{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EPT6QWEPD7V3MLINF5WLQC2ZIG","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":"8220d08c39ff4b228745bdcec8f1c210a98698a41ad3bb2218ba19691b27afce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-03T03:00:02Z","title_canon_sha256":"babfeb1e7956a88da45d444a85840cee937a560cb1e8285b3b43f932d8a0e772"},"schema_version":"1.0","source":{"id":"2508.01556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01556","created_at":"2026-07-05T11:47:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01556v1","created_at":"2026-07-05T11:47:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01556","created_at":"2026-07-05T11:47:41Z"},{"alias_kind":"pith_short_12","alias_value":"EPT6QWEPD7V3","created_at":"2026-07-05T11:47:41Z"},{"alias_kind":"pith_short_16","alias_value":"EPT6QWEPD7V3MLIN","created_at":"2026-07-05T11:47:41Z"},{"alias_kind":"pith_short_8","alias_value":"EPT6QWEP","created_at":"2026-07-05T11:47:41Z"}],"graph_snapshots":[{"event_id":"sha256:b76b767929e0cb85dba68d4258150fdfa3005632fc74588c20e27d323d8d9ca7","target":"graph","created_at":"2026-07-05T11:47:41Z","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/2508.01556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data preparation is a critical step in enhancing the usability of tabular data and thus boosts downstream data-driven tasks. Traditional methods often face challenges in capturing the intricate relationships within tables and adapting to the tasks involved. Recent advances in Language Models (LMs), especially in Large Language Models (LLMs), offer new opportunities to automate and support tabular data preparation. However, why LMs suit tabular data preparation (i.e., how their capabilities match task demands) and how to use them effectively across phases still remain to be systematically explo","authors_text":"Jianwei Wang, Kai Wang, Mengshi Chen, Tengchao Li, Wenjie Zhang, Xuemin Lin, Ying Zhang, Yuxiang Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-03T03:00:02Z","title":"Empowering Tabular Data Preparation with Language Models: Why and How?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01556","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":"sha256:368cfa5f767090048b3c96ec3cfa1eec89cc8d8ba07703c10a9bf4e9d728d37f","target":"record","created_at":"2026-07-05T11:47:41Z","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":"8220d08c39ff4b228745bdcec8f1c210a98698a41ad3bb2218ba19691b27afce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-03T03:00:02Z","title_canon_sha256":"babfeb1e7956a88da45d444a85840cee937a560cb1e8285b3b43f932d8a0e772"},"schema_version":"1.0","source":{"id":"2508.01556","kind":"arxiv","version":1}},"canonical_sha256":"23e7e8588f1febb62d0d2f6cb80b594190e31629eda24d9fdf48163f819eb9b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23e7e8588f1febb62d0d2f6cb80b594190e31629eda24d9fdf48163f819eb9b6","first_computed_at":"2026-07-05T11:47:41.116585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:41.116585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cDxp23LP4l1BHaxxr2e+K75YnlwYORRHo55u7K2SQwHsDqiVxnGmJYBunj6WQwzaPUA6O5/cwzbjfVfSRM+vAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:41.117053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:368cfa5f767090048b3c96ec3cfa1eec89cc8d8ba07703c10a9bf4e9d728d37f","sha256:b76b767929e0cb85dba68d4258150fdfa3005632fc74588c20e27d323d8d9ca7"],"state_sha256":"e5251cb705f01a7ad7ae74842601843e3adcbadd75d0a3548b962faac9dea977"}