{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4XHUVYNHMYHAKFH73GJOBCYVHD","short_pith_number":"pith:4XHUVYNH","schema_version":"1.0","canonical_sha256":"e5cf4ae1a7660e0514ffd992e08b1538f1d229519628ab19558e1d81b81b3021","source":{"kind":"arxiv","id":"2507.08686","version":1},"attestation_state":"computed","paper":{"title":"Forget Me Not: Fighting Local Overfitting with Knowledge Fusion and Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daphna Weinshall, Eli Corn, Uri Stern","submitted_at":"2025-07-11T15:37:24Z","abstract_excerpt":"Overfitting in deep neural networks occurs less frequently than expected. This is a puzzling observation, as theory predicts that greater model capacity should eventually lead to overfitting -- yet this is rarely seen in practice. But what if overfitting does occur, not globally, but in specific sub-regions of the data space? In this work, we introduce a novel score that measures the forgetting rate of deep models on validation data, capturing what we term local overfitting: a performance degradation confined to certain regions of the input space. We demonstrate that local overfitting can aris"},"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":"2507.08686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T15:37:24Z","cross_cats_sorted":[],"title_canon_sha256":"55dbb279d85338b1c127b24c2eec2d823ccde4b36b6dd426339283eb0b0220cd","abstract_canon_sha256":"0763c8d870b572ed9e7f380890af76a1a963a8036ff352e4d2352b4fe91c5437"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:44.847335Z","signature_b64":"1UtfAA2+nOIKV0lUdE5FgmeRYvHNGNWRRkW21dbYdUKhx5tezkiO0Bmn9ozyq0bSyTWRVnrBQChU5u0iX2ezAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5cf4ae1a7660e0514ffd992e08b1538f1d229519628ab19558e1d81b81b3021","last_reissued_at":"2026-07-05T11:35:44.846810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:44.846810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forget Me Not: Fighting Local Overfitting with Knowledge Fusion and Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daphna Weinshall, Eli Corn, Uri Stern","submitted_at":"2025-07-11T15:37:24Z","abstract_excerpt":"Overfitting in deep neural networks occurs less frequently than expected. This is a puzzling observation, as theory predicts that greater model capacity should eventually lead to overfitting -- yet this is rarely seen in practice. But what if overfitting does occur, not globally, but in specific sub-regions of the data space? In this work, we introduce a novel score that measures the forgetting rate of deep models on validation data, capturing what we term local overfitting: a performance degradation confined to certain regions of the input space. We demonstrate that local overfitting can aris"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08686","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/2507.08686/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":"2507.08686","created_at":"2026-07-05T11:35:44.846874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08686v1","created_at":"2026-07-05T11:35:44.846874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08686","created_at":"2026-07-05T11:35:44.846874+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XHUVYNHMYHA","created_at":"2026-07-05T11:35:44.846874+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XHUVYNHMYHAKFH7","created_at":"2026-07-05T11:35:44.846874+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XHUVYNH","created_at":"2026-07-05T11:35:44.846874+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/4XHUVYNHMYHAKFH73GJOBCYVHD","json":"https://pith.science/pith/4XHUVYNHMYHAKFH73GJOBCYVHD.json","graph_json":"https://pith.science/api/pith-number/4XHUVYNHMYHAKFH73GJOBCYVHD/graph.json","events_json":"https://pith.science/api/pith-number/4XHUVYNHMYHAKFH73GJOBCYVHD/events.json","paper":"https://pith.science/paper/4XHUVYNH"},"agent_actions":{"view_html":"https://pith.science/pith/4XHUVYNHMYHAKFH73GJOBCYVHD","download_json":"https://pith.science/pith/4XHUVYNHMYHAKFH73GJOBCYVHD.json","view_paper":"https://pith.science/paper/4XHUVYNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08686&json=true","fetch_graph":"https://pith.science/api/pith-number/4XHUVYNHMYHAKFH73GJOBCYVHD/graph.json","fetch_events":"https://pith.science/api/pith-number/4XHUVYNHMYHAKFH73GJOBCYVHD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XHUVYNHMYHAKFH73GJOBCYVHD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XHUVYNHMYHAKFH73GJOBCYVHD/action/storage_attestation","attest_author":"https://pith.science/pith/4XHUVYNHMYHAKFH73GJOBCYVHD/action/author_attestation","sign_citation":"https://pith.science/pith/4XHUVYNHMYHAKFH73GJOBCYVHD/action/citation_signature","submit_replication":"https://pith.science/pith/4XHUVYNHMYHAKFH73GJOBCYVHD/action/replication_record"}},"created_at":"2026-07-05T11:35:44.846874+00:00","updated_at":"2026-07-05T11:35:44.846874+00:00"}