{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:O7WJNLUNRWNLPQMK2DGPO7GUAA","short_pith_number":"pith:O7WJNLUN","schema_version":"1.0","canonical_sha256":"77ec96ae8d8d9ab7c18ad0ccf77cd40022d9f72ed2446a890cce7245ecb8eefb","source":{"kind":"arxiv","id":"2209.01975","version":1},"attestation_state":"computed","paper":{"title":"Selective Annotation Makes Language Models Better Few-Shot Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Henry Wu, Hongjin Su, Jiayi Xin, Jungo Kasai, Luke Zettlemoyer, Mari Ostendorf, Noah A. Smith, Rui Zhang, Tao Yu, Tianlu Wang, Weijia Shi","submitted_at":"2022-09-05T14:01:15Z","abstract_excerpt":"Many recent approaches to natural language tasks are built on the remarkable abilities of large language models. Large language models can perform in-context learning, where they learn a new task from a few task demonstrations, without any parameter updates. This work examines the implications of in-context learning for the creation of datasets for new natural language tasks. Departing from recent in-context learning methods, we formulate an annotation-efficient, two-step framework: selective annotation that chooses a pool of examples to annotate from unlabeled data in advance, followed by pro"},"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":"2209.01975","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-09-05T14:01:15Z","cross_cats_sorted":[],"title_canon_sha256":"a8cc7856c10232fa438d6e758f448c605769206f1d32b73438eee7fa7226cbac","abstract_canon_sha256":"e4c9650ae0abaa454996b1dec19a3d7092b6cc410ecc0561c762fff7feb9feed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:36.404823Z","signature_b64":"BFh+XMXv/FXbHtcSHXRG6t7exhE9KF890ZRWZr11IXxJ62PdplkAJ3YldpU2cmx5lMMkDxFlCI2veZ+mjvrbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77ec96ae8d8d9ab7c18ad0ccf77cd40022d9f72ed2446a890cce7245ecb8eefb","last_reissued_at":"2026-07-05T04:54:36.404425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:36.404425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective Annotation Makes Language Models Better Few-Shot Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chen Henry Wu, Hongjin Su, Jiayi Xin, Jungo Kasai, Luke Zettlemoyer, Mari Ostendorf, Noah A. Smith, Rui Zhang, Tao Yu, Tianlu Wang, Weijia Shi","submitted_at":"2022-09-05T14:01:15Z","abstract_excerpt":"Many recent approaches to natural language tasks are built on the remarkable abilities of large language models. Large language models can perform in-context learning, where they learn a new task from a few task demonstrations, without any parameter updates. This work examines the implications of in-context learning for the creation of datasets for new natural language tasks. Departing from recent in-context learning methods, we formulate an annotation-efficient, two-step framework: selective annotation that chooses a pool of examples to annotate from unlabeled data in advance, followed by pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.01975","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/2209.01975/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":"2209.01975","created_at":"2026-07-05T04:54:36.404482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.01975v1","created_at":"2026-07-05T04:54:36.404482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.01975","created_at":"2026-07-05T04:54:36.404482+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7WJNLUNRWNL","created_at":"2026-07-05T04:54:36.404482+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7WJNLUNRWNLPQMK","created_at":"2026-07-05T04:54:36.404482+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7WJNLUN","created_at":"2026-07-05T04:54:36.404482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2210.03493","citing_title":"Automatic Chain of Thought Prompting in Large Language Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA","json":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA.json","graph_json":"https://pith.science/api/pith-number/O7WJNLUNRWNLPQMK2DGPO7GUAA/graph.json","events_json":"https://pith.science/api/pith-number/O7WJNLUNRWNLPQMK2DGPO7GUAA/events.json","paper":"https://pith.science/paper/O7WJNLUN"},"agent_actions":{"view_html":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA","download_json":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA.json","view_paper":"https://pith.science/paper/O7WJNLUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.01975&json=true","fetch_graph":"https://pith.science/api/pith-number/O7WJNLUNRWNLPQMK2DGPO7GUAA/graph.json","fetch_events":"https://pith.science/api/pith-number/O7WJNLUNRWNLPQMK2DGPO7GUAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA/action/storage_attestation","attest_author":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA/action/author_attestation","sign_citation":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA/action/citation_signature","submit_replication":"https://pith.science/pith/O7WJNLUNRWNLPQMK2DGPO7GUAA/action/replication_record"}},"created_at":"2026-07-05T04:54:36.404482+00:00","updated_at":"2026-07-05T04:54:36.404482+00:00"}