{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX","short_pith_number":"pith:NRDUUBFJ","schema_version":"1.0","canonical_sha256":"6c474a04a9d272527f1da4e1e76e1bc5c74091fd4c7279309a4f19634b993768","source":{"kind":"arxiv","id":"2412.12968","version":2},"attestation_state":"computed","paper":{"title":"On Local Overfitting and Forgetting in Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daphna Weinshall, Tomer Yaacoby, Uri Stern","submitted_at":"2024-12-17T14:53:38Z","abstract_excerpt":"The infrequent occurrence of overfitting in deep neural networks is perplexing: contrary to theoretical expectations, increasing model size often enhances performance in practice. But what if overfitting does occur, though restricted to specific sub-regions of the data space? In this work, we propose a novel score that captures the forgetting rate of deep models on validation data. We posit that this score quantifies local overfitting: a decline in performance confined to certain regions of the data space. We then show empirically that local overfitting occurs regardless of the presence of tra"},"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":"2412.12968","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T14:53:38Z","cross_cats_sorted":[],"title_canon_sha256":"5af0ba9dd15d04c90a2c94a9461c02669133230b14e3ff2312b775047d646436","abstract_canon_sha256":"2d8fb3c49def356e978326b9b6175a2c9f4e32bab411e6695df7722a46dd145a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:49.359875Z","signature_b64":"q0wmB2//hs41tO0mabA3vjAsJoLqM7sheJJQVusk6+PKlALWfw7ZS9YiKb+vZQBeoV766ytCfYK358e97tVbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c474a04a9d272527f1da4e1e76e1bc5c74091fd4c7279309a4f19634b993768","last_reissued_at":"2026-07-05T09:57:49.359284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:49.359284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Local Overfitting and Forgetting in Deep Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daphna Weinshall, Tomer Yaacoby, Uri Stern","submitted_at":"2024-12-17T14:53:38Z","abstract_excerpt":"The infrequent occurrence of overfitting in deep neural networks is perplexing: contrary to theoretical expectations, increasing model size often enhances performance in practice. But what if overfitting does occur, though restricted to specific sub-regions of the data space? In this work, we propose a novel score that captures the forgetting rate of deep models on validation data. We posit that this score quantifies local overfitting: a decline in performance confined to certain regions of the data space. We then show empirically that local overfitting occurs regardless of the presence of tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12968","kind":"arxiv","version":2},"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/2412.12968/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":"2412.12968","created_at":"2026-07-05T09:57:49.359356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12968v2","created_at":"2026-07-05T09:57:49.359356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12968","created_at":"2026-07-05T09:57:49.359356+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRDUUBFJ2JZF","created_at":"2026-07-05T09:57:49.359356+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRDUUBFJ2JZFE7Y5","created_at":"2026-07-05T09:57:49.359356+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRDUUBFJ","created_at":"2026-07-05T09:57:49.359356+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08686","citing_title":"Forget Me Not: Fighting Local Overfitting with Knowledge Fusion and Distillation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX","json":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX.json","graph_json":"https://pith.science/api/pith-number/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/graph.json","events_json":"https://pith.science/api/pith-number/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/events.json","paper":"https://pith.science/paper/NRDUUBFJ"},"agent_actions":{"view_html":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX","download_json":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX.json","view_paper":"https://pith.science/paper/NRDUUBFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12968&json=true","fetch_graph":"https://pith.science/api/pith-number/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/graph.json","fetch_events":"https://pith.science/api/pith-number/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/action/storage_attestation","attest_author":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/action/author_attestation","sign_citation":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/action/citation_signature","submit_replication":"https://pith.science/pith/NRDUUBFJ2JZFE7Y5UTQ6O3Q3YX/action/replication_record"}},"created_at":"2026-07-05T09:57:49.359356+00:00","updated_at":"2026-07-05T09:57:49.359356+00:00"}