{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VD2RP63QTDHBE2VXRD2DY566UR","short_pith_number":"pith:VD2RP63Q","schema_version":"1.0","canonical_sha256":"a8f517fb7098ce126ab788f43c77dea47c4d1a8df8a96b0c5c31271580676314","source":{"kind":"arxiv","id":"2309.13205","version":1},"attestation_state":"computed","paper":{"title":"A Practical Survey on Zero-shot Prompt Design for In-context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.LG"],"primary_cat":"cs.CL","authors_text":"Yinheng Li","submitted_at":"2023-09-22T23:00:34Z","abstract_excerpt":"The remarkable advancements in large language models (LLMs) have brought about significant improvements in Natural Language Processing(NLP) tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on different types of prompts, including discrete, continuous, few-shot, and zero-shot, and their impact on LLM performance. We explore various approaches to prompt design, such as manual design, optimization algorithms, and evaluation methods, to optimize LLM performance across diverse tasks. Our review covers key research studies in prompt engineering, discussin"},"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":"2309.13205","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-22T23:00:34Z","cross_cats_sorted":["cs.AI","cs.ET","cs.LG"],"title_canon_sha256":"36de7a54c4549cf95ba716a615c9eb64a7730adab20f9f1c65072d44653014d3","abstract_canon_sha256":"2c990a29373d73e3fffe54f0ab59d43e586e7fe2b3e9da5a795246d56a48dc59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:48.656224Z","signature_b64":"L/2wZ8pz54swnRtzm1jQxCPnRtV+PkSj/xoFUoum4+uNLx1vNxEEgZXjplcBWv9wK32qXeyk0t/SlCDLnFV7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8f517fb7098ce126ab788f43c77dea47c4d1a8df8a96b0c5c31271580676314","last_reissued_at":"2026-07-05T06:53:48.655649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:48.655649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Practical Survey on Zero-shot Prompt Design for In-context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.ET","cs.LG"],"primary_cat":"cs.CL","authors_text":"Yinheng Li","submitted_at":"2023-09-22T23:00:34Z","abstract_excerpt":"The remarkable advancements in large language models (LLMs) have brought about significant improvements in Natural Language Processing(NLP) tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on different types of prompts, including discrete, continuous, few-shot, and zero-shot, and their impact on LLM performance. We explore various approaches to prompt design, such as manual design, optimization algorithms, and evaluation methods, to optimize LLM performance across diverse tasks. Our review covers key research studies in prompt engineering, discussin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13205","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/2309.13205/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":"2309.13205","created_at":"2026-07-05T06:53:48.655736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13205v1","created_at":"2026-07-05T06:53:48.655736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13205","created_at":"2026-07-05T06:53:48.655736+00:00"},{"alias_kind":"pith_short_12","alias_value":"VD2RP63QTDHB","created_at":"2026-07-05T06:53:48.655736+00:00"},{"alias_kind":"pith_short_16","alias_value":"VD2RP63QTDHBE2VX","created_at":"2026-07-05T06:53:48.655736+00:00"},{"alias_kind":"pith_short_8","alias_value":"VD2RP63Q","created_at":"2026-07-05T06:53:48.655736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07288","citing_title":"LLM-Net: Democratizing LLMs-as-a-Service through Blockchain-based Expert Networks","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR","json":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR.json","graph_json":"https://pith.science/api/pith-number/VD2RP63QTDHBE2VXRD2DY566UR/graph.json","events_json":"https://pith.science/api/pith-number/VD2RP63QTDHBE2VXRD2DY566UR/events.json","paper":"https://pith.science/paper/VD2RP63Q"},"agent_actions":{"view_html":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR","download_json":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR.json","view_paper":"https://pith.science/paper/VD2RP63Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13205&json=true","fetch_graph":"https://pith.science/api/pith-number/VD2RP63QTDHBE2VXRD2DY566UR/graph.json","fetch_events":"https://pith.science/api/pith-number/VD2RP63QTDHBE2VXRD2DY566UR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR/action/storage_attestation","attest_author":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR/action/author_attestation","sign_citation":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR/action/citation_signature","submit_replication":"https://pith.science/pith/VD2RP63QTDHBE2VXRD2DY566UR/action/replication_record"}},"created_at":"2026-07-05T06:53:48.655736+00:00","updated_at":"2026-07-05T06:53:48.655736+00:00"}