{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5ZAW5K7KCOXV6NEJDU5OF3NTTJ","short_pith_number":"pith:5ZAW5K7K","schema_version":"1.0","canonical_sha256":"ee416eabea13af5f34891d3ae2edb39a6099a9e7a58e86446cba2b380e97fede","source":{"kind":"arxiv","id":"2305.14264","version":2},"attestation_state":"computed","paper":{"title":"Active Learning Principles for In-Context Learning with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jane Dwivedi-Yu, Katerina Margatina, Nikolaos Aletras, Timo Schick","submitted_at":"2023-05-23T17:16:04Z","abstract_excerpt":"The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings. By using only a small number of labeled examples, referred to as demonstrations, LLMs can effectively grasp the task at hand through in-context learning. However, the process of selecting appropriate demonstrations has received limited attention in prior work. This paper addresses the issue of identifying the most informative demonstrations for few-shot learning by approaching it as a pool-based Active Learning (AL) problem over a single iteration. Our objectiv"},"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":"2305.14264","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:16:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"adb5699aea74760d44690c7f407bf572272650d4969b098f1b7f2b5875d4ac0d","abstract_canon_sha256":"79921572659f3d01be960a9dbdada7f0b4bb193578e58d4bd085b80160ef5620"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:15:14.331123Z","signature_b64":"Q0IexFdiS4sOAAiC8VEariqsqelleomFHHIyr9aocFcJkOoa/Nkb4TcfbRCHdkckPDXyRZbLu5iRclc/5e2DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee416eabea13af5f34891d3ae2edb39a6099a9e7a58e86446cba2b380e97fede","last_reissued_at":"2026-07-05T07:15:14.330649Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:15:14.330649Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Learning Principles for In-Context Learning with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jane Dwivedi-Yu, Katerina Margatina, Nikolaos Aletras, Timo Schick","submitted_at":"2023-05-23T17:16:04Z","abstract_excerpt":"The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings. By using only a small number of labeled examples, referred to as demonstrations, LLMs can effectively grasp the task at hand through in-context learning. However, the process of selecting appropriate demonstrations has received limited attention in prior work. This paper addresses the issue of identifying the most informative demonstrations for few-shot learning by approaching it as a pool-based Active Learning (AL) problem over a single iteration. Our objectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14264","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/2305.14264/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":"2305.14264","created_at":"2026-07-05T07:15:14.330705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14264v2","created_at":"2026-07-05T07:15:14.330705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14264","created_at":"2026-07-05T07:15:14.330705+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZAW5K7KCOXV","created_at":"2026-07-05T07:15:14.330705+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZAW5K7KCOXV6NEJ","created_at":"2026-07-05T07:15:14.330705+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZAW5K7K","created_at":"2026-07-05T07:15:14.330705+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.03247","citing_title":"Towards Multimodal Active Learning: Efficient Learning with Limited Paired Data","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ","json":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ.json","graph_json":"https://pith.science/api/pith-number/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/graph.json","events_json":"https://pith.science/api/pith-number/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/events.json","paper":"https://pith.science/paper/5ZAW5K7K"},"agent_actions":{"view_html":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ","download_json":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ.json","view_paper":"https://pith.science/paper/5ZAW5K7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14264&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/action/storage_attestation","attest_author":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/action/author_attestation","sign_citation":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/action/citation_signature","submit_replication":"https://pith.science/pith/5ZAW5K7KCOXV6NEJDU5OF3NTTJ/action/replication_record"}},"created_at":"2026-07-05T07:15:14.330705+00:00","updated_at":"2026-07-05T07:15:14.330705+00:00"}