{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:756H32HFZAM2634P6N553XN3PB","short_pith_number":"pith:756H32HF","schema_version":"1.0","canonical_sha256":"ff7c7de8e5c819af6f8ff37bddddbb7879eccfbd0b8aaba3355a9ffc60a480ba","source":{"kind":"arxiv","id":"2212.10375","version":2},"attestation_state":"computed","paper":{"title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiacheng Ye, Lingpeng Kong, Yaoxiang Wang, Zhiyong Wu","submitted_at":"2022-12-20T15:55:21Z","abstract_excerpt":"Despite the surprising few-shot performance of in-context learning (ICL), it is still a common practice to randomly sample examples to serve as context. This paper advocates a new principle for ICL: self-adaptive in-context learning. The self-adaption mechanism is introduced to help each sample find an in-context example permutation (i.e., selection and ordering) that can derive the correct prediction, thus maximizing performance. To validate the effectiveness of self-adaptive ICL, we propose a general select-then-rank framework and instantiate it with new selection and ranking algorithms. Upo"},"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":"2212.10375","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T15:55:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff76a7eb8b9529cfc25ebb203f6be8efc015a4b91c2e7a0073f1a198645778a9","abstract_canon_sha256":"05c0054ae843b53b9b7afd37262aa3974bfb2535acf28f05af1e34d7f7d49016"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:06:42.458442Z","signature_b64":"XXa3tznHCNpfIg1xA3YAgLuDnhQGtuwL27/Xnbl+3a0M0xIzJdW1Juz85kg+Bg/jGji/klPFDEQ2jLQDpz54Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff7c7de8e5c819af6f8ff37bddddbb7879eccfbd0b8aaba3355a9ffc60a480ba","last_reissued_at":"2026-07-05T06:06:42.457940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:06:42.457940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiacheng Ye, Lingpeng Kong, Yaoxiang Wang, Zhiyong Wu","submitted_at":"2022-12-20T15:55:21Z","abstract_excerpt":"Despite the surprising few-shot performance of in-context learning (ICL), it is still a common practice to randomly sample examples to serve as context. This paper advocates a new principle for ICL: self-adaptive in-context learning. The self-adaption mechanism is introduced to help each sample find an in-context example permutation (i.e., selection and ordering) that can derive the correct prediction, thus maximizing performance. To validate the effectiveness of self-adaptive ICL, we propose a general select-then-rank framework and instantiate it with new selection and ranking algorithms. Upo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10375","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/2212.10375/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":"2212.10375","created_at":"2026-07-05T06:06:42.458000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10375v2","created_at":"2026-07-05T06:06:42.458000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10375","created_at":"2026-07-05T06:06:42.458000+00:00"},{"alias_kind":"pith_short_12","alias_value":"756H32HFZAM2","created_at":"2026-07-05T06:06:42.458000+00:00"},{"alias_kind":"pith_short_16","alias_value":"756H32HFZAM2634P","created_at":"2026-07-05T06:06:42.458000+00:00"},{"alias_kind":"pith_short_8","alias_value":"756H32HF","created_at":"2026-07-05T06:06:42.458000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB","json":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB.json","graph_json":"https://pith.science/api/pith-number/756H32HFZAM2634P6N553XN3PB/graph.json","events_json":"https://pith.science/api/pith-number/756H32HFZAM2634P6N553XN3PB/events.json","paper":"https://pith.science/paper/756H32HF"},"agent_actions":{"view_html":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB","download_json":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB.json","view_paper":"https://pith.science/paper/756H32HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10375&json=true","fetch_graph":"https://pith.science/api/pith-number/756H32HFZAM2634P6N553XN3PB/graph.json","fetch_events":"https://pith.science/api/pith-number/756H32HFZAM2634P6N553XN3PB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB/action/storage_attestation","attest_author":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB/action/author_attestation","sign_citation":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB/action/citation_signature","submit_replication":"https://pith.science/pith/756H32HFZAM2634P6N553XN3PB/action/replication_record"}},"created_at":"2026-07-05T06:06:42.458000+00:00","updated_at":"2026-07-05T06:06:42.458000+00:00"}