{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6BWCBASSBYVVLNDQVCN5RWUZXB","short_pith_number":"pith:6BWCBASS","schema_version":"1.0","canonical_sha256":"f06c2082520e2b55b470a89bd8da99b8654f5c5c58695c737b8bb8c031177cce","source":{"kind":"arxiv","id":"2012.12960","version":1},"attestation_state":"computed","paper":{"title":"Active Deep Learning on Entity Resolution by Risk Sampling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haiyang He, Qun Chen, Tianyi Duan, Xingyu Lu, Youcef Nafa, Zhanhuai Li, Zhaoqiang Chen","submitted_at":"2020-12-23T20:38:25Z","abstract_excerpt":"While the state-of-the-art performance on entity resolution (ER) has been achieved by deep learning, its effectiveness depends on large quantities of accurately labeled training data. To alleviate the data labeling burden, Active Learning (AL) presents itself as a feasible solution that focuses on data deemed useful for model training. \nBuilding upon the recent advances in risk analysis for ER, which can provide a more refined estimate on label misprediction risk than the simpler classifier outputs, we propose a novel AL approach of risk sampling for ER. Risk sampling leverages misprediction r"},"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":"2012.12960","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-23T20:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"1707fc52c95b3c8dbcc2faee69226a38a16c36a96dce711314cfb61b2d2068c3","abstract_canon_sha256":"888a45476f1ccb269dfc7fa93d9d4643f3e0c87fb10b966be73720b6d8ce7d1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:46.230303Z","signature_b64":"sqIwp45k30hYwp/Jt5GTMXziihTfaMIiVNrUi6jJJAZ9P59Dwr28juuzEikY7uCxWJeApm2rertnL47CPn3iDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f06c2082520e2b55b470a89bd8da99b8654f5c5c58695c737b8bb8c031177cce","last_reissued_at":"2026-07-05T02:01:46.229875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:46.229875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Deep Learning on Entity Resolution by Risk Sampling","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haiyang He, Qun Chen, Tianyi Duan, Xingyu Lu, Youcef Nafa, Zhanhuai Li, Zhaoqiang Chen","submitted_at":"2020-12-23T20:38:25Z","abstract_excerpt":"While the state-of-the-art performance on entity resolution (ER) has been achieved by deep learning, its effectiveness depends on large quantities of accurately labeled training data. To alleviate the data labeling burden, Active Learning (AL) presents itself as a feasible solution that focuses on data deemed useful for model training. \nBuilding upon the recent advances in risk analysis for ER, which can provide a more refined estimate on label misprediction risk than the simpler classifier outputs, we propose a novel AL approach of risk sampling for ER. Risk sampling leverages misprediction r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.12960","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/2012.12960/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":"2012.12960","created_at":"2026-07-05T02:01:46.229938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.12960v1","created_at":"2026-07-05T02:01:46.229938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.12960","created_at":"2026-07-05T02:01:46.229938+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BWCBASSBYVV","created_at":"2026-07-05T02:01:46.229938+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BWCBASSBYVVLNDQ","created_at":"2026-07-05T02:01:46.229938+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BWCBASS","created_at":"2026-07-05T02:01:46.229938+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/6BWCBASSBYVVLNDQVCN5RWUZXB","json":"https://pith.science/pith/6BWCBASSBYVVLNDQVCN5RWUZXB.json","graph_json":"https://pith.science/api/pith-number/6BWCBASSBYVVLNDQVCN5RWUZXB/graph.json","events_json":"https://pith.science/api/pith-number/6BWCBASSBYVVLNDQVCN5RWUZXB/events.json","paper":"https://pith.science/paper/6BWCBASS"},"agent_actions":{"view_html":"https://pith.science/pith/6BWCBASSBYVVLNDQVCN5RWUZXB","download_json":"https://pith.science/pith/6BWCBASSBYVVLNDQVCN5RWUZXB.json","view_paper":"https://pith.science/paper/6BWCBASS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.12960&json=true","fetch_graph":"https://pith.science/api/pith-number/6BWCBASSBYVVLNDQVCN5RWUZXB/graph.json","fetch_events":"https://pith.science/api/pith-number/6BWCBASSBYVVLNDQVCN5RWUZXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BWCBASSBYVVLNDQVCN5RWUZXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BWCBASSBYVVLNDQVCN5RWUZXB/action/storage_attestation","attest_author":"https://pith.science/pith/6BWCBASSBYVVLNDQVCN5RWUZXB/action/author_attestation","sign_citation":"https://pith.science/pith/6BWCBASSBYVVLNDQVCN5RWUZXB/action/citation_signature","submit_replication":"https://pith.science/pith/6BWCBASSBYVVLNDQVCN5RWUZXB/action/replication_record"}},"created_at":"2026-07-05T02:01:46.229938+00:00","updated_at":"2026-07-05T02:01:46.229938+00:00"}