{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7SM7UZFRXF3ABBMUJZYDY7U6RZ","short_pith_number":"pith:7SM7UZFR","schema_version":"1.0","canonical_sha256":"fc99fa64b1b9760085944e703c7e9e8e6f51d471b3fbb89771a0e1feb4aba24f","source":{"kind":"arxiv","id":"2203.08773","version":1},"attestation_state":"computed","paper":{"title":"Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Michael Zeng, Ruochen Xu, Shuohang Wang, Siqi Sun, Yang Liu, Yichong Xu, Yuwei Fang","submitted_at":"2022-03-16T17:37:27Z","abstract_excerpt":"Retrieval-based methods have been shown to be effective in NLP tasks via introducing external knowledge. However, the indexing and retrieving of large-scale corpora bring considerable computational cost. Surprisingly, we found that REtrieving from the traINing datA (REINA) only can lead to significant gains on multiple NLG and NLU tasks. We retrieve the labeled training instances most similar to the input text and then concatenate them with the input to feed into the model to generate the output. Experimental results show that this simple method can achieve significantly better performance on "},"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":"2203.08773","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T17:37:27Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"15fa587b16c24753bb773dcb0cae9ef7a1b62c27d066335e8b67b0c31f670f66","abstract_canon_sha256":"b5075cf69be29387a0e77177c07474ac60c25125c00c6f3e5652f42ea71c88ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:48.774904Z","signature_b64":"uAY1/UnjWq7KAKHBQwPJl93mqKog7Om4SSq8utJNG/4iktyp00ALl4OPmHyQbttIbVGTO6V+yb3pbIBIYz0DBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc99fa64b1b9760085944e703c7e9e8e6f51d471b3fbb89771a0e1feb4aba24f","last_reissued_at":"2026-07-05T04:05:48.774436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:48.774436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Michael Zeng, Ruochen Xu, Shuohang Wang, Siqi Sun, Yang Liu, Yichong Xu, Yuwei Fang","submitted_at":"2022-03-16T17:37:27Z","abstract_excerpt":"Retrieval-based methods have been shown to be effective in NLP tasks via introducing external knowledge. However, the indexing and retrieving of large-scale corpora bring considerable computational cost. Surprisingly, we found that REtrieving from the traINing datA (REINA) only can lead to significant gains on multiple NLG and NLU tasks. We retrieve the labeled training instances most similar to the input text and then concatenate them with the input to feed into the model to generate the output. Experimental results show that this simple method can achieve significantly better performance on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08773","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/2203.08773/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":"2203.08773","created_at":"2026-07-05T04:05:48.774493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08773v1","created_at":"2026-07-05T04:05:48.774493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08773","created_at":"2026-07-05T04:05:48.774493+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SM7UZFRXF3A","created_at":"2026-07-05T04:05:48.774493+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SM7UZFRXF3ABBMU","created_at":"2026-07-05T04:05:48.774493+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SM7UZFR","created_at":"2026-07-05T04:05:48.774493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05380","citing_title":"TabPack: Efficient Hyperparameter Ensembles for Tabular Deep Learning","ref_index":99,"is_internal_anchor":true},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ","json":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ.json","graph_json":"https://pith.science/api/pith-number/7SM7UZFRXF3ABBMUJZYDY7U6RZ/graph.json","events_json":"https://pith.science/api/pith-number/7SM7UZFRXF3ABBMUJZYDY7U6RZ/events.json","paper":"https://pith.science/paper/7SM7UZFR"},"agent_actions":{"view_html":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ","download_json":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ.json","view_paper":"https://pith.science/paper/7SM7UZFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08773&json=true","fetch_graph":"https://pith.science/api/pith-number/7SM7UZFRXF3ABBMUJZYDY7U6RZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7SM7UZFRXF3ABBMUJZYDY7U6RZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ/action/storage_attestation","attest_author":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ/action/author_attestation","sign_citation":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ/action/citation_signature","submit_replication":"https://pith.science/pith/7SM7UZFRXF3ABBMUJZYDY7U6RZ/action/replication_record"}},"created_at":"2026-07-05T04:05:48.774493+00:00","updated_at":"2026-07-05T04:05:48.774493+00:00"}