{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VWT6467TSOYI6Z6PL2SWHD7FMA","short_pith_number":"pith:VWT6467T","schema_version":"1.0","canonical_sha256":"ada7ee7bf393b08f67cf5ea5638fe5603114d3fd984627866a3e69d144594cf3","source":{"kind":"arxiv","id":"2305.11170","version":1},"attestation_state":"computed","paper":{"title":"Efficient Prompting via Dynamic In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mrinmaya Sachan, Ryan Cotterell, Wangchunshu Zhou, Yuchen Eleanor Jiang","submitted_at":"2023-05-18T17:58:31Z","abstract_excerpt":"The primary way of building AI applications is shifting from training specialist models to prompting generalist models. A common practice for prompting generalist models, often referred to as in-context learning, is to append a few examples (demonstrations) to the prompt to help the model better understand the task. While effective, in-context learning can be inefficient because it makes the input prompt much longer, consuming valuable space in the context window and leading to larger computational costs. In this paper, we propose DynaICL, a recipe for efficient prompting with black-box genera"},"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":"2305.11170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T17:58:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"01da0d36567b3780141253eb2272ddb33f391076c7bc0e6bd9f2a2e3c8d8d982","abstract_canon_sha256":"1d21634200ba2e160af6fa9c661e516dd8514ab6e25f356ac3180e0b4eb19510"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:31.046288Z","signature_b64":"/xSns5KlLOqPPcXPgeAW8uvGlqKoiWwBD8wYL19iNwjKdtU7AKSp+DV6/Tzcop7H6ppYEc+5igcFv/Fe4BXWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ada7ee7bf393b08f67cf5ea5638fe5603114d3fd984627866a3e69d144594cf3","last_reissued_at":"2026-07-05T06:11:31.045809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:31.045809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Prompting via Dynamic In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mrinmaya Sachan, Ryan Cotterell, Wangchunshu Zhou, Yuchen Eleanor Jiang","submitted_at":"2023-05-18T17:58:31Z","abstract_excerpt":"The primary way of building AI applications is shifting from training specialist models to prompting generalist models. A common practice for prompting generalist models, often referred to as in-context learning, is to append a few examples (demonstrations) to the prompt to help the model better understand the task. While effective, in-context learning can be inefficient because it makes the input prompt much longer, consuming valuable space in the context window and leading to larger computational costs. In this paper, we propose DynaICL, a recipe for efficient prompting with black-box genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11170","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/2305.11170/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":"2305.11170","created_at":"2026-07-05T06:11:31.045866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11170v1","created_at":"2026-07-05T06:11:31.045866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11170","created_at":"2026-07-05T06:11:31.045866+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWT6467TSOYI","created_at":"2026-07-05T06:11:31.045866+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWT6467TSOYI6Z6P","created_at":"2026-07-05T06:11:31.045866+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWT6467T","created_at":"2026-07-05T06:11:31.045866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA","json":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA.json","graph_json":"https://pith.science/api/pith-number/VWT6467TSOYI6Z6PL2SWHD7FMA/graph.json","events_json":"https://pith.science/api/pith-number/VWT6467TSOYI6Z6PL2SWHD7FMA/events.json","paper":"https://pith.science/paper/VWT6467T"},"agent_actions":{"view_html":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA","download_json":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA.json","view_paper":"https://pith.science/paper/VWT6467T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11170&json=true","fetch_graph":"https://pith.science/api/pith-number/VWT6467TSOYI6Z6PL2SWHD7FMA/graph.json","fetch_events":"https://pith.science/api/pith-number/VWT6467TSOYI6Z6PL2SWHD7FMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA/action/storage_attestation","attest_author":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA/action/author_attestation","sign_citation":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA/action/citation_signature","submit_replication":"https://pith.science/pith/VWT6467TSOYI6Z6PL2SWHD7FMA/action/replication_record"}},"created_at":"2026-07-05T06:11:31.045866+00:00","updated_at":"2026-07-05T06:11:31.045866+00:00"}