{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:Z35C3PNLABJW4PEWJSCBZMGVTW","short_pith_number":"pith:Z35C3PNL","schema_version":"1.0","canonical_sha256":"cefa2dbdab00536e3c964c841cb0d59db1223607f1063738340cfe60acb5424c","source":{"kind":"arxiv","id":"1712.05055","version":2},"attestation_state":"computed","paper":{"title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Fei-Fei, Li-Jia Li, Lu Jiang, Thomas Leung, Zhengyuan Zhou","submitted_at":"2017-12-14T00:02:37Z","abstract_excerpt":"Recent deep networks are capable of memorizing the entire data even when the labels are completely random. To overcome the overfitting on corrupted labels, we propose a novel technique of learning another neural network, called MentorNet, to supervise the training of the base deep networks, namely, StudentNet. During training, MentorNet provides a curriculum (sample weighting scheme) for StudentNet to focus on the sample the label of which is probably correct. Unlike the existing curriculum that is usually predefined by human experts, MentorNet learns a data-driven curriculum dynamically with "},"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":"1712.05055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-14T00:02:37Z","cross_cats_sorted":[],"title_canon_sha256":"e7ce87467b33d631dd4e27461f9fc8d57c3bc7912ee698aea5815922250877ed","abstract_canon_sha256":"9a99469a6a5a4345cb8a3197f38c1ff46250488679381ffd847e50a43c54d9a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:15.709344Z","signature_b64":"U9M4aHydQJfBsgjCYmSniuZxV669kp/9+vqGwb2qXAcUD1QfCq9xYNpcCp5U9MEDYzN1YSNzHAPzezwzNI83Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cefa2dbdab00536e3c964c841cb0d59db1223607f1063738340cfe60acb5424c","last_reissued_at":"2026-05-18T00:08:15.708902Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:15.708902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Fei-Fei, Li-Jia Li, Lu Jiang, Thomas Leung, Zhengyuan Zhou","submitted_at":"2017-12-14T00:02:37Z","abstract_excerpt":"Recent deep networks are capable of memorizing the entire data even when the labels are completely random. To overcome the overfitting on corrupted labels, we propose a novel technique of learning another neural network, called MentorNet, to supervise the training of the base deep networks, namely, StudentNet. During training, MentorNet provides a curriculum (sample weighting scheme) for StudentNet to focus on the sample the label of which is probably correct. Unlike the existing curriculum that is usually predefined by human experts, MentorNet learns a data-driven curriculum dynamically with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.05055","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":""},"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":"1712.05055","created_at":"2026-05-18T00:08:15.708978+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.05055v2","created_at":"2026-05-18T00:08:15.708978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.05055","created_at":"2026-05-18T00:08:15.708978+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z35C3PNLABJW","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z35C3PNLABJW4PEW","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z35C3PNL","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2010.01412","citing_title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW","json":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW.json","graph_json":"https://pith.science/api/pith-number/Z35C3PNLABJW4PEWJSCBZMGVTW/graph.json","events_json":"https://pith.science/api/pith-number/Z35C3PNLABJW4PEWJSCBZMGVTW/events.json","paper":"https://pith.science/paper/Z35C3PNL"},"agent_actions":{"view_html":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW","download_json":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW.json","view_paper":"https://pith.science/paper/Z35C3PNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.05055&json=true","fetch_graph":"https://pith.science/api/pith-number/Z35C3PNLABJW4PEWJSCBZMGVTW/graph.json","fetch_events":"https://pith.science/api/pith-number/Z35C3PNLABJW4PEWJSCBZMGVTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW/action/storage_attestation","attest_author":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW/action/author_attestation","sign_citation":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW/action/citation_signature","submit_replication":"https://pith.science/pith/Z35C3PNLABJW4PEWJSCBZMGVTW/action/replication_record"}},"created_at":"2026-05-18T00:08:15.708978+00:00","updated_at":"2026-05-18T00:08:15.708978+00:00"}