{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z6XAMQSTMY6GTTJFXAHNVZHMM7","short_pith_number":"pith:Z6XAMQST","schema_version":"1.0","canonical_sha256":"cfae064253663c69cd25b80edae4ec67e0eb3503309ff62e7caa8e00151aac61","source":{"kind":"arxiv","id":"2402.17595","version":1},"attestation_state":"computed","paper":{"title":"Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Thanh Lam, Hong T.M. Chu, Soumendu Sundar Mukherjee, Subhro Ghosh","submitted_at":"2024-02-27T15:28:01Z","abstract_excerpt":"The phenomenon of implicit regularization has attracted interest in recent years as a fundamental aspect of the remarkable generalizing ability of neural networks. In a nutshell, it entails that gradient descent dynamics in many neural nets, even without any explicit regularizer in the loss function, converges to the solution of a regularized learning problem. However, known results attempting to theoretically explain this phenomenon focus overwhelmingly on the setting of linear neural nets, and the simplicity of the linear structure is particularly crucial to existing arguments. In this paper"},"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":"2402.17595","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T15:28:01Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"7849dfd19b00384b509b0bcb9d6d393b08a75cb7bd36d2685d71bf0bcccb0d24","abstract_canon_sha256":"1d3a64f65f483e3bdd3701014444d2a07c2fce05bac85e759803e050e4a2df6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:48.894950Z","signature_b64":"V9Y9RcRgR52KM4fm/hnqDvNh5QgLbtgQ40SHiVKlfef9MmQt5AvgIds91VQ5sVfzEaJvrEpn65yZF0HtLIJWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfae064253663c69cd25b80edae4ec67e0eb3503309ff62e7caa8e00151aac61","last_reissued_at":"2026-07-05T07:49:48.894576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:48.894576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Thanh Lam, Hong T.M. Chu, Soumendu Sundar Mukherjee, Subhro Ghosh","submitted_at":"2024-02-27T15:28:01Z","abstract_excerpt":"The phenomenon of implicit regularization has attracted interest in recent years as a fundamental aspect of the remarkable generalizing ability of neural networks. In a nutshell, it entails that gradient descent dynamics in many neural nets, even without any explicit regularizer in the loss function, converges to the solution of a regularized learning problem. However, known results attempting to theoretically explain this phenomenon focus overwhelmingly on the setting of linear neural nets, and the simplicity of the linear structure is particularly crucial to existing arguments. In this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17595","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/2402.17595/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":"2402.17595","created_at":"2026-07-05T07:49:48.894633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17595v1","created_at":"2026-07-05T07:49:48.894633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17595","created_at":"2026-07-05T07:49:48.894633+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6XAMQSTMY6G","created_at":"2026-07-05T07:49:48.894633+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6XAMQSTMY6GTTJF","created_at":"2026-07-05T07:49:48.894633+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6XAMQST","created_at":"2026-07-05T07:49:48.894633+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.09088","citing_title":"An entropy formula for the Deep Linear Network","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7","json":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7.json","graph_json":"https://pith.science/api/pith-number/Z6XAMQSTMY6GTTJFXAHNVZHMM7/graph.json","events_json":"https://pith.science/api/pith-number/Z6XAMQSTMY6GTTJFXAHNVZHMM7/events.json","paper":"https://pith.science/paper/Z6XAMQST"},"agent_actions":{"view_html":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7","download_json":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7.json","view_paper":"https://pith.science/paper/Z6XAMQST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17595&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6XAMQSTMY6GTTJFXAHNVZHMM7/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6XAMQSTMY6GTTJFXAHNVZHMM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7/action/storage_attestation","attest_author":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7/action/author_attestation","sign_citation":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7/action/citation_signature","submit_replication":"https://pith.science/pith/Z6XAMQSTMY6GTTJFXAHNVZHMM7/action/replication_record"}},"created_at":"2026-07-05T07:49:48.894633+00:00","updated_at":"2026-07-05T07:49:48.894633+00:00"}