{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:WLTTJ2NYNURJQU7TRPKOHPRXK6","short_pith_number":"pith:WLTTJ2NY","schema_version":"1.0","canonical_sha256":"b2e734e9b86d229853f38bd4e3be37579282fd63fec102ab184e4a2e95c7a3bb","source":{"kind":"arxiv","id":"1208.1927","version":1},"attestation_state":"computed","paper":{"title":"CrowdER: Crowdsourcing Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jianhua Feng, Jiannan Wang, Michael J. Franklin, Tim Kraska","submitted_at":"2012-08-09T14:46:38Z","abstract_excerpt":"Entity resolution is central to data integration and data cleaning. Algorithmic approaches have been improving in quality, but remain far from perfect. Crowdsourcing platforms offer a more accurate but expensive (and slow) way to bring human insight into the process. Previous work has proposed batching verification tasks for presentation to human workers but even with batching, a human-only approach is infeasible for data sets of even moderate size, due to the large numbers of matches to be tested. Instead, we propose a hybrid human-machine approach in which machines are used to do an initial,"},"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":"1208.1927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-08-09T14:46:38Z","cross_cats_sorted":[],"title_canon_sha256":"39f62423076c285ad6f6fd0119cec6dbd2b5376f4b29818cb51aac8cc925f88d","abstract_canon_sha256":"4269399c3f6c01b889528cb6ffd48549ffee05f09ca9f1e533f0bd317204509f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:49:09.666780Z","signature_b64":"a7qDj6NKBGBgSOaArDt41DNY638XpOULR3spzhGdtqO5GVztv3a88eRavr75CjSGHMn0k6nKA7iKvXk6Hlh8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2e734e9b86d229853f38bd4e3be37579282fd63fec102ab184e4a2e95c7a3bb","last_reissued_at":"2026-05-18T03:49:09.666291Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:49:09.666291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrowdER: Crowdsourcing Entity Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Jianhua Feng, Jiannan Wang, Michael J. Franklin, Tim Kraska","submitted_at":"2012-08-09T14:46:38Z","abstract_excerpt":"Entity resolution is central to data integration and data cleaning. Algorithmic approaches have been improving in quality, but remain far from perfect. Crowdsourcing platforms offer a more accurate but expensive (and slow) way to bring human insight into the process. Previous work has proposed batching verification tasks for presentation to human workers but even with batching, a human-only approach is infeasible for data sets of even moderate size, due to the large numbers of matches to be tested. Instead, we propose a hybrid human-machine approach in which machines are used to do an initial,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.1927","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":""},"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":"1208.1927","created_at":"2026-05-18T03:49:09.666389+00:00"},{"alias_kind":"arxiv_version","alias_value":"1208.1927v1","created_at":"2026-05-18T03:49:09.666389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.1927","created_at":"2026-05-18T03:49:09.666389+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLTTJ2NYNURJ","created_at":"2026-05-18T12:27:25.539911+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLTTJ2NYNURJQU7T","created_at":"2026-05-18T12:27:25.539911+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLTTJ2NY","created_at":"2026-05-18T12:27:25.539911+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.25814","citing_title":"Adaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6","json":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6.json","graph_json":"https://pith.science/api/pith-number/WLTTJ2NYNURJQU7TRPKOHPRXK6/graph.json","events_json":"https://pith.science/api/pith-number/WLTTJ2NYNURJQU7TRPKOHPRXK6/events.json","paper":"https://pith.science/paper/WLTTJ2NY"},"agent_actions":{"view_html":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6","download_json":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6.json","view_paper":"https://pith.science/paper/WLTTJ2NY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1208.1927&json=true","fetch_graph":"https://pith.science/api/pith-number/WLTTJ2NYNURJQU7TRPKOHPRXK6/graph.json","fetch_events":"https://pith.science/api/pith-number/WLTTJ2NYNURJQU7TRPKOHPRXK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6/action/storage_attestation","attest_author":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6/action/author_attestation","sign_citation":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6/action/citation_signature","submit_replication":"https://pith.science/pith/WLTTJ2NYNURJQU7TRPKOHPRXK6/action/replication_record"}},"created_at":"2026-05-18T03:49:09.666389+00:00","updated_at":"2026-05-18T03:49:09.666389+00:00"}