{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JOGTPT3O2B3LIZQTECR2ERXWMB","short_pith_number":"pith:JOGTPT3O","schema_version":"1.0","canonical_sha256":"4b8d37cf6ed076b4661320a3a246f6604bef5253abafe7e9bc80897fbe067df0","source":{"kind":"arxiv","id":"1908.09375","version":1},"attestation_state":"computed","paper":{"title":"Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrzej Banburski, Qianli Liao, Tomaso Poggio","submitted_at":"2019-08-25T19:12:56Z","abstract_excerpt":"While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1) representation power of deep networks 2) optimization of the empirical risk 3) generalization properties of gradient descent techniques --- why the expected error does not suffer, despite the absence of explicit regularization, when the networks are overparametrized? In this review we discuss recent advances in the three areas. In approximation theory both 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":"1908.09375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-25T19:12:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cdf80808b31ae6a46b998986440fdb778f7806464aa84555124f7c1522db5556","abstract_canon_sha256":"1c0d22f8d5c9f4efa548673a7801340567dbce6a52c9553f14c5906d6c0f7b54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:39.581099Z","signature_b64":"gobdhHsDbHV5unFE/mdRTmE4iEAgvd7AnkuE8xLO4PJ2xGtZ+FwBIoj3yw4vljTFml8SNtnB9yx9fgTJSoSPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b8d37cf6ed076b4661320a3a246f6604bef5253abafe7e9bc80897fbe067df0","last_reissued_at":"2026-07-04T23:59:39.580622Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:39.580622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrzej Banburski, Qianli Liao, Tomaso Poggio","submitted_at":"2019-08-25T19:12:56Z","abstract_excerpt":"While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1) representation power of deep networks 2) optimization of the empirical risk 3) generalization properties of gradient descent techniques --- why the expected error does not suffer, despite the absence of explicit regularization, when the networks are overparametrized? In this review we discuss recent advances in the three areas. In approximation theory both s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09375","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/1908.09375/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":"1908.09375","created_at":"2026-07-04T23:59:39.580679+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09375v1","created_at":"2026-07-04T23:59:39.580679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09375","created_at":"2026-07-04T23:59:39.580679+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOGTPT3O2B3L","created_at":"2026-07-04T23:59:39.580679+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOGTPT3O2B3LIZQT","created_at":"2026-07-04T23:59:39.580679+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOGTPT3O","created_at":"2026-07-04T23:59:39.580679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.09375","citing_title":"Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB","json":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB.json","graph_json":"https://pith.science/api/pith-number/JOGTPT3O2B3LIZQTECR2ERXWMB/graph.json","events_json":"https://pith.science/api/pith-number/JOGTPT3O2B3LIZQTECR2ERXWMB/events.json","paper":"https://pith.science/paper/JOGTPT3O"},"agent_actions":{"view_html":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB","download_json":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB.json","view_paper":"https://pith.science/paper/JOGTPT3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09375&json=true","fetch_graph":"https://pith.science/api/pith-number/JOGTPT3O2B3LIZQTECR2ERXWMB/graph.json","fetch_events":"https://pith.science/api/pith-number/JOGTPT3O2B3LIZQTECR2ERXWMB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB/action/storage_attestation","attest_author":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB/action/author_attestation","sign_citation":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB/action/citation_signature","submit_replication":"https://pith.science/pith/JOGTPT3O2B3LIZQTECR2ERXWMB/action/replication_record"}},"created_at":"2026-07-04T23:59:39.580679+00:00","updated_at":"2026-07-04T23:59:39.580679+00:00"}