{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CUQ7RMUZFQMQDQGCVWOYPAYSZS","short_pith_number":"pith:CUQ7RMUZ","schema_version":"1.0","canonical_sha256":"1521f8b2992c1901c0c2ad9d878312ccbb2b320788aa91ad1e4449bac23b590b","source":{"kind":"arxiv","id":"2212.09865","version":2},"attestation_state":"computed","paper":{"title":"Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Iz Beltagy, Luke Zettlemoyer, Sewon Min, Xinxi Lyu","submitted_at":"2022-12-19T21:34:26Z","abstract_excerpt":"Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new zero-shot method that closes the gap by constructing pseudo-demonstrations for a given test input using a raw text corpus. Concretely, pseudo-demonstrations are constructed by (1) finding the nearest neighbors to the test input from the corpus and pairing them with random task labels, and (2) applying a set of techniques to reduce the amount of direct copying the model does from the resulting demonstr"},"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":"2212.09865","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-19T21:34:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3604749a09d39a69c6a69e58cf83df0aa7fa19d163396075dbb8895a5522c532","abstract_canon_sha256":"54ec17d4fcccd5369fe3a3b82cc834a5c47857a5448046f7a9f8ea0736e1be15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:03.508972Z","signature_b64":"uCSMbS+FQGhL78QH2dTmx1utbih3MgVGjcOA4OG28B3Nyp/HNBJiEHe554CvcsxEzjZ1lZSLuBptM0e+dd1xAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1521f8b2992c1901c0c2ad9d878312ccbb2b320788aa91ad1e4449bac23b590b","last_reissued_at":"2026-07-05T06:17:03.508565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:03.508565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Iz Beltagy, Luke Zettlemoyer, Sewon Min, Xinxi Lyu","submitted_at":"2022-12-19T21:34:26Z","abstract_excerpt":"Although large language models can be prompted for both zero- and few-shot learning, performance drops significantly when no demonstrations are available. In this paper, we introduce Z-ICL, a new zero-shot method that closes the gap by constructing pseudo-demonstrations for a given test input using a raw text corpus. Concretely, pseudo-demonstrations are constructed by (1) finding the nearest neighbors to the test input from the corpus and pairing them with random task labels, and (2) applying a set of techniques to reduce the amount of direct copying the model does from the resulting demonstr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.09865","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/2212.09865/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":"2212.09865","created_at":"2026-07-05T06:17:03.508619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.09865v2","created_at":"2026-07-05T06:17:03.508619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.09865","created_at":"2026-07-05T06:17:03.508619+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUQ7RMUZFQMQ","created_at":"2026-07-05T06:17:03.508619+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUQ7RMUZFQMQDQGC","created_at":"2026-07-05T06:17:03.508619+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUQ7RMUZ","created_at":"2026-07-05T06:17:03.508619+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/CUQ7RMUZFQMQDQGCVWOYPAYSZS","json":"https://pith.science/pith/CUQ7RMUZFQMQDQGCVWOYPAYSZS.json","graph_json":"https://pith.science/api/pith-number/CUQ7RMUZFQMQDQGCVWOYPAYSZS/graph.json","events_json":"https://pith.science/api/pith-number/CUQ7RMUZFQMQDQGCVWOYPAYSZS/events.json","paper":"https://pith.science/paper/CUQ7RMUZ"},"agent_actions":{"view_html":"https://pith.science/pith/CUQ7RMUZFQMQDQGCVWOYPAYSZS","download_json":"https://pith.science/pith/CUQ7RMUZFQMQDQGCVWOYPAYSZS.json","view_paper":"https://pith.science/paper/CUQ7RMUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.09865&json=true","fetch_graph":"https://pith.science/api/pith-number/CUQ7RMUZFQMQDQGCVWOYPAYSZS/graph.json","fetch_events":"https://pith.science/api/pith-number/CUQ7RMUZFQMQDQGCVWOYPAYSZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUQ7RMUZFQMQDQGCVWOYPAYSZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUQ7RMUZFQMQDQGCVWOYPAYSZS/action/storage_attestation","attest_author":"https://pith.science/pith/CUQ7RMUZFQMQDQGCVWOYPAYSZS/action/author_attestation","sign_citation":"https://pith.science/pith/CUQ7RMUZFQMQDQGCVWOYPAYSZS/action/citation_signature","submit_replication":"https://pith.science/pith/CUQ7RMUZFQMQDQGCVWOYPAYSZS/action/replication_record"}},"created_at":"2026-07-05T06:17:03.508619+00:00","updated_at":"2026-07-05T06:17:03.508619+00:00"}