{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3OINIOWTUBQ53DO7EVATSE7WO6","short_pith_number":"pith:3OINIOWT","schema_version":"1.0","canonical_sha256":"db90d43ad3a061dd8ddf25413913f67799039cee2afc6ca77430120110331de8","source":{"kind":"arxiv","id":"1908.09822","version":3},"attestation_state":"computed","paper":{"title":"Confidence Regularized Self-Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"B. V. K. Vijaya Kumar, Jinsong Wang, Xiaofeng Liu, Yang Zou, Zhiding Yu","submitted_at":"2019-08-26T17:56:13Z","abstract_excerpt":"Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident predictions as pseudo-labels for retraining. However, since pseudo-labels can be noisy, self-training can put overconfident label belief on wrong classes, leading to deviated solutions with propagated errors. To address the problem, we propose a confidence regularized self-training (CRST) framework, formulated as regularized self-training. Our method treats ps"},"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":"1908.09822","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2019-08-26T17:56:13Z","cross_cats_sorted":["cs.LG","cs.MM","cs.RO"],"title_canon_sha256":"cf3f072fc6809f97a29cc626ccfb304306f685891b7f5c55e140a979303a326a","abstract_canon_sha256":"35e01bfada318335cb1f567f78c5d346c2615484a0de7c4c806c367c4a850ca8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:24.729348Z","signature_b64":"izxSqz7eHziz6JTmnDIb7+YQLG/eMOdlzNe4ZSTQAc5/Vb0SBtgFGLMRElwB3iki9iuubUlNe9JHGNPjpFqoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db90d43ad3a061dd8ddf25413913f67799039cee2afc6ca77430120110331de8","last_reissued_at":"2026-07-05T01:19:24.728870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:24.728870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence Regularized Self-Training","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"B. V. K. Vijaya Kumar, Jinsong Wang, Xiaofeng Liu, Yang Zou, Zhiding Yu","submitted_at":"2019-08-26T17:56:13Z","abstract_excerpt":"Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident predictions as pseudo-labels for retraining. However, since pseudo-labels can be noisy, self-training can put overconfident label belief on wrong classes, leading to deviated solutions with propagated errors. To address the problem, we propose a confidence regularized self-training (CRST) framework, formulated as regularized self-training. Our method treats ps"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09822","kind":"arxiv","version":3},"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/1908.09822/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":"1908.09822","created_at":"2026-07-05T01:19:24.728933+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09822v3","created_at":"2026-07-05T01:19:24.728933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09822","created_at":"2026-07-05T01:19:24.728933+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OINIOWTUBQ5","created_at":"2026-07-05T01:19:24.728933+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OINIOWTUBQ53DO7","created_at":"2026-07-05T01:19:24.728933+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OINIOWT","created_at":"2026-07-05T01:19:24.728933+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/3OINIOWTUBQ53DO7EVATSE7WO6","json":"https://pith.science/pith/3OINIOWTUBQ53DO7EVATSE7WO6.json","graph_json":"https://pith.science/api/pith-number/3OINIOWTUBQ53DO7EVATSE7WO6/graph.json","events_json":"https://pith.science/api/pith-number/3OINIOWTUBQ53DO7EVATSE7WO6/events.json","paper":"https://pith.science/paper/3OINIOWT"},"agent_actions":{"view_html":"https://pith.science/pith/3OINIOWTUBQ53DO7EVATSE7WO6","download_json":"https://pith.science/pith/3OINIOWTUBQ53DO7EVATSE7WO6.json","view_paper":"https://pith.science/paper/3OINIOWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09822&json=true","fetch_graph":"https://pith.science/api/pith-number/3OINIOWTUBQ53DO7EVATSE7WO6/graph.json","fetch_events":"https://pith.science/api/pith-number/3OINIOWTUBQ53DO7EVATSE7WO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OINIOWTUBQ53DO7EVATSE7WO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OINIOWTUBQ53DO7EVATSE7WO6/action/storage_attestation","attest_author":"https://pith.science/pith/3OINIOWTUBQ53DO7EVATSE7WO6/action/author_attestation","sign_citation":"https://pith.science/pith/3OINIOWTUBQ53DO7EVATSE7WO6/action/citation_signature","submit_replication":"https://pith.science/pith/3OINIOWTUBQ53DO7EVATSE7WO6/action/replication_record"}},"created_at":"2026-07-05T01:19:24.728933+00:00","updated_at":"2026-07-05T01:19:24.728933+00:00"}