{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KNFLBHXMKKU7PHRMMHMCF4SLLX","short_pith_number":"pith:KNFLBHXM","schema_version":"1.0","canonical_sha256":"534ab09eec52a9f79e2c61d822f24b5dd5c29997504e71fa4438b3c83c7f59bd","source":{"kind":"arxiv","id":"2107.10590","version":3},"attestation_state":"computed","paper":{"title":"Frost: A Platform for Benchmarking and Exploring Data Matching Results","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Fabian Panse, Felix Naumann, Florian Papsdorf, Florian Sold, Lukas Laskowski, Martin Graf, Roland Gremmelspacher","submitted_at":"2021-07-22T11:39:16Z","abstract_excerpt":"\"Bad\" data has a direct impact on 88% of companies, with the average company losing 12% of its revenue due to it. Duplicates - multiple but different representations of the same real-world entities - are among the main reasons for poor data quality, so finding and configuring the right deduplication solution is essential. Existing data matching benchmarks focus on the quality of matching results and neglect other important factors, such as business requirements. Additionally, they often do not support the exploration of data matching results. To address this gap between the mere counting of re"},"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":"2107.10590","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2021-07-22T11:39:16Z","cross_cats_sorted":[],"title_canon_sha256":"dc3e55930a4577e2043f4f31d951a1c606e5575fd86cc0984b88f1fc1bb2fc40","abstract_canon_sha256":"2e61056bd0500307db28c72e7cfcd3d92be8db38ab9fcc5d33fc1862d96d78bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:54:15.127992Z","signature_b64":"etdEHASgyoUNIXh9q5WZo9xVDPLM0fUDdvex3SaE42RdXmbMuQXjkOwXJwkIU16jJrPVH5xa8tnuVL581n9oCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"534ab09eec52a9f79e2c61d822f24b5dd5c29997504e71fa4438b3c83c7f59bd","last_reissued_at":"2026-07-05T04:54:15.127603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:54:15.127603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frost: A Platform for Benchmarking and Exploring Data Matching Results","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Fabian Panse, Felix Naumann, Florian Papsdorf, Florian Sold, Lukas Laskowski, Martin Graf, Roland Gremmelspacher","submitted_at":"2021-07-22T11:39:16Z","abstract_excerpt":"\"Bad\" data has a direct impact on 88% of companies, with the average company losing 12% of its revenue due to it. Duplicates - multiple but different representations of the same real-world entities - are among the main reasons for poor data quality, so finding and configuring the right deduplication solution is essential. Existing data matching benchmarks focus on the quality of matching results and neglect other important factors, such as business requirements. Additionally, they often do not support the exploration of data matching results. To address this gap between the mere counting of re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.10590","kind":"arxiv","version":3},"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/2107.10590/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":"2107.10590","created_at":"2026-07-05T04:54:15.127664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.10590v3","created_at":"2026-07-05T04:54:15.127664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.10590","created_at":"2026-07-05T04:54:15.127664+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNFLBHXMKKU7","created_at":"2026-07-05T04:54:15.127664+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNFLBHXMKKU7PHRM","created_at":"2026-07-05T04:54:15.127664+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNFLBHXM","created_at":"2026-07-05T04:54:15.127664+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/KNFLBHXMKKU7PHRMMHMCF4SLLX","json":"https://pith.science/pith/KNFLBHXMKKU7PHRMMHMCF4SLLX.json","graph_json":"https://pith.science/api/pith-number/KNFLBHXMKKU7PHRMMHMCF4SLLX/graph.json","events_json":"https://pith.science/api/pith-number/KNFLBHXMKKU7PHRMMHMCF4SLLX/events.json","paper":"https://pith.science/paper/KNFLBHXM"},"agent_actions":{"view_html":"https://pith.science/pith/KNFLBHXMKKU7PHRMMHMCF4SLLX","download_json":"https://pith.science/pith/KNFLBHXMKKU7PHRMMHMCF4SLLX.json","view_paper":"https://pith.science/paper/KNFLBHXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.10590&json=true","fetch_graph":"https://pith.science/api/pith-number/KNFLBHXMKKU7PHRMMHMCF4SLLX/graph.json","fetch_events":"https://pith.science/api/pith-number/KNFLBHXMKKU7PHRMMHMCF4SLLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNFLBHXMKKU7PHRMMHMCF4SLLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNFLBHXMKKU7PHRMMHMCF4SLLX/action/storage_attestation","attest_author":"https://pith.science/pith/KNFLBHXMKKU7PHRMMHMCF4SLLX/action/author_attestation","sign_citation":"https://pith.science/pith/KNFLBHXMKKU7PHRMMHMCF4SLLX/action/citation_signature","submit_replication":"https://pith.science/pith/KNFLBHXMKKU7PHRMMHMCF4SLLX/action/replication_record"}},"created_at":"2026-07-05T04:54:15.127664+00:00","updated_at":"2026-07-05T04:54:15.127664+00:00"}