{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UVI4O6R5LTS5VZNEFLRKFTD4VZ","short_pith_number":"pith:UVI4O6R5","schema_version":"1.0","canonical_sha256":"a551c77a3d5ce5dae5a42ae2a2cc7cae5adf49a0d7b1f5a450ff7aeb64f27ff4","source":{"kind":"arxiv","id":"2402.13874","version":3},"attestation_state":"computed","paper":{"title":"$Se^2$: Sequential Example Selection for In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hao Sun, Haoyu Liu, Jianfeng Liu, Qi Zhang, Shaohan Huang, Weiwei Deng, Yuefeng Zhan","submitted_at":"2024-02-21T15:35:04Z","abstract_excerpt":"The remarkable capability of large language models (LLMs) for in-context learning (ICL) needs to be activated by demonstration examples. Prior work has extensively explored the selection of examples for ICL, predominantly following the \"select then organize\" paradigm, such approaches often neglect the internal relationships between examples and exist an inconsistency between the training and inference. In this paper, we formulate the problem as a $Se$quential $Se$lection problem and introduce $Se^2$, a sequential-aware method that leverages the LLM's feedback on varying context, aiding in capt"},"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":"2402.13874","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T15:35:04Z","cross_cats_sorted":[],"title_canon_sha256":"e5f5d4a77b092a88fcfdc0eb716314f4511de9983d73c11c0eb13e396ccc2bc0","abstract_canon_sha256":"6fa27d62fce80a354ef67cad54939752086862de282a4d0c9794366901c164aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:06.507141Z","signature_b64":"5+NOnx+qoq20JBfzqmVkGypWBxeCgFlubDRCPDy9xFYHt2DlTQFaRov1FzmdxXOHqYar2izIEGhK/tYOvgmwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a551c77a3d5ce5dae5a42ae2a2cc7cae5adf49a0d7b1f5a450ff7aeb64f27ff4","last_reissued_at":"2026-07-05T08:28:06.506727Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:06.506727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$Se^2$: Sequential Example Selection for In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hao Sun, Haoyu Liu, Jianfeng Liu, Qi Zhang, Shaohan Huang, Weiwei Deng, Yuefeng Zhan","submitted_at":"2024-02-21T15:35:04Z","abstract_excerpt":"The remarkable capability of large language models (LLMs) for in-context learning (ICL) needs to be activated by demonstration examples. Prior work has extensively explored the selection of examples for ICL, predominantly following the \"select then organize\" paradigm, such approaches often neglect the internal relationships between examples and exist an inconsistency between the training and inference. In this paper, we formulate the problem as a $Se$quential $Se$lection problem and introduce $Se^2$, a sequential-aware method that leverages the LLM's feedback on varying context, aiding in capt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13874","kind":"arxiv","version":3},"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/2402.13874/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":"2402.13874","created_at":"2026-07-05T08:28:06.506783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13874v3","created_at":"2026-07-05T08:28:06.506783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13874","created_at":"2026-07-05T08:28:06.506783+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVI4O6R5LTS5","created_at":"2026-07-05T08:28:06.506783+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVI4O6R5LTS5VZNE","created_at":"2026-07-05T08:28:06.506783+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVI4O6R5","created_at":"2026-07-05T08:28:06.506783+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/UVI4O6R5LTS5VZNEFLRKFTD4VZ","json":"https://pith.science/pith/UVI4O6R5LTS5VZNEFLRKFTD4VZ.json","graph_json":"https://pith.science/api/pith-number/UVI4O6R5LTS5VZNEFLRKFTD4VZ/graph.json","events_json":"https://pith.science/api/pith-number/UVI4O6R5LTS5VZNEFLRKFTD4VZ/events.json","paper":"https://pith.science/paper/UVI4O6R5"},"agent_actions":{"view_html":"https://pith.science/pith/UVI4O6R5LTS5VZNEFLRKFTD4VZ","download_json":"https://pith.science/pith/UVI4O6R5LTS5VZNEFLRKFTD4VZ.json","view_paper":"https://pith.science/paper/UVI4O6R5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13874&json=true","fetch_graph":"https://pith.science/api/pith-number/UVI4O6R5LTS5VZNEFLRKFTD4VZ/graph.json","fetch_events":"https://pith.science/api/pith-number/UVI4O6R5LTS5VZNEFLRKFTD4VZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVI4O6R5LTS5VZNEFLRKFTD4VZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVI4O6R5LTS5VZNEFLRKFTD4VZ/action/storage_attestation","attest_author":"https://pith.science/pith/UVI4O6R5LTS5VZNEFLRKFTD4VZ/action/author_attestation","sign_citation":"https://pith.science/pith/UVI4O6R5LTS5VZNEFLRKFTD4VZ/action/citation_signature","submit_replication":"https://pith.science/pith/UVI4O6R5LTS5VZNEFLRKFTD4VZ/action/replication_record"}},"created_at":"2026-07-05T08:28:06.506783+00:00","updated_at":"2026-07-05T08:28:06.506783+00:00"}