{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NYX3JOQPSJFEATW4VHNPOF4OGY","short_pith_number":"pith:NYX3JOQP","schema_version":"1.0","canonical_sha256":"6e2fb4ba0f924a404edca9daf7178e360ac4d3b2ebab985d52c44c2805819b66","source":{"kind":"arxiv","id":"2310.08847","version":4},"attestation_state":"computed","paper":{"title":"On the Over-Memorization During Natural, Robust and Catastrophic Overfitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Chaojian Yu, Runqi Lin, Tongliang Liu","submitted_at":"2023-10-13T04:14:51Z","abstract_excerpt":"Overfitting negatively impacts the generalization ability of deep neural networks (DNNs) in both natural and adversarial training. Existing methods struggle to consistently address different types of overfitting, typically designing strategies that focus separately on either natural or adversarial patterns. In this work, we adopt a unified perspective by solely focusing on natural patterns to explore different types of overfitting. Specifically, we examine the memorization effect in DNNs and reveal a shared behaviour termed over-memorization, which impairs their generalization capacity. This b"},"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":"2310.08847","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-13T04:14:51Z","cross_cats_sorted":[],"title_canon_sha256":"9c4e5b314c019432de66efeed10bd8ac0ff9ca6d7db838d991d58b8cc6a34292","abstract_canon_sha256":"c7e2f0bcc0ecd869c1b3beb9b703f2df46058b0b8d092bb42dbf3891f18f39c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:55.441955Z","signature_b64":"/uW4jDCJBizhTOTbTbthzL2jlm8eYgyqjM1aMf2dBnjjUByR3GMzogAIV0tT2TfxiotBqBpEj7V7pIJVrkbKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e2fb4ba0f924a404edca9daf7178e360ac4d3b2ebab985d52c44c2805819b66","last_reissued_at":"2026-07-05T09:06:55.441492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:55.441492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Over-Memorization During Natural, Robust and Catastrophic Overfitting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Chaojian Yu, Runqi Lin, Tongliang Liu","submitted_at":"2023-10-13T04:14:51Z","abstract_excerpt":"Overfitting negatively impacts the generalization ability of deep neural networks (DNNs) in both natural and adversarial training. Existing methods struggle to consistently address different types of overfitting, typically designing strategies that focus separately on either natural or adversarial patterns. In this work, we adopt a unified perspective by solely focusing on natural patterns to explore different types of overfitting. Specifically, we examine the memorization effect in DNNs and reveal a shared behaviour termed over-memorization, which impairs their generalization capacity. This b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08847","kind":"arxiv","version":4},"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/2310.08847/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":"2310.08847","created_at":"2026-07-05T09:06:55.441547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08847v4","created_at":"2026-07-05T09:06:55.441547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08847","created_at":"2026-07-05T09:06:55.441547+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYX3JOQPSJFE","created_at":"2026-07-05T09:06:55.441547+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYX3JOQPSJFEATW4","created_at":"2026-07-05T09:06:55.441547+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYX3JOQP","created_at":"2026-07-05T09:06:55.441547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00738","citing_title":"SORA: Free Second-Order Attacks in Fast Adversarial Training","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY","json":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY.json","graph_json":"https://pith.science/api/pith-number/NYX3JOQPSJFEATW4VHNPOF4OGY/graph.json","events_json":"https://pith.science/api/pith-number/NYX3JOQPSJFEATW4VHNPOF4OGY/events.json","paper":"https://pith.science/paper/NYX3JOQP"},"agent_actions":{"view_html":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY","download_json":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY.json","view_paper":"https://pith.science/paper/NYX3JOQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08847&json=true","fetch_graph":"https://pith.science/api/pith-number/NYX3JOQPSJFEATW4VHNPOF4OGY/graph.json","fetch_events":"https://pith.science/api/pith-number/NYX3JOQPSJFEATW4VHNPOF4OGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY/action/storage_attestation","attest_author":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY/action/author_attestation","sign_citation":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY/action/citation_signature","submit_replication":"https://pith.science/pith/NYX3JOQPSJFEATW4VHNPOF4OGY/action/replication_record"}},"created_at":"2026-07-05T09:06:55.441547+00:00","updated_at":"2026-07-05T09:06:55.441547+00:00"}