{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GZK6HPDREL7X7GQR6G65XSLZTG","short_pith_number":"pith:GZK6HPDR","schema_version":"1.0","canonical_sha256":"3655e3bc7122ff7f9a11f1bddbc97999a584908f6b18db71f3205e3dd4e584b1","source":{"kind":"arxiv","id":"1904.09331","version":2},"attestation_state":"computed","paper":{"title":"Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Liyuan Liu, Maosen Zhang, Qinyuan Ye, Xiang Ren","submitted_at":"2019-04-19T20:23:27Z","abstract_excerpt":"In recent years there is a surge of interest in applying distant supervision (DS) to automatically generate training data for relation extraction (RE). In this paper, we study the problem what limits the performance of DS-trained neural models, conduct thorough analyses, and identify a factor that can influence the performance greatly, shifted label distribution. Specifically, we found this problem commonly exists in real-world DS datasets, and without special handing, typical DS-RE models cannot automatically adapt to this shift, thus achieving deteriorated performance. To further validate ou"},"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":"1904.09331","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-19T20:23:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dfd2dae3d8223b3fdf5271b04e1f440c29a673c181923207c62698c19593fd9e","abstract_canon_sha256":"540b9fc26e244ffa515bbf0cceffda643f4665aa3b4a01e5640f98262ba5bda0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:14.550417Z","signature_b64":"rOQc3MJexiiPSQDv9EoTe+T6v/QQGIap6t8/8fMFRdDyVJ1zXjvBOUMY2wI5g6qABtQZNntvxsb/pzgFUz5YAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3655e3bc7122ff7f9a11f1bddbc97999a584908f6b18db71f3205e3dd4e584b1","last_reissued_at":"2026-07-05T00:03:14.549968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:14.549968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Liyuan Liu, Maosen Zhang, Qinyuan Ye, Xiang Ren","submitted_at":"2019-04-19T20:23:27Z","abstract_excerpt":"In recent years there is a surge of interest in applying distant supervision (DS) to automatically generate training data for relation extraction (RE). In this paper, we study the problem what limits the performance of DS-trained neural models, conduct thorough analyses, and identify a factor that can influence the performance greatly, shifted label distribution. Specifically, we found this problem commonly exists in real-world DS datasets, and without special handing, typical DS-RE models cannot automatically adapt to this shift, thus achieving deteriorated performance. To further validate ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09331","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/1904.09331/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":"1904.09331","created_at":"2026-07-05T00:03:14.550027+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09331v2","created_at":"2026-07-05T00:03:14.550027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09331","created_at":"2026-07-05T00:03:14.550027+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZK6HPDREL7X","created_at":"2026-07-05T00:03:14.550027+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZK6HPDREL7X7GQR","created_at":"2026-07-05T00:03:14.550027+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZK6HPDR","created_at":"2026-07-05T00:03:14.550027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05002","citing_title":"Learning Stable Predictors from Weak Supervision under Distribution Shift","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05002","citing_title":"Learning Stable Predictors from Weak Supervision under Distribution Shift","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG","json":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG.json","graph_json":"https://pith.science/api/pith-number/GZK6HPDREL7X7GQR6G65XSLZTG/graph.json","events_json":"https://pith.science/api/pith-number/GZK6HPDREL7X7GQR6G65XSLZTG/events.json","paper":"https://pith.science/paper/GZK6HPDR"},"agent_actions":{"view_html":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG","download_json":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG.json","view_paper":"https://pith.science/paper/GZK6HPDR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09331&json=true","fetch_graph":"https://pith.science/api/pith-number/GZK6HPDREL7X7GQR6G65XSLZTG/graph.json","fetch_events":"https://pith.science/api/pith-number/GZK6HPDREL7X7GQR6G65XSLZTG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG/action/storage_attestation","attest_author":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG/action/author_attestation","sign_citation":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG/action/citation_signature","submit_replication":"https://pith.science/pith/GZK6HPDREL7X7GQR6G65XSLZTG/action/replication_record"}},"created_at":"2026-07-05T00:03:14.550027+00:00","updated_at":"2026-07-05T00:03:14.550027+00:00"}