{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TZNH2GXLGHZC6TYVNYOXNL4OFW","short_pith_number":"pith:TZNH2GXL","schema_version":"1.0","canonical_sha256":"9e5a7d1aeb31f22f4f156e1d76af8e2db80f782cd48c44e2d387d669020a1667","source":{"kind":"arxiv","id":"2411.02830","version":1},"attestation_state":"computed","paper":{"title":"Mixtures of In-Context Learners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Edoardo Ponti, Emile van Krieken, Giwon Hong, Nikolay Malkin, Pasquale Minervini","submitted_at":"2024-11-05T06:02:41Z","abstract_excerpt":"In-context learning (ICL) adapts LLMs by providing demonstrations without fine-tuning the model parameters; however, it does not differentiate between demonstrations and quadratically increases the complexity of Transformer LLMs, exhausting the memory. As a solution, we propose Mixtures of In-Context Learners (MoICL), a novel approach to treat subsets of demonstrations as experts and learn a weighting function to merge their output distributions based on a training set. In our experiments, we show performance improvements on 5 out of 7 classification datasets compared to a set of strong baseli"},"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":"2411.02830","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-05T06:02:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d68f886e76dd125382e1a927e57fac4985ffdfe572087301975924bd0b952d49","abstract_canon_sha256":"99f92cab7a74a8b2d9df13ef5ac4f5bafaebc8280d408c12165259d4344d06cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:18.840922Z","signature_b64":"lSzoZSrcxy6xSo2ib7DhQnbvqKSX0R8jVxXDq8fLi8aydbnIpCAaes1QC9eczm+vexvRR9DwEcfvZOyZ/zgxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e5a7d1aeb31f22f4f156e1d76af8e2db80f782cd48c44e2d387d669020a1667","last_reissued_at":"2026-07-05T09:31:18.840436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:18.840436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mixtures of In-Context Learners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Edoardo Ponti, Emile van Krieken, Giwon Hong, Nikolay Malkin, Pasquale Minervini","submitted_at":"2024-11-05T06:02:41Z","abstract_excerpt":"In-context learning (ICL) adapts LLMs by providing demonstrations without fine-tuning the model parameters; however, it does not differentiate between demonstrations and quadratically increases the complexity of Transformer LLMs, exhausting the memory. As a solution, we propose Mixtures of In-Context Learners (MoICL), a novel approach to treat subsets of demonstrations as experts and learn a weighting function to merge their output distributions based on a training set. In our experiments, we show performance improvements on 5 out of 7 classification datasets compared to a set of strong baseli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02830","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/2411.02830/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":"2411.02830","created_at":"2026-07-05T09:31:18.840496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02830v1","created_at":"2026-07-05T09:31:18.840496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02830","created_at":"2026-07-05T09:31:18.840496+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZNH2GXLGHZC","created_at":"2026-07-05T09:31:18.840496+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZNH2GXLGHZC6TYV","created_at":"2026-07-05T09:31:18.840496+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZNH2GXL","created_at":"2026-07-05T09:31:18.840496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW","json":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW.json","graph_json":"https://pith.science/api/pith-number/TZNH2GXLGHZC6TYVNYOXNL4OFW/graph.json","events_json":"https://pith.science/api/pith-number/TZNH2GXLGHZC6TYVNYOXNL4OFW/events.json","paper":"https://pith.science/paper/TZNH2GXL"},"agent_actions":{"view_html":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW","download_json":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW.json","view_paper":"https://pith.science/paper/TZNH2GXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02830&json=true","fetch_graph":"https://pith.science/api/pith-number/TZNH2GXLGHZC6TYVNYOXNL4OFW/graph.json","fetch_events":"https://pith.science/api/pith-number/TZNH2GXLGHZC6TYVNYOXNL4OFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW/action/storage_attestation","attest_author":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW/action/author_attestation","sign_citation":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW/action/citation_signature","submit_replication":"https://pith.science/pith/TZNH2GXLGHZC6TYVNYOXNL4OFW/action/replication_record"}},"created_at":"2026-07-05T09:31:18.840496+00:00","updated_at":"2026-07-05T09:31:18.840496+00:00"}