{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZWSOAPS7SPWYX5FG3VNTG35P77","short_pith_number":"pith:ZWSOAPS7","schema_version":"1.0","canonical_sha256":"cda4e03e5f93ed8bf4a6dd5b336faffffdbac539073c0c122646d1a09cd0c54c","source":{"kind":"arxiv","id":"1906.05301","version":4},"attestation_state":"computed","paper":{"title":"Learning Curves for Deep Neural Networks: A Gaussian Field Theory Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.NE","physics.data-an","stat.ML"],"primary_cat":"cs.LG","authors_text":"Omry Cohen, Or Malka, Zohar Ringel","submitted_at":"2019-06-12T18:00:10Z","abstract_excerpt":"In the past decade, deep neural networks (DNNs) came to the fore as the leading machine learning algorithms for a variety of tasks. Their raise was founded on market needs and engineering craftsmanship, the latter based more on trial and error than on theory. While still far behind the application forefront, the theoretical study of DNNs has recently made important advancements in analyzing the highly over-parameterized regime where some exact results have been obtained. Leveraging these ideas and adopting a more physics-like approach, here we construct a versatile field-theory formalism for s"},"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":"1906.05301","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-12T18:00:10Z","cross_cats_sorted":["cond-mat.stat-mech","cs.NE","physics.data-an","stat.ML"],"title_canon_sha256":"4506f95b5c1063c8a60166c27bc9d9657c7e175d8f7c45f19eced1402a648b19","abstract_canon_sha256":"c8781a2ca6fb744674b519e390bd12aca7fb99ed8cbc3bcad19d7e664da20056"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:36.844703Z","signature_b64":"AIxUJvljjSxyG4X7odQ3xUUhFUC1bfiGU3oPMljYCDurkzYSVACwOymdRKzL4op97HSA54G09KQpSa/+gKxfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cda4e03e5f93ed8bf4a6dd5b336faffffdbac539073c0c122646d1a09cd0c54c","last_reissued_at":"2026-07-05T02:31:36.844346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:36.844346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Curves for Deep Neural Networks: A Gaussian Field Theory Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.NE","physics.data-an","stat.ML"],"primary_cat":"cs.LG","authors_text":"Omry Cohen, Or Malka, Zohar Ringel","submitted_at":"2019-06-12T18:00:10Z","abstract_excerpt":"In the past decade, deep neural networks (DNNs) came to the fore as the leading machine learning algorithms for a variety of tasks. Their raise was founded on market needs and engineering craftsmanship, the latter based more on trial and error than on theory. While still far behind the application forefront, the theoretical study of DNNs has recently made important advancements in analyzing the highly over-parameterized regime where some exact results have been obtained. Leveraging these ideas and adopting a more physics-like approach, here we construct a versatile field-theory formalism for s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05301","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/1906.05301/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":"1906.05301","created_at":"2026-07-05T02:31:36.844405+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05301v4","created_at":"2026-07-05T02:31:36.844405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05301","created_at":"2026-07-05T02:31:36.844405+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWSOAPS7SPWY","created_at":"2026-07-05T02:31:36.844405+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWSOAPS7SPWYX5FG","created_at":"2026-07-05T02:31:36.844405+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWSOAPS7","created_at":"2026-07-05T02:31:36.844405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19680","citing_title":"Feature learning is decoupled from generalization in high capacity neural networks","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77","json":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77.json","graph_json":"https://pith.science/api/pith-number/ZWSOAPS7SPWYX5FG3VNTG35P77/graph.json","events_json":"https://pith.science/api/pith-number/ZWSOAPS7SPWYX5FG3VNTG35P77/events.json","paper":"https://pith.science/paper/ZWSOAPS7"},"agent_actions":{"view_html":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77","download_json":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77.json","view_paper":"https://pith.science/paper/ZWSOAPS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05301&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWSOAPS7SPWYX5FG3VNTG35P77/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWSOAPS7SPWYX5FG3VNTG35P77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77/action/storage_attestation","attest_author":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77/action/author_attestation","sign_citation":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77/action/citation_signature","submit_replication":"https://pith.science/pith/ZWSOAPS7SPWYX5FG3VNTG35P77/action/replication_record"}},"created_at":"2026-07-05T02:31:36.844405+00:00","updated_at":"2026-07-05T02:31:36.844405+00:00"}