{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N2ZQKCJ3UXUMUD4GAIQDTPC366","short_pith_number":"pith:N2ZQKCJ3","schema_version":"1.0","canonical_sha256":"6eb305093ba5e8ca0f86022039bc5bf7ba0fd8c361f73d885657111b643c69dc","source":{"kind":"arxiv","id":"2302.04931","version":1},"attestation_state":"computed","paper":{"title":"In-Context Learning with Many Demonstration Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiangtao Feng, Jun Zhang, Lingpeng Kong, Mukai Li, Shansan Gong, Yiheng Xu, Zhiyong Wu","submitted_at":"2023-02-09T20:53:12Z","abstract_excerpt":"Large pre-training language models (PLMs) have shown promising in-context learning abilities. However, due to the backbone transformer architecture, existing PLMs are bottlenecked by the memory and computational cost when scaling up to a large context size, leaving instruction tuning and in-context learning of many demonstration examples, as well as long-range language modeling under-explored. In this study, we propose a long-range language model EVALM based on an efficient transformer mechanism. EVALM is trained with 8k tokens per batch line and can test up to 256k-lengthed contexts with extr"},"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":"2302.04931","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-09T20:53:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"709fc8ebf41ba57f7584dcb05732966c5d1b7ea5c0a5f411deb45b3034b0efff","abstract_canon_sha256":"b6aba7f4c935bf4808ee393dfb6271b0f858ac5a495d726858453bd13e0e9217"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:23.032863Z","signature_b64":"QmsSYTX8Q3Skoz6LhcFrqJWVeHs2ZSVj8PorkZPFDuFaFo3krXiyYYiKyaPGblpmlkMQ2yt8N3jtblqSIXlNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb305093ba5e8ca0f86022039bc5bf7ba0fd8c361f73d885657111b643c69dc","last_reissued_at":"2026-07-05T05:40:23.032473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:23.032473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning with Many Demonstration Examples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiangtao Feng, Jun Zhang, Lingpeng Kong, Mukai Li, Shansan Gong, Yiheng Xu, Zhiyong Wu","submitted_at":"2023-02-09T20:53:12Z","abstract_excerpt":"Large pre-training language models (PLMs) have shown promising in-context learning abilities. However, due to the backbone transformer architecture, existing PLMs are bottlenecked by the memory and computational cost when scaling up to a large context size, leaving instruction tuning and in-context learning of many demonstration examples, as well as long-range language modeling under-explored. In this study, we propose a long-range language model EVALM based on an efficient transformer mechanism. EVALM is trained with 8k tokens per batch line and can test up to 256k-lengthed contexts with extr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04931","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/2302.04931/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":"2302.04931","created_at":"2026-07-05T05:40:23.032530+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04931v1","created_at":"2026-07-05T05:40:23.032530+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04931","created_at":"2026-07-05T05:40:23.032530+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2ZQKCJ3UXUM","created_at":"2026-07-05T05:40:23.032530+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2ZQKCJ3UXUMUD4G","created_at":"2026-07-05T05:40:23.032530+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2ZQKCJ3","created_at":"2026-07-05T05:40:23.032530+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":198,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03644","citing_title":"AdapShot: Adaptive Many-Shot In-Context Learning with Semantic-Aware KV Cache Reuse","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366","json":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366.json","graph_json":"https://pith.science/api/pith-number/N2ZQKCJ3UXUMUD4GAIQDTPC366/graph.json","events_json":"https://pith.science/api/pith-number/N2ZQKCJ3UXUMUD4GAIQDTPC366/events.json","paper":"https://pith.science/paper/N2ZQKCJ3"},"agent_actions":{"view_html":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366","download_json":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366.json","view_paper":"https://pith.science/paper/N2ZQKCJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04931&json=true","fetch_graph":"https://pith.science/api/pith-number/N2ZQKCJ3UXUMUD4GAIQDTPC366/graph.json","fetch_events":"https://pith.science/api/pith-number/N2ZQKCJ3UXUMUD4GAIQDTPC366/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366/action/storage_attestation","attest_author":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366/action/author_attestation","sign_citation":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366/action/citation_signature","submit_replication":"https://pith.science/pith/N2ZQKCJ3UXUMUD4GAIQDTPC366/action/replication_record"}},"created_at":"2026-07-05T05:40:23.032530+00:00","updated_at":"2026-07-05T05:40:23.032530+00:00"}