{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4E3OZBACG4K4FC45JCTYZBS7VL","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":"c51c70784c7bcd8612478306005271f2aad2504e21ebd4491f8d96843754a83c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T23:27:24Z","title_canon_sha256":"7ab9eaf1cb78d88abacf7a2657efbebac005a90d321b01477f1a26d1bd2c6f6d"},"schema_version":"1.0","source":{"id":"2507.12677","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12677","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12677v1","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12677","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"4E3OZBACG4K4","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"pith_short_16","alias_value":"4E3OZBACG4K4FC45","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"pith_short_8","alias_value":"4E3OZBAC","created_at":"2026-07-05T11:38:37Z"}],"graph_snapshots":[{"event_id":"sha256:5acaf3c0de7e6b17aaa54309f47fe64da071ad8253e018536cf068c468c63f21","target":"graph","created_at":"2026-07-05T11:38:37Z","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/2507.12677/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data heterogeneity is a prevalent issue, stemming from various conflicting factors, making its utilization complex. This uncertainty, particularly resulting from disparities in data formats, frequently necessitates the involvement of experts to find resolutions. Current methodologies primarily address conflicts related to data structures and schemas, often overlooking the pivotal role played by data transformation. As the utilization of artificial intelligence (AI) continues to expand, there is a growing demand for a more streamlined data preparation process, and data transformation becomes pa","authors_text":"Chanyoung Jung, Chanyoung Yoon, Geonyeong Son, Hyein Hong, Jaeyoung Lee, Jungsoo Park, Misuk Kim, Sangbong Yoo, Seongbum Seo, Soobin Yim, Yun Jang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T23:27:24Z","title":"Data Transformation Strategies to Remove Heterogeneity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12677","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:d849b2e72d0aedefd3d8d785c83dd816c3ec111660d097f5a64f380235cb46cd","target":"record","created_at":"2026-07-05T11:38:37Z","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":"c51c70784c7bcd8612478306005271f2aad2504e21ebd4491f8d96843754a83c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T23:27:24Z","title_canon_sha256":"7ab9eaf1cb78d88abacf7a2657efbebac005a90d321b01477f1a26d1bd2c6f6d"},"schema_version":"1.0","source":{"id":"2507.12677","kind":"arxiv","version":1}},"canonical_sha256":"e136ec84023715c28b9d48a78c865faae6762f5c7087ed200692f9ea98dc4e80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e136ec84023715c28b9d48a78c865faae6762f5c7087ed200692f9ea98dc4e80","first_computed_at":"2026-07-05T11:38:37.156310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:37.156310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KrjJ07dApMIy+wyhTKY06lFUh2lJ9jyVQ0fwQ8+O4oPnMJbecCVPNVStaw/aqw1/GvVZMtPB2TIa0evd1AY3Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:37.156821Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12677","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d849b2e72d0aedefd3d8d785c83dd816c3ec111660d097f5a64f380235cb46cd","sha256:5acaf3c0de7e6b17aaa54309f47fe64da071ad8253e018536cf068c468c63f21"],"state_sha256":"a51caaee66d00015dd6f29a17ddd45b805bf4c1d1570b80c1f477fa580782b54"}