{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MIGFJLZPEPMVLIROK5WR6YD2FD","short_pith_number":"pith:MIGFJLZP","schema_version":"1.0","canonical_sha256":"620c54af2f23d955a22e576d1f607a28f27a907ae20dbbb62f8a6b13c734915d","source":{"kind":"arxiv","id":"2506.04172","version":1},"attestation_state":"computed","paper":{"title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.LG","authors_text":"Lydia Manikonda, Shreenidhi Srinivasan","submitted_at":"2025-06-04T17:15:19Z","abstract_excerpt":"Generating realistic synthetic tabular data presents a critical challenge in machine learning. It adds another layer of complexity when this data contain class imbalance problems. This paper presents a novel token-aware data imputation method that leverages the in-context learning capabilities of large language models. This is achieved through the combination of a structured group-wise CSV-style prompting technique and the elimination of irrelevant contextual information in the input prompt. We test this approach with two class-imbalanced binary classification datasets and evaluate the effecti"},"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":"2506.04172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T17:15:19Z","cross_cats_sorted":["cs.ET"],"title_canon_sha256":"d6f98ac4ac3ab7eb64be548f77584de41ad2e94805cd19d7607cdf0e544fe282","abstract_canon_sha256":"552fda6ea258ee9cd60f627656c39a51717061054c5d2a164f04044ed82587b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:58.276532Z","signature_b64":"4wOywhMreQwKulNdeWnEMmitkl9etEXcf63Ugl/4jbrbDyedW1p2KkEaAKpDE8vTevyGV8cqNJbPeQVs8nyPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"620c54af2f23d955a22e576d1f607a28f27a907ae20dbbb62f8a6b13c734915d","last_reissued_at":"2026-07-05T11:15:58.276026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:58.276026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.ET"],"primary_cat":"cs.LG","authors_text":"Lydia Manikonda, Shreenidhi Srinivasan","submitted_at":"2025-06-04T17:15:19Z","abstract_excerpt":"Generating realistic synthetic tabular data presents a critical challenge in machine learning. It adds another layer of complexity when this data contain class imbalance problems. This paper presents a novel token-aware data imputation method that leverages the in-context learning capabilities of large language models. This is achieved through the combination of a structured group-wise CSV-style prompting technique and the elimination of irrelevant contextual information in the input prompt. We test this approach with two class-imbalanced binary classification datasets and evaluate the effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04172","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/2506.04172/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":"2506.04172","created_at":"2026-07-05T11:15:58.276092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04172v1","created_at":"2026-07-05T11:15:58.276092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04172","created_at":"2026-07-05T11:15:58.276092+00:00"},{"alias_kind":"pith_short_12","alias_value":"MIGFJLZPEPMV","created_at":"2026-07-05T11:15:58.276092+00:00"},{"alias_kind":"pith_short_16","alias_value":"MIGFJLZPEPMVLIRO","created_at":"2026-07-05T11:15:58.276092+00:00"},{"alias_kind":"pith_short_8","alias_value":"MIGFJLZP","created_at":"2026-07-05T11:15:58.276092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD","json":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD.json","graph_json":"https://pith.science/api/pith-number/MIGFJLZPEPMVLIROK5WR6YD2FD/graph.json","events_json":"https://pith.science/api/pith-number/MIGFJLZPEPMVLIROK5WR6YD2FD/events.json","paper":"https://pith.science/paper/MIGFJLZP"},"agent_actions":{"view_html":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD","download_json":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD.json","view_paper":"https://pith.science/paper/MIGFJLZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04172&json=true","fetch_graph":"https://pith.science/api/pith-number/MIGFJLZPEPMVLIROK5WR6YD2FD/graph.json","fetch_events":"https://pith.science/api/pith-number/MIGFJLZPEPMVLIROK5WR6YD2FD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/action/storage_attestation","attest_author":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/action/author_attestation","sign_citation":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/action/citation_signature","submit_replication":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/action/replication_record"}},"created_at":"2026-07-05T11:15:58.276092+00:00","updated_at":"2026-07-05T11:15:58.276092+00:00"}