{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RNXGU4PTSCZLWRUXGBPMDSW7UM","short_pith_number":"pith:RNXGU4PT","schema_version":"1.0","canonical_sha256":"8b6e6a71f390b2bb4697305ec1cadfa33624ac10e5d9b8e6de9061456ca22a14","source":{"kind":"arxiv","id":"2507.11807","version":1},"attestation_state":"computed","paper":{"title":"CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongyu Zhang, Elke Rundensteiner, Huayi Zhang, Ruofan Hu","submitted_at":"2025-07-16T00:03:07Z","abstract_excerpt":"Learning with noisy labels (LNL) is essential for training deep neural networks with imperfect data. Meta-learning approaches have achieved success by using a clean unbiased labeled set to train a robust model. However, this approach heavily depends on the availability of a clean labeled meta-dataset, which is difficult to obtain in practice. In this work, we thus tackle the challenge of meta-learning for noisy label scenarios without relying on a clean labeled dataset. Our approach leverages the data itself while bypassing the need for labels. Building on the insight that clean samples effect"},"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":"2507.11807","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T00:03:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa7d304b417b3f48eebc66be4f9ae1d08e73d6b27e402140a2a3455d510be6e4","abstract_canon_sha256":"3386efb6d44950d4e7ffcd127423c5da749f4dea595b1d2d6de5cef8d51b2b7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:51.230453Z","signature_b64":"AfC0LAt4ZhvN2LKbA4A9u6flQ0Ans5sKRf0N78u2xKeMIHqYO1ptBpsujafruYAO/ZN+xilEDln8Xl7pgaS/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b6e6a71f390b2bb4697305ec1cadfa33624ac10e5d9b8e6de9061456ca22a14","last_reissued_at":"2026-07-05T11:37:51.229927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:51.229927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongyu Zhang, Elke Rundensteiner, Huayi Zhang, Ruofan Hu","submitted_at":"2025-07-16T00:03:07Z","abstract_excerpt":"Learning with noisy labels (LNL) is essential for training deep neural networks with imperfect data. Meta-learning approaches have achieved success by using a clean unbiased labeled set to train a robust model. However, this approach heavily depends on the availability of a clean labeled meta-dataset, which is difficult to obtain in practice. In this work, we thus tackle the challenge of meta-learning for noisy label scenarios without relying on a clean labeled dataset. Our approach leverages the data itself while bypassing the need for labels. Building on the insight that clean samples effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11807","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/2507.11807/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":"2507.11807","created_at":"2026-07-05T11:37:51.229997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11807v1","created_at":"2026-07-05T11:37:51.229997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11807","created_at":"2026-07-05T11:37:51.229997+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNXGU4PTSCZL","created_at":"2026-07-05T11:37:51.229997+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNXGU4PTSCZLWRUX","created_at":"2026-07-05T11:37:51.229997+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNXGU4PT","created_at":"2026-07-05T11:37:51.229997+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/RNXGU4PTSCZLWRUXGBPMDSW7UM","json":"https://pith.science/pith/RNXGU4PTSCZLWRUXGBPMDSW7UM.json","graph_json":"https://pith.science/api/pith-number/RNXGU4PTSCZLWRUXGBPMDSW7UM/graph.json","events_json":"https://pith.science/api/pith-number/RNXGU4PTSCZLWRUXGBPMDSW7UM/events.json","paper":"https://pith.science/paper/RNXGU4PT"},"agent_actions":{"view_html":"https://pith.science/pith/RNXGU4PTSCZLWRUXGBPMDSW7UM","download_json":"https://pith.science/pith/RNXGU4PTSCZLWRUXGBPMDSW7UM.json","view_paper":"https://pith.science/paper/RNXGU4PT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11807&json=true","fetch_graph":"https://pith.science/api/pith-number/RNXGU4PTSCZLWRUXGBPMDSW7UM/graph.json","fetch_events":"https://pith.science/api/pith-number/RNXGU4PTSCZLWRUXGBPMDSW7UM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNXGU4PTSCZLWRUXGBPMDSW7UM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNXGU4PTSCZLWRUXGBPMDSW7UM/action/storage_attestation","attest_author":"https://pith.science/pith/RNXGU4PTSCZLWRUXGBPMDSW7UM/action/author_attestation","sign_citation":"https://pith.science/pith/RNXGU4PTSCZLWRUXGBPMDSW7UM/action/citation_signature","submit_replication":"https://pith.science/pith/RNXGU4PTSCZLWRUXGBPMDSW7UM/action/replication_record"}},"created_at":"2026-07-05T11:37:51.229997+00:00","updated_at":"2026-07-05T11:37:51.229997+00:00"}