{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ALJMHQTDALZNEIY3GV7OZXPGEX","short_pith_number":"pith:ALJMHQTD","schema_version":"1.0","canonical_sha256":"02d2c3c26302f2d2231b357eecdde625d242091a39ea1ccd573235546c554083","source":{"kind":"arxiv","id":"2502.16414","version":1},"attestation_state":"computed","paper":{"title":"TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aiwei Liu, Hengrui Zhang, Henry Peng Zou, Liancheng Fang, Philip S. Yu, Weizhi Zhang","submitted_at":"2025-02-23T02:51:58Z","abstract_excerpt":"Large Language models (LLMs) have achieved encouraging results in tabular data generation. However, existing approaches require fine-tuning, which is computationally expensive. This paper explores an alternative: prompting a fixed LLM with in-context examples. We observe that using randomly selected in-context examples hampers the LLM's performance, resulting in sub-optimal generation quality. To address this, we propose a novel in-context learning framework: TabGen-ICL, to enhance the in-context learning ability of LLMs for tabular data generation. TabGen-ICL operates iteratively, retrieving "},"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":"2502.16414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-23T02:51:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5d02be13d02af15355a94b62a56977d8f304605eaec0f2e183f410bf67c92c6","abstract_canon_sha256":"bdbf21d3b1d9a4af05eab262d5aab8d45b1e5ad1375025a0f4b34a3d3ed79f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:53.040064Z","signature_b64":"bZobV+XQcyOtbZopKvMZ9/s31s15p2yZuKHdZRnGYU7IN7IieHlrhgukkNldJSNOzsxUBT2PoSu+quBVvUyaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02d2c3c26302f2d2231b357eecdde625d242091a39ea1ccd573235546c554083","last_reissued_at":"2026-07-05T10:18:53.039609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:53.039609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabGen-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aiwei Liu, Hengrui Zhang, Henry Peng Zou, Liancheng Fang, Philip S. Yu, Weizhi Zhang","submitted_at":"2025-02-23T02:51:58Z","abstract_excerpt":"Large Language models (LLMs) have achieved encouraging results in tabular data generation. However, existing approaches require fine-tuning, which is computationally expensive. This paper explores an alternative: prompting a fixed LLM with in-context examples. We observe that using randomly selected in-context examples hampers the LLM's performance, resulting in sub-optimal generation quality. To address this, we propose a novel in-context learning framework: TabGen-ICL, to enhance the in-context learning ability of LLMs for tabular data generation. TabGen-ICL operates iteratively, retrieving "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.16414","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/2502.16414/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":"2502.16414","created_at":"2026-07-05T10:18:53.039667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.16414v1","created_at":"2026-07-05T10:18:53.039667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.16414","created_at":"2026-07-05T10:18:53.039667+00:00"},{"alias_kind":"pith_short_12","alias_value":"ALJMHQTDALZN","created_at":"2026-07-05T10:18:53.039667+00:00"},{"alias_kind":"pith_short_16","alias_value":"ALJMHQTDALZNEIY3","created_at":"2026-07-05T10:18:53.039667+00:00"},{"alias_kind":"pith_short_8","alias_value":"ALJMHQTD","created_at":"2026-07-05T10:18:53.039667+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/ALJMHQTDALZNEIY3GV7OZXPGEX","json":"https://pith.science/pith/ALJMHQTDALZNEIY3GV7OZXPGEX.json","graph_json":"https://pith.science/api/pith-number/ALJMHQTDALZNEIY3GV7OZXPGEX/graph.json","events_json":"https://pith.science/api/pith-number/ALJMHQTDALZNEIY3GV7OZXPGEX/events.json","paper":"https://pith.science/paper/ALJMHQTD"},"agent_actions":{"view_html":"https://pith.science/pith/ALJMHQTDALZNEIY3GV7OZXPGEX","download_json":"https://pith.science/pith/ALJMHQTDALZNEIY3GV7OZXPGEX.json","view_paper":"https://pith.science/paper/ALJMHQTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.16414&json=true","fetch_graph":"https://pith.science/api/pith-number/ALJMHQTDALZNEIY3GV7OZXPGEX/graph.json","fetch_events":"https://pith.science/api/pith-number/ALJMHQTDALZNEIY3GV7OZXPGEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ALJMHQTDALZNEIY3GV7OZXPGEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ALJMHQTDALZNEIY3GV7OZXPGEX/action/storage_attestation","attest_author":"https://pith.science/pith/ALJMHQTDALZNEIY3GV7OZXPGEX/action/author_attestation","sign_citation":"https://pith.science/pith/ALJMHQTDALZNEIY3GV7OZXPGEX/action/citation_signature","submit_replication":"https://pith.science/pith/ALJMHQTDALZNEIY3GV7OZXPGEX/action/replication_record"}},"created_at":"2026-07-05T10:18:53.039667+00:00","updated_at":"2026-07-05T10:18:53.039667+00:00"}