{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ENES5S4IRMCJMNUT3KBTZ5BYBD","short_pith_number":"pith:ENES5S4I","schema_version":"1.0","canonical_sha256":"23492ecb888b04963693da833cf43808df6badd654e5d78997648ff73eae36e3","source":{"kind":"arxiv","id":"2210.17041","version":1},"attestation_state":"computed","paper":{"title":"GPS: Genetic Prompt Search for Efficient Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyu Li, Hanwei Xu, Nan Shao, Yanggang Wang, Yujun Chen, Yulun Du, Zhilin Yang","submitted_at":"2022-10-31T03:36:21Z","abstract_excerpt":"Prompt-based techniques have demostrated great potential for improving the few-shot generalization of pretrained language models. However, their performance heavily relies on the manual design of prompts and thus requires a lot of human efforts. In this paper, we introduce Genetic Prompt Search (GPS) to improve few-shot learning with prompts, which utilizes a genetic algorithm to automatically search for high-performing prompts. GPS is gradient-free and requires no update of model parameters but only a small validation set. Experiments on diverse datasets proved the effectiveness of GPS, which"},"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":"2210.17041","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T03:36:21Z","cross_cats_sorted":[],"title_canon_sha256":"a7ecbe52efd92c0a6cfd977a50c0bfd3dead36a12c3d78cca25fe66613d7762d","abstract_canon_sha256":"36090a0cb01167743a35166e6ca28ce072893ef892b8346162b8c49b6210ec19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:54.171376Z","signature_b64":"oUntVNrBHFrIzPIb5pTgo8RDqXbM6j004TFVIHLiCpOuFWW9oo5kMvs7y/yrUCpS9AuUu3BJn4oJysiqPakFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23492ecb888b04963693da833cf43808df6badd654e5d78997648ff73eae36e3","last_reissued_at":"2026-07-05T05:11:54.170886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:54.170886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GPS: Genetic Prompt Search for Efficient Few-shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyu Li, Hanwei Xu, Nan Shao, Yanggang Wang, Yujun Chen, Yulun Du, Zhilin Yang","submitted_at":"2022-10-31T03:36:21Z","abstract_excerpt":"Prompt-based techniques have demostrated great potential for improving the few-shot generalization of pretrained language models. However, their performance heavily relies on the manual design of prompts and thus requires a lot of human efforts. In this paper, we introduce Genetic Prompt Search (GPS) to improve few-shot learning with prompts, which utilizes a genetic algorithm to automatically search for high-performing prompts. GPS is gradient-free and requires no update of model parameters but only a small validation set. Experiments on diverse datasets proved the effectiveness of GPS, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17041","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/2210.17041/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":"2210.17041","created_at":"2026-07-05T05:11:54.170945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.17041v1","created_at":"2026-07-05T05:11:54.170945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17041","created_at":"2026-07-05T05:11:54.170945+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENES5S4IRMCJ","created_at":"2026-07-05T05:11:54.170945+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENES5S4IRMCJMNUT","created_at":"2026-07-05T05:11:54.170945+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENES5S4I","created_at":"2026-07-05T05:11:54.170945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22803","citing_title":"Towards Fast Domain Adaptation and Fine-Grained User Simulation for Evaluating Conversational Recommender Systems","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04661","citing_title":"CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03409","citing_title":"Large Language Models as Optimizers","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD","json":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD.json","graph_json":"https://pith.science/api/pith-number/ENES5S4IRMCJMNUT3KBTZ5BYBD/graph.json","events_json":"https://pith.science/api/pith-number/ENES5S4IRMCJMNUT3KBTZ5BYBD/events.json","paper":"https://pith.science/paper/ENES5S4I"},"agent_actions":{"view_html":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD","download_json":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD.json","view_paper":"https://pith.science/paper/ENES5S4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.17041&json=true","fetch_graph":"https://pith.science/api/pith-number/ENES5S4IRMCJMNUT3KBTZ5BYBD/graph.json","fetch_events":"https://pith.science/api/pith-number/ENES5S4IRMCJMNUT3KBTZ5BYBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD/action/storage_attestation","attest_author":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD/action/author_attestation","sign_citation":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD/action/citation_signature","submit_replication":"https://pith.science/pith/ENES5S4IRMCJMNUT3KBTZ5BYBD/action/replication_record"}},"created_at":"2026-07-05T05:11:54.170945+00:00","updated_at":"2026-07-05T05:11:54.170945+00:00"}