{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CLBP2JIWIWY4N6PXIHGYVXVZR6","short_pith_number":"pith:CLBP2JIW","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"},"canonical_sha256":"12c2fd251645b1c6f9f741cd8adeb98f9d1fae053e49e8f42465cb0c8db45d1f","source":{"kind":"arxiv","id":"2207.04122","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04122","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04122v2","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04122","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"CLBP2JIWIWY4","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"CLBP2JIWIWY4N6PX","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"CLBP2JIW","created_at":"2026-07-05T05:05:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CLBP2JIWIWY4N6PXIHGYVXVZR6","target":"record","payload":{"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"},"canonical_sha256":"12c2fd251645b1c6f9f741cd8adeb98f9d1fae053e49e8f42465cb0c8db45d1f","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"},"source_kind":"arxiv","source_id":"2207.04122","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:05:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hdgkcB9E5FlDAzZUoWY7wG1aG4R7cODXFAsQjjkywmAPlTlbwDpPZI81TbT1NQS2rQ3xNRwFOqud4qZyrv19Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:57:12.583986Z"},"content_sha256":"a960d119092c8ba1f3e7a9d4e4c87cf58ecf22772d0ece7824ac9c903ef43ffc","schema_version":"1.0","event_id":"sha256:a960d119092c8ba1f3e7a9d4e4c87cf58ecf22772d0ece7824ac9c903ef43ffc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CLBP2JIWIWY4N6PXIHGYVXVZR6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:05:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aJrM3n7aZQq/3LvVGwJKdeo9SaDRJVnRmGvxAZG5GL97Mtgn7+ec9izpHNgr0gCs7kgEq9frWLInYku2LC3vCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:57:12.584965Z"},"content_sha256":"4147cfd7f65fc0646a8b3bbd570ad4a098610f62a8dc1e202f86f2aad90f76df","schema_version":"1.0","event_id":"sha256:4147cfd7f65fc0646a8b3bbd570ad4a098610f62a8dc1e202f86f2aad90f76df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/bundle.json","state_url":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T04:57:12Z","links":{"resolver":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6","bundle":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/bundle.json","state":"https://pith.science/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CLBP2JIWIWY4N6PXIHGYVXVZR6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CLBP2JIWIWY4N6PXIHGYVXVZR6","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":"af6229b020e27d018efcd0ab7d5978d78e31b09e4170068c553ea38ead0a6263","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-07-08T20:45:49Z","title_canon_sha256":"3a3b5d9b9032cd17d045d5e8ade658bafcc6b2c058f0d8b0385f8bb06421b7cf"},"schema_version":"1.0","source":{"id":"2207.04122","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.04122","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"arxiv_version","alias_value":"2207.04122v2","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04122","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"pith_short_12","alias_value":"CLBP2JIWIWY4","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"pith_short_16","alias_value":"CLBP2JIWIWY4N6PX","created_at":"2026-07-05T05:05:07Z"},{"alias_kind":"pith_short_8","alias_value":"CLBP2JIW","created_at":"2026-07-05T05:05:07Z"}],"graph_snapshots":[{"event_id":"sha256:4147cfd7f65fc0646a8b3bbd570ad4a098610f62a8dc1e202f86f2aad90f76df","target":"graph","created_at":"2026-07-05T05:05:07Z","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/2207.04122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jin Wang, Runhui Wang, Yuliang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-07-08T20:45:49Z","title":"Sudowoodo: Contrastive Self-supervised Learning for Multi-purpose Data Integration and Preparation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04122","kind":"arxiv","version":2},"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:a960d119092c8ba1f3e7a9d4e4c87cf58ecf22772d0ece7824ac9c903ef43ffc","target":"record","created_at":"2026-07-05T05:05:07Z","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":"af6229b020e27d018efcd0ab7d5978d78e31b09e4170068c553ea38ead0a6263","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2022-07-08T20:45:49Z","title_canon_sha256":"3a3b5d9b9032cd17d045d5e8ade658bafcc6b2c058f0d8b0385f8bb06421b7cf"},"schema_version":"1.0","source":{"id":"2207.04122","kind":"arxiv","version":2}},"canonical_sha256":"12c2fd251645b1c6f9f741cd8adeb98f9d1fae053e49e8f42465cb0c8db45d1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12c2fd251645b1c6f9f741cd8adeb98f9d1fae053e49e8f42465cb0c8db45d1f","first_computed_at":"2026-07-05T05:05:07.563781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:07.563781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EXny0a+ykq37ywnapRz6fE6EQC0OGM2OvxRmdZNi5neCEi4rmDdQuwjhRi8iP8K6T+qY5bHcZiNaRZofQcZSCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:07.564233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.04122","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a960d119092c8ba1f3e7a9d4e4c87cf58ecf22772d0ece7824ac9c903ef43ffc","sha256:4147cfd7f65fc0646a8b3bbd570ad4a098610f62a8dc1e202f86f2aad90f76df"],"state_sha256":"88d20658fd06aae6bb6c01908ef94b56612dbd2dd2c9e2d57fa9ebb641767d8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xOMTeSvnsdVYOeKej1jqFyqlIKTeBHtANjk2ux6+itD8NL7a/jMDNN1hNRfgBs++RCQdYz4tfa7EQuRu1/7kCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:57:12.591932Z","bundle_sha256":"f4e799719095696cf2637acda37e85c7d0fadf333b44b071b6bcaf50d9b23bc5"}}