{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CLBP2JIWIWY4N6PXIHGYVXVZR6","short_pith_number":"pith:CLBP2JIW","schema_version":"1.0","canonical_sha256":"12c2fd251645b1c6f9f741cd8adeb98f9d1fae053e49e8f42465cb0c8db45d1f","source":{"kind":"arxiv","id":"2207.04122","version":2},"attestation_state":"computed","paper":{"title":"Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and Preparation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jin Wang, Runhui Wang, Yuliang Li","submitted_at":"2022-07-08T20:45:49Z","abstract_excerpt":"Machine learning (ML) is playing an increasingly important role in data management tasks, particularly in Data Integration and Preparation (DI&P). The success of ML-based approaches, however, heavily relies on the availability of large-scale, high-quality labeled datasets for different tasks. Moreover, the wide variety of DI&P tasks and pipelines oftentimes requires customizing ML solutions which can incur a significant cost for model engineering and experimentation. These factors inevitably hold back the adoption of ML-based approaches to new domains and tasks.\n  In this paper, we propose Sud"},"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":"2207.04122","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-07-08T20:45:49Z","cross_cats_sorted":[],"title_canon_sha256":"3a3b5d9b9032cd17d045d5e8ade658bafcc6b2c058f0d8b0385f8bb06421b7cf","abstract_canon_sha256":"af6229b020e27d018efcd0ab7d5978d78e31b09e4170068c553ea38ead0a6263"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:07.564233Z","signature_b64":"EXny0a+ykq37ywnapRz6fE6EQC0OGM2OvxRmdZNi5neCEi4rmDdQuwjhRi8iP8K6T+qY5bHcZiNaRZofQcZSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12c2fd251645b1c6f9f741cd8adeb98f9d1fae053e49e8f42465cb0c8db45d1f","last_reissued_at":"2026-07-05T05:05:07.563781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:07.563781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and Preparation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jin Wang, Runhui Wang, Yuliang Li","submitted_at":"2022-07-08T20:45:49Z","abstract_excerpt":"Machine learning (ML) is playing an increasingly important role in data management tasks, particularly in Data Integration and Preparation (DI&P). The success of ML-based approaches, however, heavily relies on the availability of large-scale, high-quality labeled datasets for different tasks. Moreover, the wide variety of DI&P tasks and pipelines oftentimes requires customizing ML solutions which can incur a significant cost for model engineering and experimentation. These factors inevitably hold back the adoption of ML-based approaches to new domains and tasks.\n  In this paper, we propose Sud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04122","kind":"arxiv","version":2},"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/2207.04122/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":"2207.04122","created_at":"2026-07-05T05:05:07.563832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04122v2","created_at":"2026-07-05T05:05:07.563832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04122","created_at":"2026-07-05T05:05:07.563832+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLBP2JIWIWY4","created_at":"2026-07-05T05:05:07.563832+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLBP2JIWIWY4N6PX","created_at":"2026-07-05T05:05:07.563832+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLBP2JIW","created_at":"2026-07-05T05:05:07.563832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04006","citing_title":"TransClean: Finding False Positives in Multi-Source Entity Matching under Real-World Conditions via Transitive Consistency","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6","json":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6.json","graph_json":"https://pith.science/api/pith-number/CLBP2JIWIWY4N6PXIHGYVXVZR6/graph.json","events_json":"https://pith.science/api/pith-number/CLBP2JIWIWY4N6PXIHGYVXVZR6/events.json","paper":"https://pith.science/paper/CLBP2JIW"},"agent_actions":{"view_html":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6","download_json":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6.json","view_paper":"https://pith.science/paper/CLBP2JIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04122&json=true","fetch_graph":"https://pith.science/api/pith-number/CLBP2JIWIWY4N6PXIHGYVXVZR6/graph.json","fetch_events":"https://pith.science/api/pith-number/CLBP2JIWIWY4N6PXIHGYVXVZR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/action/storage_attestation","attest_author":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/action/author_attestation","sign_citation":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/action/citation_signature","submit_replication":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/action/replication_record"}},"created_at":"2026-07-05T05:05:07.563832+00:00","updated_at":"2026-07-05T05:05:07.563832+00:00"}