{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OE6ALLG72LNXLFCXUPPXQHVWRP","short_pith_number":"pith:OE6ALLG7","schema_version":"1.0","canonical_sha256":"713c05acdfd2db759457a3df781eb68bcfbca69b77591b553fa4f1d8d39dc0c0","source":{"kind":"arxiv","id":"2301.09521","version":2},"attestation_state":"computed","paper":{"title":"WDC Products: A Multi-Dimensional Entity Matching Benchmark","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christian Bizer, Ralph Peeters, Reng Chiz Der","submitted_at":"2023-01-23T16:12:18Z","abstract_excerpt":"The difficulty of an entity matching task depends on a combination of multiple factors such as the amount of corner-case pairs, the fraction of entities in the test set that have not been seen during training, and the size of the development set. Current entity matching benchmarks usually represent single points in the space along such dimensions or they provide for the evaluation of matching methods along a single dimension, for instance the amount of training data. This paper presents WDC Products, an entity matching benchmark which provides for the systematic evaluation of matching systems "},"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":"2301.09521","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-23T16:12:18Z","cross_cats_sorted":[],"title_canon_sha256":"9feded629592c0db7ee8d2d8d5c6deb8005ab549f077754b7c08c81d4e4dc996","abstract_canon_sha256":"9344da2c0ad06189f79a0157fb85df8c98798c209ca55e1aac2e3faeebbfb77d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:17.976263Z","signature_b64":"6ePLg1RN9elC0hhjHdbJhXomPzXFNJcE4xMyibMaEorAnE9rvO8qrzd03REb4gd9JrAH/iaXOi7/z1k+B2iPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"713c05acdfd2db759457a3df781eb68bcfbca69b77591b553fa4f1d8d39dc0c0","last_reissued_at":"2026-07-05T06:26:17.975692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:17.975692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WDC Products: A Multi-Dimensional Entity Matching Benchmark","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christian Bizer, Ralph Peeters, Reng Chiz Der","submitted_at":"2023-01-23T16:12:18Z","abstract_excerpt":"The difficulty of an entity matching task depends on a combination of multiple factors such as the amount of corner-case pairs, the fraction of entities in the test set that have not been seen during training, and the size of the development set. Current entity matching benchmarks usually represent single points in the space along such dimensions or they provide for the evaluation of matching methods along a single dimension, for instance the amount of training data. This paper presents WDC Products, an entity matching benchmark which provides for the systematic evaluation of matching systems "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09521","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/2301.09521/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":"2301.09521","created_at":"2026-07-05T06:26:17.975760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.09521v2","created_at":"2026-07-05T06:26:17.975760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09521","created_at":"2026-07-05T06:26:17.975760+00:00"},{"alias_kind":"pith_short_12","alias_value":"OE6ALLG72LNX","created_at":"2026-07-05T06:26:17.975760+00:00"},{"alias_kind":"pith_short_16","alias_value":"OE6ALLG72LNXLFCX","created_at":"2026-07-05T06:26:17.975760+00:00"},{"alias_kind":"pith_short_8","alias_value":"OE6ALLG7","created_at":"2026-07-05T06:26:17.975760+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24407","citing_title":"Entity Resolution via Batched Oracle Queries","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27342","citing_title":"Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17524","citing_title":"Learning to Refine Hidden States for Reliable LLM Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27342","citing_title":"Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP","json":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP.json","graph_json":"https://pith.science/api/pith-number/OE6ALLG72LNXLFCXUPPXQHVWRP/graph.json","events_json":"https://pith.science/api/pith-number/OE6ALLG72LNXLFCXUPPXQHVWRP/events.json","paper":"https://pith.science/paper/OE6ALLG7"},"agent_actions":{"view_html":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP","download_json":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP.json","view_paper":"https://pith.science/paper/OE6ALLG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.09521&json=true","fetch_graph":"https://pith.science/api/pith-number/OE6ALLG72LNXLFCXUPPXQHVWRP/graph.json","fetch_events":"https://pith.science/api/pith-number/OE6ALLG72LNXLFCXUPPXQHVWRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP/action/storage_attestation","attest_author":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP/action/author_attestation","sign_citation":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP/action/citation_signature","submit_replication":"https://pith.science/pith/OE6ALLG72LNXLFCXUPPXQHVWRP/action/replication_record"}},"created_at":"2026-07-05T06:26:17.975760+00:00","updated_at":"2026-07-05T06:26:17.975760+00:00"}