{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZDL54TIQVCVWPIPZEKBAPHNX2I","short_pith_number":"pith:ZDL54TIQ","schema_version":"1.0","canonical_sha256":"c8d7de4d10a8ab67a1f92282079db7d23c15a1c1fafd5a5a67a4fe021e53e968","source":{"kind":"arxiv","id":"1911.09537","version":1},"attestation_state":"computed","paper":{"title":"Neural Network Memorization Dissection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jindong Gu, Volker Tresp","submitted_at":"2019-11-21T15:24:55Z","abstract_excerpt":"Deep neural networks (DNNs) can easily fit a random labeling of the training data with zero training error. What is the difference between DNNs trained with random labels and the ones trained with true labels? Our paper answers this question with two contributions. First, we study the memorization properties of DNNs. Our empirical experiments shed light on how DNNs prioritize the learning of simple input patterns. In the second part, we propose to measure the similarity between what different DNNs have learned and memorized. With the proposed approach, we analyze and compare DNNs trained on da"},"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":"1911.09537","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-21T15:24:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9ffcb50a671fed6de81ebc631e2c599057dfe6ab251097e609e5f7f16cddeb63","abstract_canon_sha256":"9dac5cf06ced9b90ed4e8ce01afadf96c0beef4e1336746c900bc5e108070720"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:01.926406Z","signature_b64":"+Y00TynRMXoLsdK/D39KA/7/CZsjhgU5lygwXasStu65B4Q7SD2M1eJpTKqz/Xp93rhZrb/oSGZpQQOvioNyDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8d7de4d10a8ab67a1f92282079db7d23c15a1c1fafd5a5a67a4fe021e53e968","last_reissued_at":"2026-07-05T00:21:01.926018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:01.926018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Network Memorization Dissection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jindong Gu, Volker Tresp","submitted_at":"2019-11-21T15:24:55Z","abstract_excerpt":"Deep neural networks (DNNs) can easily fit a random labeling of the training data with zero training error. What is the difference between DNNs trained with random labels and the ones trained with true labels? Our paper answers this question with two contributions. First, we study the memorization properties of DNNs. Our empirical experiments shed light on how DNNs prioritize the learning of simple input patterns. In the second part, we propose to measure the similarity between what different DNNs have learned and memorized. With the proposed approach, we analyze and compare DNNs trained on da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09537","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/1911.09537/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":"1911.09537","created_at":"2026-07-05T00:21:01.926075+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.09537v1","created_at":"2026-07-05T00:21:01.926075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09537","created_at":"2026-07-05T00:21:01.926075+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDL54TIQVCVW","created_at":"2026-07-05T00:21:01.926075+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDL54TIQVCVWPIPZ","created_at":"2026-07-05T00:21:01.926075+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDL54TIQ","created_at":"2026-07-05T00:21:01.926075+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/ZDL54TIQVCVWPIPZEKBAPHNX2I","json":"https://pith.science/pith/ZDL54TIQVCVWPIPZEKBAPHNX2I.json","graph_json":"https://pith.science/api/pith-number/ZDL54TIQVCVWPIPZEKBAPHNX2I/graph.json","events_json":"https://pith.science/api/pith-number/ZDL54TIQVCVWPIPZEKBAPHNX2I/events.json","paper":"https://pith.science/paper/ZDL54TIQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZDL54TIQVCVWPIPZEKBAPHNX2I","download_json":"https://pith.science/pith/ZDL54TIQVCVWPIPZEKBAPHNX2I.json","view_paper":"https://pith.science/paper/ZDL54TIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.09537&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDL54TIQVCVWPIPZEKBAPHNX2I/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDL54TIQVCVWPIPZEKBAPHNX2I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDL54TIQVCVWPIPZEKBAPHNX2I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDL54TIQVCVWPIPZEKBAPHNX2I/action/storage_attestation","attest_author":"https://pith.science/pith/ZDL54TIQVCVWPIPZEKBAPHNX2I/action/author_attestation","sign_citation":"https://pith.science/pith/ZDL54TIQVCVWPIPZEKBAPHNX2I/action/citation_signature","submit_replication":"https://pith.science/pith/ZDL54TIQVCVWPIPZEKBAPHNX2I/action/replication_record"}},"created_at":"2026-07-05T00:21:01.926075+00:00","updated_at":"2026-07-05T00:21:01.926075+00:00"}