{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RBC4ML2QIEZNCRSAQDMABBKS37","short_pith_number":"pith:RBC4ML2Q","schema_version":"1.0","canonical_sha256":"8845c62f504132d1464080d8008552dfee98b4f49e37fb47da54c151cc5924dc","source":{"kind":"arxiv","id":"2506.02154","version":1},"attestation_state":"computed","paper":{"title":"Z-Error Loss for Training Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guillaume Godin","submitted_at":"2025-06-02T18:35:30Z","abstract_excerpt":"Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that minimizes outlier influence during training by masking the contribution of data points identified as out-of-distribution within each batch. This method leverages batch-level statistics to automatically detect and exclude anomalous samples, allowing the model to focus its learning on the true underlying data structure. Our approach is robust, adaptive to data quality"},"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":"2506.02154","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-02T18:35:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f6f57910761b1f7f21322d3fda6d0f5244737836ca115453cc7e26f4db871182","abstract_canon_sha256":"61060704d98805fe89ef7c94e6a5b4b104f786a7a00fb1b4e4a72f42ce6eec10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:33.435113Z","signature_b64":"z+m1wB5Ox/ZfRaQ5KL9hJPWmwm20s9qGd3J/wd5Co/Y1CkVNVtpVuSbG2qG6pfrOvYmwAwT0qMpkynBhv+RMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8845c62f504132d1464080d8008552dfee98b4f49e37fb47da54c151cc5924dc","last_reissued_at":"2026-07-05T11:14:33.434672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:33.434672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Z-Error Loss for Training Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guillaume Godin","submitted_at":"2025-06-02T18:35:30Z","abstract_excerpt":"Outliers introduce significant training challenges in neural networks by propagating erroneous gradients, which can degrade model performance and generalization. We propose the Z-Error Loss, a statistically principled approach that minimizes outlier influence during training by masking the contribution of data points identified as out-of-distribution within each batch. This method leverages batch-level statistics to automatically detect and exclude anomalous samples, allowing the model to focus its learning on the true underlying data structure. Our approach is robust, adaptive to data quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02154","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/2506.02154/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":"2506.02154","created_at":"2026-07-05T11:14:33.434729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02154v1","created_at":"2026-07-05T11:14:33.434729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02154","created_at":"2026-07-05T11:14:33.434729+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBC4ML2QIEZN","created_at":"2026-07-05T11:14:33.434729+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBC4ML2QIEZNCRSA","created_at":"2026-07-05T11:14:33.434729+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBC4ML2Q","created_at":"2026-07-05T11:14:33.434729+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/RBC4ML2QIEZNCRSAQDMABBKS37","json":"https://pith.science/pith/RBC4ML2QIEZNCRSAQDMABBKS37.json","graph_json":"https://pith.science/api/pith-number/RBC4ML2QIEZNCRSAQDMABBKS37/graph.json","events_json":"https://pith.science/api/pith-number/RBC4ML2QIEZNCRSAQDMABBKS37/events.json","paper":"https://pith.science/paper/RBC4ML2Q"},"agent_actions":{"view_html":"https://pith.science/pith/RBC4ML2QIEZNCRSAQDMABBKS37","download_json":"https://pith.science/pith/RBC4ML2QIEZNCRSAQDMABBKS37.json","view_paper":"https://pith.science/paper/RBC4ML2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02154&json=true","fetch_graph":"https://pith.science/api/pith-number/RBC4ML2QIEZNCRSAQDMABBKS37/graph.json","fetch_events":"https://pith.science/api/pith-number/RBC4ML2QIEZNCRSAQDMABBKS37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBC4ML2QIEZNCRSAQDMABBKS37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBC4ML2QIEZNCRSAQDMABBKS37/action/storage_attestation","attest_author":"https://pith.science/pith/RBC4ML2QIEZNCRSAQDMABBKS37/action/author_attestation","sign_citation":"https://pith.science/pith/RBC4ML2QIEZNCRSAQDMABBKS37/action/citation_signature","submit_replication":"https://pith.science/pith/RBC4ML2QIEZNCRSAQDMABBKS37/action/replication_record"}},"created_at":"2026-07-05T11:14:33.434729+00:00","updated_at":"2026-07-05T11:14:33.434729+00:00"}