{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MIGFJLZPEPMVLIROK5WR6YD2FD","short_pith_number":"pith:MIGFJLZP","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"},"canonical_sha256":"620c54af2f23d955a22e576d1f607a28f27a907ae20dbbb62f8a6b13c734915d","source":{"kind":"arxiv","id":"2506.04172","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04172","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04172v1","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04172","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"MIGFJLZPEPMV","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"MIGFJLZPEPMVLIRO","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"MIGFJLZP","created_at":"2026-07-05T11:15:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MIGFJLZPEPMVLIROK5WR6YD2FD","target":"record","payload":{"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"},"canonical_sha256":"620c54af2f23d955a22e576d1f607a28f27a907ae20dbbb62f8a6b13c734915d","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"},"source_kind":"arxiv","source_id":"2506.04172","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nXTicNbPLDBEHJM3g+VVFdN5NSKiwm79+z3x2qgacdhfeYJ1bUBtrwczXVxyQkU+Pru9enjAsNiUuzkgoEPTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:09:49.193199Z"},"content_sha256":"893b06fb8506859e825b5c727e4c73269c29930ba7eb1b93cda2f260c4ecd900","schema_version":"1.0","event_id":"sha256:893b06fb8506859e825b5c727e4c73269c29930ba7eb1b93cda2f260c4ecd900"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MIGFJLZPEPMVLIROK5WR6YD2FD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vesMmyBHVFeJVDb7xJe5tRd3lV+UCMz/ktexTXaU8nFOWWNmYLSGPRpJTcVB/q8vpjwdxaSEHvePfpWSyVp3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:09:49.193705Z"},"content_sha256":"66960318b36e2671013f3ce5c8df6a13cc5b47fb1c74153dab446a2af7cd669c","schema_version":"1.0","event_id":"sha256:66960318b36e2671013f3ce5c8df6a13cc5b47fb1c74153dab446a2af7cd669c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/bundle.json","state_url":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T20:09:49Z","links":{"resolver":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD","bundle":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/bundle.json","state":"https://pith.science/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MIGFJLZPEPMVLIROK5WR6YD2FD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MIGFJLZPEPMVLIROK5WR6YD2FD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"552fda6ea258ee9cd60f627656c39a51717061054c5d2a164f04044ed82587b9","cross_cats_sorted":["cs.ET"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T17:15:19Z","title_canon_sha256":"d6f98ac4ac3ab7eb64be548f77584de41ad2e94805cd19d7607cdf0e544fe282"},"schema_version":"1.0","source":{"id":"2506.04172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04172","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04172v1","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04172","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_12","alias_value":"MIGFJLZPEPMV","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_16","alias_value":"MIGFJLZPEPMVLIRO","created_at":"2026-07-05T11:15:58Z"},{"alias_kind":"pith_short_8","alias_value":"MIGFJLZP","created_at":"2026-07-05T11:15:58Z"}],"graph_snapshots":[{"event_id":"sha256:66960318b36e2671013f3ce5c8df6a13cc5b47fb1c74153dab446a2af7cd669c","target":"graph","created_at":"2026-07-05T11:15:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.04172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lydia Manikonda, Shreenidhi Srinivasan","cross_cats":["cs.ET"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T17:15:19Z","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04172","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:893b06fb8506859e825b5c727e4c73269c29930ba7eb1b93cda2f260c4ecd900","target":"record","created_at":"2026-07-05T11:15:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"552fda6ea258ee9cd60f627656c39a51717061054c5d2a164f04044ed82587b9","cross_cats_sorted":["cs.ET"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-04T17:15:19Z","title_canon_sha256":"d6f98ac4ac3ab7eb64be548f77584de41ad2e94805cd19d7607cdf0e544fe282"},"schema_version":"1.0","source":{"id":"2506.04172","kind":"arxiv","version":1}},"canonical_sha256":"620c54af2f23d955a22e576d1f607a28f27a907ae20dbbb62f8a6b13c734915d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"620c54af2f23d955a22e576d1f607a28f27a907ae20dbbb62f8a6b13c734915d","first_computed_at":"2026-07-05T11:15:58.276026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:58.276026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4wOywhMreQwKulNdeWnEMmitkl9etEXcf63Ugl/4jbrbDyedW1p2KkEaAKpDE8vTevyGV8cqNJbPeQVs8nyPBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:58.276532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:893b06fb8506859e825b5c727e4c73269c29930ba7eb1b93cda2f260c4ecd900","sha256:66960318b36e2671013f3ce5c8df6a13cc5b47fb1c74153dab446a2af7cd669c"],"state_sha256":"ccd4d6cbb821a5fa8a0e420b82c6e6d144914785c4efdce8a86ebeb44286646b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WS7eIlNHnH7qBSEwN6G1KhafSP8hsuu2HUsQK5xjAzE1WvOWUm8OQg4Uqfk5RwkL0d9dIC6f4tipn3U0lncrCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:09:49.197876Z","bundle_sha256":"6557dcfc3aec288af6850c32526d81d5d1649b87fa8ae62267250ccfd8048f92"}}