{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ADQVVB6JEWJDEPL7H6OEB5V6EY","short_pith_number":"pith:ADQVVB6J","schema_version":"1.0","canonical_sha256":"00e15a87c92592323d7f3f9c40f6be2608349dbcff672a21d819b1a380f44923","source":{"kind":"arxiv","id":"2402.10738","version":2},"attestation_state":"computed","paper":{"title":"Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawei Liu, Qikai Cheng, Wei Lu, Xiang Shi, Yinpeng Liu, Yong Huang","submitted_at":"2024-02-16T14:55:33Z","abstract_excerpt":"Demonstration ordering, which is an important strategy for in-context learning (ICL), can significantly affects the performance of large language models (LLMs). However, most of the current approaches of ordering require high computational costs to introduce the priori knowledge. In this paper, inspired by the human learning process, we propose a simple but effective demonstration ordering method for ICL, named the few-shot In-Context Curriculum Learning (ICCL). The ICCL implies gradually increasing the complexity of prompt demonstrations during the inference process. The difficulty can be ass"},"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":"2402.10738","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T14:55:33Z","cross_cats_sorted":[],"title_canon_sha256":"de9dc0870b9989a38547a11b278540aa1850975f13797c0ac94b0774abaa10f4","abstract_canon_sha256":"5aebb0be9ead538cba3f8dc4546a3047e40c341adb6fba0b5e8af9fb44211c07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:36.818817Z","signature_b64":"BxLzrCOjwDHcXv1ATJnA0+/CLvT/7mJXJOomcHtPhOVWTMIRTCzVhJwobQnc3WQKKA7vDOSDgoiWF0qyZmgyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00e15a87c92592323d7f3f9c40f6be2608349dbcff672a21d819b1a380f44923","last_reissued_at":"2026-07-05T08:32:36.818350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:36.818350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawei Liu, Qikai Cheng, Wei Lu, Xiang Shi, Yinpeng Liu, Yong Huang","submitted_at":"2024-02-16T14:55:33Z","abstract_excerpt":"Demonstration ordering, which is an important strategy for in-context learning (ICL), can significantly affects the performance of large language models (LLMs). However, most of the current approaches of ordering require high computational costs to introduce the priori knowledge. In this paper, inspired by the human learning process, we propose a simple but effective demonstration ordering method for ICL, named the few-shot In-Context Curriculum Learning (ICCL). The ICCL implies gradually increasing the complexity of prompt demonstrations during the inference process. The difficulty can be ass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10738","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/2402.10738/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":"2402.10738","created_at":"2026-07-05T08:32:36.818408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10738v2","created_at":"2026-07-05T08:32:36.818408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10738","created_at":"2026-07-05T08:32:36.818408+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADQVVB6JEWJD","created_at":"2026-07-05T08:32:36.818408+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADQVVB6JEWJDEPL7","created_at":"2026-07-05T08:32:36.818408+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADQVVB6J","created_at":"2026-07-05T08:32:36.818408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19349","citing_title":"Where to Place the Query? Unveiling and Mitigating Positional Bias in In-Context Learning for Diffusion LLMs via Decoding Dynamics","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18117","citing_title":"Online In-Context Distillation for Low-Resource Vision Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13502","citing_title":"SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08766","citing_title":"UserGPT Technical Report","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY","json":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY.json","graph_json":"https://pith.science/api/pith-number/ADQVVB6JEWJDEPL7H6OEB5V6EY/graph.json","events_json":"https://pith.science/api/pith-number/ADQVVB6JEWJDEPL7H6OEB5V6EY/events.json","paper":"https://pith.science/paper/ADQVVB6J"},"agent_actions":{"view_html":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY","download_json":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY.json","view_paper":"https://pith.science/paper/ADQVVB6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10738&json=true","fetch_graph":"https://pith.science/api/pith-number/ADQVVB6JEWJDEPL7H6OEB5V6EY/graph.json","fetch_events":"https://pith.science/api/pith-number/ADQVVB6JEWJDEPL7H6OEB5V6EY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY/action/storage_attestation","attest_author":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY/action/author_attestation","sign_citation":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY/action/citation_signature","submit_replication":"https://pith.science/pith/ADQVVB6JEWJDEPL7H6OEB5V6EY/action/replication_record"}},"created_at":"2026-07-05T08:32:36.818408+00:00","updated_at":"2026-07-05T08:32:36.818408+00:00"}