{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CMCCRJZB7JLOENSTJR3GKL5UMQ","short_pith_number":"pith:CMCCRJZB","schema_version":"1.0","canonical_sha256":"130428a721fa56e236534c76652fb464032a2a97d8f8da0e70d5ba8c666c0ced","source":{"kind":"arxiv","id":"2506.04006","version":1},"attestation_state":"computed","paper":{"title":"TransClean: Finding False Positives in Multi-Source Entity Matching under Real-World Conditions via Transitive Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Branka Hadji Misheva, Fernando de Meer Pardo, Kurt Stockinger, Martin Braschler","submitted_at":"2025-06-04T14:33:41Z","abstract_excerpt":"We present TransClean, a method for detecting false positive predictions of entity matching algorithms under real-world conditions characterized by large-scale, noisy, and unlabeled multi-source datasets that undergo distributional shifts. TransClean is explicitly designed to operate with multiple data sources in an efficient, robust and fast manner while accounting for edge cases and requiring limited manual labeling. TransClean leverages the Transitive Consistency of a matching, a measure of the consistency of a pairwise matching model f_theta on the matching it produces G_f_theta, based bot"},"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":"2506.04006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-06-04T14:33:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7d4173f742f816578710975b881d4dcc157c0e9b2ce69c9ede94a6d44937ddfd","abstract_canon_sha256":"ecd8d95e70cc03efbbfa87fbf40c9a6cbfc097bc061ecd38d70f674ffc4c3578"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:55.183939Z","signature_b64":"eOHVsnc1sbw3c80P8oHe8gs8Qneb4cYgSYVcFwnYxydi/KFOmbbAbJC3NAUkSfw56GysNZ7oFFIeyPeKl6ToAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"130428a721fa56e236534c76652fb464032a2a97d8f8da0e70d5ba8c666c0ced","last_reissued_at":"2026-07-05T11:15:55.183532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:55.183532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TransClean: Finding False Positives in Multi-Source Entity Matching under Real-World Conditions via Transitive Consistency","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Branka Hadji Misheva, Fernando de Meer Pardo, Kurt Stockinger, Martin Braschler","submitted_at":"2025-06-04T14:33:41Z","abstract_excerpt":"We present TransClean, a method for detecting false positive predictions of entity matching algorithms under real-world conditions characterized by large-scale, noisy, and unlabeled multi-source datasets that undergo distributional shifts. TransClean is explicitly designed to operate with multiple data sources in an efficient, robust and fast manner while accounting for edge cases and requiring limited manual labeling. TransClean leverages the Transitive Consistency of a matching, a measure of the consistency of a pairwise matching model f_theta on the matching it produces G_f_theta, based bot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04006","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/2506.04006/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":"2506.04006","created_at":"2026-07-05T11:15:55.183591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04006v1","created_at":"2026-07-05T11:15:55.183591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04006","created_at":"2026-07-05T11:15:55.183591+00:00"},{"alias_kind":"pith_short_12","alias_value":"CMCCRJZB7JLO","created_at":"2026-07-05T11:15:55.183591+00:00"},{"alias_kind":"pith_short_16","alias_value":"CMCCRJZB7JLOENST","created_at":"2026-07-05T11:15:55.183591+00:00"},{"alias_kind":"pith_short_8","alias_value":"CMCCRJZB","created_at":"2026-07-05T11:15:55.183591+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/CMCCRJZB7JLOENSTJR3GKL5UMQ","json":"https://pith.science/pith/CMCCRJZB7JLOENSTJR3GKL5UMQ.json","graph_json":"https://pith.science/api/pith-number/CMCCRJZB7JLOENSTJR3GKL5UMQ/graph.json","events_json":"https://pith.science/api/pith-number/CMCCRJZB7JLOENSTJR3GKL5UMQ/events.json","paper":"https://pith.science/paper/CMCCRJZB"},"agent_actions":{"view_html":"https://pith.science/pith/CMCCRJZB7JLOENSTJR3GKL5UMQ","download_json":"https://pith.science/pith/CMCCRJZB7JLOENSTJR3GKL5UMQ.json","view_paper":"https://pith.science/paper/CMCCRJZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04006&json=true","fetch_graph":"https://pith.science/api/pith-number/CMCCRJZB7JLOENSTJR3GKL5UMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CMCCRJZB7JLOENSTJR3GKL5UMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CMCCRJZB7JLOENSTJR3GKL5UMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CMCCRJZB7JLOENSTJR3GKL5UMQ/action/storage_attestation","attest_author":"https://pith.science/pith/CMCCRJZB7JLOENSTJR3GKL5UMQ/action/author_attestation","sign_citation":"https://pith.science/pith/CMCCRJZB7JLOENSTJR3GKL5UMQ/action/citation_signature","submit_replication":"https://pith.science/pith/CMCCRJZB7JLOENSTJR3GKL5UMQ/action/replication_record"}},"created_at":"2026-07-05T11:15:55.183591+00:00","updated_at":"2026-07-05T11:15:55.183591+00:00"}