{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BF353SZEXG6UFK5LJIKCJ3F24U","short_pith_number":"pith:BF353SZE","schema_version":"1.0","canonical_sha256":"0977ddcb24b9bd42abab4a1424ecbae530ea1abae6470bd9ac5e16554ca648e4","source":{"kind":"arxiv","id":"2212.10670","version":1},"attestation_state":"computed","paper":{"title":"In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kathleen McKeown, Yanda Chen, Yukun Huang, Zhou Yu","submitted_at":"2022-12-20T22:11:35Z","abstract_excerpt":"Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine in-context learning objectives with language modeling objectives to distill both the ability to read in-context examples and task knowledge to the smaller models. We perform in-context learning distillation under two different few-shot learning paradigms: Meta In-context Tuning (Meta-ICT) and Multitask In-context Tuning (Multitask-ICT). Multitask-ICT performs bet"},"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":"2212.10670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T22:11:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2f6bf1ab91c8622f607312e83707f42e791ad2efb77b2565445bd0dc020d0d0f","abstract_canon_sha256":"b56818ccca164faf459ad358cf43385388f6dbe1e0504e71a70dce8fc5d957c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:10.568099Z","signature_b64":"sN8lIe0rFj2LuEyTzv3qbDSbt+cZ2gcQB4JQCpzafyhNjZzwNK8ge2psj6gYRmb6aMjFZxvBKQk6JeLvp22OCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0977ddcb24b9bd42abab4a1424ecbae530ea1abae6470bd9ac5e16554ca648e4","last_reissued_at":"2026-07-05T05:27:10.567690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:10.567690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Kathleen McKeown, Yanda Chen, Yukun Huang, Zhou Yu","submitted_at":"2022-12-20T22:11:35Z","abstract_excerpt":"Given the success with in-context learning of large pre-trained language models, we introduce in-context learning distillation to transfer in-context few-shot learning ability from large models to smaller models. We propose to combine in-context learning objectives with language modeling objectives to distill both the ability to read in-context examples and task knowledge to the smaller models. We perform in-context learning distillation under two different few-shot learning paradigms: Meta In-context Tuning (Meta-ICT) and Multitask In-context Tuning (Multitask-ICT). Multitask-ICT performs bet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10670","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/2212.10670/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":"2212.10670","created_at":"2026-07-05T05:27:10.567747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10670v1","created_at":"2026-07-05T05:27:10.567747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10670","created_at":"2026-07-05T05:27:10.567747+00:00"},{"alias_kind":"pith_short_12","alias_value":"BF353SZEXG6U","created_at":"2026-07-05T05:27:10.567747+00:00"},{"alias_kind":"pith_short_16","alias_value":"BF353SZEXG6UFK5L","created_at":"2026-07-05T05:27:10.567747+00:00"},{"alias_kind":"pith_short_8","alias_value":"BF353SZE","created_at":"2026-07-05T05:27:10.567747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17497","citing_title":"Self-Supervised On-Policy Distillation for Reasoning Language Models","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08842","citing_title":"XPERT: Expert Knowledge Transfer for Effective Training of Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07783","citing_title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07941","citing_title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26573","citing_title":"PAINT: Partial-Solution Adaptive Interpolated Training for Self-Distilled Reasoners","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U","json":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U.json","graph_json":"https://pith.science/api/pith-number/BF353SZEXG6UFK5LJIKCJ3F24U/graph.json","events_json":"https://pith.science/api/pith-number/BF353SZEXG6UFK5LJIKCJ3F24U/events.json","paper":"https://pith.science/paper/BF353SZE"},"agent_actions":{"view_html":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U","download_json":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U.json","view_paper":"https://pith.science/paper/BF353SZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10670&json=true","fetch_graph":"https://pith.science/api/pith-number/BF353SZEXG6UFK5LJIKCJ3F24U/graph.json","fetch_events":"https://pith.science/api/pith-number/BF353SZEXG6UFK5LJIKCJ3F24U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U/action/storage_attestation","attest_author":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U/action/author_attestation","sign_citation":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U/action/citation_signature","submit_replication":"https://pith.science/pith/BF353SZEXG6UFK5LJIKCJ3F24U/action/replication_record"}},"created_at":"2026-07-05T05:27:10.567747+00:00","updated_at":"2026-07-05T05:27:10.567747+00:00"}