"Questions Are All You Need to Train a Dense Passage Retriever","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Devendra Singh Sachan, Joelle Pineau, Luke Zettlemoyer, Manzil Zaheer, Mike Lewis","submitted_at":"2022-06-21T18:16:31Z","abstract_excerpt":"We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where state-of-the-art methods typically require large supervised datasets with custom hard-negative mining and denoising of positive examples. ART, in contrast, only requires access to unpaired inputs and outputs (e.g. questions and potential answer documents). It uses a new document-retrieval autoencoding scheme, where (1) an input question is used to retrieve a set of evi"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.10658","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T18:16:31Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"d271fe842adc5ff2a854783e6e8c2d1097e55a7eed7fea797f70ad9f3999926f","abstract_canon_sha256":"c91b49bd252655e7f4fbd8c469d51e312e2fc02a91e80b1a3c057bda41d86b1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:11.779032Z","signature_b64":"Fey/+/J7j92SC7WNuy9srvUSo51Is+pHG7iTH6tTVBBea4Wb92eg9R+67gsoS4rtyR2Gkrh94g5BK1xxYEgcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fb219901238e03eca8713339b26593d603b9f0a5b63e7dc5d4a12f32a236379","last_reissued_at":"2026-07-05T05:57:11.778496Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:11.778496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Questions Are All You Need to Train a Dense Passage Retriever","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Devendra Singh Sachan, Joelle Pineau, Luke Zettlemoyer, Manzil Zaheer, Mike Lewis","submitted_at":"2022-06-21T18:16:31Z","abstract_excerpt":"We introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, such as Open QA, where state-of-the-art methods typically require large supervised datasets with custom hard-negative mining and denoising of positive examples. ART, in contrast, only requires access to unpaired inputs and outputs (e.g. questions and potential answer documents). It uses a new document-retrieval autoencoding scheme, where (1) an input question is used to retrieve a set of evi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10658","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.10658/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2206.10658","created_at":"2026-07-05T05:57:11.778567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.10658v4","created_at":"2026-07-05T05:57:11.778567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10658","created_at":"2026-07-05T05:57:11.778567+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6ZBTEASHDQD","created_at":"2026-07-05T05:57:11.778567+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6ZBTEASHDQD5SUH","created_at":"2026-07-05T05:57:11.778567+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6ZBTEAS","created_at":"2026-07-05T05:57:11.778567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV","json":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV.json","graph_json":"https://pith.science/api/pith-number/H6ZBTEASHDQD5SUHCMZZWJSZHV/graph.json","events_json":"https://pith.science/api/pith-number/H6ZBTEASHDQD5SUHCMZZWJSZHV/events.json","paper":"https://pith.science/paper/H6ZBTEAS"},"agent_actions":{"view_html":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV","download_json":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV.json","view_paper":"https://pith.science/paper/H6ZBTEAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.10658&json=true","fetch_graph":"https://pith.science/api/pith-number/H6ZBTEASHDQD5SUHCMZZWJSZHV/graph.json","fetch_events":"https://pith.science/api/pith-number/H6ZBTEASHDQD5SUHCMZZWJSZHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV/action/storage_attestation","attest_author":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV/action/author_attestation","sign_citation":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV/action/citation_signature","submit_replication":"https://pith.science/pith/H6ZBTEASHDQD5SUHCMZZWJSZHV/action/replication_record"}},"created_at":"2026-07-05T05:57:11.778567+00:00","updated_at":"2026-07-05T05:57:11.778567+00:00"}