{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AMEE7I7S2VBCMHZPOXY7CXA4E4","short_pith_number":"pith:AMEE7I7S","schema_version":"1.0","canonical_sha256":"03084fa3f2d542261f2f75f1f15c1c270b7d22406ac89b9d5e0f7680387588c8","source":{"kind":"arxiv","id":"2111.15090","version":2},"attestation_state":"computed","paper":{"title":"The Geometric Occam's Razor Implicit in Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benoit Dherin, David G.T. Barrett, Michael Munn","submitted_at":"2021-11-30T03:05:11Z","abstract_excerpt":"In over-parameterized deep neural networks there can be many possible parameter configurations that fit the training data exactly. However, the properties of these interpolating solutions are poorly understood. We argue that over-parameterized neural networks trained with stochastic gradient descent are subject to a Geometric Occam's Razor; that is, these networks are implicitly regularized by the geometric model complexity. For one-dimensional regression, the geometric model complexity is simply given by the arc length of the function. For higher-dimensional settings, the geometric model comp"},"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":"2111.15090","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-30T03:05:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"06234a1cb8014c6a89c6de012fe3434c6ef15066f26c3526991e8d9da74f90fc","abstract_canon_sha256":"91ec0c51c3f2a5c0774dd8139255e1418f5f8130acd6a72e60894ecc575f2dce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:41.406755Z","signature_b64":"7eSkQFynWw+oPeQBN1o1COaFTT39P1HLWsLIqixMrkwl6ioTTb+u8sOAWH/qZ4vacVt9Gdu4+ruRzHh4zaJaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03084fa3f2d542261f2f75f1f15c1c270b7d22406ac89b9d5e0f7680387588c8","last_reissued_at":"2026-07-05T03:36:41.406250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:41.406250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Geometric Occam's Razor Implicit in Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Benoit Dherin, David G.T. Barrett, Michael Munn","submitted_at":"2021-11-30T03:05:11Z","abstract_excerpt":"In over-parameterized deep neural networks there can be many possible parameter configurations that fit the training data exactly. However, the properties of these interpolating solutions are poorly understood. We argue that over-parameterized neural networks trained with stochastic gradient descent are subject to a Geometric Occam's Razor; that is, these networks are implicitly regularized by the geometric model complexity. For one-dimensional regression, the geometric model complexity is simply given by the arc length of the function. For higher-dimensional settings, the geometric model comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.15090","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/2111.15090/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":"2111.15090","created_at":"2026-07-05T03:36:41.406309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.15090v2","created_at":"2026-07-05T03:36:41.406309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.15090","created_at":"2026-07-05T03:36:41.406309+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMEE7I7S2VBC","created_at":"2026-07-05T03:36:41.406309+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMEE7I7S2VBCMHZP","created_at":"2026-07-05T03:36:41.406309+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMEE7I7S","created_at":"2026-07-05T03:36:41.406309+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/AMEE7I7S2VBCMHZPOXY7CXA4E4","json":"https://pith.science/pith/AMEE7I7S2VBCMHZPOXY7CXA4E4.json","graph_json":"https://pith.science/api/pith-number/AMEE7I7S2VBCMHZPOXY7CXA4E4/graph.json","events_json":"https://pith.science/api/pith-number/AMEE7I7S2VBCMHZPOXY7CXA4E4/events.json","paper":"https://pith.science/paper/AMEE7I7S"},"agent_actions":{"view_html":"https://pith.science/pith/AMEE7I7S2VBCMHZPOXY7CXA4E4","download_json":"https://pith.science/pith/AMEE7I7S2VBCMHZPOXY7CXA4E4.json","view_paper":"https://pith.science/paper/AMEE7I7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.15090&json=true","fetch_graph":"https://pith.science/api/pith-number/AMEE7I7S2VBCMHZPOXY7CXA4E4/graph.json","fetch_events":"https://pith.science/api/pith-number/AMEE7I7S2VBCMHZPOXY7CXA4E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMEE7I7S2VBCMHZPOXY7CXA4E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMEE7I7S2VBCMHZPOXY7CXA4E4/action/storage_attestation","attest_author":"https://pith.science/pith/AMEE7I7S2VBCMHZPOXY7CXA4E4/action/author_attestation","sign_citation":"https://pith.science/pith/AMEE7I7S2VBCMHZPOXY7CXA4E4/action/citation_signature","submit_replication":"https://pith.science/pith/AMEE7I7S2VBCMHZPOXY7CXA4E4/action/replication_record"}},"created_at":"2026-07-05T03:36:41.406309+00:00","updated_at":"2026-07-05T03:36:41.406309+00:00"}