{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6MEVQZI7LCZ63BR3TQOD3DTTZT","short_pith_number":"pith:6MEVQZI7","schema_version":"1.0","canonical_sha256":"f30958651f58b3ed863b9c1c3d8e73ccf3b393c364b8297fad2e170c09f2f746","source":{"kind":"arxiv","id":"2110.06282","version":4},"attestation_state":"computed","paper":{"title":"The Rich Get Richer: Disparate Impact of Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Tianyi Luo, Yang Liu, Zhaowei Zhu","submitted_at":"2021-10-12T19:05:06Z","abstract_excerpt":"Semi-supervised learning (SSL) has demonstrated its potential to improve the model accuracy for a variety of learning tasks when the high-quality supervised data is severely limited. Although it is often established that the average accuracy for the entire population of data is improved, it is unclear how SSL fares with different sub-populations. Understanding the above question has substantial fairness implications when different sub-populations are defined by the demographic groups that we aim to treat fairly. In this paper, we reveal the disparate impacts of deploying SSL: the sub-populatio"},"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":"2110.06282","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-12T19:05:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d778ae8f6874ccd81755b9175b3797d94c1270a168ff21f1e78e54aa77b33485","abstract_canon_sha256":"50b17089d677016522da16b20a866755187b4062b039f6a4d221486a78c1709d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:42.615382Z","signature_b64":"mY/jY0prwJyJGOMIKMbmsjOq3Z9U2glfEVODnSnZF/Dl5rK+YT/tk/upXc/SEFJ757wc42j0efvnKy2Y1An6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f30958651f58b3ed863b9c1c3d8e73ccf3b393c364b8297fad2e170c09f2f746","last_reissued_at":"2026-07-05T06:46:42.614818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:42.614818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Rich Get Richer: Disparate Impact of Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Tianyi Luo, Yang Liu, Zhaowei Zhu","submitted_at":"2021-10-12T19:05:06Z","abstract_excerpt":"Semi-supervised learning (SSL) has demonstrated its potential to improve the model accuracy for a variety of learning tasks when the high-quality supervised data is severely limited. Although it is often established that the average accuracy for the entire population of data is improved, it is unclear how SSL fares with different sub-populations. Understanding the above question has substantial fairness implications when different sub-populations are defined by the demographic groups that we aim to treat fairly. In this paper, we reveal the disparate impacts of deploying SSL: the sub-populatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06282","kind":"arxiv","version":4},"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/2110.06282/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":"2110.06282","created_at":"2026-07-05T06:46:42.614877+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06282v4","created_at":"2026-07-05T06:46:42.614877+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06282","created_at":"2026-07-05T06:46:42.614877+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MEVQZI7LCZ6","created_at":"2026-07-05T06:46:42.614877+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MEVQZI7LCZ63BR3","created_at":"2026-07-05T06:46:42.614877+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MEVQZI7","created_at":"2026-07-05T06:46:42.614877+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11959","citing_title":"Noise-Resilient Point-wise Anomaly Detection in Time Series Using Weak Segment Labels","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT","json":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT.json","graph_json":"https://pith.science/api/pith-number/6MEVQZI7LCZ63BR3TQOD3DTTZT/graph.json","events_json":"https://pith.science/api/pith-number/6MEVQZI7LCZ63BR3TQOD3DTTZT/events.json","paper":"https://pith.science/paper/6MEVQZI7"},"agent_actions":{"view_html":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT","download_json":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT.json","view_paper":"https://pith.science/paper/6MEVQZI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06282&json=true","fetch_graph":"https://pith.science/api/pith-number/6MEVQZI7LCZ63BR3TQOD3DTTZT/graph.json","fetch_events":"https://pith.science/api/pith-number/6MEVQZI7LCZ63BR3TQOD3DTTZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT/action/storage_attestation","attest_author":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT/action/author_attestation","sign_citation":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT/action/citation_signature","submit_replication":"https://pith.science/pith/6MEVQZI7LCZ63BR3TQOD3DTTZT/action/replication_record"}},"created_at":"2026-07-05T06:46:42.614877+00:00","updated_at":"2026-07-05T06:46:42.614877+00:00"}