{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2XESC6B7U572AA4T6K73H6OBTU","short_pith_number":"pith:2XESC6B7","schema_version":"1.0","canonical_sha256":"d5c921783fa77fa00393f2bfb3f9c19d3b408567f8da1f690543dad092a2f380","source":{"kind":"arxiv","id":"2202.01110","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Retrieval-Augmented Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deng Cai, Huayang Li, Lemao Liu, Yan Wang, Yixuan Su","submitted_at":"2022-02-02T16:18:41Z","abstract_excerpt":"Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and particularly has achieved state-of-the-art performance in many NLP tasks. This paper aims to conduct a survey about retrieval-augmented text generation. It firstly highlights the generic paradigm of retrieval-augmented generation, and then it reviews notable approaches according to different tasks including dialogue response generation, machine translation, and oth"},"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":"2202.01110","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-02T16:18:41Z","cross_cats_sorted":[],"title_canon_sha256":"60002e2cdd9b8742a7947b9045e04c5ebd876b933d05889fd9b71fd8121e3c79","abstract_canon_sha256":"d85225788f90b3ec8142b29deb8d4b05a0ee3844838fa38e4cb867b2339836d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:34.293990Z","signature_b64":"f0DYv8Qi/+TmAIXcJG+aI3gkOWaJIFn0McezCEjeO7rLIuKpIWg4+S22Zb7TkxK4A83BrgWqPms+xWhAkS4ZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5c921783fa77fa00393f2bfb3f9c19d3b408567f8da1f690543dad092a2f380","last_reissued_at":"2026-07-05T03:56:34.293502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:34.293502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Retrieval-Augmented Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deng Cai, Huayang Li, Lemao Liu, Yan Wang, Yixuan Su","submitted_at":"2022-02-02T16:18:41Z","abstract_excerpt":"Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-augmented text generation has remarkable advantages and particularly has achieved state-of-the-art performance in many NLP tasks. This paper aims to conduct a survey about retrieval-augmented text generation. It firstly highlights the generic paradigm of retrieval-augmented generation, and then it reviews notable approaches according to different tasks including dialogue response generation, machine translation, and oth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01110","kind":"arxiv","version":2},"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/2202.01110/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":"2202.01110","created_at":"2026-07-05T03:56:34.293566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01110v2","created_at":"2026-07-05T03:56:34.293566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01110","created_at":"2026-07-05T03:56:34.293566+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XESC6B7U572","created_at":"2026-07-05T03:56:34.293566+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XESC6B7U572AA4T","created_at":"2026-07-05T03:56:34.293566+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XESC6B7","created_at":"2026-07-05T03:56:34.293566+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.10981","citing_title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13193","citing_title":"Retrieval-Augmented Generation for Natural Language Processing: A Survey","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2411.08249","citing_title":"Retrieval Augmented Time Series Forecasting","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25401","citing_title":"DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2303.09014","citing_title":"ART: Automatic multi-step reasoning and tool-use for large language models","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15884","citing_title":"Corrective Retrieval Augmented Generation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU","json":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU.json","graph_json":"https://pith.science/api/pith-number/2XESC6B7U572AA4T6K73H6OBTU/graph.json","events_json":"https://pith.science/api/pith-number/2XESC6B7U572AA4T6K73H6OBTU/events.json","paper":"https://pith.science/paper/2XESC6B7"},"agent_actions":{"view_html":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU","download_json":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU.json","view_paper":"https://pith.science/paper/2XESC6B7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01110&json=true","fetch_graph":"https://pith.science/api/pith-number/2XESC6B7U572AA4T6K73H6OBTU/graph.json","fetch_events":"https://pith.science/api/pith-number/2XESC6B7U572AA4T6K73H6OBTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU/action/storage_attestation","attest_author":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU/action/author_attestation","sign_citation":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU/action/citation_signature","submit_replication":"https://pith.science/pith/2XESC6B7U572AA4T6K73H6OBTU/action/replication_record"}},"created_at":"2026-07-05T03:56:34.293566+00:00","updated_at":"2026-07-05T03:56:34.293566+00:00"}