{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NTLQRZOCAYWPBFYIQP2A4MVJSO","short_pith_number":"pith:NTLQRZOC","schema_version":"1.0","canonical_sha256":"6cd708e5c2062cf0970883f40e32a993bdc2d479ed59e92034dd335bcf26f225","source":{"kind":"arxiv","id":"2508.09697","version":3},"attestation_state":"computed","paper":{"title":"Towards Label-Noise Resistant Learning via Optimal Brain Damage Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chuanyi Zhang, Fan Cheng, Fan Liu, Qian Li, Xinlei Zhang, Yuhui Zheng","submitted_at":"2025-08-13T10:51:46Z","abstract_excerpt":"Noisy labels are inevitable in real-world scenarios. Due to the strong capacity of deep neural networks to memorize corrupted labels, these noisy labels cause significant performance degradation. Existing noise-robust methods have mainly focused on robust loss functions and sample selection, with comparatively limited exploration of dynamic architectural adaptation. In this paper, we rethink the role of model connectivity in the presence of label noise. Intuitively, performance degradation caused by noisy labels stems from the backpropagation of noisy gradients. Since the final classifier laye"},"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":"2508.09697","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-13T10:51:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"19335ad6ec0f472d712db45835d056b4429a8b7c286080d8093d22914b68b702","abstract_canon_sha256":"243777ec1c533d339ba81f520c54ebe507aedca441b88e65991db0c8c4b32390"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:15.345056Z","signature_b64":"SgzPjeJsAz7JGocaTpqFWsCCwq9BydIcOAzgFovKXbwCHLTtCN/j4vwOME+Obh+vqDYGSbgTgEL1NVOUueA1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cd708e5c2062cf0970883f40e32a993bdc2d479ed59e92034dd335bcf26f225","last_reissued_at":"2026-06-05T01:15:15.344173Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:15.344173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Label-Noise Resistant Learning via Optimal Brain Damage Masking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chuanyi Zhang, Fan Cheng, Fan Liu, Qian Li, Xinlei Zhang, Yuhui Zheng","submitted_at":"2025-08-13T10:51:46Z","abstract_excerpt":"Noisy labels are inevitable in real-world scenarios. Due to the strong capacity of deep neural networks to memorize corrupted labels, these noisy labels cause significant performance degradation. Existing noise-robust methods have mainly focused on robust loss functions and sample selection, with comparatively limited exploration of dynamic architectural adaptation. In this paper, we rethink the role of model connectivity in the presence of label noise. Intuitively, performance degradation caused by noisy labels stems from the backpropagation of noisy gradients. Since the final classifier laye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09697","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/2508.09697/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":"2508.09697","created_at":"2026-06-05T01:15:15.344270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09697v3","created_at":"2026-06-05T01:15:15.344270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09697","created_at":"2026-06-05T01:15:15.344270+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTLQRZOCAYWP","created_at":"2026-06-05T01:15:15.344270+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTLQRZOCAYWPBFYI","created_at":"2026-06-05T01:15:15.344270+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTLQRZOC","created_at":"2026-06-05T01:15:15.344270+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/NTLQRZOCAYWPBFYIQP2A4MVJSO","json":"https://pith.science/pith/NTLQRZOCAYWPBFYIQP2A4MVJSO.json","graph_json":"https://pith.science/api/pith-number/NTLQRZOCAYWPBFYIQP2A4MVJSO/graph.json","events_json":"https://pith.science/api/pith-number/NTLQRZOCAYWPBFYIQP2A4MVJSO/events.json","paper":"https://pith.science/paper/NTLQRZOC"},"agent_actions":{"view_html":"https://pith.science/pith/NTLQRZOCAYWPBFYIQP2A4MVJSO","download_json":"https://pith.science/pith/NTLQRZOCAYWPBFYIQP2A4MVJSO.json","view_paper":"https://pith.science/paper/NTLQRZOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09697&json=true","fetch_graph":"https://pith.science/api/pith-number/NTLQRZOCAYWPBFYIQP2A4MVJSO/graph.json","fetch_events":"https://pith.science/api/pith-number/NTLQRZOCAYWPBFYIQP2A4MVJSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTLQRZOCAYWPBFYIQP2A4MVJSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTLQRZOCAYWPBFYIQP2A4MVJSO/action/storage_attestation","attest_author":"https://pith.science/pith/NTLQRZOCAYWPBFYIQP2A4MVJSO/action/author_attestation","sign_citation":"https://pith.science/pith/NTLQRZOCAYWPBFYIQP2A4MVJSO/action/citation_signature","submit_replication":"https://pith.science/pith/NTLQRZOCAYWPBFYIQP2A4MVJSO/action/replication_record"}},"created_at":"2026-06-05T01:15:15.344270+00:00","updated_at":"2026-06-05T01:15:15.344270+00:00"}