{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZKGOT6CKEAAAD5VYYYPU4XQCPP","short_pith_number":"pith:ZKGOT6CK","schema_version":"1.0","canonical_sha256":"ca8ce9f84a200001f6b8c61f4e5e027bc93f93b6257ddf68d45867f157a80e59","source":{"kind":"arxiv","id":"2206.08082","version":1},"attestation_state":"computed","paper":{"title":"Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hyuhng Joon Kim, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, Taeuk Kim","submitted_at":"2022-06-16T10:52:13Z","abstract_excerpt":"Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt without being explicitly tuned for the desired downstream task. Such a process (i.e., in-context learning), however, naturally leads to high reliance on the demonstrations which are usually selected from external datasets. In this paper, we propose self-generated in-context learning (SG-ICL), which generates demonstrations for in-context learning from PLM itself to minimize the reliance on the external demonstration. "},"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":"2206.08082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-16T10:52:13Z","cross_cats_sorted":[],"title_canon_sha256":"bed57efe98b8708af2f4778a40a5c58eea4e11f72f29eab13809e013d032ceac","abstract_canon_sha256":"5050c443192099c58a1dc6b42ddf31f0e93583bd3b653731c31f535d41a65667"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:22.062679Z","signature_b64":"yAqK+Whr2WRpb09R+aYgoWdpGpA6UUTCmPY1k3yNkpP7Eu46HvMGnwObs8WYqOhUsuyl1ewBMWJmU0smVhGkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca8ce9f84a200001f6b8c61f4e5e027bc93f93b6257ddf68d45867f157a80e59","last_reissued_at":"2026-07-05T04:32:22.062143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:22.062143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hyuhng Joon Kim, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, Taeuk Kim","submitted_at":"2022-06-16T10:52:13Z","abstract_excerpt":"Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt without being explicitly tuned for the desired downstream task. Such a process (i.e., in-context learning), however, naturally leads to high reliance on the demonstrations which are usually selected from external datasets. In this paper, we propose self-generated in-context learning (SG-ICL), which generates demonstrations for in-context learning from PLM itself to minimize the reliance on the external demonstration. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08082","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/2206.08082/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":"2206.08082","created_at":"2026-07-05T04:32:22.062209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08082v1","created_at":"2026-07-05T04:32:22.062209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08082","created_at":"2026-07-05T04:32:22.062209+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKGOT6CKEAAA","created_at":"2026-07-05T04:32:22.062209+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKGOT6CKEAAAD5VY","created_at":"2026-07-05T04:32:22.062209+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKGOT6CK","created_at":"2026-07-05T04:32:22.062209+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23180","citing_title":"Self-Improving In-Context Learning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14197","citing_title":"The PICCO Framework for Large Language Model Prompting: A Taxonomy and Reference Architecture for Prompt Structure","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05533","citing_title":"Experience Transfer for Multimodal LLM Agents in Minecraft Game","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP","json":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP.json","graph_json":"https://pith.science/api/pith-number/ZKGOT6CKEAAAD5VYYYPU4XQCPP/graph.json","events_json":"https://pith.science/api/pith-number/ZKGOT6CKEAAAD5VYYYPU4XQCPP/events.json","paper":"https://pith.science/paper/ZKGOT6CK"},"agent_actions":{"view_html":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP","download_json":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP.json","view_paper":"https://pith.science/paper/ZKGOT6CK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08082&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKGOT6CKEAAAD5VYYYPU4XQCPP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKGOT6CKEAAAD5VYYYPU4XQCPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP/action/storage_attestation","attest_author":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP/action/author_attestation","sign_citation":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP/action/citation_signature","submit_replication":"https://pith.science/pith/ZKGOT6CKEAAAD5VYYYPU4XQCPP/action/replication_record"}},"created_at":"2026-07-05T04:32:22.062209+00:00","updated_at":"2026-07-05T04:32:22.062209+00:00"}