{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3GUEYWU2IUY3H2BX6VMDHCJW6J","short_pith_number":"pith:3GUEYWU2","schema_version":"1.0","canonical_sha256":"d9a84c5a9a4531b3e837f558338936f242e80a13b9a3870bb4770cd9da65b24d","source":{"kind":"arxiv","id":"2310.03331","version":1},"attestation_state":"computed","paper":{"title":"Fine-tune Language Models to Approximate Unbiased In-context Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chiwun Yang, Timothy Chu, Zhao Song","submitted_at":"2023-10-05T06:16:01Z","abstract_excerpt":"In-context learning (ICL) is an astonishing emergent ability of large language models (LLMs). By presenting a prompt that includes multiple input-output pairs as examples and introducing a new query input, models can generate the corresponding output. However, the performance of models heavily relies on the quality of the input prompt when implementing in-context learning. Biased or imbalanced input prompts can significantly degrade the performance of language models. To address this issue, we introduce a reweighted algorithm called RICL (Reweighted In-context Learning). This algorithm fine-tu"},"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":"2310.03331","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T06:16:01Z","cross_cats_sorted":[],"title_canon_sha256":"6925a0d08c2e17211a46132d89be672f95fea94920dfd51ae8788d8947788d9e","abstract_canon_sha256":"c7faa03fd3466c0d170e2572a06c10422647c74df747270f2ef128ad8b9a74de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:31.800193Z","signature_b64":"9C45uWWJ8DzKdcmkMSY4bDqUqfT1yFEl5gIUz7E0znv8p47HNEr8cj6GibNbFBNDjbH3Li8cu+iaGts6/fDiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9a84c5a9a4531b3e837f558338936f242e80a13b9a3870bb4770cd9da65b24d","last_reissued_at":"2026-07-05T06:57:31.799754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:31.799754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tune Language Models to Approximate Unbiased In-context Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chiwun Yang, Timothy Chu, Zhao Song","submitted_at":"2023-10-05T06:16:01Z","abstract_excerpt":"In-context learning (ICL) is an astonishing emergent ability of large language models (LLMs). By presenting a prompt that includes multiple input-output pairs as examples and introducing a new query input, models can generate the corresponding output. However, the performance of models heavily relies on the quality of the input prompt when implementing in-context learning. Biased or imbalanced input prompts can significantly degrade the performance of language models. To address this issue, we introduce a reweighted algorithm called RICL (Reweighted In-context Learning). This algorithm fine-tu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03331","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/2310.03331/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":"2310.03331","created_at":"2026-07-05T06:57:31.799810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03331v1","created_at":"2026-07-05T06:57:31.799810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03331","created_at":"2026-07-05T06:57:31.799810+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GUEYWU2IUY3","created_at":"2026-07-05T06:57:31.799810+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GUEYWU2IUY3H2BX","created_at":"2026-07-05T06:57:31.799810+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GUEYWU2","created_at":"2026-07-05T06:57:31.799810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2306.14048","citing_title":"H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J","json":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J.json","graph_json":"https://pith.science/api/pith-number/3GUEYWU2IUY3H2BX6VMDHCJW6J/graph.json","events_json":"https://pith.science/api/pith-number/3GUEYWU2IUY3H2BX6VMDHCJW6J/events.json","paper":"https://pith.science/paper/3GUEYWU2"},"agent_actions":{"view_html":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J","download_json":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J.json","view_paper":"https://pith.science/paper/3GUEYWU2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03331&json=true","fetch_graph":"https://pith.science/api/pith-number/3GUEYWU2IUY3H2BX6VMDHCJW6J/graph.json","fetch_events":"https://pith.science/api/pith-number/3GUEYWU2IUY3H2BX6VMDHCJW6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J/action/storage_attestation","attest_author":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J/action/author_attestation","sign_citation":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J/action/citation_signature","submit_replication":"https://pith.science/pith/3GUEYWU2IUY3H2BX6VMDHCJW6J/action/replication_record"}},"created_at":"2026-07-05T06:57:31.799810+00:00","updated_at":"2026-07-05T06:57:31.799810+00:00"}