{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SATEHR4DNAYJGNCPPMCA37C3PX","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":"abe43a4a09a2a28a750779cfe2ce85fbbe2265150b21b36379d51f2fdfa6144a","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:51:21Z","title_canon_sha256":"154ec04c3680ab3530aad25da40613d570a4577cf74fe1d50054dd50eb66b72f"},"schema_version":"1.0","source":{"id":"2306.11843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11843","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11843v1","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11843","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_12","alias_value":"SATEHR4DNAYJ","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_16","alias_value":"SATEHR4DNAYJGNCP","created_at":"2026-07-05T06:23:07Z"},{"alias_kind":"pith_short_8","alias_value":"SATEHR4D","created_at":"2026-07-05T06:23:07Z"}],"graph_snapshots":[{"event_id":"sha256:be10c8ff98f3624f66b63618a8f6b64dbcb826e0bc9cace76f9cd8b77cacfab2","target":"graph","created_at":"2026-07-05T06:23:07Z","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/2306.11843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data preparation, also called data wrangling, is considered one of the most expensive and time-consuming steps when performing analytics or building machine learning models. Preparing data typically involves collecting and merging data from complex heterogeneous, and often large-scale data sources, such as data lakes. In this paper, we introduce a novel approach toward automatic data wrangling in an attempt to alleviate the effort of end-users, e.g. data analysts, in structuring dynamic views from data lakes in the form of tabular data. We aim to address table augmentation tasks, including row","authors_text":"Alfio Gliozzo, Ankita Rajaram Naik, Gaetano Rossiello, Michael Glass, Xueqing Wu","cross_cats":["cs.AI","cs.DB","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:51:21Z","title":"Retrieval-Based Transformer for Table Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11843","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:b23dbbf205aa3cb4a8f57df01a11d0612e2af55aeed4725aef89862ee7adb652","target":"record","created_at":"2026-07-05T06:23:07Z","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":"abe43a4a09a2a28a750779cfe2ce85fbbe2265150b21b36379d51f2fdfa6144a","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:51:21Z","title_canon_sha256":"154ec04c3680ab3530aad25da40613d570a4577cf74fe1d50054dd50eb66b72f"},"schema_version":"1.0","source":{"id":"2306.11843","kind":"arxiv","version":1}},"canonical_sha256":"902643c783683093344f7b040dfc5b7dec656ed8b1479097f7cf1cbcbada8e1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"902643c783683093344f7b040dfc5b7dec656ed8b1479097f7cf1cbcbada8e1c","first_computed_at":"2026-07-05T06:23:07.482992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:07.482992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yPx6RtiDIvOV+GhNyUvRem3YV5Bd2ZrgffekejYP+06lsalRh5tUycPsy5TFoUBgk1NWU9JYXqSCE1SFDKftCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:07.483412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b23dbbf205aa3cb4a8f57df01a11d0612e2af55aeed4725aef89862ee7adb652","sha256:be10c8ff98f3624f66b63618a8f6b64dbcb826e0bc9cace76f9cd8b77cacfab2"],"state_sha256":"d786493578645666e6576a18efd6ff9b133450f2aaebc4e2b12bed43f9f80720"}