{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2PLC2XMQ3ZLK2ISAT6PHNAJRXH","short_pith_number":"pith:2PLC2XMQ","schema_version":"1.0","canonical_sha256":"d3d62d5d90de56ad22409f9e768131b9ffb032da256e163cc531d0ec6247ab2e","source":{"kind":"arxiv","id":"2002.07394","version":1},"attestation_state":"computed","paper":{"title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junnan Li, Richard Socher, Steven C.H. Hoi","submitted_at":"2020-02-18T06:20:06Z","abstract_excerpt":"Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set wit"},"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":"2002.07394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-18T06:20:06Z","cross_cats_sorted":[],"title_canon_sha256":"b4f529fa9d8bd36503795f7cec3f164d5c40e975516d3c48f9c4c48c50b9e1e5","abstract_canon_sha256":"86787e0cdd01ca3d3125c36c4cea4781572422e06faa88c4d57008d614bc7dce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:24.081706Z","signature_b64":"pAfMpicn4hKtKe+rEnRIZYMPLyrnGz2VzP9M54aGoAeNJy3tJ8Yoz05iVkXKzKf/9ciQVkKD5JPmCs6ceYAGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3d62d5d90de56ad22409f9e768131b9ffb032da256e163cc531d0ec6247ab2e","last_reissued_at":"2026-07-05T00:42:24.081208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:24.081208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junnan Li, Richard Socher, Steven C.H. Hoi","submitted_at":"2020-02-18T06:20:06Z","abstract_excerpt":"Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07394","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/2002.07394/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":"2002.07394","created_at":"2026-07-05T00:42:24.081265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.07394v1","created_at":"2026-07-05T00:42:24.081265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07394","created_at":"2026-07-05T00:42:24.081265+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PLC2XMQ3ZLK","created_at":"2026-07-05T00:42:24.081265+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PLC2XMQ3ZLK2ISA","created_at":"2026-07-05T00:42:24.081265+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PLC2XMQ","created_at":"2026-07-05T00:42:24.081265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05394","citing_title":"Weak-to-Strong Generalization via Direct On-Policy Distillation","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11583","citing_title":"Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11695","citing_title":"Noise-Aware Framework for Correcting Corrupted Labels","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":287,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04306","citing_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","ref_index":265,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":287,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24475","citing_title":"Robust Fuzzy Multi-view Learning under View Conflict","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29837","citing_title":"Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2408.11338","citing_title":"Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20725","citing_title":"Holistic Reliability Propagation: Decoupling Annotation and Prediction for Robust Noisy-Label","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20727","citing_title":"GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17833","citing_title":"Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20786","citing_title":"LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.26158","citing_title":"Towards Continual Expansion of Data Coverage: Automatic Text-guided Edge-case Synthesis","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09315","citing_title":"Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03993","citing_title":"Can LLMs Learn to Reason Robustly under Noisy Supervision?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11383","citing_title":"HamBR: Active Decision Boundary Restoration Based on Hamiltonian Dynamics for Learning with Noisy Labels","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25845","citing_title":"Model-agnostic information transfer and fusion for classification with label noise","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24952","citing_title":"Learning from Noisy Preferences: A Semi-Supervised Learning Approach to Direct Preference Optimization","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04721","citing_title":"SEI-SHIELD: Robust Specific Emitter Identification Under Label Noise Via Self-Supervised Filtering and Iterative Rescue","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12469","citing_title":"Analyzing the Effect of Noise in LLM Fine-tuning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12832","citing_title":"Detecting and refurbishing ground truth errors during training of deep learning-based echocardiography segmentation models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01874","citing_title":"Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11162","citing_title":"Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06468","citing_title":"Conformal Margin Risk Minimization: An Envelope Framework for Robust Learning under Label Noise","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH","json":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH.json","graph_json":"https://pith.science/api/pith-number/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/graph.json","events_json":"https://pith.science/api/pith-number/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/events.json","paper":"https://pith.science/paper/2PLC2XMQ"},"agent_actions":{"view_html":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH","download_json":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH.json","view_paper":"https://pith.science/paper/2PLC2XMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.07394&json=true","fetch_graph":"https://pith.science/api/pith-number/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/graph.json","fetch_events":"https://pith.science/api/pith-number/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/action/storage_attestation","attest_author":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/action/author_attestation","sign_citation":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/action/citation_signature","submit_replication":"https://pith.science/pith/2PLC2XMQ3ZLK2ISAT6PHNAJRXH/action/replication_record"}},"created_at":"2026-07-05T00:42:24.081265+00:00","updated_at":"2026-07-05T00:42:24.081265+00:00"}