{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FGOVA3XF2JO26QZ2GQX3V3BGEN","short_pith_number":"pith:FGOVA3XF","schema_version":"1.0","canonical_sha256":"299d506ee5d25daf433a342fbaec26235b58687a7112ea1c913594723d255ad3","source":{"kind":"arxiv","id":"2212.04461","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Unlabeled Data to Track Memorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanie Sedghi, Mahsa Forouzesh, Patrick Thiran","submitted_at":"2022-12-08T18:36:41Z","abstract_excerpt":"Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We propose a metric, called susceptibility, to gauge such memorization for neural networks. Susceptibility is simple and easy to compute during training. Moreover, it does not require access to ground-truth labels and it only uses unlabeled data. We empirically show the effectiveness of our metric in tracking memorization on various architectures and datasets and p"},"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":"2212.04461","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-08T18:36:41Z","cross_cats_sorted":[],"title_canon_sha256":"a015056cb1b4f5f12cb4738df316421999ba04b35c7a2cd2dcd4fbb591a565e6","abstract_canon_sha256":"d301c114efc48d62de411c57ee7fb24da63b1cf22b175ee4520bba114cd1a3c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:41.469720Z","signature_b64":"5gA4aSZEW8zRlL0SJDs0muEAxvgAuK8bKsuTx3x7snH/3vEQNrk17zZb9rnpNz4pzYFUXHE1vtXpMtNwRdLZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"299d506ee5d25daf433a342fbaec26235b58687a7112ea1c913594723d255ad3","last_reissued_at":"2026-07-05T05:23:41.469272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:41.469272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Unlabeled Data to Track Memorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hanie Sedghi, Mahsa Forouzesh, Patrick Thiran","submitted_at":"2022-12-08T18:36:41Z","abstract_excerpt":"Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We propose a metric, called susceptibility, to gauge such memorization for neural networks. Susceptibility is simple and easy to compute during training. Moreover, it does not require access to ground-truth labels and it only uses unlabeled data. We empirically show the effectiveness of our metric in tracking memorization on various architectures and datasets and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04461","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/2212.04461/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":"2212.04461","created_at":"2026-07-05T05:23:41.469325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04461v1","created_at":"2026-07-05T05:23:41.469325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04461","created_at":"2026-07-05T05:23:41.469325+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGOVA3XF2JO2","created_at":"2026-07-05T05:23:41.469325+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGOVA3XF2JO26QZ2","created_at":"2026-07-05T05:23:41.469325+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGOVA3XF","created_at":"2026-07-05T05:23:41.469325+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/FGOVA3XF2JO26QZ2GQX3V3BGEN","json":"https://pith.science/pith/FGOVA3XF2JO26QZ2GQX3V3BGEN.json","graph_json":"https://pith.science/api/pith-number/FGOVA3XF2JO26QZ2GQX3V3BGEN/graph.json","events_json":"https://pith.science/api/pith-number/FGOVA3XF2JO26QZ2GQX3V3BGEN/events.json","paper":"https://pith.science/paper/FGOVA3XF"},"agent_actions":{"view_html":"https://pith.science/pith/FGOVA3XF2JO26QZ2GQX3V3BGEN","download_json":"https://pith.science/pith/FGOVA3XF2JO26QZ2GQX3V3BGEN.json","view_paper":"https://pith.science/paper/FGOVA3XF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04461&json=true","fetch_graph":"https://pith.science/api/pith-number/FGOVA3XF2JO26QZ2GQX3V3BGEN/graph.json","fetch_events":"https://pith.science/api/pith-number/FGOVA3XF2JO26QZ2GQX3V3BGEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGOVA3XF2JO26QZ2GQX3V3BGEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGOVA3XF2JO26QZ2GQX3V3BGEN/action/storage_attestation","attest_author":"https://pith.science/pith/FGOVA3XF2JO26QZ2GQX3V3BGEN/action/author_attestation","sign_citation":"https://pith.science/pith/FGOVA3XF2JO26QZ2GQX3V3BGEN/action/citation_signature","submit_replication":"https://pith.science/pith/FGOVA3XF2JO26QZ2GQX3V3BGEN/action/replication_record"}},"created_at":"2026-07-05T05:23:41.469325+00:00","updated_at":"2026-07-05T05:23:41.469325+00:00"}