{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4PW27FXWXLTZ5LJVBYTLKU4DAT","short_pith_number":"pith:4PW27FXW","schema_version":"1.0","canonical_sha256":"e3edaf96f6bae79ead350e26b5538304cd25aa0d24aba18532634c58e0578e77","source":{"kind":"arxiv","id":"2208.03197","version":1},"attestation_state":"computed","paper":{"title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adri\\`a de Gispert, Bill Byrne, Gianni Barlacchi, Marco Del Tredici, Svitlana Vakulenko, Xiaoyu Shen","submitted_at":"2022-08-05T14:35:03Z","abstract_excerpt":"Dense retrieval (DR) approaches based on powerful pre-trained language models (PLMs) achieved significant advances and have become a key component for modern open-domain question-answering systems. However, they require large amounts of manual annotations to perform competitively, which is infeasible to scale. To address this, a growing body of research works have recently focused on improving DR performance under low-resource scenarios. These works differ in what resources they require for training and employ a diverse set of techniques. Understanding such differences is crucial for choosing "},"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":"2208.03197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-05T14:35:03Z","cross_cats_sorted":[],"title_canon_sha256":"516990178e6197c99c0c9c281656a2c6a058d73ee25246d30250a8c451eb9de0","abstract_canon_sha256":"c88773513f40777644d47c4ec18fcf2829dc5d35219385358150adbca15ef8ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:21.339101Z","signature_b64":"646X4Och5HjiVFL6PedifBVV8UuQ/7gOf+c+veEaiT9XLU8PqlZZkfB8iCD4BSzKvu3tMd6gwZfMkyVMVrOGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3edaf96f6bae79ead350e26b5538304cd25aa0d24aba18532634c58e0578e77","last_reissued_at":"2026-07-05T04:46:21.338645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:21.338645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adri\\`a de Gispert, Bill Byrne, Gianni Barlacchi, Marco Del Tredici, Svitlana Vakulenko, Xiaoyu Shen","submitted_at":"2022-08-05T14:35:03Z","abstract_excerpt":"Dense retrieval (DR) approaches based on powerful pre-trained language models (PLMs) achieved significant advances and have become a key component for modern open-domain question-answering systems. However, they require large amounts of manual annotations to perform competitively, which is infeasible to scale. To address this, a growing body of research works have recently focused on improving DR performance under low-resource scenarios. These works differ in what resources they require for training and employ a diverse set of techniques. Understanding such differences is crucial for choosing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.03197","kind":"arxiv","version":1},"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/2208.03197/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":"2208.03197","created_at":"2026-07-05T04:46:21.338703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.03197v1","created_at":"2026-07-05T04:46:21.338703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.03197","created_at":"2026-07-05T04:46:21.338703+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PW27FXWXLTZ","created_at":"2026-07-05T04:46:21.338703+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PW27FXWXLTZ5LJV","created_at":"2026-07-05T04:46:21.338703+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PW27FXW","created_at":"2026-07-05T04:46:21.338703+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/4PW27FXWXLTZ5LJVBYTLKU4DAT","json":"https://pith.science/pith/4PW27FXWXLTZ5LJVBYTLKU4DAT.json","graph_json":"https://pith.science/api/pith-number/4PW27FXWXLTZ5LJVBYTLKU4DAT/graph.json","events_json":"https://pith.science/api/pith-number/4PW27FXWXLTZ5LJVBYTLKU4DAT/events.json","paper":"https://pith.science/paper/4PW27FXW"},"agent_actions":{"view_html":"https://pith.science/pith/4PW27FXWXLTZ5LJVBYTLKU4DAT","download_json":"https://pith.science/pith/4PW27FXWXLTZ5LJVBYTLKU4DAT.json","view_paper":"https://pith.science/paper/4PW27FXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.03197&json=true","fetch_graph":"https://pith.science/api/pith-number/4PW27FXWXLTZ5LJVBYTLKU4DAT/graph.json","fetch_events":"https://pith.science/api/pith-number/4PW27FXWXLTZ5LJVBYTLKU4DAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PW27FXWXLTZ5LJVBYTLKU4DAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PW27FXWXLTZ5LJVBYTLKU4DAT/action/storage_attestation","attest_author":"https://pith.science/pith/4PW27FXWXLTZ5LJVBYTLKU4DAT/action/author_attestation","sign_citation":"https://pith.science/pith/4PW27FXWXLTZ5LJVBYTLKU4DAT/action/citation_signature","submit_replication":"https://pith.science/pith/4PW27FXWXLTZ5LJVBYTLKU4DAT/action/replication_record"}},"created_at":"2026-07-05T04:46:21.338703+00:00","updated_at":"2026-07-05T04:46:21.338703+00:00"}