{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VWM3HUPWDCFKVRDNWCFJTEX36Z","short_pith_number":"pith:VWM3HUPW","schema_version":"1.0","canonical_sha256":"ad99b3d1f6188aaac46db08a9992fbf64adb8c9ad018b3b3be176e74490975ad","source":{"kind":"arxiv","id":"2405.00200","version":2},"attestation_state":"computed","paper":{"title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amanda Bertsch, Emily Xiao, Graham Neubig, Jonathan Berant, Maor Ivgi, Matthew R. Gormley, Uri Alon","submitted_at":"2024-04-30T21:06:52Z","abstract_excerpt":"As model context lengths continue to increase, the number of demonstrations that can be provided in-context approaches the size of entire training datasets. We study the behavior of in-context learning (ICL) at this extreme scale on multiple datasets and models. We show that, for many datasets with large label spaces, performance continues to increase with thousands of demonstrations. We contrast this with example retrieval and finetuning: example retrieval shows excellent performance at low context lengths but has diminished gains with more demonstrations; finetuning is more data hungry than "},"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":"2405.00200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-30T21:06:52Z","cross_cats_sorted":[],"title_canon_sha256":"27b921344bab84bba63337f1d054e8e9d0315968c271a2535ffb7a4326f2340a","abstract_canon_sha256":"9a6b8c2bf84cd4319aa892f9aea2f22e94230db29dfc271170ddf3916eb43913"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:19.374730Z","signature_b64":"JTTgctX13k0qadBQX1v/HSkuSW1lCalanWD7TLKh3QVD3guk5GoaKO+oY5yVbZdqWaxKgixcx0Yz6c42EJL7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad99b3d1f6188aaac46db08a9992fbf64adb8c9ad018b3b3be176e74490975ad","last_reissued_at":"2026-07-05T10:23:19.373730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:19.373730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning with Long-Context Models: An In-Depth Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amanda Bertsch, Emily Xiao, Graham Neubig, Jonathan Berant, Maor Ivgi, Matthew R. Gormley, Uri Alon","submitted_at":"2024-04-30T21:06:52Z","abstract_excerpt":"As model context lengths continue to increase, the number of demonstrations that can be provided in-context approaches the size of entire training datasets. We study the behavior of in-context learning (ICL) at this extreme scale on multiple datasets and models. We show that, for many datasets with large label spaces, performance continues to increase with thousands of demonstrations. We contrast this with example retrieval and finetuning: example retrieval shows excellent performance at low context lengths but has diminished gains with more demonstrations; finetuning is more data hungry than "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00200","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/2405.00200/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":"2405.00200","created_at":"2026-07-05T10:23:19.373859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00200v2","created_at":"2026-07-05T10:23:19.373859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00200","created_at":"2026-07-05T10:23:19.373859+00:00"},{"alias_kind":"pith_short_12","alias_value":"VWM3HUPWDCFK","created_at":"2026-07-05T10:23:19.373859+00:00"},{"alias_kind":"pith_short_16","alias_value":"VWM3HUPWDCFKVRDN","created_at":"2026-07-05T10:23:19.373859+00:00"},{"alias_kind":"pith_short_8","alias_value":"VWM3HUPW","created_at":"2026-07-05T10:23:19.373859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11853","citing_title":"Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning","ref_index":201,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29119","citing_title":"Knowing in Advance When an Evolutionary Outer Loop Will Not Help: A Pre-Registered Cheap-Baseline Screening Rule","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23598","citing_title":"When Youth Enter the Algorithmic Wild: Discovering and Understanding Potentially Harmful Teen Videos on Douyin and Kwai","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05257","citing_title":"Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06608","citing_title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11974","citing_title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23371","citing_title":"When Context Sticks: Studying Interference in In-Context Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10946","citing_title":"Learning to Adapt: In-Context Learning Beyond Stationarity","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2404.06654","citing_title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z","json":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z.json","graph_json":"https://pith.science/api/pith-number/VWM3HUPWDCFKVRDNWCFJTEX36Z/graph.json","events_json":"https://pith.science/api/pith-number/VWM3HUPWDCFKVRDNWCFJTEX36Z/events.json","paper":"https://pith.science/paper/VWM3HUPW"},"agent_actions":{"view_html":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z","download_json":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z.json","view_paper":"https://pith.science/paper/VWM3HUPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00200&json=true","fetch_graph":"https://pith.science/api/pith-number/VWM3HUPWDCFKVRDNWCFJTEX36Z/graph.json","fetch_events":"https://pith.science/api/pith-number/VWM3HUPWDCFKVRDNWCFJTEX36Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z/action/storage_attestation","attest_author":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z/action/author_attestation","sign_citation":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z/action/citation_signature","submit_replication":"https://pith.science/pith/VWM3HUPWDCFKVRDNWCFJTEX36Z/action/replication_record"}},"created_at":"2026-07-05T10:23:19.373859+00:00","updated_at":"2026-07-05T10:23:19.373859+00:00"}