{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UJWN42D75WBM6X3YMZA2F3IWOP","short_pith_number":"pith:UJWN42D7","schema_version":"1.0","canonical_sha256":"a26cde687fed82cf5f786641a2ed1673f9badc45191838c92314403704ad3cc0","source":{"kind":"arxiv","id":"2408.14358","version":3},"attestation_state":"computed","paper":{"title":"An Embedding is Worth a Thousand Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Christian Ledig, Francesco Di Salvo, Ines Rieger, Sebastian Doerrich","submitted_at":"2024-08-26T15:32:31Z","abstract_excerpt":"The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address label noise exhibit severe limitations due to computational complexity and application dependency. In this work, we propose WANN, a Weighted Adaptive Nearest Neighbor approach that builds on self-supervised feature representations obtained from foundation models. To guide the weighted voting scheme, we introduce a reliability score $\\eta$, which measures the l"},"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":"2408.14358","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T15:32:31Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"ec08f729df48a0fa7ddb2d5c5fb2a6ffe5e4ecd2837a22614d6ed769190fc961","abstract_canon_sha256":"ba63adf001974caeb6320f85de763ee3e13a560005d18c91d16f2a824142ad5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:18.811070Z","signature_b64":"A3O/AVa2bPkaU/jSL9G1Qj1d/pgCo3F0J8XK0vzFv6KA0aQ9TVJ2oGJ47KqdKnO3JFATxKEpEoeqy//hXtM9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a26cde687fed82cf5f786641a2ed1673f9badc45191838c92314403704ad3cc0","last_reissued_at":"2026-07-05T10:48:18.810606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:18.810606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Embedding is Worth a Thousand Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Christian Ledig, Francesco Di Salvo, Ines Rieger, Sebastian Doerrich","submitted_at":"2024-08-26T15:32:31Z","abstract_excerpt":"The performance of deep neural networks scales with dataset size and label quality, rendering the efficient mitigation of low-quality data annotations crucial for building robust and cost-effective systems. Existing strategies to address label noise exhibit severe limitations due to computational complexity and application dependency. In this work, we propose WANN, a Weighted Adaptive Nearest Neighbor approach that builds on self-supervised feature representations obtained from foundation models. To guide the weighted voting scheme, we introduce a reliability score $\\eta$, which measures the l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14358","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/2408.14358/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":"2408.14358","created_at":"2026-07-05T10:48:18.810659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14358v3","created_at":"2026-07-05T10:48:18.810659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14358","created_at":"2026-07-05T10:48:18.810659+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJWN42D75WBM","created_at":"2026-07-05T10:48:18.810659+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJWN42D75WBM6X3Y","created_at":"2026-07-05T10:48:18.810659+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJWN42D7","created_at":"2026-07-05T10:48:18.810659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29837","citing_title":"Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29720","citing_title":"Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP","json":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP.json","graph_json":"https://pith.science/api/pith-number/UJWN42D75WBM6X3YMZA2F3IWOP/graph.json","events_json":"https://pith.science/api/pith-number/UJWN42D75WBM6X3YMZA2F3IWOP/events.json","paper":"https://pith.science/paper/UJWN42D7"},"agent_actions":{"view_html":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP","download_json":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP.json","view_paper":"https://pith.science/paper/UJWN42D7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14358&json=true","fetch_graph":"https://pith.science/api/pith-number/UJWN42D75WBM6X3YMZA2F3IWOP/graph.json","fetch_events":"https://pith.science/api/pith-number/UJWN42D75WBM6X3YMZA2F3IWOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP/action/storage_attestation","attest_author":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP/action/author_attestation","sign_citation":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP/action/citation_signature","submit_replication":"https://pith.science/pith/UJWN42D75WBM6X3YMZA2F3IWOP/action/replication_record"}},"created_at":"2026-07-05T10:48:18.810659+00:00","updated_at":"2026-07-05T10:48:18.810659+00:00"}