{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SATEHR4DNAYJGNCPPMCA37C3PX","short_pith_number":"pith:SATEHR4D","schema_version":"1.0","canonical_sha256":"902643c783683093344f7b040dfc5b7dec656ed8b1479097f7cf1cbcbada8e1c","source":{"kind":"arxiv","id":"2306.11843","version":1},"attestation_state":"computed","paper":{"title":"Retrieval-Based Transformer for Table Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Alfio Gliozzo, Ankita Rajaram Naik, Gaetano Rossiello, Michael Glass, Xueqing Wu","submitted_at":"2023-06-20T18:51:21Z","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"},"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":"2306.11843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-20T18:51:21Z","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"title_canon_sha256":"154ec04c3680ab3530aad25da40613d570a4577cf74fe1d50054dd50eb66b72f","abstract_canon_sha256":"abe43a4a09a2a28a750779cfe2ce85fbbe2265150b21b36379d51f2fdfa6144a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:07.483412Z","signature_b64":"yPx6RtiDIvOV+GhNyUvRem3YV5Bd2ZrgffekejYP+06lsalRh5tUycPsy5TFoUBgk1NWU9JYXqSCE1SFDKftCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"902643c783683093344f7b040dfc5b7dec656ed8b1479097f7cf1cbcbada8e1c","last_reissued_at":"2026-07-05T06:23:07.482992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:07.482992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Based Transformer for Table Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Alfio Gliozzo, Ankita Rajaram Naik, Gaetano Rossiello, Michael Glass, Xueqing Wu","submitted_at":"2023-06-20T18:51:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11843","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/2306.11843/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":"2306.11843","created_at":"2026-07-05T06:23:07.483043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.11843v1","created_at":"2026-07-05T06:23:07.483043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11843","created_at":"2026-07-05T06:23:07.483043+00:00"},{"alias_kind":"pith_short_12","alias_value":"SATEHR4DNAYJ","created_at":"2026-07-05T06:23:07.483043+00:00"},{"alias_kind":"pith_short_16","alias_value":"SATEHR4DNAYJGNCP","created_at":"2026-07-05T06:23:07.483043+00:00"},{"alias_kind":"pith_short_8","alias_value":"SATEHR4D","created_at":"2026-07-05T06:23:07.483043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX","json":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX.json","graph_json":"https://pith.science/api/pith-number/SATEHR4DNAYJGNCPPMCA37C3PX/graph.json","events_json":"https://pith.science/api/pith-number/SATEHR4DNAYJGNCPPMCA37C3PX/events.json","paper":"https://pith.science/paper/SATEHR4D"},"agent_actions":{"view_html":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX","download_json":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX.json","view_paper":"https://pith.science/paper/SATEHR4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.11843&json=true","fetch_graph":"https://pith.science/api/pith-number/SATEHR4DNAYJGNCPPMCA37C3PX/graph.json","fetch_events":"https://pith.science/api/pith-number/SATEHR4DNAYJGNCPPMCA37C3PX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX/action/storage_attestation","attest_author":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX/action/author_attestation","sign_citation":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX/action/citation_signature","submit_replication":"https://pith.science/pith/SATEHR4DNAYJGNCPPMCA37C3PX/action/replication_record"}},"created_at":"2026-07-05T06:23:07.483043+00:00","updated_at":"2026-07-05T06:23:07.483043+00:00"}