{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RKOKA6MWUTTWOL2DZSLIVEHQCV","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":"caa241d894135a1a8644abf0341de7905a5c5a643ffe202bbc84a11e841ccd9b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-03-29T19:08:03Z","title_canon_sha256":"290367fa42bac2e027429419dcee6ef5754262bbe4433f122c27c83b758dc3d9"},"schema_version":"1.0","source":{"id":"2003.13114","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13114","created_at":"2026-07-05T00:51:12Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13114v1","created_at":"2026-07-05T00:51:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13114","created_at":"2026-07-05T00:51:12Z"},{"alias_kind":"pith_short_12","alias_value":"RKOKA6MWUTTW","created_at":"2026-07-05T00:51:12Z"},{"alias_kind":"pith_short_16","alias_value":"RKOKA6MWUTTWOL2D","created_at":"2026-07-05T00:51:12Z"},{"alias_kind":"pith_short_8","alias_value":"RKOKA6MW","created_at":"2026-07-05T00:51:12Z"}],"graph_snapshots":[{"event_id":"sha256:51322129e435451ed5c718c1475a731a8cf7ba23dde5e3d9041a7282a43e139b","target":"graph","created_at":"2026-07-05T00:51:12Z","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/2003.13114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entity Matching (EM) is a core data cleaning task, aiming to identify different mentions of the same real-world entity. Active learning is one way to address the challenge of scarce labeled data in practice, by dynamically collecting the necessary examples to be labeled by an Oracle and refining the learned model (classifier) upon them. In this paper, we build a unified active learning benchmark framework for EM that allows users to easily combine different learning algorithms with applicable example selection algorithms. The goal of the framework is to enable concrete guidelines for practitio","authors_text":"Lucian Popa, Mohamed Sarwat, Prithviraj Sen, Venkata Vamsikrishna Meduri","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-03-29T19:08:03Z","title":"A Comprehensive Benchmark Framework for Active Learning Methods in Entity Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13114","kind":"arxiv","version":1},"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:b31bfd955480e3597787f308e8ed41728fa4435f9f5cba49b6c18d0a17cfbd15","target":"record","created_at":"2026-07-05T00:51:12Z","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":"caa241d894135a1a8644abf0341de7905a5c5a643ffe202bbc84a11e841ccd9b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2020-03-29T19:08:03Z","title_canon_sha256":"290367fa42bac2e027429419dcee6ef5754262bbe4433f122c27c83b758dc3d9"},"schema_version":"1.0","source":{"id":"2003.13114","kind":"arxiv","version":1}},"canonical_sha256":"8a9ca07996a4e7672f43cc968a90f01566990b17443c2ca5f36a3c98afe5c0ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a9ca07996a4e7672f43cc968a90f01566990b17443c2ca5f36a3c98afe5c0ec","first_computed_at":"2026-07-05T00:51:12.737524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:12.737524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VCnQDqZ1CxrSPAj3WDXNJ+r6Avn8IEHF+Vu/WD8wv9qaIMyDAZwD3RMvY30OkW5xzVZld+Ru0/UQoJDFM+RpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:12.737890Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.13114","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b31bfd955480e3597787f308e8ed41728fa4435f9f5cba49b6c18d0a17cfbd15","sha256:51322129e435451ed5c718c1475a731a8cf7ba23dde5e3d9041a7282a43e139b"],"state_sha256":"bd80121076e15537c84f457bbba5ad65dfece3dd44451e1a8642cdf570da2672"}